智慧製造與生產線上的數據科學polab.im.ntu.edu.tw/talk/data_science_in_manufacturing.pdf智慧製造與生產線上的數據科學...

智慧製造與生產線上的數據科學

Manufacturing Data ScienceFrom Predictive to Prescriptive

Chia-Yen Lee PhD (李家岩博士)

台灣人工智慧學校

Department of Information Management (資訊管理學系)

National Taiwan University (國立台灣大學)

生產力最佳化實驗室NTU 智慧製造與生產線上的數據科學李家岩 (台大資訊管理學系) 2

Experience

教授國立台灣大學資訊管理學系

教授兼所長國立成功大學資訊工程學系暨製造資訊與系統研究所

副編輯IEEE Transactions on Automation Science and Engineering (SCI)

半導體廠科技顧問台積電工業工程師陸軍少尉資訊官

Award

IEEE Senior Member(2021)呂鳳章先生紀念獎(2019)

美光教師Micron Teacher Award (2018)

李國鼎科技與人文講座研究獎 (2018)

科技部吳大猷先生紀念獎 (2017)

Research Interest 製造數據科學智慧型製造系統生產力與效率分析生產經濟學多目標決策

Education

PhD 工業與系統工程 Texas AampM University USA(Major Operations Research作業研究運籌學)

MS工業工程與工程管理國立清華大學

BS amp BBA應用數學暨資訊管理國立政治大學

生產力最佳化實驗室NTU 智慧製造與生產線上的數據科學李家岩 (台大資訊管理學系)

Hype Cycle 2020

3

httpswwwxeroxcomen-gdinnovationinsightshype-cycle-report


Outline

4

1 智慧製造與資料預處理技巧

Intelligent Manufacturing and Data Preprocessing

2 重要參數篩選與品質預測

Empirical Case Studies

3 自動化生產排程與演算法

Automatic Production Scheduling Algorithms

4 從預測性思維到處方性決策

From Predictive to Prescriptive


智慧製造與資料預處理技巧Intelligent Manufacturing and Data Preprocessing

5


What is ldquoManufacturingrdquo

Manufacturing is hellipManufacturing is hellip

Manufacturing is the realization (具現化) of product

Manus (hand) Factus (make)

Starting

material

Material in

processing

Processed

material

Value-added

Swann J 2003 Manufacturing Systems Course Lecture Notes Georgia Institute of Technology


Intelligent ishellip

7

Shutterstock (wwwshutterstockcom)


Knowledge

詮釋的觀點

思辨的過程

科學的原理


迷思資料資訊

如果老闆跟你要一份報告hellip

email打開後是hellip

9

Advanced Analytics ndash Intel SETFI Manufacturing data Semiconductor tool fault isolation Causality Workbench Repository

httpwwwcausalityinfethzch repositoryphp (2008)


Transformation from Data Information to Knowledge

10

北南

Etu蔣居裕 (2013)


Experiencehellip

ExperienceDecisionProblem權衡的觀點

失敗的藝術

人生的歷練


知識與經驗之

融會貫通(思辨與討論)

httpwwwherogamingjobscom20140107experience-vs-knowledge

Wisdom ishellip


Wisdom ishellip

13

Moioli Fabio (2019) The most important skill in the future will be the ability to connect the dots in your own way

httpswwwlinkedincompulsemost-important-skill-future-ability-connect-dots-your-fabio-moioli

The most important skill in the future will be the ability to

ldquoconnect the dotsrdquo in your own way (Moioli 2019)

13


Smart Factory is a decision-oriented system which has

the computational intelligence and self-learning ability to

optimize the manufacturing process

計算智慧rarr Based on Data (資料處理與分析)

自我學習rarr Real-time Feedback Control (回饋控制)

智慧工廠


Tolga Bozdana (2012)

15

智慧工廠

智慧製造

製造智慧


Manufacturing System

(製造系統)

16


Value and Profit

Value

Manufacturing is value-added process for the realization of the product

Value ndash Price ndash Cost (VPC) framework

Customer Surplus vs Producer Surplus

17

Price

Value

Cost

Consumer

Surplus

Producer

Surplus

Wikipedia (2016)


製造智慧決策

18

Source International SEMATECH e-Diagnostics and EEC Guidance 2003

Predictive Maintenance (PdM)

SPC APC VM RMS

Carbon

Emission

Water

Recycle

Laser Vision Guidance WiFi-based Positioning

Energy

MgmtProactive Decision

(Prediction+Optimization)

VRARAI

Cloud

Computing

Cyber-

Physical

System

Prognostic amp Health Management (PHM)Dashboard

RFIDSmart Labels

Inductive Dynamic Wireless Charging

Unmanned GroundAerial Vehicle (UGVUAV)

Self-Maintenance Engineering Immune Systems


Difference between Manufacturing and Service

Now manufacturing system moves toward service system

Manufacturing vs Service

System Manufacturing Service

Input Material Labor

ProcessCapital-intensiveBuild SOP

Labor-intensiveBuilding SOP is difficult

Output Physical product

IntangibleNon-separableNon-stableNon-storableTime-concerned

feedbackQuality ControlPerformance criteria

Difficult to measure quality and performance


Manufacturing system vs Service system

Main difference is ldquoInventoryrdquo

Inventory

Raw materials Components Work-in-process (WIP) Finished goods

Capacity + Lead Time + Uncertainty = Inventory

Inventory Reduction

Reduce material and production lead time (includes transport)

Reduce information delay times (長鞭效應 Bullwhip effect)

Improve quality of information (reduce uncertainty)



半導體製造管理指標

Chien et al (2004)


Why is it difficult to manage a

manufacturing systems

22


Diverse Resources and KPIs (資源與KPI的多樣性)

23

簡禎富胡志翰(2011)


管理階層與製造現場間目標的衝突 (ICT 系統導入的挑戰)

24

ProfDr Engelbert Westkaumlmper Fraunhofer IPA Stuttgart Germany ldquoFactories of the Future beyond 2013 The role of ICTrdquo

httpcordiseuropaeufp7ictmicro-nanosystemsdocsfof-beyond-2013-workshopwestkaemper-manufuture_enpdf

目標的衝突為了營收與價格維持rarr差異化 (少量多樣)

為了效率與品質要求rarr低成本 (大量生產)


Variability is anything that causes the system to depart from

regular predictable behavior

Sources of Variability

setups workpace variation

machine failures differential skill levels

materials shortages engineering change orders

yield loss customer orders

rework product differentiation

operator unavailability material handling

Variability (變異)

Variability from Resource


迷思變異不確定性

現場「變異(variability)」是不好的

26

但沒有變異如何rdquo改善rdquo

就如同考試成績有好有壞才能對症下藥~



其實hellip

變異某種程度上也代表了rdquo資訊量rdquo

27

English Math

Student_A 80 76

Student_B 80 91

Student_C 80 83

Student_D 80 62

Student_E 80 88

Layer X Layer Y

Machine_A 81 76

Machine_B 80 91

Machine_C 79 83

Machine_D 80 62

Machine_E 82 88

Benchmarking Learn from the BEST PRACTICE

來自於變異


生產規劃與控制

製程控制生產管理

MES

APC

FDC

SPC

VM

R2R

RMS

Preventive Maintenance

Predictive Maintenance

Yield Management

hellipetc

Demand Forecast

Long-Run Capacity Planning

Short-Run Capacity Planning

CapEx

Cost Structure

MPS amp MRP

Scheduling amp Dispatching

Inventory Management

Order Releasing

hellipetcQuality

Productivity

Cost Down

Cycle Time

28


CIM and Automation

29

Waldner Jean-Baptiste (September 1992) Principles of Computer-Integrated Manufacturing London John Wiley amp Sons pp 128ndashp132

ISBN 0-471-93450-X

Digital Twin Operation Automation

Replace Human Efforts

Benefits

Reduce HR Cost

Reduce MO

Improve CT and Improve

Productivity

Engineering Automation

Support Engineer for decision-

making or trouble-shooting

Benefits

Sustain EQ variance

Improve quality amp Yield

Support RD

Reduce Engineering Cost

Improve Time-to-Market


CIM and Automation

30王邦明 2012半導體生產自動化與智慧工廠 httpwwwdigitimescomtwtechb2bseminarservicedownload051a105220051a105220_ep3lyifjml6ggy8h5s4vpdf


自動化並不全然意味著大量投資

機器人與設備hellip

31


事實上自動化是製造哲學上的

轉變hellip

透過消除浪費降低產線不平衡

達到生產標準化且具有彈性的

一種改善過程

32


Lean (identify non-value-added process and remove it)

Value and Conflict Value Stream Mapping (VSM)

Waste elimination (8 muda Womack and Jones 2003)

1 Transportation

2 Inventory

3 Motion

4 Waiting

5 Overproduction

6 Overprocessing

7 Defects

8 Eschewed Talents

Continuous flow

Line Balancing

Pull production system

Lean Manufacturing

不要把浪費自動化了

33

組織演化與新制度的建立

AI並非取代人力hellip

人機共存相輔相成


CIM and Automation

34

AMHS

MES APC

FMEC

On-Time Delivery Quality amp Efficiency

Cycle Time Reduction Green Environment

Big Data

Analytics

KNOWLEDGE DISCOVERY IN DATABASES (KDD)

Data

Warehouse

Knowledge

Source rdquoFrom Data Mining to Knowledge Discovery An Overviewrdquo Advances in Knowledge Discovery and Data Mining AAAI PressThe MIT Press 1996

Selection

Preprocessing

Target Data

Preprocessed

Data

Pattern

Transformed

Data

Data Mining

Transformation

Interpretation

Evaluation

ETL (Extract-Transform-Load)

Storage and Calculation

IT Infrastructure

Pattern Extraction

Value Interpretation for Profitability

Business Applications

35

Edge

Computing


How to improve a complex

manufacturing system

Pittsburgh Technology Council (2014) httpwwwpghtechorgmedia64942panoupdatedjpg


Get to the ldquoBottomrdquo of Our

Problems

(問題本質的探索)

(The Characteristics of Manufacturing)


製造現場

Manufacturing Field (problem clarification)

Ask ldquoWhyrdquo in shop floor level (在製造現場問rdquo為什麼rdquo)

一言九鼎(頂)

No support (labormachinematerialmanagementsupplierinventoryhellip)

Manufacturing Dataset (data for analysishellipbut no data)

Ask Why

I donrsquot knowhellipno ideahellip

Long long time agohellip

No one take over the hellip

None of my businesshellip

Please ask somebodywindowdeptsupplierbusiness(competitor)

I am the newcomerhellip

Data is not accurate becausehellip

38


生產線數據

Data Type in Manufacturing

39

Type Example Represented(feature-to-response)

Characteristic

Pure Feature-

Value 119909(one-to-one)

bull Cross correlation

(between features)

Signals and Vibrations Vector 119961 = 119891(119905)(many-to-one)

bull Temporal correlation

bull Functional structure

bull High-dimensional

Multichannel Signals

and Grayscale Images

Matrix 119935(many-to-one)

bull Spatial correlation



Color Images 3D

Scans and Videos

Tensor 120039(many-to-one)

bull Temporal-spatial

correlation



Paynabar K (2019) Data science for manufacturing automation low dimensional learning from high dimensional data

IEEE CASE 2019 Data Science Workshop


製造現場與其資料特性

40

Characteristics Data amp Management Issues

Batch size (生產批量) Lot ID decomposition lot tracing mergesplit

Parallel machine (平行機台) Missing value high dimension multicollinearity

Golden machine (黃金機台) Utilization class imbalance rarr Inference bias

Recipe and parts(處方與零件)

Nominal or categorical variable rarr too many levels rarr too many dummy variables rarr high dimension

Sampling testing (抽樣檢測) Missing value multi-response delay figure (AOI)

Engineering or RampD lot (工程與實驗貨)

Outlier machine contamination setup capacity loss small dataset

Maintenance (維修保養) When how (大保養 or 小保養) capacity loss reliability typing error text choosing ldquoothersrdquo

Changeover (換線換模) Sequence-dependent setup time capacity loss

Bottleneck shift(瓶頸站轉移) Different treatment WIP transfer product-mix

Queue time limit(等候時間限制) Defects WIP

Data imbalance (資料不平衡) Inference bias Inventory = Lead Time + Uncertainty

Lee and Chien (2020)


製造數據科學要做到hellip

看到資料就能對應到現場的

特性與問題


Knowledge Discovery in Databases (KDD)

Data Analytics Framework

Data Preprocessing

42

Data

Warehouse

Knowledge

Selection

Preprocessing

Target Data

Preprocessed

Data

Pattern

Transformed

Data

Transformation

Data Mining

Interpretation

Evaluation


混批拆批併(合)批 Data Merge (trace back for recipe diagnosis)

良率計算 (yield calculation)

Lot ID Sub Lot IDInspectionPass or Fail

Lot001 Lot001 Pass

Lot002 Lot002_1 Pass

Lot002 Lot002_2 Fail

Lot003 Lot003_1_1 Pass



平行黃金處方抽樣 RampD 維修換模等候合併不平衡瓶頸混批

Lot ID Pass or Fail

Lot001 Pass

Lot002 Pass

Lot003 Fail

Lot004 Pass

Lot ID Pass or Fail Lot size

Lot001 Pass 20

Lot002 Pass 25

Lot003 Fail 10

Lot004 Pass 15

75 857

Lot ID WS1_A WS1_B WS2_A WS2_B hellip

Lot002 hellip

Sub Lot ID WS7_A WS7_B

Lot002_1

Lot002_2


Parallel Machine

Not identical (有機差) rarr Tool Matching

Data Preparation

Missing Value

44

Lot IDWS_A_Mach_1_Temp

WS_A_Mach_2_Temp

Lot001 820 NA

Lot002 820 NA

Lot003 NA 840

Lot004 NA 840

Lot IDWS_A_Temp

WS_A_Mach_Type

Lot001 820 1

Lot002 820 1

Lot003 840 2

Lot004 840 2

WS_A_Mach_1

WS_A_Mach_2

混批黃金處方抽樣 RampD平行維修換模等候合併不平衡瓶頸


Golden Machine

推論的偏誤 (inference bias)

Missing Value

45


WS_A_Mach_2_Temp

Lot001 820 NA

Lot002 820 NA

Lot003 820 NA

Lot004 830 NA

Lot005 820 NA

Lot006 820 NA

Lot007 825 NA

Lot008 830 120

Lot009 820 130

Lot010 NA 120


WS_A_Mach_2_Temp

Mach_1 Mach_2

Lot001 820 Avg 1 0

Lot002 820 Avg 1 0

Lot003 820 Avg 1 0

Lot004 830 Avg 1 0

Lot005 820 Avg 1 0

Lot006 820 Avg 1 0

Lot007 825 Avg 1 0

Lot008 830 120 1 1

Lot009 820 130 1 1

Lot010 Avg 120 0 1

混批平行處方抽樣 RampD黃金維修換模等候合併不平衡瓶頸


Recipe Parts- Nominal (名目) or Categorical (類別) Variable

Transfer to dummy variable (啞變數虛擬變數) (One-hot encoding)

Given N levels the method will generate N-1 dummy variables

46

Lot IDWS_A_Mach_1_Parts

Lot001 PartsA

Lot002 PartsB

Lot003 PartsA

Lot004 PartsC

Lot005 PartsD

Lot006 PartsE

Lot007 PartsB

Lot008 PartsA

Lot009 PartsC

Lot010 PartsE

Lot IDWS_A_Mach_1_PartsA

WS_A_Mach_1_PartsB

WS_A_Mach_1_PartsC

WS_A_Mach_1_PartsD

Lot001 1 0 0 0

Lot002 0 1 0 0

Lot003 1 0 0 0

Lot004 0 0 1 0

Lot005 0 0 0 1

Lot006 0 0 0 0

Lot007 0 1 0 0

Lot008 1 0 0 0

Lot009 0 0 1 0

Lot010 0 0 0 0

混批平行黃金抽樣 RampD處方維修換模等候合併不平衡瓶頸


某類別變數level過多 (Recipe or Parts數目過多)

轉成Dummy Variables會產生許多新變數

Issue Curse of Dimensionality (維度的詛咒)

建議方式

將部分level整合 (grouping)

eg 產品rarr產品族

eg tool rarr tool group

選取特定時間區間的資料進行分析

降低該變數level的數目

將某類別中只有出現一次觀測值的level刪除

沒有再現性

47



抽樣檢測

48

混批平行黃金處方 RampD

手機外殼(同產品)

材質供應商 hellip 長度檢驗寬度檢驗

NO001 鋁 A 13723 7235

NO002 鋁 B NA NA

NO003 鋁 B 13728 7237

NO099 鋁 B NA NA

NO100 鋁 A 13726 7236

X Y (抽檢)

沒被抽檢

沒被抽檢

抽樣

填補遺漏值

Skills of missing value imputation

1 平均數四分位數眾數2 K-Nearest NeighborsInverse Distance Weighting

3 Prediction Model

httpwwwtheanalysisfactorcomseven-ways-to-make-

up-data-common-methods-to-imputing-missing-data

維修換模等候合併不平衡瓶頸


實驗貨工程貨主要是研發產品或機台測試校正用資料上有時會呈現Outlier

若針對一般性產品資料分析需要在分析前先濾掉或移除

一般而言有特殊的LotID在收集資料時可先過濾掉或在預處理中進行若無給定特殊LotID那需要在資料中觀察例如使用特殊機台特殊recipe該產品只經過某些特定製程等

49

混批平行黃金處方抽樣維修換模等候合併不平衡瓶頸RampD

特性階段實驗貨工程貨一般正常貨

資料量剛起步較少 (nltltp) 較多 (大量生產) (ngtgtp)

資料數值實驗設計參數較分散很多參數已成為定值

成本需要反覆試驗較高大量生產較低

良率較低較高且穩定

分析方法最佳化方法無母數實驗設計

田口方法LASSOSVMForward Stepwise

有母數GLMRandom

Forests Boosting Deep

Learninghellip


換線換模

當產線要生產不同的產品時會針對機台進行換線模的動作

同樣產品類型的儘可能排在一起以減少換模(線)次數

以大批量生產的方式分攤換模(線)的時間

大批量生產方式會增加無訂單的庫存因此必須預估數量設定

經濟生產批量(Economic Lot Sizing)rdquo來因應

50

Machine A A A

setup time for changeover

Machine A B


B B B

A B A B

cycle time reduction

混批平行黃金處方抽樣 RampD 維修等候合併不平衡瓶頸換模


總完工時間(makespan) vs 換模次數

原則上換模次數愈少makespan下降然而hellip當有大單時hellip

需留意多個平行機台(parallel machine)進行排程時的取捨(tradeoff)

資料會反應這件事情

不單只是排程良率也會因換模狀況而有所改變

51

MachineI2

A A AMachine1

B B


A A A

Machine2

A A AMachine1

A A A

B

B

總完工時間較長換模次數2

總完工時間較短換模次數4


瓶頸 (bottleneck)

一般來說瓶頸機台常是利用率高且週期時間長的機台rarrWIP堆積多

內部瓶頸特定機台或工作站的產能限制

薪資水準或工作環境無法吸引到優秀員工

搬運運輸物流形成為生產的瓶頸

現場管理團隊能力生產規劃團隊的排程規劃

管理階層對於系統產能不正確假設認知

52

混批平行黃金處方抽樣 RampD

120

unitsday

140

unitsday

80

unitsday

120

unitsday

100

unitsday

瓶頸

80 unitsday

外部瓶頸原物料的供應

特定區域的人力供給

(勞工和幹部)

公司產品的品牌知名度

公司產品的配銷通路

楊大和(2016)



等候時間限制 (Queue Time Limit)

由於半導體製程晶圓表面上為化學物質若長期曝露於一般空氣中會造成氧化反應而導致缺陷(defect)產生

為了避免在製品於生產線上等待過久而造成製程缺陷會根據製程與產品特性在特定製程完成加工之後規定等候時間的限制（Queue Time

Limit）以維持產品良率為了延遲此限制多於FOUP中填充惰性氣體

等候時間若發生在批次工作站(例如爐管製程 furnace)問題可能更嚴重對於到達此工作站之晶圓除了需要等前一批次加工完還需要另外等候集批(Form Batch)換言之需要等待多個批量後(有相同的recipe製程條件)該工作站才進行作業此加工型態會造成產品的等候時間過長甚至超出等候時間限制而造成不良品產生

通常可計算Qtime當作獨立變數(x)來對良率(y)進行建模以瞭解Qtime長短如何影響良率的情況

estimated by the difference between check-out of A and check-in of B

53

混批平行黃金處方抽樣 RampD 維修換模合併不平衡瓶頸等候



假設某產品A規定在每個stage加工後等候時間限制為1小時就需要進入下一站若發現等候時間異常且超過等候時間限制須立即通報以免不良品往下游輸送

54

IDProduct

TypeStage

Process

Time (hrs)

Start

Time

Lot1 A 1 1 20161226 1450

Lot1 A 2 1 20161226 1600

Lot1 A 3 05 20161226 1720

Lot1 A 4 1 20161226 1800

Lot1 A 5 05 20161226 2030

等候超過1小時rarr Alarm



資料合併表單串接 ndash 注意必須為相同的欄位名稱 ie KEY

Key通常為Lot ID Machine ID等

兩種不同類型的資料紀錄該如何合併串接呢 Which one could be ldquoMain Tablerdquo

55

Time SVID 101 SVID102 hellip

211 000000

211 010000

211 020000

211 230000

Time SVID 1 SVID 2 hellip

211 000629

211 001041

211 034109

211 231157

Period-based recordEvent-based record

混批平行黃金處方抽樣 RampD 維修換模等候合併不平衡瓶頸


Data Merge

56

比較表以 Event 為基準做串聯以 Periodic 為基準做串聯

記錄方式有rdquo事件rdquo才記錄例如機台換模停機人為調機等

固定rdquo週期rdquo記錄例如1小時一次

串接前表單特性

資料筆數通常較少且稀疏資料筆數通常較完整

串接後優點資料較完整(串接後可能遺漏值較少)

可觀察週期性變化

串接後缺點可能有某rdquo長rdquo時間區段無資料資料可能有部分缺失(串Event會造成大量遺漏值)

建議串接方法

Rolling Forward

Nearest time

Rolling Forward

Rolling Backward

Nearest time

目的或使用時機

Troubleshooting Monitoring


Lee and Dong (2019)


維修保養(調機)

定期保養 (年保季保月保機台生產10000產品hellip)

若有收集保養資料可直接找出保養時間點若無可藉由推估

機台up與down的時間 (Overall Equipment Effectiveness OEE)

產品的queue time

機台參數(eg status variable identification SVID)的監控

再與相關部門(例如設備)進行確認

57

STA

GE

x_S

VID

x

0 5

10

1

5

2

0

2

5

0 200 400 600 800 1000Lot or

Time

混批平行黃金處方抽樣 RampD 換模等候合併不平衡瓶頸維修


維修保養troubleshooting

機台故障表單 + MES (含Recipe跟使用的零組件材料) + 良率

針對某一機台ID用rdquo時間rdquo進行資料的合併串接

58


Time Downcode

Repair Recipe Part Material Yield

2017-05-07140528

Run No或NA Recip18 Part01 Mater05 943

2017-05-07161214

Run No Recip18 Part01 Mater05 931

2017-05-07174130

Down04 Part19(換零件)

hellip Recip18 Part19 Mater05 hellip 825或內插

2017-05-07192243


2017-05-07201817


機台故障表單 MES 良率

931 times 17 41 30 minus 16 12 14 + 825 times 19 22 43 minus 17 41 30

19 22 43 minus (16 12 14)

換模等候合併不平衡瓶頸維修


DataClass Imbalance原因 of qualified product extremely dominates the of defective product

資料不平衡大多發生於類別型態的資料上(一般泛指兩類) 若以連續分佈的資料來說資料不平衡代表資料可能集中在某些區段而這些區段也可以稱作rdquo群類別rdquo

資料不平衡的情況可能出現在獨立變數或是相依變數

資料多不平衡才算不平衡

For the two classes (0 and 1) rule of thumbhellip

10 vs 90 5 vs 95 or 1 vs 99

It dependshellip on your industry applications

From a theoretical viewpoint it occurs if it skews the model training for

predictionhellip

也就是說如果你訓練的模型準確率rdquo異常地高rdquo

Overfitting Class Imbalance

59



Lot ID X1 hellip X100 Inspection

Lot01 PASS

Lot02 PASS

Lot03 PASS

Lot04 PASS

Lot05 PASS

Lot06 PASS

Lot07 FAIL

Lot08 PASS

Lot09 PASS

Lot10 PASS

Lot11 PASS

Lot12 PASS

預測Inspection的結果

由於只有1筆FAIL

預測模型全部都猜PASS

不需要分析變數X1~X100

準確度可達 1112 = 917



迷思

攝氏溫度200度是100度的兩倍

61


資料整合與清理

62

問題原因步驟不正確的資料資料的值超出合理範圍

資料整合

不一致的資料不同來源資料整合後所出現的分歧數值不一致資料內容不一致欄位不一致

重複的資料(Duplication)

重複記錄的欄位或數值(data type single doublehellip) (同樣的資料卻不同的寫法ldquo做了36顆rdquo ldquo打出36粒rdquo ldquo生產36個rdquordquo左上角區塊有產生defectsrdquo ldquodefects發現於左上方區域rdquo)

冗餘的資料(Redundant)

出現相同意義的資料或欄位具有相同意義或彼此間存有已知數學關係的欄位此變數的屬性或意義可由另一變數推導而得 (有些冗餘資料可以經由相關分析偵測到) eg 地址vs地區

遺漏值量測設備或人為因素所造成的資料遺漏

資料清理雜訊資料本身的誤差或資料輸入的偏差

離群值資料本身的特性不當量測或資料輸入錯誤

資料尺度不適資料格式不符合挖礦工具的假設資料轉換(正規化)

資料太多資料或維度過高資料化約

(簡禎富許嘉裕2014)


迷思補遺漏值

遺漏值填補是hellip補「資料」

63

English Math

Student_A 80 76

Student_B 80 91

Student_C 80 83

Student_D 80 62

Student_E 80

Avg 80

Max 91

Min 62

Avg 78


迷思補遺漏值

64

填補遺漏值一般會造成部分失真或偏差

使用者應根據製造rdquo資料特性rdquo以及rdquo分析目的rdquo來決定填補遺漏值的方法以避免忽略原本應有的資訊

方法(補值一定要找關係)

忽略變數值 (ldquoNArdquo 與 ldquo0rdquo 是不一樣的)

移除觀測值 (remove the tuple)當依變數Y遺漏時

人工填寫遺失值

使用一個全域常數填充遺漏值 (eg NA)

使用屬性平均值

使用與給定變數值屬於同一類別的所有樣本之平均值

模型簡單多元線性迴歸類神經網路最鄰近估計法K-Nearest

Neighbor (KNN) Random Forest rdquoMICErdquo Inverse Distance

Weighting (IDW)hellip

64


補值一定要找關係

利用其他變數與遺漏值之間的關係來估計遺漏值

補值可利用其他變數與遺漏值之間的關係來估計遺漏值

例如若「收入水準」變數發生遺漏值或許可能用「房子坪數」這變數來做預測

假設在現有的資料庫中發現某一顧客其購買反應的態度為一遺漏值

顧客性別年齡薪水購買反應A 女 27 $19000 No

B 男 51 $64000 Yes

C 男 52 $105000 Yes

D 女 33 $55000 Yes

E 男 45 $45000 No

F 女 45 $100000

最鄰近估計法 (Nearest Neighbor Estimator)

65


最鄰近估計法K-Nearest Neighbor (KNN)

66

K=3

K=5

Wikipedia httpszhwikipediaorgwikiE69C80E8BF91E984B0E5B185E6B395

perClass 2017 kb16 Visualize the effect of a change of parameters in a trained classifier httpperclasscomdockb16html


迷思補遺漏值

67

觀測值原始資料值第 11筆遺漏利用平均數估計利用標準差估計

1 00886 00886 00886 00886

2 00684 00684 00684 00684

3 03515 03515 03515 03515

4 09874 09874 09874 09874

5 04713 04713 04713 04713

6 06115 06115 06115 06115

7 02573 02573 02573 02573

8 02914 02914 02914 02914

9 01662 01662 01662 01662

10 044 044 044 044

11 06939 03731 06622

平均值 04023 03731 03731 03994

標準差 02785 02753 02612 02753

誤差值 03208 00317

不偏估計量 vs變異程度



數據品質

68

數據理解就是選取資料(範圍)資料異質資料品質數據維度

檢視量化資料的三個維度樣本個數(n)變數特徵個數(p)異質性

一個母體平均數的單尾檢定時當樣本數佔母體總數的比例R=80時顯著水準005 要調整為00001 (馬瀰嘉2019)

樣本大到接近母體不需要檢定直接敘述統計視覺化

變數太多造成維度過高使分析時間過長rarr維度詛咒

資料品質

Univariate

Statistics mean(median mode) variance skewness kurtosis

Visualized plot missing values noise outlierhellip

Regression 119910 = 1205730 + 120573119894119909119894 + 120576 Check 120573119894 violating the engineering experience

Eg Milling time (x) and thickness (y) should be with negative 120573119894

Multiple Column

Correlation or Covariance between two variables

Eg machine temperature vs utilization is positive

Validity and Reliability (信度與效度)

數據品質


數據品質企業系統長期累積的積習hellip

69

httpsstackoverflowcomquestions23660839need-help-on-an-er-diagram-for-an-automobile-company

Data Quality Investigation- Entity-Relationship (ER) Model

Automobile Company

Metadata It describes the

types versions relationships

and other characteristics of

digital materials


ldquoIn God we trust all others must bring datardquo- Edward Deming (1900-1993)

ldquoWhat gets measured gets managedrdquo- Peter Drucker (1909-2005)


重要參數篩選與精度預測


71


當接起電話常聽到的議題hellip

老師hellip大家正在談工業40我老闆想做所以hellip

老師hellip如何觀察產線上不易察覺的浪費

老師hellip庫存或在製品WIP太多該如何處理

老師hellip機台稼動率不高怎麼辦

老師hellip我們想做排程 (或想替代現有的人工排程)hellip

老師hellip需求該如何預測

老師hellip我有一堆資料來Mining一下吧~

老師hellip製程影響因子太多如何找出關鍵因子

老師hellip資料量太大了無法分析(一秒25600筆資料hellip)

老師hellip我不敢刪資料因為怕失真但是又太大了hellip

老師hellip模型挑選關鍵參數與工程經驗不一致如何處理

老師hellip資料量少因為現場都是有問題後才開始收集資料

72


Process Diagnosis Troubleshooting

(製程診斷)案例一

QualityYieldSpec Prediction

(良率精度預測)案例三

Feature Selection

(重要工程參數篩選)案例二


(預測保養)案例四


案例一製程診斷

74

案例1 Process Diagnosis Troubleshooting (製程診斷)



半導體製程良率的挑戰生產製程冗長且複雜前後製程具交互影響

線寬的微縮製程容忍度下降

人機料法AMHS的整合困難

量測機台的有限產能及生產週期時間(cycle time)的要求採用抽樣檢測(sampling)的方式不易即時偵錯

75

材料

設計

光罩

積體電路生產廠房

測試

封裝

最後測試

加熱製程

微影製程

離子佈植

金屬化化學機械研磨

介電質沉積

晶圓

蝕刻與光阻剝除

Over 1000 stages

蕭宏(2004)半導體製程技術導論Prentice Hall



Wafer Bin Map (晶圓圖分類)

Wafer bin maps that show specific spatial patterns can provide clue to

identify process failures in the semiconductor manufacturing

In practice most companies rely on experienced for troubleshooting

However as IC feature size is continuously shrinking WBM patterns

become complicated and thus human judgments become inconsistent

and unreliable

In the semiconductor fabrication process the circuit probe (CP) test is

used to detect specific failures of each die and thus indicate the test

results with the corresponding bin values

76

(Liu and Chien 2013)



77


Root Cause As-Is

Engineering Experience

Troubleshooting Team

To-Be

Data Science

Automation


分群 (Clustering) (eg Wardrsquos Method華德法 1963)

群內相似度高群間相似度低

空間統計量 The spatial correlation of two groups of data can be tested by the odd

ratio hypothesis test

H0晶圓圖上故障晶片或正常晶片呈現隨機

H1呈現非隨機分佈 (即發現有特殊群聚或是離散現象出現)


78

K

C

H

E

A

G

I

J

F

L

OR

DS

BP M

N

Q

(Hsu and Chien 2007)



分類 (Classification) (eg分類與迴歸樹 CART Breiman et al 1984)

決策樹 Decision Tree

Rule Extraction

If Temp le 580degC then ldquoBadrdquo (Accuracy 100)

If Temp gt 580degC and Parts_xxx= 1 then ldquoBadrdquo (Accuracy 100)

If Temp gt 580degC and Parts_xxx= 0 then ldquoGoodrdquo (Accuracy 96)

79

Good 68 68

Bad 32 32

Good - -

Bad 23 100

Good 68 88

Bad 9 12

Good - -

Bad 6 100

Good 68 96

Bad 3 4

Temp gt 580degCTemp le 580degC

Parts_xxx= 0 Parts_xxx= 1

1 愈往上層因子愈重要2 考慮因子間交互作用


OK

NG

NG

NG

NG

NG NG NG

OK

OK

OKOK OKOK

NG

YES NO

YES

YES YES

YESYES

YES

NO

NO

NO

NO NO

NO

80

Map clustering for

systematic defects

12 defect patterns

and build WBM bank

Decision tree for root

cause identification



(Lee and Tsai 2019)



81

SPC製程監控Defect Wafer

(Lee et al 2020）自動化工程系統

故障診斷與模式建構

(Wang2012）

良率提升方法論

12 Data preprocessing

14 Median for Centerline

13 Training amp testing data

29 Alarm

16 Prediction model

training

15 EWMA for Target

Baseline (TB)

22 Distance calculation

between Prediction and TB

24 Predicted

CUSUM out of

control

25 Pre-alarmYes

No

28 Actual

CUSUM out of

control

Yes

No

23 CUSUM control chart

21 New sample

prediction


between Actual and TB

17 Model validation

34 Continuous

monitoring

11 Data collection

26 Engineering

Validation amp

Troubleshooting

31 Loss calculation

between Prediction and Actual

32 CUSUM

control chart

33 Loss

CUSUM out of

control

310 Add new samples

in ILPM training data

311 ILPM model

retraining mechanism

Yes

Off-line training

In-line prediction

Concept drift

Pre-alarm stage

Alarm-confirm stage210 Alarm confirmation amp

correction

No

All good products

37 Bayesian

monitoring out

of control

35 Equipment

parameter monitoring

Phase I- Process Parameter Monitoring Phase II- Equipment Parameter Monitoring

39 Update posterior

in Bayesian monitoringNo

38 Alarm and

equipment

maintenance

Yes

Model misalignment

(predicted value error)

Equipment

misalignment

(actual value error)

36 Lifetime

out of control

No

Yes



82

標準化(standardization)rarr制度化(institutionalization)

降低浪費標準化與制度化rarr成本降低cost down

Wikiwand (2016) httpwwwwikiwandcomenPDCA

Continuous Improvement by PDCA


Convolutional Neural Network (CNN) Fault Diagnosis

83

Padding for control the size of feature dimension and the

zero-padding for preventing the dimension loss

Wen L Li X Gao L and Zhang Y 2018 A new convolutional neural network-based data-driven

fault diagnosis method IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS 65 (7) 5990-5998

Self-Priming

Centrifugal Pump


案例二重要參數篩選與特徵工程

84




Feature Selection

Feature Engineering

85

Data

Warehouse

Knowledge

Selection

Preprocessing

Target Data

Preprocessed

Data

Pattern

Transformed

Data

Transformation

Data Mining

Interpretation

Evaluation


案例2 Feature Selection (重要參數篩選與特徵工程)

為什麼要選重要參數因子

易於決策判斷

看rdquo____rdquo就知道要不要決定出去旅遊

看rdquo____rdquo就知道這衣服適不適合

量rdquo____rdquo就知道身體健康狀況

製造現場篩選重要因子的目的 Troubleshooting

掌握影響機台品質變異的主要因子上下游因子的交互作用

Engineering Process Control (EPC)

建立管理機制簡單法則

看Bottleneck就可推估現場WIP level

精度預測

提升預測準確度

On-line real-time prediction

監控Monitoring rarr用較低成本較少管制圖

環境因子監控機台參數監控

86


案例2 Feature Selection (重要工程參數篩選)

Feature Selection

In a large-scale dataset select a few important variables (ie columns)

In particular of variables (p) much larger than of observations (n)

ie p gtgt n issue

Address ldquoCurse of Dimensionalityrdquo

The number of observations required exponentially grows to

estimate the function or model parameters

87

An

p

Xn

k k ltlt p



Objective (Guyon and Elisseeff 2003)

improving the prediction performance of the predictors

providing faster and more cost-effective predictors

providing a better understanding of the underlying process that

generated the data (eg for process monitoring)

Types

FeatureVariable selection select the ldquobestrdquo subset of the existing

variablesfeatures without a transformation

Supervised Learning (監督式學習) with ldquoYrdquo as label

Eg stepwise regression LASSO random forest etc

Dimension Reduction (feature extraction variable transformation)

transforming the existing variables into a lower dimensional space

Unsupervised Learning (非監督式學習) with only ldquoXrdquo

Eg independent component analysis (ICA) principal component analysis

(PCA) etc

88



篩選原則(Selection Principle)

Mutually-Exclusive Collectively-Exhaustive (MECE) Feature Selection

claims that the important variables should not contain overlapping

information and should provide sufficient information

89

Lee and Chen (2018)



90

Prepared

Dataset

Feature

Selection

LASSO SVMStepwise

Regression

Voting

by Sampling or K-fold Cross-Validation

Pivot

Analysis

Engineering

Experience

Feature

Validation

BoostingRandom

ForestPCA Random

Sampling

Data

Reduction

(pgtgtn)

Imbalance

Correlation

Coefficient

Independence

Testhellip

Data

Preprocessing

hellip

Yes

No

Knowledge

Management (KM)

Documentation

Lee and Tsai (2019)

iterative

process



變數挑選的邏輯天下雨rarr地濕 (若A則BA稱為B的充分條件B稱為A的必要條件)

地濕rarr不一定天下雨 (B不一定則A)

地沒濕rarr天一定沒下雨 (非B則非A)

同理hellip

因果rarr相關

相關rarr不一定因果

沒相關rarr絕對沒因果

結論當變數欄位太多時可試著透過X跟Y的相關係數來刪除低相關的變數

欄位 (強假設因子之間無交互作用)

接著應該做實驗設計(DOE)Fused LassoTree-based Method etc

確認交互作用影響

91

(Lee and Chien 2020)



Stepwise Regression (ie 逐步迴歸) (Hocking 1976)

Starting with no variables in the model then adding the variable (if any)

that improves the model the most (with smallest p-value)

Forward selection (119910 1199091 1199092 1199093 1199094)

92

119910 = 120572 + 1205731199091 + 120576

119910 = 120572 + 1205731199092 + 120576

119910 = 120572 + 1205731199093 + 120576

119910 = 120572 + 1205731199094 + 120576

119910 = 120572 + 12057321199092 + 1205731199091 + 120576

119910 = 120572 + 12057321199092 + 1205731199093 + 120576

119910 = 120572 + 12057321199092 + 1205731199094 + 120576

119910 = 120572 + 12057321199092 + 12057341199094 + 1205731199091 + 120576

119910 = 120572 + 12057321199092 + 12057341199094 + 1205731199093 + 120576

統計顯著的變數1199092 and 1199094


LASSO Regression (Tibshirani 1996)

መ120573119897119886119904119904119900 = argmin120573

σ119894=1119873 (119910119894 minus 1205730 minus σ119895=1

119875 119909119894119895120573119895)2

Subject to σ119895=1119875 120573119895 le 119905

Lagrangian form መ120573119897119886119904119904119900 = argmin120573

1

2σ119894=1119873 (119910119894 minus 1205730 minus σ119895=1

119875 119909119894119895120573119895)2 + 120582σ119895=1

119875 120573119895

93


Penalty( 120582 ) x1 x2 x3 x4 x5 x6 x7

120582 = 0

120582 = 40

120582 = 418

120582 = 419

120582 = 42

120582 = 50

Shrinkage Factor s= 119905σ119895=1119875 መ120573119895

Lee and Cai (2019)Hastie et al (2008)



94

httpswwwkdnuggetscom201710random-forests-explainedhtml

x12

x11

x10

x9

x8

x7

x6

x5

x4

x3

x2

x1

Feature Importance



Voting (投票法)

When using several selection methods calculate the selecting

frequency for ldquorobustrdquo variable selection

95

SVID Stepwise LASSORandom

ForestBoosting Voting

SVID_003 4

SVID_101 3

SVID_021 3

SVID_040 3

SVID_002 3

SVID_128 2

SVID_062 2

SVID_077 2

hellip hellip hellip



K-fold Cross Validation

eg 10-fold cross validation

96

Test

Test

Test

Test

training fold testing fold

1st iter

2nd iter

3rd iter

10th iter

hellip

Error1

Error2

Error3

Error10

Minimize Error=1

10σ119894=110 Error119894



97

Class Imbalance Solutions

Undersampling

samples a subset of the majority class Due to ignoring many majority class

examples we generally sample several times (resampling)

Example

For Y label 良品 vs 不良品 = 1000 50

Samples 50 良品 at a time for model training

of replications 20 times

Rank the variables by the ldquovotingrdquo

Hint 11 can be properly extended to 51

Oversampling (eg SMOTE)

Others cost-sensitive ensemble-based autoencoder GANhellip

SVIDVoting by

Undersampling

SVID_003 19

SVID_101 18

SVID_021 18

SVID_040 18

SVID_002 17

SVID_128 17

SVID_062 17

SVID_077 17

hellip hellip



Feature Selection by Pivot Analysis (樞紐分析)

98

SVID 良品_Avg 不良品_avg RangeAvg

SVID_003 09487 02583 11439

SVID_101 02078 05434 08934

SVID_021 04105 08377 06845

SVID_040 5208 7169 03170

SVID_002 27256 21025 02581

SVID_128 80523 85336 00580

SVID_062 09430 09747 00330

SVID_077 1569 1603 00216


Mach_ID FAIL TOTAL RATIO

Photo_06 12 384 00313

Etch_10 3 295 00102

Photo_32 10 1011 00099

Photo_17 4 410 00098

PVD_02 1 123 00081

CVD_14 9 3456 00026

Diff_09 1 495 00020

Etch_07 5 2769 00018


只有1筆沒有rdquo再現性rdquo

良品119886119907119892 minus不良品119886119907119892

119860119907119892

RATIO = FAIL TOTAL



Engineering Experience Validation (工程驗證)

重要工程參數的說明變數名稱物理意義幾何圖形調升與調降如何影響製程結果Y

99

Silicon etch rate in cryogenic

etching process versus O2

percentage in the SF6O2 gas

mixture or O2 gas flow

Smyrnakis A Almpanis E Constantoudis V Papanikolaou N and Gogolides E Optical properties of high aspect ratio plasma

etched silicon nanowires fabrication-induced variability dramatically reduces reflectance Nanotechnology vol 26 no 8 085301 2015


迷思

愈重要的工程參數(變數)

統計方法愈容易找出來

100

How about 某一個欄位所有的觀測值都一樣hellip


Feature Engineering

is to manipulate the new feature manually from the original features

Temporal Features 時間特徵

For date time we can transform to timestamp and extract ldquodayrdquo ldquomonthrdquo

and ldquoyearrdquo as new columns

ldquohourrdquo can be binning as ldquomorningafternoonnightrdquo or different shifts(早晚班)

ldquodayrdquo can be binning as ldquoweekdayrdquo ldquoweekendrdquo

For weather holiday or event we can build ldquois_national_holidayrdquo

ldquohas_xxxx_eventsrdquo (eg related to company fab machine labor hellip)

119903 = 11990912 + 1199092

2

120579 = arctan11990921199091


101

httpswwwkdnuggetscom201812feature-engineering-explainedhtml

119903

120579

1199091

1199092


迷思重要因子沒有選進來

數據理解 (原則分而治之Divide-and-Conquer)

資料區間取長時間資料rarr generalized的因子選入

橫向展開將因子分類後各別類別篩選因子 (MECE)

供需(量)時間序列上下游產品互補品替代品等

價格時間序列上下游產品互補品替代品

總體經濟GDPM1BPMICPI(或年增率)Interest RateExchange Rate等

地域(空間)相關政治經濟文化經緯度空間距離地形地貌time lag等

新聞輿情相關社群網路報章雜誌hellip

縱向分解時間序列分解信號分解

Time Series Decomposition

Trend (趨勢)

Cyclicality (long cycle) (週期)

Seasonality (short cycle) (季節)

Randomness (隨機)

Hilbert-Huang Transform

Empirical mode decomposition

Intrinsic mode functions (IMF)

102

Σ

A

A1 A2

B

B1 B2

C

C1 C2

人

人



案例三品質良率精度預測

103


案例3 Yield Prediction (良率精度預測)

製程預測透過製程的處方設定 (recipe)來進行反應變數(Y)的推論eg 長寬預測

厚度預測精度預測虛擬量測hellip

預測

良品不良品

膜厚(thickness)線寬(Critical Dimension CD)覆蓋(Overlay)缺陷數(defects)缺陷面積大小(area)缺陷位置層(layer) 良率(yield)等hellip

方法推論rarr就是進行「因果關係」的建構

解釋rarr就是進行「物理特性」的說明

Benefits

協助機台校正或產品開發

降低抽樣頻率 (協同製程能力Cp Cpk)

發展預測保養 (predictive maintenance)

104



105

Dataset with

selected variable

Prediction

Classification

Model

PLS BPNN CNN

K-fold Cross-Validation

R-Squared

MSE

Confusion

Matrix

Model

Evaluation

BoostingDecision

TreeSVR

Random

Sampling

Data

Transformation

Imbalance

Categorical to

Dummy VarFeature

Extraction

Feature

Selection

hellip

Yes

No

Knowledge

Management (KM)

Documentation

Hung Lee and Lin (2020)

Z-scores

Data Partition (training vs testing)

iterative

process



Supervised Learning Models Regression Logistic regression Partial

Least Squares (PLS) Multivariate

Adaptive Regression Splines (MARS)

SVMSVR Decision Tree Random

Forest LightGBM Deep learning (DNN

CNN RNN graphCNN) GANhellip

Time Series ARIMA SARIMAX LSTM

convolutional LSTM GRU hellip

Accuracy Enhancement Ensemble

Stacking Attention Transformerhellip

Issues Curse of Dimensionality Overfitting vs

Underfitting Accuracy vs Interpretation

Data Imbalance

106

Arrieta et al Explainable artificial intelligence (XAI) concepts taxonomies opportunities and challenges toward responsible AI

httpsarxivorgpdf191010045pdf

Arrieta et al (2019)



Backpropagation Network (BPNN) (Werbos 1974 Rumelhart amp McClelland 1985)

Multi-Layer Feedforward Network + Error Back Propagation (EBP)

Minimize the error between NN output and desired output by ldquo(stochastic)

gradient descentrdquo (a large number of hidden layers rarr Deep Learning)

107

helliphellip

Input

Layer

Hidden

Layer

Output

Layer

hellip

helliphellip

helliphellip

helliphellip

helliphellip

helliphellip

helliphellip

x1

x2

xm

ො1199101

ො1199102

ො119910n

y1

y2

yn

NN

Output

Desired

Output

Loss MinimizationError back propagation


案例3 Yield Prediction (良率精度預測) Boosting (eg Gradient Boosting Machine GBM)

108

1-node decision trees

ldquodecision stumpsrdquovery simple classifiers

Alexander Ihler (2012) httpsliicsucieduClasses2012F-273a action=downloadampupname=10-ensemblespdf



預測的結果 Testing Dataset with R2 Adjusted R2 Mean Squared Error(MSE) etc

109

Yie

ld

Pre

cis

ion

Metr

olo

gy V

alu

e

Lot

Real value

Predictive value (Model A)



Statistical Control Chart for Classification (分類)

預測一個rdquo值rdquo本身沒有對錯的問題

預測一個rdquo類別rdquo就有對錯的問題

110

UCL

LCL

Yie

ld

Pre

cis

ion

Metr

olo

gy V

alu

e

Lot

Real value


Predictive value (Model B)


分類結果- Confusion Matrix

以測試組資料的結果來客觀評估較佳的分類模型

假設是二元分類模型也就是只有兩種類別的模型例如

（良品不良品）（陽性陰性）（有病沒病）（發生不發生）等

根據分類結果可計算出正確率FNFPTNTP

TNTP

+++

+=Accuracy


預測類別

類別1 (不良品) 類別2 (良品)

實際類別

類別1

(不良品)TP (true positive)

FN (false negative)

(Type II error)

(miss)

類別2

(良品)

FP (false positive)

(Type I error)

(false alarm)

TN (true negative)

111



敏感度 (Sensitivity Recall)

為實際類別1(不良品)當中被正確預測的比率

Miss (漏報) Rate = 1 － Sensitivity

明確度 (Specificity)

為實際類別2(良品)當中被正確預測的比率

False Alarm (假警報) Rate = 1 － Specificity

精確度 (Precision)

為預測類別1(不良品)當中被正確預測的比率

112

TPSensitivity

TP+FN=

TNSpecificity

TN+FP=

預測

類別1 類別2

實際

類別1 TP FN

類別2 FP TN

描述當資料屬於類別1(不良品)時被正確判斷的機率

當資料不屬於類別1(不良品)時被誤判的機率 (Type I error)

FP Rate = 1 － Specificity

TP

Rate

= S

ensitiv

ity

Model A

Model B

Precision=TP

TP+FP 一般來說右下方的面積愈大該模型的分類效果愈佳

ROC曲線(Receiver Operating

Characteristic curve)



113

Testing

Accuracy TP Rate TN Rate AUC

Model A 719 897 517 702

Model B 781 691 883 789

Model A預測

Bad Good

實際Bad 61 7

Good 29 31

Model B預測

Bad Good

實際Bad 47 21

Good 7 53

AUC Area under the Curve of ROC

精度良率預測

Model performance (128個觀測值)



Process Adjustment (製程控管與調整)

Manipulate the compensating variables of a process to achieve the

desired process behavior (eg output close to a target)

114

Time

Y

UCL

LCL

Time

Y

UCL

LCL



Advanced Process Control (APCR2R)

exponentially weighted moving average (EWMA)

double EWMA

model predictive control (MPC)

optimizing adaptive quality controller (OAQC)

artificial neural network (ANN)

EWMA Control

with linear equation 119910119896 = 119886119896 + 119887119906119896 + 120576119896 It regulates the process with time-varying intercept by adjusting 119886119896 ie

115

Liu K Chen Y Zhang T Tian S amp Zhang X 2018 A survey of run-to-run control for batch processes ISA Transactions 83 107-125

Liu et al (2018)


案例四預測保養

116


維修保養

Reactive (RM or CM) Service or replace equipment after it fails

Preventive Servicereplace machine according to the manufacturerrsquos suggested

schedule the amount of time it has been in service or operational observations

Condition-based (CBM) Service or replace equipment based on monitoring

performed to assess its current condition

Predictive maintenance (PdM) Maintaining components according to fact-based

expectations for when they will fail or require service ie remaining useful life

117

案例四預測保養(PdM)

Ran et al (2019) A survey of predictive maintenance systems pruposes and approaches IEEE Communications Surveys amp Tutorials


案例四預測保養(PdM) PdM- Supervised Learning

predict the condition of equipment to estimate when the equipment is likely to

fail and decide which maintenance activity should be performed such that a

good trade-off between maintenance frequency and cost can be achieved

Purpose eliminate unexpected downtime improve overall availabilityreliability of

systems and reduce operating costs

PdM issues are differentcustomized across industries plants and machines

118


Lei et al (2018) Machinery health prognostics A systematic review from data acquisition to RUL prediction Mechanical Systems and

Signal Processing 104 799-834

HI Health Indicator HS Health Stage RUL Remaining Useful Life



機台預測保養(Predictive Maintenance PdM)

雙週月保季保年保check list

都是手寫表單要key-in到系統裡hellip

字跡潦草 hellip rarr「其他」

年保資料最完整但hellip

資料量少(因為一年一次)解析度差看不到一年內機台狀態的改變

只有保養後的資料沒有保養前的狀態hellip

雙週月保資料相對多但零散難以拼湊hellip

這台機台拆一個零件下來裝到另一台上

憑經驗調參數不一定要恢復到rdquo最佳狀態rdquo先rdquo可用rdquo救火再說hellip

有些保養後70分hellip有些保養後50分hellip

到底換了哪個零組件不清楚rarr帳料不符

就像修電腦一樣拆了一堆power主機板RAM插上去能用再說hellip

數據問題有沒有什麼rdquo替代資料rdquo也rdquo間接rdquo地量測機台狀態

預測保養rarr關鍵零組件rarr關鍵零組件的可靠度分析庫存管理

現有rdquo預防保養rdquo制度的檢討 eg 年保改季保動態保養

除了時間還可考慮機台使用耗材(eg刀具線材)的採購狀況來推估零件磨損的速度

119



馬達軸承壽命預測 Remaining Useful Life (RUL) Prediction

120

httpwwwli-mingcomtwindexphpoption=com_contentampview=articleampid=225ampItemid=351amplang=

No 名稱 No 名稱

1 油封 9 波型華司

2 馬達前蓋 10 定子線圈

3 滾珠軸承 11 馬達機殼

4 R扣環 12 風扇

5 馬達齒軸 13 固定螺絲

6 S扣環 14 風罩

7 轉子 15 十字頭螺絲

8 滾珠軸承 16 護線扣環

馬達結構示意圖



Vibration Dataset

121

Amplitude

Time

(Obs)

Lee C-Y T-S Huang M-K Liu and C-Y Lan 2019 Data Science for Vibration Heteroscedasticity and Predictive Maintenance of

Rotary Bearings Energies 12 (5) 801

Lee et al (2019)



Prediction of the Deterioration

Vibration acceleration signal

122

revised from Grall et al (2002) and Rocchi et al (2014)

Inspection

zone

Preventive

replacement

zone

Corrective

replacement

zone

Failure level

Replacement level

Data collection RUL



Health assessment of alternator (發電機) components

123

(Lee et al 2014)

Lee et al (2014) Prognostics and health management design for rotary machinery systems- Reviews methodology

and applications Mechanical Sysetms and Signal Processing 42 314-334

EquipmentSensor Data Collection

Modelling Visualization


案例四預測保養(PdM) Feature Engineering (Time Domain Frequency Domain Time-frequency Domain)

Root Mean Square (RMS) Mean Variance Skewness Kurtosis and

Crest FactorMaxMin hellip

Time synchronous averaged (TSA) signal sliding window residual

signal (RES) difference signal (DIF) hellip

Time series decomposition Hilbert vibration decomposition empirical

mode decomposition intrinsic mode functions (IMF) hellip

Regression (intercept slope) exponential degradation θexp(βt)

(amplitude θ slope β) autoregression hellip

124

Lee et al (2014) Prognostics and health management design for rotary machinery systems- Reviews

methodology and applications Mechanical Sysetms and Signal Processing 42 314-334



Feature Engineering

125

Peak-

to-

peak

W Jiang Y Hong B Zhou X He and C Cheng ldquoA gan-based anomaly detection approach for imbalanced industrial time seriesrdquoIEEE Access vol 7 pp 143 608ndash143 619 2019

httpswwwquoracomIs-the-DC-voltage-the-same-in-the-RMS-voltage


Data

Collection

Data

Preprocessing

Take the early stageCombine all of the data files

Data 1 Data 2 hellip Data n

Feature

Extraction

Feature

Selection

Remove high

correlated variables

Variance Inflation Factor

(VIF)

Select Important Variables

Random Forest Stepwise Regression

Important

Variables

Predict

Linear Regression

(OLS)

BackkpropagationNeural Network

Prediction Result

Partial Least Squared

Regression (PLS)

Prediction

Model

OLS

Adjusted R2 = 082 amp MSE = 1234567

PLS


BPNN

MSE = 123456789

Feature Engineering

(製造資料)





127



Feature Engineering

Feature Selection RUL Prediction


給我們的啟發是hellip

如果能夠製造出來好的Featurehellip

預測可簡單易解釋且效果好

事實上只有少數幾個sensors或features才真正提供有用的信號hellip



129




29 Alarm

16 Prediction model

training

15 EWMA for Target

Baseline (TB)



24 Predicted

CUSUM out of

control

25 Pre-alarmYes

No

28 Actual

CUSUM out of

control

Yes

No


21 New sample

prediction



17 Model validation

34 Continuous

monitoring

11 Data collection

26 Engineering

Validation amp

Troubleshooting

31 Loss calculation


32 CUSUM

control chart

33 Loss

CUSUM out of

control

310 Add new samples


311 ILPM model


Yes

Off-line training

In-line prediction

Concept drift

Pre-alarm stage


correction

No

All good products

37 Bayesian

monitoring out

of control

35 Equipment



39 Update posterior


38 Alarm and

equipment

maintenance

Yes

Model misalignment


Equipment

misalignment


36 Lifetime

out of control

No

Yes

Lee C-Y Wu C-S and Hung Y-H 2020 In-line Predictive Monitoring Framework IEEE Transactions on Automation Science and

Engineering

In-line Predictive Monitoring

Phase I Process parameter monitoring

Phase II Equipment parameter monitoring


還有很多議題hellip

資料科學模型建構的議題還有hellip

預測要預測什麼

如果樣本數不夠怎麼辦

如何決定資料收集的時間區間與數量

如果資料有些偏差該如何發展穩健(robust)的模型

Training dataset與testing dataset如何切割與決定

抽樣所造成的資料不完整與不平衡如何處理

產品組合持續改變該如何分析

前後工作站間的交互作用如何衡量

預測模型何時需要重新修正或重建(re-train)

預測模型可以實際上線的標準如何訂定

模型挑選關鍵參數與工程經驗不一致如何處理

如何確認該關鍵參數是潛在因子

hellip

130



然而製造現場的議題還有hellip

在製品WIP太多如何處理

批量大小該如何決定

機台轉速或throughput的調整

生產排程與派工的法則

操作員或員工排班的最佳化

產能彈性如何建構以應變需求波動

每年度的生產力target該如何訂定與提升

產品組合product-mix如何決定

如何減少浪費看板式管理如何進行

專案管理如何Continuous Delivery敏捷開發

抽樣檢驗計畫該如何動態調整

多種零組件與原物料庫存管理如何訂定

hellip

131

資料科學可否協助解決這些議題


創業者的世界裡只有兩樣東西

有待解決的問題正在嘗試的方法

這兩個東西合起來就是一個詞

ldquo機會rdquo

罗振宇 (Dec 31 2016)罗辑思维时间的朋友2016 跨年演讲

132


自動化生產排程與演算法

Automated Production Scheduling

133


很多時候我們

也不知道自己要做什麼題目

134

事實上hellip


現場改善

資料科學

系統整合

資料品質確認

問題方法績效目標

浪費與WIP

瓶頸站生產力

人機比

設施佈置

環境公安衛生

精實管理價值流

流程再造BPR

時間動作研究

動線與熱點分析

SOP amp 標準工時

浪費移除

產線平衡

資料格式與收集

IT基礎建設

Make-or-Buy

需求預測

產銷平衡

排程與交期

特徵選取

Troubleshooting

機台維修保養

統計方法視覺化

預測方法

數學規劃最佳化

啟發式演算法

機器學習

品管圖根因分析信號處理分析

系統開發

供應鏈平台JIT

統計製程控制SPC

錯誤偵測分類FDC

製程能力優化

良率提升

產品週期顧客關係

預測健康監控PHM

組件剩餘壽命

能源與汙染控管

資料不一致

產品組合差異化

Big Data IoT amp Cloud

Real-Time amp Online OptimizationLearning

ValueSupply Chain Integration

Decision Science

New Business Model

Dashboard (戰情表)

Price Maintenance

Manufacturing Intelligence

Sustainability

資料分析確認

Lee and Chien

(2020)


可能會問hellip

那hellip那如果我們什麼資料都沒有

或資料還沒有標準化地著手收集

那我們要怎麼開始呢

136


資料科學

資料科學並非要有一堆數學模型或一大堆資料hellip

一開始可以先嘗試找到問題

為了改善針對這問題無論如何都要收集到資料

方法資料庫 (但資料可能時間過久現況已與當時不同久未校正或有誤差)

詢問專家 (但可能已經離開專案小組或轉調不同部門組織)

現場觀察

現場觀察是一非常強且客觀的方法rarr眼見為憑

137


話說hellip

於201X年企業參訪觀察工廠製造現場與流程

某廠區稼動率116200 = 58

初步參訪的疑惑為何機台(資金)閒置

是否是景氣不佳訂單需求不足

現場人員數目不足操作機台

過多機台換模具調整維修保養中

老舊機台(閒置)設備過多

工廠稼動率的合理性驗證

138


人機比與工作研究

139

魚骨圖

法

修理機台順序錯誤

運送傳送效率不佳

環境

客戶插單更改訂單

少量多樣

溝通管道

其他

交班傳達不周

人

人力缺乏

問題未及時通報請假休息

團隊合作協調不佳

等待人員操作

機

機台維修保養

模具更換

調參數規格RampD佔用中

待料

來料與排程不一致

料

原料缺乏來源品質變異

在製品堆放

機台稼動率低

排程作業流程未優化

作業不熟練

需求變異

工程變更

政策法規改變

傳承關係

組織制度設計資訊不透明



人機程序圖紀錄人和機台之間的動作

案例

時間20170211 2pm開始觀察3小時 (此處資料為模擬產生非實際數據)

對象製造部A員操作3台機台

記錄人的操作行為與機台做動的時間

計算機台稼動率 = (機台作業生產時間) (總觀察時間)

eg (56+160+138 mins)(180+180+180 mins)

=656

140




案例





eg (56+160+138 mins)(180+180+180 mins)

=656

141

時間操作員作業耗時

(分)作業

耗時

(分)作業

耗時

(分)作業

耗時

(分)

1400-1411 調整機台參數規格 11 停機調規格 11

1411-1416 將不良品移置廢品區 5

1416-1427 填寫機台檢查紀錄表 11

1427-1430 產品品質檢測 3

1430-1443 電腦資料輸入 13

1443-1450 停機量測產品尺寸 7

1450-1454 電腦工程分析 4

1454-1500 領取原物料 6

1500-1515 休息 15

1515-1528 領取模具 13

1528-1533 產品品質檢測 5


1543-1548 換模具 5


1601-1610 領取模具 9

1610-1617 產品品質檢測 7

1617-1622 存放載具 5

1622-1631 產品品質檢測 9


1640-1647 產品品質檢測 7


1652-1655 領取原物料 3

1655-1700 電腦資料輸入 5

機器加工

(產品D)

機器加工

(產品C)

13

124

機台B機台A 機台C

停機

等待換規格

換模

停機

待料

機器加工

(產品A)

機器加工

(產品B)

機器加工

(產品C)

43

140

20

88

42

50

機器加工

(產品B)



工廠稼動率條件強假設人員動rarr車台動rarr物料動

車台的稼動率基本上會低於人員的工作效率

觀察操作員的時間分解人員工作效率80 ～ 85

因此機台稼動率之上限即為人員工作效率(80 ～ 85)

200 80 = 160 (台) 到 200 85 = 170 (台) 之間為理想機台運作數

小結每天若在戰情表(Dashboard)上看到機台只有160台在Run (並不糟喔)

改善改善人員操作的作業順序 (eg 有機台停機時要先處理而非填表單)

142



人機比計算方法

=供給rarr人需求rarr機

=人力實際供給時數天

單位機台人力需求時數天

=單位人力工作時長times工作效率

此時長times機台於此時長內需要人力之比率

=工作效率

機台需要人力之比率

cong工作效率(Labor Eff)

1minus稼動率(Machine Util)

=08

1minus0656= 233 (台)

因此長官可以知道買多少機台需要搭配多少人力

143



收集資料rarr現場觀察 (工作研究 time-motion study)

優點資料準確客觀

為當下現況資料 (較即時)

缺點很花時間

觀察的時間會很分散片段 (某製程工序這次沒觀察到要等下次)

缺少現場實務經驗資料解釋不易 (需現場人員協助)

建議可與學校合作~

學校不只是只有理論與方法的地方

更是培育人才的地方 (其實對現場來說就是因為學生很多不懂rarr才能把觀察到的事實講出來rarr藉機學習也與業界腦力激盪)

144


生產排程Scheduling

老師hellip我要做排程

Q 那那一個層級排程呢

A 全部hellip

現場rarr瓶頸站

排程也不單只有現場

現場應該先導Leanhellip

Sales vs 排程人員 Sales rarr只管接單

排程rarr只管達交

目標的衝突

排程 vs 稼動率(utilization)

145

Strategic Level

Financial PlanningStrategic Business

Planning

Marketing

Planning

Make-or-Buy

Strategy

Tactical Level

Aggregate Production

Planning

Vendor Selection amp

Order Allocation

Master Production

Schedule

Resource Planning

Rough-Cut Capacity

Planning

Capacity Require

Planning

Material Require

Planning

Monthly Material

Planning

Capacity Planning

Productivity amp

Efficiency Analysis

Vendor Relationship

MgmtDemand Mgmt

Outsourcing Planning

Purchasing

Vendor Scheduling amp

Daily Assignment

Order Releasing

Shop Floor Operation

Scheduling

Shop Floor Control amp

Data CollectionFollow-Up

Production

Activity ControlIn-house Outsourcing

Operational Level

Logistics Mgmt

Long Term

Mid Term

Short Term

Facility Layout

Lee and Johnson (2013)



Overall Equipment Effectiveness (OEE) revisitedndash Nakajima (1988) de Ron and Rooda (2005)

ndash Machine idleness is identified explicitly through this definition

146

EffQuality Eff RateEff lOperationaEff Available

units actualfor timeproduction Theortical

units effectivefor timeproduction Theortical

timeProduction


uptimeEquipment

timeProduction

timeTotal

uptimeEquipment

timeTotal

units effectivefor timeproduction TheorticalOEE

=

=

=

Nonscheduled

state

Unscheduled

down state

Scheduled

down state

Engineering

state

Standby

state

Productive

state

Equipment

uptime

Equipment

downtime

Operations

time

Production

time

Total

time


現場生產排程系統困難與挑戰

147

顧客訂單產品

交期變動插單

工程變更

少量多樣加工時間不一

訂單優先順序顧客重要性

等批等候時間限制

操作員

人力不足

MO

訓練不足換模技術不一

人員配置

個人績效(競合)影響整體績效

機台設備廠務

製程(瓶頸)加工時間變異大

不確定性(當機維修保養)

特定產品機台能力不同模具僅通用於特定機台

換線機台整備模具耗損

廠區間的Backup

料件模具供應商

來料與公司排程不同

停工待料

不允許料閒置太久(先進先出)

外包時程變異

進料品質變異

人bull 人力不足bull 顧客交期變動

機bull 機台當機bull 換線時間

料bull 來料不同bull 停工待料

半自動化多目標生產排程

好的排程有效提升機台稼動率

利用率 (utilization)

有效縮短生產週期前置時間 (cycle time)

Time-to-Market 產品達交

Wu Min-You (吳民友) and Chia-Yen Lee 2015 Sampling-based NSGA-II for Stochastic Scheduling in Auto Parts Manufacturer (抽樣多目標遺傳演算法於汽車零組件製造商之隨機排程最佳化) 2015 Chinese Institute of Industrial Engineers (CIIE) Conference amp Annual Meeting Taichung Taiwan



排程 (Scheduling) (Graves 1981)

『在一段時間內配置可用的資源來處理一群工作以達成所設定的目標』

Scheduling is the allocation of limited resources over time to perform a

given set of jobs or activities 換言之是決定所有工作在機器上加工的起始時間以及加工順序所以乃是同時考慮資源限制和執行限制之最佳化問題

排程重點針對對現場特定績效指標對不同工作做最佳的資源配置

148

Chien and Chen (2007)



目標概念加工時間最短(每個訂單)

先進先出(未照排程到料)

優先順序

日期達交

可量化(最小化)

最小最大完成時間(Makespan)

總加權完成時間(The total weighted completion time)

Cycle time machine idleness

總整備時間 (The total sequence-dependent setup time)

生產線平衡(Line Balancing)

最少換模換線次數時間

延遲訂單數量(The number of tardy jobs)

總加權延遲時間(The total weighted tardiness)- Meet due date

總加權提早及延遲時間(The total weighted earliness and tardiness)

On-time delivery WIP reduction149

衝突目標

Makespan

The total weighted earliness and tardiness

(TWET)

交期

利用率

庫存時間

吳民友李家岩 (2015)


排程應用範疇

排程應用範疇航空公司機師空服員排班

機場飛機起降

車輛路徑派遣 (Vehicle Routing)

高鐵火車公車排班

電梯設定

微處理器系統

醫院排班

醫院復健排程

醫師手術排班

預約系統 (eg 看病餐廳航班等)

對於服務顧客的管制

人機料的生產排程(協調多重資源的排程)

150


現場人工排程 MRP後按照設定加工時間(processing time)推算預計投料時間點

排程目標滿足達交率rarr依到期日(Due day)排序工單

人工排程邏輯

訂單資料

依到期日排序

同一天依顧客工程優先程度排序

預估單

工作號賦予

當日機台產能是否足夠

完成所有訂單排定

考量機台能力限制開始排程

Yes

No

刪除優先程度最低訂單

No

公司日排程報表

現場組長確認與修正Yes



優先順序法則

Dispatching

is to release of orders and instructions for starting of the production for

an item in accordance with the lsquoroute sheetrsquo and schedule charts

Dispatching Rule (優先順序法則 ) 用來選擇欲處理工作次序的一種簡單啟發式方法

FCFS (First Come First Served) 先到先服務

SPT (Shortest Processing Time) 最短處理時間

EDD (Earliest Due Date) 到期日

Moore (Moorersquos Algorithm) 到期日+

CR (Critical Ratio) 關鍵性比率

SO (Slack per Operation) 每個作業的寬裕時間

Rush 緊急事件

152

119862119877 =到期時間 minus 現在時間

現場需要加工時間

119878119874 =到期時間 minus 現在時間 minus現場需要加工時間

剩餘作業數


Examining the scheduling of n jobs on 1 machine (or the

handling of the bottleneck machine)

Performance Metrics

Mean Flow Time

Average Job tardiness

Tardiness is nonnegative however the lateness can be negative

Number of Tardy Jobs

Lateness vs Tardiness

119871119895 = 119888119895 minus 119889119895 where 119888119895 is completion time and 119889119895 is due date

119879119895 = max0 119871119895

Letrsquos try FCFS SPT EDD and CR

N Jobs on 1 Machine


N Jobs on 1 Machine

Example (Nahmais 2005)

Machine shop has 5 unprocessed jobs (J1 J2 J3 J4 J5) numbers by

order they entered Bottleneck machines queue

Notations

119901119895 process time

119888119895 completion time

119889119895 due date

154

Job Process Time (119901119894) Due Date (119889119894)

1 11 61

2 29 45

3 31 31

4 1 33

5 2 32


N Jobs on 1 Machine

FCFS

Mean Flow Time (268)5 = 534

Avg Tardiness (121)5 = 242

Tardy Jobs 3

155

Sequence P Time Comp Time D Date Tardiness

J1 11 11 61 0

J2 29 40 45 0

J3 31 71 31 40

J4 1 72 33 39

J5 2 74 32 42

Totals 74 268 121

The ldquomakespanrdquo is fixed

in this case (N jobs on 1 machine)

Only consider the ldquojob sequencerdquo


N Jobs on 1 Machine

SPT



Tardy 1

156


J4 1 1 33 0

J5 2 3 32 0

J1 11 14 61 0

J2 29 43 45 0

J3 31 74 31 43

Totals 74 135 45


N Jobs on 1 Machine

EDD



Tardy 4

157


J3 31 31 31 0

J5 2 33 32 1

J4 1 34 33 1

J2 29 63 45 18

J1 11 74 61 13

Totals 74 235 33


N Jobs on 1 Machine

CR Iterative Process looks at time remaining between current time and due date

considers processing time as a percentage of remaining time

CR = 10 means just enough time

CR gt 1 0 more than enough time

CR lt 10 not enough time

Compute

Current time updates after each selection by adding scheduled Process Time to current time

158

119862119877 =119863119906119890_119863119886119905119890 minus (119862119906119903_119879119894119898119890)

119875119903119900119888119890119904119904119894119899119892_119879119894119898119890


CR

N Jobs on 1 Machine

159

JOBPr

Time

D

DateCR

Current Time = 0

1 11 61 5546

2 29 45 1552

3 31 31 100

4 1 33 33

5 2 32 16

JOBPr

Time

D

DateCR

Current Time = 31

1 11 61 2727

2 29 45 483

4 1 33 2

5 2 32 05


N Jobs on 1 Machine

160

JOBPr

Time

D

DateCR

Current Time = 60

1 11 610091

do last

4 1 33 -27

5 2 32 -14

JOBC

Time

D

DateTardy

Summary

3 31 31 0

2 60 45 15

4 61 33 28

5 63 32 31

1 74 61 13

Total 289 87

Tie use SPT

CR

Mean F Time (289)5 = 578

Mean Tardiness (87)5 = 174

Tardy 4


Performance Comparison

FCFS

Does not consider job attributes (due dates processing times) and not do well

SPT

Minimizes total time jobs spend in the system (mean flow time)

Given great mean flow time and does well relative to tardiness but does not sider

due dates at all (Note that some job may queue forever )

EDD

Minimizes the Maximal Tardiness (Tmax) 119879119898119886119909 = max0 119871119895

Does well relative to due dates (not optimal in any case but intuitively attractive)

CR

Does worse in this example than usual

Sequencing Rules

due Time

FCFS

CRSPT

EDD


然而hellip

EDD or SPT是現場常用的rules

然而各有缺點 EDD缺點現場一直救火急件插單滿足大客戶放棄小客戶

SPT缺點有些job可能永遠都沒機會加工

此外簡單的Dispatching rule未考慮到 rdquo換線換模rdquo的時間與成本

生產線平衡(Line Balance)

延伸方法快速換模技術(Single-Minute Exchange of Die SMED)

生產線平衡技術 (Line Balancing)

162



快速換模技術

Single-Minute Exchange of Die SMED (新郷重夫Shingo 1985)

Rapid changeover and setup time reduction in converting current

manufacturing process to manufacture the next product improves

production flow and reduces lot sizes

Long setup time leads to a small number of setups larger batch sizes

larger WIP inventories and poor process flow

思維的改變新鄉重夫「快速換模絕對不是技巧的問題而是思維的問題」

豐田汽車副社長大野耐一「生產現場中rdquo人的智慧是成敗關鍵」

163

Shingo S (1985) A Revolution in Manufacturing The Smed System Productivity Press


快速換模技術

SMED流程 1記錄整個換模(線)現況過程和時間

工作研究人機程序圖時間與動作研究(time-motion study)

2區分內部換模與外部換模

內部換模指必須在機器停止生產狀態下才能進行的換模動作

外部換模指機器在生產運轉中仍然可以進行的換模動作

3將內部換模作業儘可能轉到外部換模作業

工具模具零組件標準化不尋找不移動不多用

工具預熱預裝配預設定預清潔預熱等等

4改善內部換模

平行作業

工具放置的方法位置統一尺寸統一

5改善外部作業

把工具規尺存放在機器旁邊

備好工具更換準備的核查清單提供詳細的工具更換流程記錄單

6標準化新的換模準備作業

164

科建顧問(2009)rdquo少量多樣生產的關鍵-快速換模(線)技術rdquohttpwwwkindcomtwmainphpaction=article_introampid=52


Scheduling Methodology

JSP is among the hardest combinatorial optimization problems

NP-hard problem

Heuristic Method (Priority Rule)

Shortest processing time (SPT) earliest due date (EDD) etc

Pros easy to understand

Cons poor performance for complicated production line

Meta-Heuristic Algorithm (Tabu Simulated Annealing Genetic Algorithm)

Approximated-optimization approach

Pros provide a good solution efficiently

Cons cannot guarantee the global optimum

Mathematical Programming

Optimization-based approach formulated by mixed integer programming

Pros Guarantee global optimum

Cons computational burden for large-scale problem

Local optimum

Short running time

Global optimum

Long running time


Meta-heuristics

Definition of Meta-heuristics (Glover and Laguna 1997)

A meta-heuristic refers to a master strategy that guides and modifies

other heuristics to produce solutions beyond those that are normally

generated in a quest for local optimality

For the ldquoMinimization Problemrdquohellip

166

f(x)

x

Local optimum

Global

optimum

Meta-heuristics

ldquoJUMPrdquo

119909119905+1 larr 119909119905 + 120578120597119891

120597119909

Gradient Descent (梯度下降法)

120597119891

120597119909

119909119905 119909119905+1

120578

120578 step size (learning rate)


Basis

Tabu Search (TS) has its roots in methods that cross boundaries of

feasibility and local optimality

TS was first proposed by Glover (1977)

The word tabu (or taboo) comes from Tongan a language of Polynesia

where it indicates things that cannot be touched because they are

sacred Now it means ldquoa prohibition imposed by social customrdquo

In TS tabu status of forbidden elements shift according to time and

circumstance based on an evolving memory

Tabu status can be overruled for a preferrable alternative

Hence TS uses adaptive (flexible) memory (long-term and short-term)

Neighborhood Search

exploitation (開採) of good solutions and exploration (探索) of new

promising regions

Stopping criteria (to terminate the searching procedure)

The maximal number of iteration The objective function is unchanged given

a number of iteration Running time

Tabu Search (禁忌搜尋法)


Tabu Search Algorithm (Glover and Laguna 1997)

1 Find an initial solution 1199090 isin 119883 set 119909119899119900119908 = 119909119887119890119904119905 = 1199090 initialize

memory

2 Intensification phase

21 If termination condition (eg simple iteration count no admissible

improving move no change in 119909119887119890119904119905 in so many iterations) is satisfied then

go to step 3

22 Choose the best 119909119899119890119909119905 isin 119873(119909119899119900119908) such that 119909119899119890119909119905 is not tabu or

satisfies aspiration criterion

23 Move from 119909119899119900119908 to 119909119899119890119909119905 ie set 119909119899119900119908 = 119909119899119890119909119905

24 If 119909119899119900119908 is better than 119909119887119890119904119905 then set 119909119887119890119904119905 = 119909119899119900119908

25 Update recency based memory (tabu classifications) frequency based

memory andor critical event memory (elite solutions) return to step 21

3 Diversification phase

31 If termination condition is satisfied then stop

32 Using frequency based memory andor critical event memory find a

new starting point 119909119899119900119908 return to step 2

Tabu Search Algorithm


Single-machine total weighted tardiness problem (Chern 2004)

Exhaustive enumeration method (窮舉法) 4 Cases

Iteration 1 Initial solution (2143) with total weighted tardiness

119879 2143 = 1199082max 1199012 minus 1198892 0 + 1199081max (1199012 + 1199011) minus 1198891 0

+1199084max (1199012 + 1199011 + 1199014) minus 1198894 0 + 1199083max (1199012 + 1199011 + 1199014 + 1199013) minus 1198893 0

= 12 times 10 minus 2 + 14 times 10 + 10 minus 4 + 12 times 10 + 10 + 4 minus 12+1 times 10 + 10 + 4 + 13 minus 1

= 500

Set initial Tabu list TABU = lt gt and size of tabu list = 2

Single-Machine Scheduling Problem

Jobs Process Time(119953119947)

Due Date(119941119947)

Weights (119960119947)

1 10 4 14

2 10 2 12

3 13 1 1

4 4 12 12


Iteration 2 neighborhood search at (2143)

Schedules obtained by pairwise interchanges are

(1243) (2413) and (2134)

119879 1243 = 480 119879 2413 = 436 and 119879 2134 = 652

(2413) is the best from the non-tabu results

Update Tabu list TABU = lt (14) gt



(4213) (2143) TABU and (2431)

119879 4213 = 460 119879 2143 = 500 TABU and 119879 2431 = 608


Update Tabu list TABU = lt (24) (14) gt (size of tabu list = 2)





(2413) TABU (4123) and (4231)

119879 2413 = 436 TABU 119879 4123 = 440 and 119879 4231 = 632


Update Tabu list TABU = lt (21) (24) gt



(1423) (4213) TABU and (4132)

119879 1423 = 408 119879 4213 = 460 TABU and 119879 4132 = 586





Metaheuristics

Stochastic (LocalRandom) Search

172

1199091

Solution Space1199092

1199610

Neighborhood 119873(1199610)

1199611 1199612



Global

optimum


Intensification and diversification

Intensification a form of exploitation (開採)

Based on modifying choice rules to encourage good move combinations

and solution attributes and it may lead to return to attractive regions

Examines neighbors of prerecorded elite solutions

Diversification a form of exploration (探索)

Examines unvisited regions generates different solutions

Exploitation and Exploration

exploration

exploitation

(Gen 2005)


If you hellip

If you change the size of TABU list whatrsquos the result

A trade-off between exploitation and exploration


Module Architecture of MFG Scheduling Systems

175

revised from Framinan and Ruiz (2010)

Interfaces

1 Gantt Chart

2 Dispatch List

3 Capacity Buckets

4 Throughput Diagram

Scenario

Management

System

Maintenance

Performance

Control

Algorithm

Generator

Interface

Algorithm

Generator

Scheduler amp

Dispatcher

Preprocessor

Scheduling amp

Rescheduling

Algorithms

Manufacturing

Execution

System (MES)

Enterprise

Resource

Planning (MRPII)

Production

Monitoring

System

Database

ImportExport

Synchronization

User Interface Module Schedule Generator Module

Algorithm

Library

Database Management ModuleBusiness Information System

Scheduling

Logic Unit

Order

Master

File

Shop-

Floor

Data


LEKIN (httpweb-staticsternnyueduomsoftwarelekin)

176

Gantt Chart amp Dispatch List



Multi-Objective Scheduling


Cyberplan System (Pinedo 2012)

178

Capacity Buckets



排程的好處多多先從某站點A開始做(可能是瓶頸)

做完上下游的問題自然會浮出來

上游變卡了WHY 下游變卡了WHY

改善的機會

但並不是把A產出極大化rarr上游慢則A的稼動率會很低下游慢則會堆貨

講究的是synergy

排程需整合人機料法環等資源

人員技能機台能力模具原料庫存批次工作站Queue time limit

部份手動排程調整rescheduling大部分有其必要rarr半自動化

Web-based scheduling system

排程系統長期發展應與其他系統整合

庫存管理人員排班維修保養排程產能規劃與定價()

供應鏈上下游的系統整合 (資訊透明化)

179


自動化時實務與學理的排程差異(Pinedo 2012)

靜態n個工作排程最佳化實務上是動態的因此當新的工作(job)來必須要rescheduling

Note1 設定一個未來時段排程不可變動eg 未來6hrs內的排程固定

Note2 插入空隙(slack time)於排程中以防止急單或機台當機狀況

複雜的現場環境機台能力(eg 機差)製程限制(eg 綁機)訂單相關(eg 優先權)工序

相關(eg 前置時間)時間相關(eg 等候限制)機台狀況(eg 當機維修保養)

工作優先權的動態調整學理上會固定工作工單的優先權然而實務上權重會動態調整甚至最

低優先權的工作突然變成最高優先權的工作

目標函數懲罰函數通常不是rdquo線性rdquo的線性Penalty function = max0 119888119895 minus 119889119895

非線性 Penalty function = max0 (119888119895 minus 119889119895)2

180


自動化時實務與學理的排程差異(Pinedo 2012)多個目標函數且每個目標函數的權重會隨時間動態調整

A 最小化 sum of the sequence dependent setup times rarr increase throughput

B 最小化 total weighted tardiness rarr maintain quality of service

If workload is relatively heavy then A otherwise B

排程常跟人員排班與加班有密切關係

加工時間的隨機性不易建模 98是固定值(eg 10mins) 2會加上平均數相當大的指數分配時間

自動化製造與組裝現場尤其常發生

機台或機器人平常加工很順但突發狀況會立即造成非常糟的加工時間

加工時間也常受到人員訓練(經驗曲線)以及模(刀)具耗損的影響

排程系統開發過一陣子就hellip

Out-of-fashion database without updated order upgraded-version machine

(throughput change) labor (learning curve) hellip

Rescheduling

181

由於眾多因素的複雜關係排程基本上都是rdquo客製化rdquo



如果現場的rdquo剩餘rdquo產能是足夠的某工作可以在這機台處理也可再另外一個機台 (有選擇性)

先考慮Setup time與due date rarr high priority

再考慮flexibility (有多少機台可以做這job)rarr low priority

如果現場有兩個瓶頸下游的瓶頸排程先處理 (WHY)

Hint WIP

但下游若是偏向組裝線 (ie delayed differentiation)人為調整因素較多自動化導入也就愈加困難

推拉界限(push-pull boundary)視角

182

helliphellipSupplier Customer

Pull Strategy

High Uncertainty

Push Strategy

Low Uncertainty

WIP

UtilizationCycle time

Lateness

Resource Optimization Delivery Plan


瓶頸站的重要性- Flow Variability

Bottleneck (high utilization station)

Conclusion flow variability out of a high utilization station is

determined primarily by process variability at that station

Eg 換載具換桶換產線(運輸)

Must check the variance of

processing time

Hopp W and Spearman M 2001 Factory physics 2nd ed Boston MA Irwin McGraw-Hill


HVLV HV

HVHV HV

LVLV LV

LV LVHV

Process Variability

Inflow Variability


迷思

1 開發資訊系統連結資料庫ERPMES串起來導入人工智慧AI演算法優化(eg 基因演算法GA)排程就rdquo成功rdquo了

2 排程有沒有一般化(generalized)的模組

3 排程系統真正關鍵在交接維護與持續更新教育訓練

排程是組合最佳化(Combinatorial optimization)的問題通常為NP-hard

一旦學會解這類題目應用範圍就變廣了

運輸最短路徑問題 (eg travelling salesman problem TSP)

網路結構最佳化問題 (eg minimum spanning tree MST)

財務投資組合問題人員排班問題資源優化的問題設施規劃廠址選擇

產能規劃庫存管理電信基地台架設選址問題車輛配送路徑問題等

現場動態調整

184


到這裡可以發現hellip

排程hellip好像不是要預測些什麼

FCFS SPT EDD CR 哪一個好

製造資源的最佳化rarr處方性分析

185



再過一陣子

ldquo業界缺的就不是Data Scientist而是如何將Model產生的Pattern或預測結果與公司現場內部外部的資源整合以進行Prescriptive Analysisrdquo

(范治民博士2017)

預測但不做決策預測就可惜了

然而決策是根據rdquo資源rdquo來做判斷

186



在製造業中

自動化程度愈高hellip

排程需求就愈重要

而排程就是一種Prescriptive Analysis (處方性分析)

根據資源rdquo人機料法環rdquo達成的綜效synergy

187


失敗案例與注意事項

主管對現場認知的落差 PPT製作KPI達成報喜不報憂

Sol 總經理辦公室特助出來協調

數據資訊系統與IT基礎建設進去找到問題點後發現沒有數據 (現場都是有問題後才開始收集數據)

Sol 分階段進行初步試驗性質的問題診斷

ldquo解rdquo問題過程為AI而AI 為自動化而自動化

Sol 應根據現場挑選適當的方法論

188

問題現場-Experience-based

方法導入-Methodology-based



從預測性思維到處方性決策


190


迷思

預測要愈準愈好

191


迷思

這是當然的

但另一方面預測的本質是hellip

找出關鍵因子

建構因果關係

把正或負的影響(趨勢)抓到

eg 線性回歸中的獨立變數的係數

協助決策制定以趨吉避凶

192


讓我們一起來想一下hellip

193

為什麼要預測

預測的目的是什麼

下一步為何


預測像hellip

194


預測像hellip

195

httpthewhenpixnetnetblogpost42532195-

E5A194E7BE85E58DA0E58D9C3AE68891

E8A9B2E5A682E4BD95E5A29EE58AA0E8

B2A1E9818B3F

httpwwwzou1comnewsshow-97765html


但hellip其實是hellip

196


衡量風險與不確定性


197

20170909 歐洲模式中心的五十幾種氣象模式的颱風路徑預測結果泰利侵台機會頗高

httpnewsebcnettwnewsphpnid=77898



198

20170914 中颱泰利「髮夾彎」北部東北部風雨較大

httpwwwcnacomtwnewsfirstnews201709140012-1aspx



所以rdquo決策rdquo很helliphelliphellip難做hellip

瞭解這就hellip

不要太為難你的長官 XD

199


因此hellip說穿了hellip

rdquo推論(預測)rdquo就是

透過分析資訊來降低未來不確定性的一種方法

以利決策的進行

200


其實hellip

重點不在於rdquo預測rdquo本身

重點在於我們開始rdquo動起來rdquo

透過rdquo收集資訊rdquo來降低所面對的不確定性

201


決策的類型

根據rdquo資訊rdquo收集的狀況決策的類型可以簡單分成下面三種

確定性下決策 (Decision under Certainty)

風險下決策 (Decision under Risk)

完全不確定下決策 (Decision under Strict Uncertainty)

202


小試身手hellip

天氣與決策

203

不帶傘帶傘

晴天1 笨重 (不方便)

2 弄丟 (再買一支)

雨天 1 落湯雞 (感冒)

2 搭計程車 (支出)

3 拿別人的傘

(良心不安)


小試身手hellip

204


神預測God2GO

明天一定(100)下雨hellip


小試身手hellip


205

機率02

機率08

分析資訊後的預測結果(資料科學)

天氣預測小幫手Weather2GO

方法一期望值

02 times太陽+08 times 下雨 ()

迷思- 骰子六個面

每一面16 期望值為35

賭骰子應該出現35 ()

方法二決策風險


小試身手hellip


206

機率02

機率08




minus 處方性的分析

風險成本矩陣

不帶傘帶傘

晴天

成本 $0 成本 $100

(弄丟)

雨天

成本 $200

(感冒)

成本 $0

期望成本

02x0

+08x200

=160

02x100

+08x0

=20

決策帶傘


小試身手hellip


207



風險成本矩陣

不帶傘帶傘

晴天

成本 $0 成本 $100

(弄丟)

雨天

成本 $200

(感冒)

成本 $0

期望成本

02x0

+08x200

=160

02x100

+08x0

=20

決策帶傘

切記hellip

不是因降雨機率08所以我們才帶傘主要是因為決策風險(成本)的考量後我們才決定帶傘

又或hellip

我們可以想想這件事若弄丟後買一把傘成本為100000元我們還會決定帶傘嗎


由此可知hellip

預測(降雨機率)很重要

決策風險(帶不帶傘的後果)也很重要

互為表裡相輔相成

208

Lee (2019)


小試身手hellip


209

Based on your

Preference

Structure

方案1沒有帶傘的習慣耶

方案2就每天帶把小傘吧~

沒有任何資訊I2GO



公司規劃投資產能擴充希望明年銷量愈高愈好目前公司年度營業利益約25億元

根據明年景氣狀況營業利益預估如下

210

明年景氣變化情境

方案景氣好景氣持平景氣差

併購公司A 42 21 8

購置機台 35 28 13

外包 28 25 23

你會選哪一個方案Revised from Chien (2005)



悲觀準則 (The Maximin Payoff Criterion)

小中取大報酬準則

作最壞的打算再由各最壞的報酬中選擇最好的結果

211

天氣情境

方案景氣好

景氣持平

景氣差

Min

Return

併購公司A 42 21 8 8

購置機台 35 28 13 13

外包 28 25 23 23



樂觀準則 (The Maximax Payoff Criterion)

又稱大中取大報酬準則

作最好的打算再由各最好的報酬中選擇最好的結果

212

天氣情境

方案景氣好

景氣持平

景氣差

Max

Return

併購公司A 42 21 8 42

購置機台 35 28 13 35

外包 28 25 23 28



薩維基準則 (The Minimax Regret Criterion) (Savage 1951)

又稱最小最大悔惜準則

悔惜定義為「一決策方案之報酬與相同自然狀態下可以產生最大報酬之決策方案兩者報酬的差額」

Step 1建立悔惜償付表

Step 2在悔惜償付表中採大中取小準則(minimax)

213

悔惜矩陣

景氣好

景氣持平

景氣差

Max

Regret

0 7 15 15

7 0 10 10

14 3 0 14

天氣情境

方案景氣好

景氣持平

景氣差

併購公司A 42 21 8

購置機台 35 28 13

外包 28 25 23



公司規劃投資產能擴充希望明年銷量愈高愈好

無資訊情況下理性決策並沒有對跟錯的差別

只是根據每個人的rdquo喜好結構 (preference structure)rdquo所呈現決策結果

214

天氣情境

方案景氣好

景氣持平

景氣差

併購公司A 42 21 8

購置機台 35 28 13

外包 28 25 23

你會選哪一個方案


既然決策很難做hellip

就想辦法在做決策之後

讓它變成一個好的決策

215


Capacity Planning Problem (Newsboy problem over time)

Capacity Plan A B C or D (demand)

Two Types of Risk

Capacity Shortage 產能短缺 loss of sales loss of market share

Capacity Surplus 產能過剩 machine idleness inventory holding cost

Time

Demand

Demand

A

B

C

大試身手hellip

0



其實產能規劃經常是hellip

Time

Demand

Demand


0

追高殺低


大試身手hellip

Newsboy problem 報童問題 (典型的作業研究OR問題)

每天一大早出門到批發商訂報紙送報賺錢

當日買報紙的需求是不確定的

報紙若當天沒賣出去則殘值為0 (由於時效性隔天就不能賣了)

決策議題要訂多少報紙呢

218


Capacity Planning Problem (more demand scenarios)

How about more than two demand scenarios

Two demand forecasts Marketing vs Sales

Should capacity level follow marketing or sales or hellip

Scenario Simulator

Generate capacity plans (gt10 versions) manuallyhellip

KPIs CapEX per k ROIC paybackhellip

Time

Demand

Marketing Forecast

Sales Forecast

大試身手hellip

0

Capacity Level


Empirical Study (Lee and Chiang 2016)

Empirical Study- Taiwan TFT-LCD Manufacturer

We introduce a two-phase framework to decide the best capacity level

reducing the losses (ie risks) of capacity surplus and capacity

shortage

1st stage Demand Forecast (預測模型)

Linear Regression

Autoregression

Neural Network

2nd stage Capacity Decision (最佳化模型)

Expected Value (EV 期望值)

Minimax Regret (MMR 薩維基準則)

Stochastic Programming (SP 隨機規劃)

220


Empirical Study

Capacity Regret Assessment

透過問卷調查以系統化的方法來收集決策者的風險偏好

Analytic Hierarchical Process (分析層級程序法 AHP) (Satty 1980)

221

Capacity Regret

Assessment

CustomerInventory

Market

Share

Profit

Loss

Loss of

Falling Price

Inventory

Loss

Holding

CostReputation

Lower

Capacity

Level

Higher

Capacity

Level

ALTERNATIVE

OBJECTIVE

ATTRIBUTE

119877119904ℎ119900119903119905119886119892119890 缺貨風險119877119904119906119903119901119897119906119904 存貨風險

Lee and Chiang (2016)


Empirical Study

A Tradeoff Between Two Risks

222

119877119904ℎ119900119903119905119886119892119890 缺貨風險愈大產能水準向上拉

119877119904119906119903119901119897119906119904 存貨風險愈大產能水準向下壓

119863119898119886119909

119863119898119894119899

Capacity Decision


0

10000

20000

30000

Training

Dataset

Validation

Dataset

Technology

Node A

Time

Demand

Empirical Study

Data Source

Nov 2013 to Oct 2014

Aggregate demand for a specific technology node

Dataset training data (9 months) and validation data (3 months)

Objective determine the capacity level for the future 3 months (Aug

2014 to Oct 2014) based on historical demand until July 2014

223



Empirical Study

2-stage approach

Demand Forecast

Capacity Decision

VDGP

LI latent information

(Chang et al 2014)

224



Empirical Study

1st phase Demand Forecast

linear regression (OLS) autoregression (AR) neural network (NN)

Criterion Mean Squared Error (MSE) NN lt AR lt OLS

225

0

10000

20000

30000

Training

Dataset

Validation

Dataset

Technology

Node A

Time

Demand

Linear Regression

Autoregression

Neural Network


Empirical Study

2nd phase Capacity Decision

AHP gives pair-wise comparisons of the capacity surplus and shortage

and calculate the eigenvector (特徵向量) as weights of two risks

31 individuals with TFT-LCD industrial backgrounds

2 for 0-2 yrs 9 for 2-5 yrs 13 for 6-9 yrs 7 for more than 10 yrs of service

one third have undergraduate degrees and the others for graduate degrees

119877119904ℎ119900119903119905119886119892119890 = 0521 and 119877119904119906119903119901119897119906119904 = 0479

226

Current policy builds up the capacity level based on the maximal forecast demand

Avg Reg the weighted sum of squared error (WSSE) over the number of validation periods

MonthActual

Demand

Capacity DecisionCurrentPolicy

EV MMR SP

Aug 2014 19499 20207 16941 17157 18922Sep 2014 18110 21305 17921 18306 19135Oct 2014 15059 22404 18536 19291 18885

Standard Deviation 22713 10982 8047 10681 1348Average Regret - 17960 10322 11138 8748


Empirical Study

隨機規劃(stochastic programming SP)提供一穩健決策(robust decision)

227

0

500

1000

1500

2000

0 300 600 900 1200

StandardDeviation

AverageRegret

Current

Policy

EVMMR

SP

Poor

Better

Better Poor

Lee Chia-Yen aamp Ming-Chien Chiang (2016) Aggregate Demand Forecast with Small Data and Robust Capacity Decision

in TFT-LCD Manufacturing Computers amp Industrial Engineering 99 415-422

數學規劃目標與限制

Min 119862119909 + 119864 119891 119909 ෩119863

st 119909 ge 0where for a demand forecast

119889 isin ෩119863119891 119909 119889 = Min 119875+119910+ + 119875minus119910minus

st 119889 minus 119909 = 119910+ minus 119910minus

119910+ 119910minus ge 0



我們可以透過模型來預測或模擬許多情境(scenarios)

BPNN SVM CART Boosting PLS hellip

ThenhellipWhich one is correct What is the next step

預測hellip既然不可能100準那決策上的損失風險就應該納入考量

讓我們想個簡單例子

模型A準確度95但不準時的決策會造成rdquo龐大損失rdquo

模型B準確度90但不準時的決策只會造成rdquo些許損失rdquo

我們要選模型 A還是模型B呢

預測性的思維rarr處方性的決策

228


讓我們再想一次

精度良率預測 Classification rarr探討Confusion Matrix中的trade-off rarr Cost-sensitive

權衡誤放(type-I)與誤宰(type II)風險的成本rarr處方性分析

229

Testing

Accuracy AUC

Model A 719 702

Model B 781 789

Model A預測

FAIL PASS

實際FAIL 61 7

PASS 29 31

Model B預測

FAIL PASS

實際FAIL 47 21

PASS 7 53

AUC Area under the Curve of ROC Lee (2019)


迷思

可能同時降低型一與型二誤差

230


迷思

231

170cm

165cm 175cm

172cm


讓我們整理一下hellip

232


當預測思維搭配上處方決策時hellip(極重要三顆星)

為了降低對未來的不確定性 (建構關鍵因子推論的預測模型)

資料科學並非用很複雜的數學模型~ (即使有時候讓我們方便許多)

記得 Manufacturing rarr ldquoHand Makerdquo rarr黑手~

站起來走到現場去透過觀察與討論找出rdquo推論用的關鍵因子rdquo

切記一旦收集到rdquo數據rdquo便已成歷史

如何透過歷史來探索未來 (鑑往知來)數據科學扮演關鍵角色

為了提升決策品質(建構風險權衡最佳化的決策模型)

由於預測不一定準且常有多個預測情境(scenarios)

決策風險的量測是必要的

站起來走到現場去透過觀察與討論找出rdquo權衡用的風險因子rdquo

切記rdquo魚與熊掌不可兼得rdquo 因此需要權衡得失 (風險)

如何透過有限資源來規劃未來 (見識謀斷)作業研究扮演關鍵角色

233


資料科學與大數據分析是萬靈藥(panacea)

234


方法複雜度與附加價值

235

Source CRISIL GRampA analysis

Operations Research 作業研究(多角化投資組合排程產能規劃製程監控)


什麼是分析(Analytics)

Hillier and Lieberman (2010)

ldquoAnalytics is the scientific process of transforming data into insight for

making better decisionsrdquo

Descriptive analytics (敘述性分析)

Using innovative techniques to locate the relevant data and identify the

interesting patterns in order to better describe and understand what is

going on now

Predictive analytics (預測性分析)

Using the data to predict what will happen in the future

Prescriptive analytics (處方性分析)

Using the data to prescribe what should be done in the future The

powerful optimization techniques of operations research are what are

used here

236


The Wyndor Glass Co products high-quality glass products

including windows and glass doors (Hillier and Lieberman 2010)

It has three plants Plant 1 makes aluminum frames and hardware

Plant 2 makes wood frames

Plant 3 produces the glass and assembles the products

Top management has decided to revamp the product line

Production capacity are released to launch

two new products having large sales potential

Product 1 An 8-foot glass door with aluminum framing

Product 2 A 46 foot double-hung wood-framed window

237

什麼是處方性分析

httpimgarchiexpocomimages_aephoto-g55456-4334799jpg

httpswwwandersenwindowscom


This problem can be recognized as LP problem of the classicproduct mix (產品組合) type

Linear Programming (線性規劃 LP)

Formulation as a Linear Programming Problem

x1 number of batches of product 1 produced per week


Z total profit per week from producing these two products

238


Production Time Available

TimePlant Product 1 Product 2

1 1 0 4

2 0 2 12

3 3 2 18

Profit ($1000) $3 $5 0

1823

122

4 st

53

21

21

2

1

21

+

+=

xx

xx

x

x

xxZ


Graphical Solution

The resulting region of permissible values of (x1 x2) called the

feasible region


0

1823

122

4 st

53

21

21

2

1

21

+

+=

xx

xx

x

x

xxZ


Graphical Solution

Move the objective function with fixed slope through the

feasible region in the direction of improving Z


最佳化結果

每周生產2個產品1 (x1)

6個產品2 (x2)

能使得總獲利最大

這就是處方~



遇到問題

給定資源限制條件 (限制式)

給定期望改善的KPI (目標函數)

提供solution

這就是一種處方

241


Data Scientist nerd or geek

242

Domain Knowledge

Statistical TheoryComputer Science


事實上製造資料科學是hellip

243

處方性分析

決策見樹不見林

DS in

MFG

處方性分析補足了製造資料科學的三大議題1 決策風險的測量與權衡2 一部份未解決的問題 (eg

排程庫存專案管理)

3 ldquo槓桿rdquo有限資源下的最佳化(人機料法環)

掌握rdquo趨勢rdquo釐清rdquo定位rdquo

建立rdquo格局rdquo (因為牽涉到資源)


邏輯思維數字分析(exploitation)

創意思維觀察發想(exploration)

問題解決過程問題本質探索

為大於其細

方案與方法產生

方案評選

發現問題定義問題設計對策抉擇對策

見

識

謀

斷

Do the right thing Do the thing right

發想

收斂

圖形與抽象概念

數字與事實根據

敏銳觀察格局定位槓桿資源風險權衡

執行對策

膽大心細

決策與行動

行

問題解決過程(Problem Solving)


構析(Analytics)五階段

245

Descriptive

敘述性

Diagnostic

診斷性

Predictive

預測性

Prescriptive

處方性

Automating

自動性

見

What

數據收集視覺化界定利基

What happened(定義問題)

Why

根本原因物理解釋因果關係

異質資訊因子變異趨勢週期

When

決策優化資源配置風險權衡

HowWho Where

即時監控適應性概念飄移

戰情財報

Why did it happen(解釋根因)

WhenWhat will happen next

(掌握趨勢)

How can we make it happen Who takes it

(決策格局) Where should buildroutines

(持續改善)

識謀斷行

U N I S O N


結語

Conclusion

246


迷思

Big Data資料量愈多愈好

找到的Pattern也是愈多愈好

247


迷思

對但也不完全對

統計是以樣本推論母體因此樣本愈多對母體推論愈精確

「證據愈多說話愈大聲」

並非單純資料量或資訊量的多寡

重要的是資訊的「異質性(Heterogeneity)」

猶太人的第十人理論

如何得到異質性資訊

找一些想法或背景不一樣的rdquo人rdquo加入團隊

Sensor不是裝在自家競爭者客戶而是End User身上

248


迷思

AI is black box Explainable AI (XAI)

249

洪紹嚴 2019 XAI (Explainable AI)-Introduction

httpsspeakerdeckcomskydome20xai-explainable-ai

Basic

interpretable

models

Post-hoc

Explanation

RegressionBased

Tree Based

DeepLearning

Linear Logistic

regression

Lasso Ridge

GLM GAM

Decision Tree

RF XGBoost

LightGBM

RF

DNN CNN RNN

helliphellip

β (weights)p-values

(build-in)

DataFeature

EngineeringML

Models

Prediction Result

(build-in)

X

Post-hoc Methods

解釋模型如何「理解資料」

(plug-in)

FeatureImportance

洪紹嚴 (2019)


跨越問題與方法的鴻溝

250

Yield

Time

Cost

Yield

New Tape-out (NTO)

研發導入

Device

optimization

during process

integration

Engineering

Parameter

Optimization

Design of

Experiments

成長期

Tool Matching

Benchmarking

Troubleshooting

Scheduling

Spec Setting SPC

Prognostics amp Health Management (PHM)

Virtual Metrology In-line Predictive Monitoring

Run-to-Run (R2R) Control FDC

PreventivePredictive Maintenance(PMPdM)

Automated Optical Inspection (AOI)

成熟期

快速良率提升

Yield ramp

during pilot

production

穩定生產降低成本快速錯誤診斷

Process ldquoturningrdquo

during mass

production

資料量少資料量多

In the RampD product development or the fab ramp-up

phase the small data issue is common

向rdquo上游rdquo走(愈往上游愈多不確定性hellip)

方法論 vs 產品良率及成本


機人


迷思

過去台灣製造業這幾年的歷史拉開hellip

我們的生產力與品質持續提升hellip

但為何獲利下滑

251

可能是市場競爭者政府政策等但這些都不是我們能控制的因子hellip


Market Structure and Game Theory (external analysis外部分析)

Productivity driving rarr Price reduction ()


Curse of Productivity

列強的競爭hellip

迷思

252


智慧製造與工業35

德國工業40的願景物聯網蒐集和分析所有生產過程相關的大數據

虛實整合系統以整合價值鏈的所有生產區塊

「大規模個人化生產」(mass personalization)

延遲差異化模組化

253

簡禎富 (2017 哈佛商業評論)

ldquo「工業35」是工業30和工業40之間的混合策略hellip

當務之急先發展能讓智慧製造系統發揮效能的大數據分析和彈性決策能力helliprdquo

工業30

有限的數據和資訊來預測產品的需求

建置產能然後想方法銷售

提升產能利用率和規模報酬

但由於生產數據與終端市場並沒有全面連結最後一定會因為供需落差而出現存貨和缺貨同時存在的現象

工業40

大量個人化彈性決策聰明生產

有需求才生產少量多樣高附加價值

結合終端使用者的物聯網與虛實整合使各環節上的浪費得以消除

人體神經系統偵測變化和即時決策

平台化提升對供應鏈上下游廠商的資訊穿透和掌控能力建置專屬製造平台透過網路定期更新收費服務


智慧製造與工業35 (簡禎富 2017 哈佛商業評論)

254

產業與企業層次四大策略關鍵策略關鍵1現有製造優勢與管理經驗系統化與數位化

不只是靠低成本競爭在競爭紅海中存活是賺「管理財」

很大比率早年技職體系培養年齡通常在50到65歲之間hellip

策略關鍵2產品生命週期與營收管理

讓製造系統兼顧前台客製化和後台規模化的效能需要串連設計製造銷售物流服務與保固的管理流程和大數據縮短市場端到製造端的落差

台廠高度分工個別企業難以掌握整個供應鏈的供需數據和產品生命週期各個階段的需求hellip有些公司內部甚至不同資訊系統各自為政沒有整合hellip

策略關鍵3軟硬體設備和分析能力垂直整合

台灣製造業大多中小規模專業分工受限於企業資源和決策者視野的局限以致重視硬體甚於軟體不重視數據分析和決策的軟實力和人才培養

策略關鍵4永續發展和綠色供應鏈

歐盟國家未來更可能以此做為防守其他國家製造業的戰略武器hellip

特別是台灣在資源回收和循環經濟也有隱形冠軍hellip整合到廠務與綠色供應鏈促進產業共生和資源循環利用

簡禎富(2019)工業35台灣企業邁向智慧製造與數位決策的戰略天下文化


馬雲 (201704)

第一次技術革命的能源是煤第二次技術革命的能源是石油第三次技術革命的能源主要是數據所以社會的變革會越來越大每一次技術的變革都是就業的變革hellip

一切業務不是基於數據的忘掉別做了所有數據必須業務化一切數據必須業務化只有這樣才能迎接這個時代

我們要讓機器做人做不好的事情人創造不了的事情這是我認為在Machine intelligence 上面hellip人類有責任和擔當讓機器成為人的合夥人成為人的合作夥伴而不是讓機器來取代這是我們這一代的人

未來三十年已經不是力量的競爭肌肉的競爭甚至不是知識的競爭而是服務別人能力的競爭而是體驗的競爭所以女人在未來的三十年將會蓬勃起來

我們不能一方面說轉型升級一方面還要對落後產業進行保護這是不靠譜的

小型企業創新是靠產品中型企業創新靠技術大型企業創新靠制度

智慧的競爭我們一定要想明白讓孩子們必須去學習音樂體育運動美術音樂讓人有智慧通靈體育運動讓人懂得團隊精神我們讓孩子學會畫畫有想像力我們讓孩子懂得很多知識以外的事情

255


結語

The source of complexity in manufacturing is ldquovariability (變異)rdquo

Automation (自動化) is a powerful way to reduce variability

Data Science facilitates automation and real-time decision

However hellip

1 資料科學是為了ldquo追求真理槓桿資源rdquo非單純的rdquo商業管理或IT

2 資料科學的最終目的在於rdquo決策rdquo而rdquo預測rdquo只是過程

3 如果真的要以data分析務必收集第一手資料 (田野調查訪談)

4 跟rdquo變異rdquo一起共處吧~

5 事實上 hellip凡是能rdquo量化rdquo的可都已經不有趣了 hellip

預測性思維rarr處方性決策

製造資料科學要掌握製造現場(過去現在)並協助企業策略發展(未來)

掌握每個細節製造現場的決策如何影響企業的財務指標

256


結語KPI Hierarchy

257

KPI HierarchyLee and Chien (2020)

ROE

Profit

Margin

Asset

Turnover

Financial

Leveragetimes times

Profit

Sales

Assetsdivide divide

Cost minus Accounts

ReceivableCash + Inventory +

Sales

Price

Sales

Quantity

Effective

Outputs

Realized

Demand

times

minusmin

Price

Elasticity

Fixed

Cost

Variable

Cost+

Bottleneck

Throughput

Bottleneck

Utilization

Yield

times

Bottleneck

Capacity

times

Bottleneck

Machine

MTTR

MTBFMaintenance

Bottleneck

Availability

times

Demand

vs SupplyQuality

DL

Cost

IDL

Cost

Bui amp Fac

Depre

Equip

Cost

Variable

Unit Cost

times

Other

Assets+

ID Mater

Cost

D Mater

Cost

+ + + + +

Labor MaterialFloor

Space

Non-bottle

Machine

Fin

an

cia

l Ind

ex

Ma

nu

factu

ring In

de

xR

eso

urc

e

WIP Delivery

TAT

CVP CIP

Rework

Rate

Cycle

Time

times

Finished

Goods

+

SchedulingProduct-

mixLot Size

Man Machine

Ratio

Decis

ion

TAT = Turn Around Time

CVP = Customer Volume Performance

CIP = Customer (Line) Item Performance

Line

Balancing


結語從大數據到rdquo養rdquo數據hellip

258

MFGcom

DATAcomINNOVATION

com

Technology

Migration

Analytics-oriented

- Prediction

- Troubleshooting

- Customer voice

- Integrated dataset (IoT)

Business-oriented

- New business model

- Technology amp system integration

- Sales amp marketing

- Value-added platform for

manufacturing intelligence

Analytics

Discussion

Implementation

Problem-oriented

- SOP and cost down

- Automation and sensing

- First-hand data quality

From Big to Breeding Data(it generates all kinds and diversityhellip)

Data

(empirical)

Science

(critical)

Technology

(substantial)

Data Quality

(Internal data)

Data Analysis

(Internal+external data)

Data Platform

(Insightful data)Reorganization

Process reengineering

Advanced training



放眼世界我認為「藍海」根本不存在hellip

王品若能成為市場龍頭不是因為有什麼了不起的創新而是所有同仁都老老實實的捲起袖子打拚

讓企業或個人成功的原因絕對不是什麼藍海策略而是那個做到極致絕不放棄的堅持精神

戴勝益 (2014)


致謝

260

感謝

參與AIA課程的學員與

一起為這塊土地打拼的朋友們~

以及

台灣大學資訊管理學系

成功大學資訊工程系暨

製造資訊與系統研究所

謝謝大家~


References 李家岩2015資料探勘課程講義國立成功大學工學院工程管理碩士在職專班台南台灣

簡禎富許嘉裕 2014資料挖礦與大數據分析前程文化

Dong Z-H and C-Y Lee 2017 Equipment Health Monitoring of Analytic Heretical Process Index in Semiconductor

Manufacturing 27th International Conference on Flexible Automation and Intelligent Manufacturing (FAIM2017) 27-30 June

2017 Modena Italy

Guyon I and A Elisseeff 2003 An Introduction to Variable and Feature Selection Journal of Machine Learning Research 3

1157ndash1182

Han J M Kamber and J Pei 2011 Data Mining Concepts and Techniques 3rd edition Morgan Kaufmann

Hillier F Sand G J Lieberman 2010 Introduction to Operations Research 9th ed McGraw-Hill New York

Hsu S and C Chien 2007 Hybrid Data Mining Approach for Pattern Extraction from Wafer Bin Map to Improve Yield in

Semiconductor Manufacturing International Journal of Production Economics 107 88ndash103

Hung S-Y Y L Lin C-Y Lee 2017 Data Mining for Delamination Diagnosis in the Semiconductor Assembly Process 27th

International Conference on Flexible Automation and Intelligent Manufacturing (FAIM2017) 27-30 June 2017 Modena Italy

Lee C-Y and M-C Chiang 2016 Aggregate Demand Forecast with Small Data and Robust Capacity Decision in TFT-LCD

Manufacturing Computers amp Industrial Engineering 99 415ndash422

Lee C-Y and A L Johnson 2013 Operational Efficiency book chapter edited in Badiru A B (Editor) Handbook of

Industrial and Systems Engineering 2nd Edition 17-44 CRC Press

Lee C-Y and A L Johnson 2015 Measuring Efficiency in Imperfectly Competitive Markets An Example of Rational

Inefficiency Journal of Optimization Theory and Applications 164 (2) 702ndash722

Lee C-Y and T-L Tsai 2019 Data Science Framework for Variable Selection Metrology Prediction and Process Control in

TFT-LCD Manufacturing Robotics and Computer-Integrated Manufacturing 55 76-87

Lee C-Y 2019 Pitfalls and Protocols in Practice of Manufacturing Data Science arXiv httpsarxivorgabs190604025

Liu C-W and C-F Chien 2013 An intelligent system for wafer bin map defect diagnosis An empirical study for semiconductor

manufacturing Engineering Applications of Artificial Intelligence 26 1479ndash1486

Savage L J 1951 ldquoThe theory of statistical decisionrdquo Journal of the American Statistical Association 46 55ndash67

Wu M-Y and C-Y Lee 2015 Sampling-based NSGA-II for Stochastic Scheduling in Auto Parts Manufacturer 2015 Chinese

Institute of Industrial Engineers (CIIE) Conference amp Annual Meeting Taichung Taiwan

261

Contact Information

name 李家岩 (Chia-Yen Lee)

phone 02-33661206

email chiayenleentuedutw

web httpspolabimntuedutw

感謝大家的支持跟參與還請多多指教

台灣人工智慧學校- 智慧製造與生產線上的資料科學httppolabimntuedutwTalkData_Science_in_Manufacturingpdf

- 預測之外跨越預測與決策間的鴻溝httppolabimntuedutwTalk20201114_Beyond20the20Predictionpdf


Experience

教授國立台灣大學資訊管理學系

教授兼所長國立成功大學資訊工程學系暨製造資訊與系統研究所

副編輯IEEE Transactions on Automation Science and Engineering (SCI)

半導體廠科技顧問台積電工業工程師陸軍少尉資訊官

Award

IEEE Senior Member(2021)呂鳳章先生紀念獎(2019)

美光教師Micron Teacher Award (2018)

李國鼎科技與人文講座研究獎 (2018)

科技部吳大猷先生紀念獎 (2017)

Research Interest 製造數據科學智慧型製造系統生產力與效率分析生產經濟學多目標決策

Education

PhD 工業與系統工程 Texas AampM University USA(Major Operations Research作業研究運籌學)

MS工業工程與工程管理國立清華大學

BS amp BBA應用數學暨資訊管理國立政治大學


Hype Cycle 2020

3



Outline

4











5






Starting

material

Material in

processing

Processed

material

Value-added




7



Knowledge

詮釋的觀點

思辨的過程

科學的原理


迷思資料資訊



9





10

北南

Etu蔣居裕 (2013)


Experiencehellip


失敗的藝術

人生的歷練


知識與經驗之



Wisdom ishellip


Wisdom ishellip

13





13







智慧工廠



15

智慧工廠

智慧製造

製造智慧



(製造系統)

16


Value and Profit

Value




17

Price

Value

Cost

Consumer

Surplus

Producer

Surplus

Wikipedia (2016)


製造智慧決策

18



SPC APC VM RMS

Carbon

Emission

Water

Recycle


Energy



VRARAI

Cloud

Computing

Cyber-

Physical

System


RFIDSmart Labels



















Inventory



Inventory Reduction







Chien et al (2004)




22



23




24




















26





其實hellip


27

English Math

Student_A 80 76

Student_B 80 91

Student_C 80 83

Student_D 80 62

Student_E 80 88

Layer X Layer Y

Machine_A 81 76

Machine_B 80 91

Machine_C 79 83

Machine_D 80 62

Machine_E 82 88


來自於變異




MES

APC

FDC

SPC

VM

R2R

RMS



Yield Management

hellipetc

Demand Forecast



CapEx

Cost Structure

MPS amp MRP



Order Releasing

hellipetcQuality

Productivity

Cost Down

Cycle Time

28


CIM and Automation

29


ISBN 0-471-93450-X



Benefits

Reduce HR Cost

Reduce MO


Productivity




Benefits

Sustain EQ variance


Support RD




CIM and Automation





31



轉變hellip



一種改善過程

32





1 Transportation

2 Inventory

3 Motion

4 Waiting

5 Overproduction

6 Overprocessing

7 Defects

8 Eschewed Talents

Continuous flow

Line Balancing


Lean Manufacturing


33





CIM and Automation

34

AMHS

MES APC

FMEC



Big Data

Analytics


Data

Warehouse

Knowledge


Selection

Preprocessing

Target Data

Preprocessed

Data

Pattern

Transformed

Data

Data Mining

Transformation

Interpretation

Evaluation



IT Infrastructure

Pattern Extraction



35

Edge

Computing







Problems




製造現場



一言九鼎(頂)



Ask Why








38


生產線數據


39


Characteristic

Pure Feature-



(between features)











Color Images 3D

Scans and Videos



correlation







40



















特性與問題




Data Preprocessing

42

Data

Warehouse

Knowledge

Selection

Preprocessing

Target Data

Preprocessed

Data

Pattern

Transformed

Data

Transformation

Data Mining

Interpretation

Evaluation





Lot001 Lot001 Pass







Lot ID Pass or Fail

Lot001 Pass

Lot002 Pass

Lot003 Fail

Lot004 Pass


Lot001 Pass 20

Lot002 Pass 25

Lot003 Fail 10

Lot004 Pass 15

75 857


Lot002 hellip


Lot002_1

Lot002_2


Parallel Machine


Data Preparation

Missing Value

44


WS_A_Mach_2_Temp

Lot001 820 NA

Lot002 820 NA

Lot003 NA 840

Lot004 NA 840

Lot IDWS_A_Temp

WS_A_Mach_Type

Lot001 820 1

Lot002 820 1

Lot003 840 2

Lot004 840 2

WS_A_Mach_1

WS_A_Mach_2



Golden Machine


Missing Value

45


WS_A_Mach_2_Temp

Lot001 820 NA

Lot002 820 NA

Lot003 820 NA

Lot004 830 NA

Lot005 820 NA

Lot006 820 NA

Lot007 825 NA

Lot008 830 120

Lot009 820 130

Lot010 NA 120


WS_A_Mach_2_Temp

Mach_1 Mach_2

Lot001 820 Avg 1 0

Lot002 820 Avg 1 0

Lot003 820 Avg 1 0

Lot004 830 Avg 1 0

Lot005 820 Avg 1 0

Lot006 820 Avg 1 0

Lot007 825 Avg 1 0

Lot008 830 120 1 1

Lot009 820 130 1 1

Lot010 Avg 120 0 1






46


Lot001 PartsA

Lot002 PartsB

Lot003 PartsA

Lot004 PartsC

Lot005 PartsD

Lot006 PartsE

Lot007 PartsB

Lot008 PartsA

Lot009 PartsC

Lot010 PartsE


WS_A_Mach_1_PartsB

WS_A_Mach_1_PartsC

WS_A_Mach_1_PartsD

Lot001 1 0 0 0

Lot002 0 1 0 0

Lot003 1 0 0 0

Lot004 0 0 1 0

Lot005 0 0 0 1

Lot006 0 0 0 0

Lot007 0 1 0 0

Lot008 1 0 0 0

Lot009 0 0 1 0

Lot010 0 0 0 0






建議方式







沒有再現性

47



抽樣檢測

48




NO001 鋁 A 13723 7235

NO002 鋁 B NA NA

NO003 鋁 B 13728 7237

NO099 鋁 B NA NA

NO100 鋁 A 13726 7236

X Y (抽檢)

沒被抽檢

沒被抽檢

抽樣

填補遺漏值



3 Prediction Model








49









有母數GLMRandom


Learninghellip


換線換模






50

Machine A A A


Machine A B


B B B

A B A B









51

MachineI2

A A AMachine1

B B


A A A

Machine2

A A AMachine1

A A A

B

B




瓶頸 (bottleneck)







52


120

unitsday

140

unitsday

80

unitsday

120

unitsday

100

unitsday

瓶頸

80 unitsday



(勞工和幹部)



楊大和(2016)










53





54

IDProduct

TypeStage

Process

Time (hrs)

Start

Time

Lot1 A 1 1 20161226 1450

Lot1 A 2 1 20161226 1600

Lot1 A 3 05 20161226 1720

Lot1 A 4 1 20161226 1800

Lot1 A 5 05 20161226 2030







55


211 000000

211 010000

211 020000

211 230000


211 000629

211 001041

211 034109

211 231157




Data Merge

56









建議串接方法

Rolling Forward

Nearest time

Rolling Forward

Rolling Backward

Nearest time




Lee and Dong (2019)






產品的queue time



57

STA

GE

x_S

VID

x

0 5

10

1

5

2

0

2

5

0 200 400 600 800 1000Lot or

Time






58


Time Downcode


2017-05-07140528


2017-05-07161214


2017-05-07174130



2017-05-07192243


2017-05-07201817




19 22 43 minus (16 12 14)








10 vs 90 5 vs 95 or 1 vs 99



predictionhellip



59




Lot01 PASS

Lot02 PASS

Lot03 PASS

Lot04 PASS

Lot05 PASS

Lot06 PASS

Lot07 FAIL

Lot08 PASS

Lot09 PASS

Lot10 PASS

Lot11 PASS

Lot12 PASS





準確度可達 1112 = 917



迷思


61



62


資料整合













迷思補遺漏值


63

English Math

Student_A 80 76

Student_B 80 91

Student_C 80 83

Student_D 80 62

Student_E 80

Avg 80

Max 91

Min 62

Avg 78


迷思補遺漏值

64













64








B 男 51 $64000 Yes

C 男 52 $105000 Yes

D 女 33 $55000 Yes

E 男 45 $45000 No

F 女 45 $100000


65



66

K=3

K=5




迷思補遺漏值

67


1 00886 00886 00886 00886

2 00684 00684 00684 00684

3 03515 03515 03515 03515

4 09874 09874 09874 09874

5 04713 04713 04713 04713

6 06115 06115 06115 06115

7 02573 02573 02573 02573

8 02914 02914 02914 02914

9 01662 01662 01662 01662

10 044 044 044 044

11 06939 03731 06622

平均值 04023 03731 03731 03994

標準差 02785 02753 02612 02753

誤差值 03208 00317




數據品質

68






資料品質

Univariate





Multiple Column




數據品質



69



Automobile Company




digital materials







71















72






Feature Selection






74








75

材料

設計

光罩


測試

封裝

最後測試

加熱製程

微影製程

離子佈植


介電質沉積

晶圓


Over 1000 stages










and unreliable




76




77


Root Cause As-Is



To-Be

Data Science

Automation









78

K

C

H

E

A

G

I

J

F

L

OR

DS

BP M

N

Q






Rule Extraction




79

Good 68 68

Bad 32 32

Good - -

Bad 23 100

Good 68 88

Bad 9 12

Good - -

Bad 6 100

Good 68 96

Bad 3 4





OK

NG

NG

NG

NG

NG NG NG

OK

OK

OKOK OKOK

NG

YES NO

YES

YES YES

YESYES

YES

NO

NO

NO

NO NO

NO

80

Map clustering for

systematic defects

12 defect patterns

and build WBM bank





(Lee and Tsai 2019)



81




(Wang2012）





29 Alarm

16 Prediction model

training

15 EWMA for Target

Baseline (TB)



24 Predicted

CUSUM out of

control

25 Pre-alarmYes

No

28 Actual

CUSUM out of

control

Yes

No


21 New sample

prediction



17 Model validation

34 Continuous

monitoring

11 Data collection

26 Engineering

Validation amp

Troubleshooting

31 Loss calculation


32 CUSUM

control chart

33 Loss

CUSUM out of

control

310 Add new samples


311 ILPM model


Yes

Off-line training

In-line prediction

Concept drift

Pre-alarm stage


correction

No

All good products

37 Bayesian

monitoring out

of control

35 Equipment



39 Update posterior


38 Alarm and

equipment

maintenance

Yes

Model misalignment


Equipment

misalignment


36 Lifetime

out of control

No

Yes



82







83





Self-Priming

Centrifugal Pump



84




Feature Selection

Feature Engineering

85

Data

Warehouse

Knowledge

Selection

Preprocessing

Target Data

Preprocessed

Data

Pattern

Transformed

Data

Transformation

Data Mining

Interpretation

Evaluation




易於決策判斷









精度預測





86



Feature Selection



ie p gtgt n issue




87

An

p

Xn

k k ltlt p








Types









(PCA) etc

88







89

Lee and Chen (2018)



90

Prepared

Dataset

Feature

Selection

LASSO SVMStepwise

Regression

Voting


Pivot

Analysis

Engineering

Experience

Feature

Validation

BoostingRandom

ForestPCA Random

Sampling

Data

Reduction

(pgtgtn)

Imbalance

Correlation

Coefficient

Independence

Testhellip

Data

Preprocessing

hellip

Yes

No

Knowledge

Management (KM)

Documentation

Lee and Tsai (2019)

iterative

process






同理hellip

因果rarr相關







91








92

119910 = 120572 + 1205731199091 + 120576

119910 = 120572 + 1205731199092 + 120576

119910 = 120572 + 1205731199093 + 120576

119910 = 120572 + 1205731199094 + 120576

119910 = 120572 + 12057321199092 + 1205731199091 + 120576

119910 = 120572 + 12057321199092 + 1205731199093 + 120576

119910 = 120572 + 12057321199092 + 1205731199094 + 120576

119910 = 120572 + 12057321199092 + 12057341199094 + 1205731199091 + 120576

119910 = 120572 + 12057321199092 + 12057341199094 + 1205731199093 + 120576

統計顯著的變數1199092 and 1199094



መ120573119897119886119904119904119900 = argmin120573

σ119894=1119873 (119910119894 minus 1205730 minus σ119895=1

119875 119909119894119895120573119895)2

Subject to σ119895=1119875 120573119895 le 119905


1

2σ119894=1119873 (119910119894 minus 1205730 minus σ119895=1

119875 119909119894119895120573119895)2 + 120582σ119895=1

119875 120573119895

93


Penalty( 120582 ) x1 x2 x3 x4 x5 x6 x7

120582 = 0

120582 = 40

120582 = 418

120582 = 419

120582 = 42

120582 = 50





94


x12

x11

x10

x9

x8

x7

x6

x5

x4

x3

x2

x1

Feature Importance



Voting (投票法)



95



SVID_003 4

SVID_101 3

SVID_021 3

SVID_040 3

SVID_002 3

SVID_128 2

SVID_062 2

SVID_077 2






96

Test

Test

Test

Test


1st iter

2nd iter

3rd iter

10th iter

hellip

Error1

Error2

Error3

Error10

Minimize Error=1

10σ119894=110 Error119894



97


Undersampling



Example








SVIDVoting by

Undersampling

SVID_003 19

SVID_101 18

SVID_021 18

SVID_040 18

SVID_002 17

SVID_128 17

SVID_062 17

SVID_077 17

hellip hellip




98


SVID_003 09487 02583 11439

SVID_101 02078 05434 08934

SVID_021 04105 08377 06845

SVID_040 5208 7169 03170

SVID_002 27256 21025 02581

SVID_128 80523 85336 00580

SVID_062 09430 09747 00330

SVID_077 1569 1603 00216



Photo_06 12 384 00313

Etch_10 3 295 00102

Photo_32 10 1011 00099

Photo_17 4 410 00098

PVD_02 1 123 00081

CVD_14 9 3456 00026

Diff_09 1 495 00020

Etch_07 5 2769 00018



良品119886119907119892 minus不良品119886119907119892

119860119907119892

RATIO = FAIL TOTAL





99








迷思



100



Feature Engineering









119903 = 11990912 + 1199092

2

120579 = arctan11990921199091


101


119903

120579

1199091

1199092













Trend (趨勢)



Randomness (隨機)




102

Σ

A

A1 A2

B

B1 B2

C

C1 C2

人

人




103





預測

良品不良品




Benefits




104



105

Dataset with

selected variable

Prediction

Classification

Model

PLS BPNN CNN


R-Squared

MSE

Confusion

Matrix

Model

Evaluation

BoostingDecision

TreeSVR

Random

Sampling

Data

Transformation

Imbalance

Categorical to

Dummy VarFeature

Extraction

Feature

Selection

hellip

Yes

No

Knowledge

Management (KM)

Documentation


Z-scores


iterative

process















Data Imbalance

106










107

helliphellip

Input

Layer

Hidden

Layer

Output

Layer

hellip

helliphellip

helliphellip

helliphellip

helliphellip

helliphellip

helliphellip

x1

x2

xm

ො1199101

ො1199102

ො119910n

y1

y2

yn

NN

Output

Desired

Output




108







109

Yie

ld

Pre

cis

ion

Metr

olo

gy V

alu

e

Lot

Real value







110

UCL

LCL

Yie

ld

Pre

cis

ion

Metr

olo

gy V

alu

e

Lot

Real value









TNTP

+++

+=Accuracy


預測類別


實際類別

類別1


FN (false negative)

(Type II error)

(miss)

類別2

(良品)

FP (false positive)

(Type I error)

(false alarm)

TN (true negative)

111











112

TPSensitivity

TP+FN=

TNSpecificity

TN+FP=

預測

類別1 類別2

實際

類別1 TP FN

類別2 FP TN




TP

Rate

= S

ensitiv

ity

Model A

Model B

Precision=TP






113

Testing


Model A 719 897 517 702

Model B 781 691 883 789

Model A預測

Bad Good

實際Bad 61 7

Good 29 31

Model B預測

Bad Good

實際Bad 47 21

Good 7 53


精度良率預測







114

Time

Y

UCL

LCL

Time

Y

UCL

LCL





double EWMA




EWMA Control


115


Liu et al (2018)



116


維修保養








117











118
























119




120


No 名稱 No 名稱




4 R扣環 12 風扇


6 S扣環 14 風罩






Vibration Dataset

121

Amplitude

Time

(Obs)



Lee et al (2019)





122


Inspection

zone

Preventive

replacement

zone

Corrective

replacement

zone

Failure level

Replacement level

Data collection RUL




123

(Lee et al 2014)















124





Feature Engineering

125

Peak-

to-

peak




Data

Collection

Data

Preprocessing



Feature

Extraction

Feature

Selection

Remove high



(VIF)



Important

Variables

Predict

Linear Regression

(OLS)


Prediction Result


Regression (PLS)

Prediction

Model

OLS


PLS


BPNN

MSE = 123456789

Feature Engineering

(製造資料)





127



Feature Engineering









129




29 Alarm

16 Prediction model

training

15 EWMA for Target

Baseline (TB)



24 Predicted

CUSUM out of

control

25 Pre-alarmYes

No

28 Actual

CUSUM out of

control

Yes

No


21 New sample

prediction



17 Model validation

34 Continuous

monitoring

11 Data collection

26 Engineering

Validation amp

Troubleshooting

31 Loss calculation


32 CUSUM

control chart

33 Loss

CUSUM out of

control

310 Add new samples


311 ILPM model


Yes

Off-line training

In-line prediction

Concept drift

Pre-alarm stage


correction

No

All good products

37 Bayesian

monitoring out

of control

35 Equipment



39 Update posterior


38 Alarm and

equipment

maintenance

Yes

Model misalignment


Equipment

misalignment


36 Lifetime

out of control

No

Yes


Engineering



















hellip

130
















hellip

131






ldquo機會rdquo


132




133


很多時候我們


134

事實上hellip


現場改善

資料科學

系統整合

資料品質確認


浪費與WIP

瓶頸站生產力

人機比

設施佈置

環境公安衛生


流程再造BPR

時間動作研究



浪費移除

產線平衡


IT基礎建設

Make-or-Buy

需求預測

產銷平衡

排程與交期

特徵選取

Troubleshooting

機台維修保養


預測方法


啟發式演算法

機器學習


系統開發

供應鏈平台JIT



製程能力優化

良率提升



組件剩餘壽命


資料不一致





Decision Science

New Business Model


Price Maintenance


Sustainability

資料分析確認

Lee and Chien

(2020)


可能會問hellip




136


資料科學






現場觀察


137


話說hellip


某廠區稼動率116200 = 58







138



139

魚骨圖

法



環境


少量多樣

溝通管道

其他

交班傳達不周

人

人力缺乏



等待人員操作

機

機台維修保養

模具更換


待料


料


在製品堆放

機台稼動率低


作業不熟練

需求變異

工程變更

政策法規改變

傳承關係





案例





eg (56+160+138 mins)(180+180+180 mins)

=656

140




案例





eg (56+160+138 mins)(180+180+180 mins)

=656

141


(分)作業

耗時

(分)作業

耗時

(分)作業

耗時

(分)




1427-1430 產品品質檢測 3

1430-1443 電腦資料輸入 13


1450-1454 電腦工程分析 4

1454-1500 領取原物料 6

1500-1515 休息 15

1515-1528 領取模具 13

1528-1533 產品品質檢測 5


1543-1548 換模具 5


1601-1610 領取模具 9

1610-1617 產品品質檢測 7

1617-1622 存放載具 5

1622-1631 產品品質檢測 9


1640-1647 產品品質檢測 7


1652-1655 領取原物料 3

1655-1700 電腦資料輸入 5

機器加工

(產品D)

機器加工

(產品C)

13

124


停機

等待換規格

換模

停機

待料

機器加工

(產品A)

機器加工

(產品B)

機器加工

(產品C)

43

140

20

88

42

50

機器加工

(產品B)







200 80 = 160 (台) 到 200 85 = 170 (台) 之間為理想機台運作數



142









=工作效率




=08

1minus0656= 233 (台)


143






缺點很花時間






144





A 全部hellip

現場rarr瓶頸站





目標的衝突


145

Strategic Level


Planning

Marketing

Planning

Make-or-Buy

Strategy

Tactical Level


Planning


Order Allocation

Master Production

Schedule

Resource Planning

Rough-Cut Capacity

Planning

Capacity Require

Planning

Material Require

Planning

Monthly Material

Planning

Capacity Planning

Productivity amp

Efficiency Analysis

Vendor Relationship

MgmtDemand Mgmt


Purchasing


Daily Assignment

Order Releasing


Scheduling



Production


Operational Level

Logistics Mgmt

Long Term

Mid Term

Short Term

Facility Layout






146




timeProduction


uptimeEquipment

timeProduction

timeTotal

uptimeEquipment

timeTotal


=

=

=

Nonscheduled

state

Unscheduled

down state

Scheduled

down state

Engineering

state

Standby

state

Productive

state

Equipment

uptime

Equipment

downtime

Operations

time

Production

time

Total

time



147

顧客訂單產品

交期變動插單

工程變更




操作員

人力不足

MO


人員配置


機台設備廠務





廠區間的Backup



停工待料


外包時程變異

進料品質變異

















148






優先順序

日期達交












衝突目標

Makespan


(TWET)

交期

利用率

庫存時間



排程應用範疇


機場飛機起降



電梯設定

微處理器系統

醫院排班

醫院復健排程

醫師手術排班




150




人工排程邏輯

訂單資料

依到期日排序


預估單

工作號賦予




Yes

No


No





優先順序法則

Dispatching










Rush 緊急事件

152




剩餘作業數




Performance Metrics

Mean Flow Time






119879119895 = max0 119871119895


N Jobs on 1 Machine


N Jobs on 1 Machine




Notations



119889119895 due date

154


1 11 61

2 29 45

3 31 31

4 1 33

5 2 32


N Jobs on 1 Machine

FCFS



Tardy Jobs 3

155


J1 11 11 61 0

J2 29 40 45 0

J3 31 71 31 40

J4 1 72 33 39

J5 2 74 32 42

Totals 74 268 121





N Jobs on 1 Machine

SPT



Tardy 1

156


J4 1 1 33 0

J5 2 3 32 0

J1 11 14 61 0

J2 29 43 45 0

J3 31 74 31 43

Totals 74 135 45


N Jobs on 1 Machine

EDD



Tardy 4

157


J3 31 31 31 0

J5 2 33 32 1

J4 1 34 33 1

J2 29 63 45 18

J1 11 74 61 13

Totals 74 235 33


N Jobs on 1 Machine






Compute


158

119862119877 =119863119906119890_119863119886119905119890 minus (119862119906119903_119879119894119898119890)

119875119903119900119888119890119904119904119894119899119892_119879119894119898119890


CR

N Jobs on 1 Machine

159

JOBPr

Time

D

DateCR

Current Time = 0

1 11 61 5546

2 29 45 1552

3 31 31 100

4 1 33 33

5 2 32 16

JOBPr

Time

D

DateCR

Current Time = 31

1 11 61 2727

2 29 45 483

4 1 33 2

5 2 32 05


N Jobs on 1 Machine

160

JOBPr

Time

D

DateCR

Current Time = 60

1 11 610091

do last

4 1 33 -27

5 2 32 -14

JOBC

Time

D

DateTardy

Summary

3 31 31 0

2 60 45 15

4 61 33 28

5 63 32 31

1 74 61 13

Total 289 87

Tie use SPT

CR

Mean F Time (289)5 = 578


Tardy 4



FCFS


SPT




EDD



CR


Sequencing Rules

due Time

FCFS

CRSPT

EDD


然而hellip








162



快速換模技術









163



快速換模技術









4改善內部換模

平行作業


5改善外部作業




164





NP-hard problem













Local optimum

Short running time

Global optimum

Long running time


Meta-heuristics






166

f(x)

x

Local optimum

Global

optimum

Meta-heuristics

ldquoJUMPrdquo

119909119905+1 larr 119909119905 + 120578120597119891

120597119909


120597119891

120597119909

119909119905 119909119905+1

120578



Basis











Neighborhood Search


promising regions








memory




go to step 3



















= 500




Due Date(119941119947)

Weights (119960119947)

1 10 4 14

2 10 2 12

3 13 1 1

4 4 12 12




(1243) (2413) and (2134)

119879 1243 = 480 119879 2413 = 436 and 119879 2134 = 652





(4213) (2143) TABU and (2431)

119879 4213 = 460 119879 2143 = 500 TABU and 119879 2431 = 608







(2413) TABU (4123) and (4231)

119879 2413 = 436 TABU 119879 4123 = 440 and 119879 4231 = 632





(1423) (4213) TABU and (4132)

119879 1423 = 408 119879 4213 = 460 TABU and 119879 4132 = 586





Metaheuristics


172

1199091


1199610


1199611 1199612



Global

optimum










exploration

exploitation

(Gen 2005)


If you hellip





175


Interfaces

1 Gantt Chart

2 Dispatch List

3 Capacity Buckets


Scenario

Management

System

Maintenance

Performance

Control

Algorithm

Generator

Interface

Algorithm

Generator

Scheduler amp

Dispatcher

Preprocessor

Scheduling amp

Rescheduling

Algorithms

Manufacturing

Execution

System (MES)

Enterprise

Resource

Planning (MRPII)

Production

Monitoring

System

Database

ImportExport

Synchronization


Algorithm

Library


Scheduling

Logic Unit

Order

Master

File

Shop-

Floor

Data



176







178

Capacity Buckets






改善的機會


講究的是synergy








179












180














Rescheduling

181








Hint WIP



182


Pull Strategy

High Uncertainty

Push Strategy

Low Uncertainty

WIP


Lateness









processing time



HVLV HV

HVHV HV

LVLV LV

LV LVHV

Process Variability

Inflow Variability


迷思










現場動態調整

184






185



再過一陣子





186



在製造業中





187









188







190


迷思


191


迷思

這是當然的


找出關鍵因子

建構因果關係




192



193

為什麼要預測


下一步為何


預測像hellip

194


預測像hellip

195




B2A1E9818B3F




196




197





198






瞭解這就hellip


199






200


其實hellip




201


決策的類型





202


小試身手hellip

天氣與決策

203

不帶傘帶傘





3 拿別人的傘

(良心不安)


小試身手hellip

204


神預測God2GO



小試身手hellip


205

機率02

機率08



方法一期望值







小試身手hellip


206

機率02

機率08





風險成本矩陣

不帶傘帶傘

晴天

成本 $0 成本 $100

(弄丟)

雨天

成本 $200

(感冒)

成本 $0

期望成本

02x0

+08x200

=160

02x100

+08x0

=20

決策帶傘


小試身手hellip


207



風險成本矩陣

不帶傘帶傘

晴天

成本 $0 成本 $100

(弄丟)

雨天

成本 $200

(感冒)

成本 $0

期望成本

02x0

+08x200

=160

02x100

+08x0

=20

決策帶傘

切記hellip


又或hellip



由此可知hellip




208

Lee (2019)


小試身手hellip


209

Based on your

Preference

Structure








210



併購公司A 42 21 8

購置機台 35 28 13

外包 28 25 23







211

天氣情境

方案景氣好

景氣持平

景氣差

Min

Return

併購公司A 42 21 8 8

購置機台 35 28 13 13

外包 28 25 23 23






212

天氣情境

方案景氣好

景氣持平

景氣差

Max

Return

併購公司A 42 21 8 42

購置機台 35 28 13 35

外包 28 25 23 28








213

悔惜矩陣

景氣好

景氣持平

景氣差

Max

Regret

0 7 15 15

7 0 10 10

14 3 0 14

天氣情境

方案景氣好

景氣持平

景氣差

併購公司A 42 21 8

購置機台 35 28 13

外包 28 25 23






214

天氣情境

方案景氣好

景氣持平

景氣差

併購公司A 42 21 8

購置機台 35 28 13

外包 28 25 23






215




Two Types of Risk



Time

Demand

Demand

A

B

C

大試身手hellip

0




Time

Demand

Demand


0

追高殺低


大試身手hellip






218






Scenario Simulator



Time

Demand

Marketing Forecast

Sales Forecast

大試身手hellip

0

Capacity Level






shortage


Linear Regression

Autoregression

Neural Network





220


Empirical Study




221

Capacity Regret

Assessment

CustomerInventory

Market

Share

Profit

Loss

Loss of

Falling Price

Inventory

Loss

Holding

CostReputation

Lower

Capacity

Level

Higher

Capacity

Level

ALTERNATIVE

OBJECTIVE

ATTRIBUTE

119877119904ℎ119900119903119905119886119892119890 缺貨風險119877119904119906119903119901119897119906119904 存貨風險



Empirical Study


222

119877119904ℎ119900119903119905119886119892119890 缺貨風險愈大產能水準向上拉

119877119904119906119903119901119897119906119904 存貨風險愈大產能水準向下壓

119863119898119886119909

119863119898119894119899

Capacity Decision


0

10000

20000

30000

Training

Dataset

Validation

Dataset

Technology

Node A

Time

Demand

Empirical Study

Data Source






223



Empirical Study

2-stage approach

Demand Forecast

Capacity Decision

VDGP


(Chang et al 2014)

224



Empirical Study




225

0

10000

20000

30000

Training

Dataset

Validation

Dataset

Technology

Node A

Time

Demand

Linear Regression

Autoregression

Neural Network


Empirical Study







119877119904ℎ119900119903119905119886119892119890 = 0521 and 119877119904119906119903119901119897119906119904 = 0479

226



MonthActual

Demand


EV MMR SP

Aug 2014 19499 20207 16941 17157 18922Sep 2014 18110 21305 17921 18306 19135Oct 2014 15059 22404 18536 19291 18885



Empirical Study


227

0

500

1000

1500

2000

0 300 600 900 1200

StandardDeviation

AverageRegret

Current

Policy

EVMMR

SP

Poor

Better

Better Poor




Min 119862119909 + 119864 119891 119909 ෩119863




119910+ 119910minus ge 0












228





229

Testing

Accuracy AUC

Model A 719 702

Model B 781 789

Model A預測

FAIL PASS

實際FAIL 61 7

PASS 29 31

Model B預測

FAIL PASS

實際FAIL 47 21

PASS 7 53



迷思


230


迷思

231

170cm

165cm 175cm

172cm



232















233



234



235











going on now






used here

236












237











238




1 1 0 4

2 0 2 12

3 3 2 18

Profit ($1000) $3 $5 0

1823

122

4 st

53

21

21

2

1

21

+

+=

xx

xx

x

x

xxZ


Graphical Solution


feasible region


0

1823

122

4 st

53

21

21

2

1

21

+

+=

xx

xx

x

x

xxZ


Graphical Solution




最佳化結果


6個產品2 (x2)


這就是處方~



遇到問題



提供solution


241



242

Domain Knowledge




243

處方性分析


DS in

MFG










為大於其細


方案評選


見

識

謀

斷


發想

收斂




執行對策

膽大心細

決策與行動

行




245

Descriptive

敘述性

Diagnostic

診斷性

Predictive

預測性

Prescriptive

處方性

Automating

自動性

見

What



Why



When


HowWho Where


戰情財報



(掌握趨勢)



(持續改善)

識謀斷行

U N I S O N


結語

Conclusion

246


迷思



247


迷思










248


迷思


249



Basic

interpretable

models

Post-hoc

Explanation

RegressionBased

Tree Based

DeepLearning

Linear Logistic

regression

Lasso Ridge

GLM GAM

Decision Tree

RF XGBoost

LightGBM

RF

DNN CNN RNN

helliphellip


(build-in)

DataFeature

EngineeringML

Models

Prediction Result

(build-in)

X

Post-hoc Methods


(plug-in)

FeatureImportance

洪紹嚴 (2019)



250

Yield

Time

Cost

Yield

New Tape-out (NTO)

研發導入

Device

optimization

during process

integration

Engineering

Parameter

Optimization

Design of

Experiments

成長期

Tool Matching

Benchmarking

Troubleshooting

Scheduling

Spec Setting SPC






成熟期

快速良率提升

Yield ramp

during pilot

production



during mass

production







機人


迷思




251








迷思

252







253




工業30





工業40








254














馬雲 (201704)








255


結語




However hellip









256


結語KPI Hierarchy

257


ROE

Profit

Margin

Asset

Turnover

Financial

Leveragetimes times

Profit

Sales

Assetsdivide divide

Cost minus Accounts


Sales

Price

Sales

Quantity

Effective

Outputs

Realized

Demand

times

minusmin

Price

Elasticity

Fixed

Cost

Variable

Cost+

Bottleneck

Throughput

Bottleneck

Utilization

Yield

times

Bottleneck

Capacity

times

Bottleneck

Machine

MTTR

MTBFMaintenance

Bottleneck

Availability

times

Demand

vs SupplyQuality

DL

Cost

IDL

Cost

Bui amp Fac

Depre

Equip

Cost

Variable

Unit Cost

times

Other

Assets+

ID Mater

Cost

D Mater

Cost

+ + + + +

Labor MaterialFloor

Space

Non-bottle

Machine

Fin

an

cia

l Ind

ex

Ma

nu

factu

ring In

de

xR

eso

urc

e

WIP Delivery

TAT

CVP CIP

Rework

Rate

Cycle

Time

times

Finished

Goods

+

SchedulingProduct-

mixLot Size

Man Machine

Ratio

Decis

ion




Line

Balancing



258

MFGcom

DATAcomINNOVATION

com

Technology

Migration

Analytics-oriented

- Prediction

- Troubleshooting

- Customer voice


Business-oriented






Analytics

Discussion

Implementation

Problem-oriented

- SOP and cost down




Data

(empirical)

Science

(critical)

Technology

(substantial)

Data Quality

(Internal data)

Data Analysis


Data Platform



Advanced training






戴勝益 (2014)


致謝

260

感謝



以及




謝謝大家~






2017 Modena Italy


1157ndash1182





















261

Contact Information


phone 02-33661206







Hype Cycle 2020

3



Outline

4











5






Starting

material

Material in

processing

Processed

material

Value-added




7



Knowledge

詮釋的觀點

思辨的過程

科學的原理


迷思資料資訊



9





10

北南

Etu蔣居裕 (2013)


Experiencehellip


失敗的藝術

人生的歷練


知識與經驗之



Wisdom ishellip


Wisdom ishellip

13





13







智慧工廠



15

智慧工廠

智慧製造

製造智慧



(製造系統)

16


Value and Profit

Value




17

Price

Value

Cost

Consumer

Surplus

Producer

Surplus

Wikipedia (2016)


製造智慧決策

18



SPC APC VM RMS

Carbon

Emission

Water

Recycle


Energy



VRARAI

Cloud

Computing

Cyber-

Physical

System


RFIDSmart Labels



















Inventory



Inventory Reduction







Chien et al (2004)




22



23




24




















26





其實hellip


27

English Math

Student_A 80 76

Student_B 80 91

Student_C 80 83

Student_D 80 62

Student_E 80 88

Layer X Layer Y

Machine_A 81 76

Machine_B 80 91

Machine_C 79 83

Machine_D 80 62

Machine_E 82 88


來自於變異




MES

APC

FDC

SPC

VM

R2R

RMS



Yield Management

hellipetc

Demand Forecast



CapEx

Cost Structure

MPS amp MRP



Order Releasing

hellipetcQuality

Productivity

Cost Down

Cycle Time

28


CIM and Automation

29


ISBN 0-471-93450-X



Benefits

Reduce HR Cost

Reduce MO


Productivity




Benefits

Sustain EQ variance


Support RD




CIM and Automation





31



轉變hellip



一種改善過程

32





1 Transportation

2 Inventory

3 Motion

4 Waiting

5 Overproduction

6 Overprocessing

7 Defects

8 Eschewed Talents

Continuous flow

Line Balancing


Lean Manufacturing


33





CIM and Automation

34

AMHS

MES APC

FMEC



Big Data

Analytics


Data

Warehouse

Knowledge


Selection

Preprocessing

Target Data

Preprocessed

Data

Pattern

Transformed

Data

Data Mining

Transformation

Interpretation

Evaluation



IT Infrastructure

Pattern Extraction



35

Edge

Computing







Problems




製造現場



一言九鼎(頂)



Ask Why








38


生產線數據


39


Characteristic

Pure Feature-



(between features)











Color Images 3D

Scans and Videos



correlation







40



















特性與問題




Data Preprocessing

42

Data

Warehouse

Knowledge

Selection

Preprocessing

Target Data

Preprocessed

Data

Pattern

Transformed

Data

Transformation

Data Mining

Interpretation

Evaluation





Lot001 Lot001 Pass







Lot ID Pass or Fail

Lot001 Pass

Lot002 Pass

Lot003 Fail

Lot004 Pass


Lot001 Pass 20

Lot002 Pass 25

Lot003 Fail 10

Lot004 Pass 15

75 857


Lot002 hellip


Lot002_1

Lot002_2


Parallel Machine


Data Preparation

Missing Value

44


WS_A_Mach_2_Temp

Lot001 820 NA

Lot002 820 NA

Lot003 NA 840

Lot004 NA 840

Lot IDWS_A_Temp

WS_A_Mach_Type

Lot001 820 1

Lot002 820 1

Lot003 840 2

Lot004 840 2

WS_A_Mach_1

WS_A_Mach_2



Golden Machine


Missing Value

45


WS_A_Mach_2_Temp

Lot001 820 NA

Lot002 820 NA

Lot003 820 NA

Lot004 830 NA

Lot005 820 NA

Lot006 820 NA

Lot007 825 NA

Lot008 830 120

Lot009 820 130

Lot010 NA 120


WS_A_Mach_2_Temp

Mach_1 Mach_2

Lot001 820 Avg 1 0

Lot002 820 Avg 1 0

Lot003 820 Avg 1 0

Lot004 830 Avg 1 0

Lot005 820 Avg 1 0

Lot006 820 Avg 1 0

Lot007 825 Avg 1 0

Lot008 830 120 1 1

Lot009 820 130 1 1

Lot010 Avg 120 0 1






46


Lot001 PartsA

Lot002 PartsB

Lot003 PartsA

Lot004 PartsC

Lot005 PartsD

Lot006 PartsE

Lot007 PartsB

Lot008 PartsA

Lot009 PartsC

Lot010 PartsE


WS_A_Mach_1_PartsB

WS_A_Mach_1_PartsC

WS_A_Mach_1_PartsD

Lot001 1 0 0 0

Lot002 0 1 0 0

Lot003 1 0 0 0

Lot004 0 0 1 0

Lot005 0 0 0 1

Lot006 0 0 0 0

Lot007 0 1 0 0

Lot008 1 0 0 0

Lot009 0 0 1 0

Lot010 0 0 0 0






建議方式







沒有再現性

47



抽樣檢測

48




NO001 鋁 A 13723 7235

NO002 鋁 B NA NA

NO003 鋁 B 13728 7237

NO099 鋁 B NA NA

NO100 鋁 A 13726 7236

X Y (抽檢)

沒被抽檢

沒被抽檢

抽樣

填補遺漏值



3 Prediction Model








49









有母數GLMRandom


Learninghellip


換線換模






50

Machine A A A


Machine A B


B B B

A B A B









51

MachineI2

A A AMachine1

B B


A A A

Machine2

A A AMachine1

A A A

B

B




瓶頸 (bottleneck)







52


120

unitsday

140

unitsday

80

unitsday

120

unitsday

100

unitsday

瓶頸

80 unitsday



(勞工和幹部)



楊大和(2016)










53





54

IDProduct

TypeStage

Process

Time (hrs)

Start

Time

Lot1 A 1 1 20161226 1450

Lot1 A 2 1 20161226 1600

Lot1 A 3 05 20161226 1720

Lot1 A 4 1 20161226 1800

Lot1 A 5 05 20161226 2030







55


211 000000

211 010000

211 020000

211 230000


211 000629

211 001041

211 034109

211 231157




Data Merge

56









建議串接方法

Rolling Forward

Nearest time

Rolling Forward

Rolling Backward

Nearest time




Lee and Dong (2019)






產品的queue time



57

STA

GE

x_S

VID

x

0 5

10

1

5

2

0

2

5

0 200 400 600 800 1000Lot or

Time






58


Time Downcode


2017-05-07140528


2017-05-07161214


2017-05-07174130



2017-05-07192243


2017-05-07201817




19 22 43 minus (16 12 14)








10 vs 90 5 vs 95 or 1 vs 99



predictionhellip



59




Lot01 PASS

Lot02 PASS

Lot03 PASS

Lot04 PASS

Lot05 PASS

Lot06 PASS

Lot07 FAIL

Lot08 PASS

Lot09 PASS

Lot10 PASS

Lot11 PASS

Lot12 PASS





準確度可達 1112 = 917



迷思


61



62


資料整合













迷思補遺漏值


63

English Math

Student_A 80 76

Student_B 80 91

Student_C 80 83

Student_D 80 62

Student_E 80

Avg 80

Max 91

Min 62

Avg 78


迷思補遺漏值

64













64








B 男 51 $64000 Yes

C 男 52 $105000 Yes

D 女 33 $55000 Yes

E 男 45 $45000 No

F 女 45 $100000


65



66

K=3

K=5




迷思補遺漏值

67


1 00886 00886 00886 00886

2 00684 00684 00684 00684

3 03515 03515 03515 03515

4 09874 09874 09874 09874

5 04713 04713 04713 04713

6 06115 06115 06115 06115

7 02573 02573 02573 02573

8 02914 02914 02914 02914

9 01662 01662 01662 01662

10 044 044 044 044

11 06939 03731 06622

平均值 04023 03731 03731 03994

標準差 02785 02753 02612 02753

誤差值 03208 00317




數據品質

68






資料品質

Univariate





Multiple Column




數據品質



69



Automobile Company




digital materials







71















72






Feature Selection






74








75

材料

設計

光罩


測試

封裝

最後測試

加熱製程

微影製程

離子佈植


介電質沉積

晶圓


Over 1000 stages










and unreliable




76




77


Root Cause As-Is



To-Be

Data Science

Automation









78

K

C

H

E

A

G

I

J

F

L

OR

DS

BP M

N

Q






Rule Extraction




79

Good 68 68

Bad 32 32

Good - -

Bad 23 100

Good 68 88

Bad 9 12

Good - -

Bad 6 100

Good 68 96

Bad 3 4





OK

NG

NG

NG

NG

NG NG NG

OK

OK

OKOK OKOK

NG

YES NO

YES

YES YES

YESYES

YES

NO

NO

NO

NO NO

NO

80

Map clustering for

systematic defects

12 defect patterns

and build WBM bank





(Lee and Tsai 2019)



81




(Wang2012）





29 Alarm

16 Prediction model

training

15 EWMA for Target

Baseline (TB)



24 Predicted

CUSUM out of

control

25 Pre-alarmYes

No

28 Actual

CUSUM out of

control

Yes

No


21 New sample

prediction



17 Model validation

34 Continuous

monitoring

11 Data collection

26 Engineering

Validation amp

Troubleshooting

31 Loss calculation


32 CUSUM

control chart

33 Loss

CUSUM out of

control

310 Add new samples


311 ILPM model


Yes

Off-line training

In-line prediction

Concept drift

Pre-alarm stage


correction

No

All good products

37 Bayesian

monitoring out

of control

35 Equipment



39 Update posterior


38 Alarm and

equipment

maintenance

Yes

Model misalignment


Equipment

misalignment


36 Lifetime

out of control

No

Yes



82







83





Self-Priming

Centrifugal Pump



84




Feature Selection

Feature Engineering

85

Data

Warehouse

Knowledge

Selection

Preprocessing

Target Data

Preprocessed

Data

Pattern

Transformed

Data

Transformation

Data Mining

Interpretation

Evaluation




易於決策判斷









精度預測





86



Feature Selection



ie p gtgt n issue




87

An

p

Xn

k k ltlt p








Types









(PCA) etc

88







89

Lee and Chen (2018)



90

Prepared

Dataset

Feature

Selection

LASSO SVMStepwise

Regression

Voting


Pivot

Analysis

Engineering

Experience

Feature

Validation

BoostingRandom

ForestPCA Random

Sampling

Data

Reduction

(pgtgtn)

Imbalance

Correlation

Coefficient

Independence

Testhellip

Data

Preprocessing

hellip

Yes

No

Knowledge

Management (KM)

Documentation

Lee and Tsai (2019)

iterative

process






同理hellip

因果rarr相關







91








92

119910 = 120572 + 1205731199091 + 120576

119910 = 120572 + 1205731199092 + 120576

119910 = 120572 + 1205731199093 + 120576

119910 = 120572 + 1205731199094 + 120576

119910 = 120572 + 12057321199092 + 1205731199091 + 120576

119910 = 120572 + 12057321199092 + 1205731199093 + 120576

119910 = 120572 + 12057321199092 + 1205731199094 + 120576

119910 = 120572 + 12057321199092 + 12057341199094 + 1205731199091 + 120576

119910 = 120572 + 12057321199092 + 12057341199094 + 1205731199093 + 120576

統計顯著的變數1199092 and 1199094



መ120573119897119886119904119904119900 = argmin120573

σ119894=1119873 (119910119894 minus 1205730 minus σ119895=1

119875 119909119894119895120573119895)2

Subject to σ119895=1119875 120573119895 le 119905


1

2σ119894=1119873 (119910119894 minus 1205730 minus σ119895=1

119875 119909119894119895120573119895)2 + 120582σ119895=1

119875 120573119895

93


Penalty( 120582 ) x1 x2 x3 x4 x5 x6 x7

120582 = 0

120582 = 40

120582 = 418

120582 = 419

120582 = 42

120582 = 50





94


x12

x11

x10

x9

x8

x7

x6

x5

x4

x3

x2

x1

Feature Importance



Voting (投票法)



95



SVID_003 4

SVID_101 3

SVID_021 3

SVID_040 3

SVID_002 3

SVID_128 2

SVID_062 2

SVID_077 2






96

Test

Test

Test

Test


1st iter

2nd iter

3rd iter

10th iter

hellip

Error1

Error2

Error3

Error10

Minimize Error=1

10σ119894=110 Error119894



97


Undersampling



Example








SVIDVoting by

Undersampling

SVID_003 19

SVID_101 18

SVID_021 18

SVID_040 18

SVID_002 17

SVID_128 17

SVID_062 17

SVID_077 17

hellip hellip




98


SVID_003 09487 02583 11439

SVID_101 02078 05434 08934

SVID_021 04105 08377 06845

SVID_040 5208 7169 03170

SVID_002 27256 21025 02581

SVID_128 80523 85336 00580

SVID_062 09430 09747 00330

SVID_077 1569 1603 00216



Photo_06 12 384 00313

Etch_10 3 295 00102

Photo_32 10 1011 00099

Photo_17 4 410 00098

PVD_02 1 123 00081

CVD_14 9 3456 00026

Diff_09 1 495 00020

Etch_07 5 2769 00018



良品119886119907119892 minus不良品119886119907119892

119860119907119892

RATIO = FAIL TOTAL





99








迷思



100



Feature Engineering









119903 = 11990912 + 1199092

2

120579 = arctan11990921199091


101


119903

120579

1199091

1199092













Trend (趨勢)



Randomness (隨機)




102

Σ

A

A1 A2

B

B1 B2

C

C1 C2

人

人




103





預測

良品不良品




Benefits




104



105

Dataset with

selected variable

Prediction

Classification

Model

PLS BPNN CNN


R-Squared

MSE

Confusion

Matrix

Model

Evaluation

BoostingDecision

TreeSVR

Random

Sampling

Data

Transformation

Imbalance

Categorical to

Dummy VarFeature

Extraction

Feature

Selection

hellip

Yes

No

Knowledge

Management (KM)

Documentation


Z-scores


iterative

process















Data Imbalance

106










107

helliphellip

Input

Layer

Hidden

Layer

Output

Layer

hellip

helliphellip

helliphellip

helliphellip

helliphellip

helliphellip

helliphellip

x1

x2

xm

ො1199101

ො1199102

ො119910n

y1

y2

yn

NN

Output

Desired

Output




108







109

Yie

ld

Pre

cis

ion

Metr

olo

gy V

alu

e

Lot

Real value







110

UCL

LCL

Yie

ld

Pre

cis

ion

Metr

olo

gy V

alu

e

Lot

Real value









TNTP

+++

+=Accuracy


預測類別


實際類別

類別1


FN (false negative)

(Type II error)

(miss)

類別2

(良品)

FP (false positive)

(Type I error)

(false alarm)

TN (true negative)

111











112

TPSensitivity

TP+FN=

TNSpecificity

TN+FP=

預測

類別1 類別2

實際

類別1 TP FN

類別2 FP TN




TP

Rate

= S

ensitiv

ity

Model A

Model B

Precision=TP






113

Testing


Model A 719 897 517 702

Model B 781 691 883 789

Model A預測

Bad Good

實際Bad 61 7

Good 29 31

Model B預測

Bad Good

實際Bad 47 21

Good 7 53


精度良率預測







114

Time

Y

UCL

LCL

Time

Y

UCL

LCL





double EWMA




EWMA Control


115


Liu et al (2018)



116


維修保養








117











118
























119




120


No 名稱 No 名稱




4 R扣環 12 風扇


6 S扣環 14 風罩






Vibration Dataset

121

Amplitude

Time

(Obs)



Lee et al (2019)





122


Inspection

zone

Preventive

replacement

zone

Corrective

replacement

zone

Failure level

Replacement level

Data collection RUL




123

(Lee et al 2014)















124





Feature Engineering

125

Peak-

to-

peak




Data

Collection

Data

Preprocessing



Feature

Extraction

Feature

Selection

Remove high



(VIF)



Important

Variables

Predict

Linear Regression

(OLS)


Prediction Result


Regression (PLS)

Prediction

Model

OLS


PLS


BPNN

MSE = 123456789

Feature Engineering

(製造資料)





127



Feature Engineering









129




29 Alarm

16 Prediction model

training

15 EWMA for Target

Baseline (TB)



24 Predicted

CUSUM out of

control

25 Pre-alarmYes

No

28 Actual

CUSUM out of

control

Yes

No


21 New sample

prediction



17 Model validation

34 Continuous

monitoring

11 Data collection

26 Engineering

Validation amp

Troubleshooting

31 Loss calculation


32 CUSUM

control chart

33 Loss

CUSUM out of

control

310 Add new samples


311 ILPM model


Yes

Off-line training

In-line prediction

Concept drift

Pre-alarm stage


correction

No

All good products

37 Bayesian

monitoring out

of control

35 Equipment



39 Update posterior


38 Alarm and

equipment

maintenance

Yes

Model misalignment


Equipment

misalignment


36 Lifetime

out of control

No

Yes


Engineering



















hellip

130
















hellip

131






ldquo機會rdquo


132




133


很多時候我們


134

事實上hellip


現場改善

資料科學

系統整合

資料品質確認


浪費與WIP

瓶頸站生產力

人機比

設施佈置

環境公安衛生


流程再造BPR

時間動作研究



浪費移除

產線平衡


IT基礎建設

Make-or-Buy

需求預測

產銷平衡

排程與交期

特徵選取

Troubleshooting

機台維修保養


預測方法


啟發式演算法

機器學習


系統開發

供應鏈平台JIT



製程能力優化

良率提升



組件剩餘壽命


資料不一致





Decision Science

New Business Model


Price Maintenance


Sustainability

資料分析確認

Lee and Chien

(2020)


可能會問hellip




136


資料科學






現場觀察


137


話說hellip


某廠區稼動率116200 = 58







138



139

魚骨圖

法



環境


少量多樣

溝通管道

其他

交班傳達不周

人

人力缺乏



等待人員操作

機

機台維修保養

模具更換


待料


料


在製品堆放

機台稼動率低


作業不熟練

需求變異

工程變更

政策法規改變

傳承關係





案例





eg (56+160+138 mins)(180+180+180 mins)

=656

140




案例





eg (56+160+138 mins)(180+180+180 mins)

=656

141


(分)作業

耗時

(分)作業

耗時

(分)作業

耗時

(分)




1427-1430 產品品質檢測 3

1430-1443 電腦資料輸入 13


1450-1454 電腦工程分析 4

1454-1500 領取原物料 6

1500-1515 休息 15

1515-1528 領取模具 13

1528-1533 產品品質檢測 5


1543-1548 換模具 5


1601-1610 領取模具 9

1610-1617 產品品質檢測 7

1617-1622 存放載具 5

1622-1631 產品品質檢測 9


1640-1647 產品品質檢測 7


1652-1655 領取原物料 3

1655-1700 電腦資料輸入 5

機器加工

(產品D)

機器加工

(產品C)

13

124


停機

等待換規格

換模

停機

待料

機器加工

(產品A)

機器加工

(產品B)

機器加工

(產品C)

43

140

20

88

42

50

機器加工

(產品B)







200 80 = 160 (台) 到 200 85 = 170 (台) 之間為理想機台運作數



142









=工作效率




=08

1minus0656= 233 (台)


143






缺點很花時間






144





A 全部hellip

現場rarr瓶頸站





目標的衝突


145

Strategic Level


Planning

Marketing

Planning

Make-or-Buy

Strategy

Tactical Level


Planning


Order Allocation

Master Production

Schedule

Resource Planning

Rough-Cut Capacity

Planning

Capacity Require

Planning

Material Require

Planning

Monthly Material

Planning

Capacity Planning

Productivity amp

Efficiency Analysis

Vendor Relationship

MgmtDemand Mgmt


Purchasing


Daily Assignment

Order Releasing


Scheduling



Production


Operational Level

Logistics Mgmt

Long Term

Mid Term

Short Term

Facility Layout






146




timeProduction


uptimeEquipment

timeProduction

timeTotal

uptimeEquipment

timeTotal


=

=

=

Nonscheduled

state

Unscheduled

down state

Scheduled

down state

Engineering

state

Standby

state

Productive

state

Equipment

uptime

Equipment

downtime

Operations

time

Production

time

Total

time



147

顧客訂單產品

交期變動插單

工程變更




操作員

人力不足

MO


人員配置


機台設備廠務





廠區間的Backup



停工待料


外包時程變異

進料品質變異

















148






優先順序

日期達交












衝突目標

Makespan


(TWET)

交期

利用率

庫存時間



排程應用範疇


機場飛機起降



電梯設定

微處理器系統

醫院排班

醫院復健排程

醫師手術排班




150




人工排程邏輯

訂單資料

依到期日排序


預估單

工作號賦予




Yes

No


No





優先順序法則

Dispatching










Rush 緊急事件

152




剩餘作業數




Performance Metrics

Mean Flow Time






119879119895 = max0 119871119895


N Jobs on 1 Machine


N Jobs on 1 Machine




Notations



119889119895 due date

154


1 11 61

2 29 45

3 31 31

4 1 33

5 2 32


N Jobs on 1 Machine

FCFS



Tardy Jobs 3

155


J1 11 11 61 0

J2 29 40 45 0

J3 31 71 31 40

J4 1 72 33 39

J5 2 74 32 42

Totals 74 268 121





N Jobs on 1 Machine

SPT



Tardy 1

156


J4 1 1 33 0

J5 2 3 32 0

J1 11 14 61 0

J2 29 43 45 0

J3 31 74 31 43

Totals 74 135 45


N Jobs on 1 Machine

EDD



Tardy 4

157


J3 31 31 31 0

J5 2 33 32 1

J4 1 34 33 1

J2 29 63 45 18

J1 11 74 61 13

Totals 74 235 33


N Jobs on 1 Machine






Compute


158

119862119877 =119863119906119890_119863119886119905119890 minus (119862119906119903_119879119894119898119890)

119875119903119900119888119890119904119904119894119899119892_119879119894119898119890


CR

N Jobs on 1 Machine

159

JOBPr

Time

D

DateCR

Current Time = 0

1 11 61 5546

2 29 45 1552

3 31 31 100

4 1 33 33

5 2 32 16

JOBPr

Time

D

DateCR

Current Time = 31

1 11 61 2727

2 29 45 483

4 1 33 2

5 2 32 05


N Jobs on 1 Machine

160

JOBPr

Time

D

DateCR

Current Time = 60

1 11 610091

do last

4 1 33 -27

5 2 32 -14

JOBC

Time

D

DateTardy

Summary

3 31 31 0

2 60 45 15

4 61 33 28

5 63 32 31

1 74 61 13

Total 289 87

Tie use SPT

CR

Mean F Time (289)5 = 578


Tardy 4



FCFS


SPT




EDD



CR


Sequencing Rules

due Time

FCFS

CRSPT

EDD


然而hellip








162



快速換模技術









163



快速換模技術









4改善內部換模

平行作業


5改善外部作業




164





NP-hard problem













Local optimum

Short running time

Global optimum

Long running time


Meta-heuristics






166

f(x)

x

Local optimum

Global

optimum

Meta-heuristics

ldquoJUMPrdquo

119909119905+1 larr 119909119905 + 120578120597119891

120597119909


120597119891

120597119909

119909119905 119909119905+1

120578



Basis











Neighborhood Search


promising regions








memory




go to step 3



















= 500




Due Date(119941119947)

Weights (119960119947)

1 10 4 14

2 10 2 12

3 13 1 1

4 4 12 12




(1243) (2413) and (2134)

119879 1243 = 480 119879 2413 = 436 and 119879 2134 = 652





(4213) (2143) TABU and (2431)

119879 4213 = 460 119879 2143 = 500 TABU and 119879 2431 = 608







(2413) TABU (4123) and (4231)

119879 2413 = 436 TABU 119879 4123 = 440 and 119879 4231 = 632





(1423) (4213) TABU and (4132)

119879 1423 = 408 119879 4213 = 460 TABU and 119879 4132 = 586





Metaheuristics


172

1199091


1199610


1199611 1199612



Global

optimum










exploration

exploitation

(Gen 2005)


If you hellip





175


Interfaces

1 Gantt Chart

2 Dispatch List

3 Capacity Buckets


Scenario

Management

System

Maintenance

Performance

Control

Algorithm

Generator

Interface

Algorithm

Generator

Scheduler amp

Dispatcher

Preprocessor

Scheduling amp

Rescheduling

Algorithms

Manufacturing

Execution

System (MES)

Enterprise

Resource

Planning (MRPII)

Production

Monitoring

System

Database

ImportExport

Synchronization


Algorithm

Library


Scheduling

Logic Unit

Order

Master

File

Shop-

Floor

Data



176







178

Capacity Buckets






改善的機會


講究的是synergy








179












180














Rescheduling

181








Hint WIP



182


Pull Strategy

High Uncertainty

Push Strategy

Low Uncertainty

WIP


Lateness









processing time



HVLV HV

HVHV HV

LVLV LV

LV LVHV

Process Variability

Inflow Variability


迷思










現場動態調整

184






185



再過一陣子





186



在製造業中





187









188







190


迷思


191


迷思

這是當然的


找出關鍵因子

建構因果關係




192



193

為什麼要預測


下一步為何


預測像hellip

194


預測像hellip

195




B2A1E9818B3F




196




197





198






瞭解這就hellip


199






200


其實hellip




201


決策的類型





202


小試身手hellip

天氣與決策

203

不帶傘帶傘





3 拿別人的傘

(良心不安)


小試身手hellip

204


神預測God2GO



小試身手hellip


205

機率02

機率08



方法一期望值







小試身手hellip


206

機率02

機率08





風險成本矩陣

不帶傘帶傘

晴天

成本 $0 成本 $100

(弄丟)

雨天

成本 $200

(感冒)

成本 $0

期望成本

02x0

+08x200

=160

02x100

+08x0

=20

決策帶傘


小試身手hellip


207



風險成本矩陣

不帶傘帶傘

晴天

成本 $0 成本 $100

(弄丟)

雨天

成本 $200

(感冒)

成本 $0

期望成本

02x0

+08x200

=160

02x100

+08x0

=20

決策帶傘

切記hellip


又或hellip



由此可知hellip




208

Lee (2019)


小試身手hellip


209

Based on your

Preference

Structure








210



併購公司A 42 21 8

購置機台 35 28 13

外包 28 25 23







211

天氣情境

方案景氣好

景氣持平

景氣差

Min

Return

併購公司A 42 21 8 8

購置機台 35 28 13 13

外包 28 25 23 23






212

天氣情境

方案景氣好

景氣持平

景氣差

Max

Return

併購公司A 42 21 8 42

購置機台 35 28 13 35

外包 28 25 23 28








213

悔惜矩陣

景氣好

景氣持平

景氣差

Max

Regret

0 7 15 15

7 0 10 10

14 3 0 14

天氣情境

方案景氣好

景氣持平

景氣差

併購公司A 42 21 8

購置機台 35 28 13

外包 28 25 23






214

天氣情境

方案景氣好

景氣持平

景氣差

併購公司A 42 21 8

購置機台 35 28 13

外包 28 25 23






215




Two Types of Risk



Time

Demand

Demand

A

B

C

大試身手hellip

0




Time

Demand

Demand


0

追高殺低


大試身手hellip






218






Scenario Simulator



Time

Demand

Marketing Forecast

Sales Forecast

大試身手hellip

0

Capacity Level






shortage


Linear Regression

Autoregression

Neural Network





220


Empirical Study




221

Capacity Regret

Assessment

CustomerInventory

Market

Share

Profit

Loss

Loss of

Falling Price

Inventory

Loss

Holding

CostReputation

Lower

Capacity

Level

Higher

Capacity

Level

ALTERNATIVE

OBJECTIVE

ATTRIBUTE

119877119904ℎ119900119903119905119886119892119890 缺貨風險119877119904119906119903119901119897119906119904 存貨風險



Empirical Study


222

119877119904ℎ119900119903119905119886119892119890 缺貨風險愈大產能水準向上拉

119877119904119906119903119901119897119906119904 存貨風險愈大產能水準向下壓

119863119898119886119909

119863119898119894119899

Capacity Decision


0

10000

20000

30000

Training

Dataset

Validation

Dataset

Technology

Node A

Time

Demand

Empirical Study

Data Source






223



Empirical Study

2-stage approach

Demand Forecast

Capacity Decision

VDGP


(Chang et al 2014)

224



Empirical Study




225

0

10000

20000

30000

Training

Dataset

Validation

Dataset

Technology

Node A

Time

Demand

Linear Regression

Autoregression

Neural Network


Empirical Study







119877119904ℎ119900119903119905119886119892119890 = 0521 and 119877119904119906119903119901119897119906119904 = 0479

226



MonthActual

Demand


EV MMR SP

Aug 2014 19499 20207 16941 17157 18922Sep 2014 18110 21305 17921 18306 19135Oct 2014 15059 22404 18536 19291 18885



Empirical Study


227

0

500

1000

1500

2000

0 300 600 900 1200

StandardDeviation

AverageRegret

Current

Policy

EVMMR

SP

Poor

Better

Better Poor




Min 119862119909 + 119864 119891 119909 ෩119863




119910+ 119910minus ge 0












228





229

Testing

Accuracy AUC

Model A 719 702

Model B 781 789

Model A預測

FAIL PASS

實際FAIL 61 7

PASS 29 31

Model B預測

FAIL PASS

實際FAIL 47 21

PASS 7 53



迷思


230


迷思

231

170cm

165cm 175cm

172cm



232















233



234



235











going on now






used here

236












237











238




1 1 0 4

2 0 2 12

3 3 2 18

Profit ($1000) $3 $5 0

1823

122

4 st

53

21

21

2

1

21

+

+=

xx

xx

x

x

xxZ


Graphical Solution


feasible region


0

1823

122

4 st

53

21

21

2

1

21

+

+=

xx

xx

x

x

xxZ


Graphical Solution




最佳化結果


6個產品2 (x2)


這就是處方~



遇到問題



提供solution


241



242

Domain Knowledge




243

處方性分析


DS in

MFG










為大於其細


方案評選


見

識

謀

斷


發想

收斂




執行對策

膽大心細

決策與行動

行




245

Descriptive

敘述性

Diagnostic

診斷性

Predictive

預測性

Prescriptive

處方性

Automating

自動性

見

What



Why



When


HowWho Where


戰情財報



(掌握趨勢)



(持續改善)

識謀斷行

U N I S O N


結語

Conclusion

246


迷思



247


迷思










248


迷思


249



Basic

interpretable

models

Post-hoc

Explanation

RegressionBased

Tree Based

DeepLearning

Linear Logistic

regression

Lasso Ridge

GLM GAM

Decision Tree

RF XGBoost

LightGBM

RF

DNN CNN RNN

helliphellip


(build-in)

DataFeature

EngineeringML

Models

Prediction Result

(build-in)

X

Post-hoc Methods


(plug-in)

FeatureImportance

洪紹嚴 (2019)



250

Yield

Time

Cost

Yield

New Tape-out (NTO)

研發導入

Device

optimization

during process

integration

Engineering

Parameter

Optimization

Design of

Experiments

成長期

Tool Matching

Benchmarking

Troubleshooting

Scheduling

Spec Setting SPC






成熟期

快速良率提升

Yield ramp

during pilot

production



during mass

production







機人


迷思




251








迷思

252







253




工業30





工業40








254














馬雲 (201704)








255


結語




However hellip









256


結語KPI Hierarchy

257


ROE

Profit

Margin

Asset

Turnover

Financial

Leveragetimes times

Profit

Sales

Assetsdivide divide

Cost minus Accounts


Sales

Price

Sales

Quantity

Effective

Outputs

Realized

Demand

times

minusmin

Price

Elasticity

Fixed

Cost

Variable

Cost+

Bottleneck

Throughput

Bottleneck

Utilization

Yield

times

Bottleneck

Capacity

times

Bottleneck

Machine

MTTR

MTBFMaintenance

Bottleneck

Availability

times

Demand

vs SupplyQuality

DL

Cost

IDL

Cost

Bui amp Fac

Depre

Equip

Cost

Variable

Unit Cost

times

Other

Assets+

ID Mater

Cost

D Mater

Cost

+ + + + +

Labor MaterialFloor

Space

Non-bottle

Machine

Fin

an

cia

l Ind

ex

Ma

nu

factu

ring In

de

xR

eso

urc

e

WIP Delivery

TAT

CVP CIP

Rework

Rate

Cycle

Time

times

Finished

Goods

+

SchedulingProduct-

mixLot Size

Man Machine

Ratio

Decis

ion




Line

Balancing



258

MFGcom

DATAcomINNOVATION

com

Technology

Migration

Analytics-oriented

- Prediction

- Troubleshooting

- Customer voice


Business-oriented






Analytics

Discussion

Implementation

Problem-oriented

- SOP and cost down




Data

(empirical)

Science

(critical)

Technology

(substantial)

Data Quality

(Internal data)

Data Analysis


Data Platform



Advanced training






戴勝益 (2014)


致謝

260

感謝



以及




謝謝大家~






2017 Modena Italy


1157ndash1182





















261

Contact Information


phone 02-33661206







Outline

4











5






Starting

material

Material in

processing

Processed

material

Value-added




7



Knowledge

詮釋的觀點

思辨的過程

科學的原理


迷思資料資訊



9





10

北南

Etu蔣居裕 (2013)


Experiencehellip


失敗的藝術

人生的歷練


知識與經驗之



Wisdom ishellip


Wisdom ishellip

13





13







智慧工廠



15

智慧工廠

智慧製造

製造智慧



(製造系統)

16


Value and Profit

Value




17

Price

Value

Cost

Consumer

Surplus

Producer

Surplus

Wikipedia (2016)


製造智慧決策

18



SPC APC VM RMS

Carbon

Emission

Water

Recycle


Energy



VRARAI

Cloud

Computing

Cyber-

Physical

System


RFIDSmart Labels



















Inventory



Inventory Reduction







Chien et al (2004)




22



23




24




















26





其實hellip


27

English Math

Student_A 80 76

Student_B 80 91

Student_C 80 83

Student_D 80 62

Student_E 80 88

Layer X Layer Y

Machine_A 81 76

Machine_B 80 91

Machine_C 79 83

Machine_D 80 62

Machine_E 82 88


來自於變異




MES

APC

FDC

SPC

VM

R2R

RMS



Yield Management

hellipetc

Demand Forecast



CapEx

Cost Structure

MPS amp MRP



Order Releasing

hellipetcQuality

Productivity

Cost Down

Cycle Time

28


CIM and Automation

29


ISBN 0-471-93450-X



Benefits

Reduce HR Cost

Reduce MO


Productivity




Benefits

Sustain EQ variance


Support RD




CIM and Automation





31



轉變hellip



一種改善過程

32





1 Transportation

2 Inventory

3 Motion

4 Waiting

5 Overproduction

6 Overprocessing

7 Defects

8 Eschewed Talents

Continuous flow

Line Balancing


Lean Manufacturing


33





CIM and Automation

34

AMHS

MES APC

FMEC



Big Data

Analytics


Data

Warehouse

Knowledge


Selection

Preprocessing

Target Data

Preprocessed

Data

Pattern

Transformed

Data

Data Mining

Transformation

Interpretation

Evaluation



IT Infrastructure

Pattern Extraction



35

Edge

Computing







Problems




製造現場



一言九鼎(頂)



Ask Why








38


生產線數據


39


Characteristic

Pure Feature-



(between features)











Color Images 3D

Scans and Videos



correlation







40



















特性與問題




Data Preprocessing

42

Data

Warehouse

Knowledge

Selection

Preprocessing

Target Data

Preprocessed

Data

Pattern

Transformed

Data

Transformation

Data Mining

Interpretation

Evaluation





Lot001 Lot001 Pass







Lot ID Pass or Fail

Lot001 Pass

Lot002 Pass

Lot003 Fail

Lot004 Pass


Lot001 Pass 20

Lot002 Pass 25

Lot003 Fail 10

Lot004 Pass 15

75 857


Lot002 hellip


Lot002_1

Lot002_2


Parallel Machine


Data Preparation

Missing Value

44


WS_A_Mach_2_Temp

Lot001 820 NA

Lot002 820 NA

Lot003 NA 840

Lot004 NA 840

Lot IDWS_A_Temp

WS_A_Mach_Type

Lot001 820 1

Lot002 820 1

Lot003 840 2

Lot004 840 2

WS_A_Mach_1

WS_A_Mach_2



Golden Machine


Missing Value

45


WS_A_Mach_2_Temp

Lot001 820 NA

Lot002 820 NA

Lot003 820 NA

Lot004 830 NA

Lot005 820 NA

Lot006 820 NA

Lot007 825 NA

Lot008 830 120

Lot009 820 130

Lot010 NA 120


WS_A_Mach_2_Temp

Mach_1 Mach_2

Lot001 820 Avg 1 0

Lot002 820 Avg 1 0

Lot003 820 Avg 1 0

Lot004 830 Avg 1 0

Lot005 820 Avg 1 0

Lot006 820 Avg 1 0

Lot007 825 Avg 1 0

Lot008 830 120 1 1

Lot009 820 130 1 1

Lot010 Avg 120 0 1






46


Lot001 PartsA

Lot002 PartsB

Lot003 PartsA

Lot004 PartsC

Lot005 PartsD

Lot006 PartsE

Lot007 PartsB

Lot008 PartsA

Lot009 PartsC

Lot010 PartsE


WS_A_Mach_1_PartsB

WS_A_Mach_1_PartsC

WS_A_Mach_1_PartsD

Lot001 1 0 0 0

Lot002 0 1 0 0

Lot003 1 0 0 0

Lot004 0 0 1 0

Lot005 0 0 0 1

Lot006 0 0 0 0

Lot007 0 1 0 0

Lot008 1 0 0 0

Lot009 0 0 1 0

Lot010 0 0 0 0






建議方式







沒有再現性

47



抽樣檢測

48




NO001 鋁 A 13723 7235

NO002 鋁 B NA NA

NO003 鋁 B 13728 7237

NO099 鋁 B NA NA

NO100 鋁 A 13726 7236

X Y (抽檢)

沒被抽檢

沒被抽檢

抽樣

填補遺漏值



3 Prediction Model








49









有母數GLMRandom


Learninghellip


換線換模






50

Machine A A A


Machine A B


B B B

A B A B









51

MachineI2

A A AMachine1

B B


A A A

Machine2

A A AMachine1

A A A

B

B




瓶頸 (bottleneck)







52


120

unitsday

140

unitsday

80

unitsday

120

unitsday

100

unitsday

瓶頸

80 unitsday



(勞工和幹部)



楊大和(2016)










53





54

IDProduct

TypeStage

Process

Time (hrs)

Start

Time

Lot1 A 1 1 20161226 1450

Lot1 A 2 1 20161226 1600

Lot1 A 3 05 20161226 1720

Lot1 A 4 1 20161226 1800

Lot1 A 5 05 20161226 2030







55


211 000000

211 010000

211 020000

211 230000


211 000629

211 001041

211 034109

211 231157




Data Merge

56









建議串接方法

Rolling Forward

Nearest time

Rolling Forward

Rolling Backward

Nearest time




Lee and Dong (2019)






產品的queue time



57

STA

GE

x_S

VID

x

0 5

10

1

5

2

0

2

5

0 200 400 600 800 1000Lot or

Time






58


Time Downcode


2017-05-07140528


2017-05-07161214


2017-05-07174130



2017-05-07192243


2017-05-07201817




19 22 43 minus (16 12 14)








10 vs 90 5 vs 95 or 1 vs 99



predictionhellip



59




Lot01 PASS

Lot02 PASS

Lot03 PASS

Lot04 PASS

Lot05 PASS

Lot06 PASS

Lot07 FAIL

Lot08 PASS

Lot09 PASS

Lot10 PASS

Lot11 PASS

Lot12 PASS





準確度可達 1112 = 917



迷思


61



62


資料整合













迷思補遺漏值


63

English Math

Student_A 80 76

Student_B 80 91

Student_C 80 83

Student_D 80 62

Student_E 80

Avg 80

Max 91

Min 62

Avg 78


迷思補遺漏值

64













64








B 男 51 $64000 Yes

C 男 52 $105000 Yes

D 女 33 $55000 Yes

E 男 45 $45000 No

F 女 45 $100000


65



66

K=3

K=5




迷思補遺漏值

67


1 00886 00886 00886 00886

2 00684 00684 00684 00684

3 03515 03515 03515 03515

4 09874 09874 09874 09874

5 04713 04713 04713 04713

6 06115 06115 06115 06115

7 02573 02573 02573 02573

8 02914 02914 02914 02914

9 01662 01662 01662 01662

10 044 044 044 044

11 06939 03731 06622

平均值 04023 03731 03731 03994

標準差 02785 02753 02612 02753

誤差值 03208 00317




數據品質

68






資料品質

Univariate





Multiple Column




數據品質



69



Automobile Company




digital materials







71















72






Feature Selection






74








75

材料

設計

光罩


測試

封裝

最後測試

加熱製程

微影製程

離子佈植


介電質沉積

晶圓


Over 1000 stages










and unreliable




76




77


Root Cause As-Is



To-Be

Data Science

Automation









78

K

C

H

E

A

G

I

J

F

L

OR

DS

BP M

N

Q






Rule Extraction




79

Good 68 68

Bad 32 32

Good - -

Bad 23 100

Good 68 88

Bad 9 12

Good - -

Bad 6 100

Good 68 96

Bad 3 4





OK

NG

NG

NG

NG

NG NG NG

OK

OK

OKOK OKOK

NG

YES NO

YES

YES YES

YESYES

YES

NO

NO

NO

NO NO

NO

80

Map clustering for

systematic defects

12 defect patterns

and build WBM bank





(Lee and Tsai 2019)



81




(Wang2012）





29 Alarm

16 Prediction model

training

15 EWMA for Target

Baseline (TB)



24 Predicted

CUSUM out of

control

25 Pre-alarmYes

No

28 Actual

CUSUM out of

control

Yes

No


21 New sample

prediction



17 Model validation

34 Continuous

monitoring

11 Data collection

26 Engineering

Validation amp

Troubleshooting

31 Loss calculation


32 CUSUM

control chart

33 Loss

CUSUM out of

control

310 Add new samples


311 ILPM model


Yes

Off-line training

In-line prediction

Concept drift

Pre-alarm stage


correction

No

All good products

37 Bayesian

monitoring out

of control

35 Equipment



39 Update posterior


38 Alarm and

equipment

maintenance

Yes

Model misalignment


Equipment

misalignment


36 Lifetime

out of control

No

Yes



82







83





Self-Priming

Centrifugal Pump



84




Feature Selection

Feature Engineering

85

Data

Warehouse

Knowledge

Selection

Preprocessing

Target Data

Preprocessed

Data

Pattern

Transformed

Data

Transformation

Data Mining

Interpretation

Evaluation




易於決策判斷









精度預測





86



Feature Selection



ie p gtgt n issue




87

An

p

Xn

k k ltlt p








Types









(PCA) etc

88







89

Lee and Chen (2018)



90

Prepared

Dataset

Feature

Selection

LASSO SVMStepwise

Regression

Voting


Pivot

Analysis

Engineering

Experience

Feature

Validation

BoostingRandom

ForestPCA Random

Sampling

Data

Reduction

(pgtgtn)

Imbalance

Correlation

Coefficient

Independence

Testhellip

Data

Preprocessing

hellip

Yes

No

Knowledge

Management (KM)

Documentation

Lee and Tsai (2019)

iterative

process






同理hellip

因果rarr相關







91








92

119910 = 120572 + 1205731199091 + 120576

119910 = 120572 + 1205731199092 + 120576

119910 = 120572 + 1205731199093 + 120576

119910 = 120572 + 1205731199094 + 120576

119910 = 120572 + 12057321199092 + 1205731199091 + 120576

119910 = 120572 + 12057321199092 + 1205731199093 + 120576

119910 = 120572 + 12057321199092 + 1205731199094 + 120576

119910 = 120572 + 12057321199092 + 12057341199094 + 1205731199091 + 120576

119910 = 120572 + 12057321199092 + 12057341199094 + 1205731199093 + 120576

統計顯著的變數1199092 and 1199094



መ120573119897119886119904119904119900 = argmin120573

σ119894=1119873 (119910119894 minus 1205730 minus σ119895=1

119875 119909119894119895120573119895)2

Subject to σ119895=1119875 120573119895 le 119905


1

2σ119894=1119873 (119910119894 minus 1205730 minus σ119895=1

119875 119909119894119895120573119895)2 + 120582σ119895=1

119875 120573119895

93


Penalty( 120582 ) x1 x2 x3 x4 x5 x6 x7

120582 = 0

120582 = 40

120582 = 418

120582 = 419

120582 = 42

120582 = 50





94


x12

x11

x10

x9

x8

x7

x6

x5

x4

x3

x2

x1

Feature Importance



Voting (投票法)



95



SVID_003 4

SVID_101 3

SVID_021 3

SVID_040 3

SVID_002 3

SVID_128 2

SVID_062 2

SVID_077 2






96

Test

Test

Test

Test


1st iter

2nd iter

3rd iter

10th iter

hellip

Error1

Error2

Error3

Error10

Minimize Error=1

10σ119894=110 Error119894



97


Undersampling



Example








SVIDVoting by

Undersampling

SVID_003 19

SVID_101 18

SVID_021 18

SVID_040 18

SVID_002 17

SVID_128 17

SVID_062 17

SVID_077 17

hellip hellip




98


SVID_003 09487 02583 11439

SVID_101 02078 05434 08934

SVID_021 04105 08377 06845

SVID_040 5208 7169 03170

SVID_002 27256 21025 02581

SVID_128 80523 85336 00580

SVID_062 09430 09747 00330

SVID_077 1569 1603 00216



Photo_06 12 384 00313

Etch_10 3 295 00102

Photo_32 10 1011 00099

Photo_17 4 410 00098

PVD_02 1 123 00081

CVD_14 9 3456 00026

Diff_09 1 495 00020

Etch_07 5 2769 00018



良品119886119907119892 minus不良品119886119907119892

119860119907119892

RATIO = FAIL TOTAL





99








迷思



100



Feature Engineering









119903 = 11990912 + 1199092

2

120579 = arctan11990921199091


101


119903

120579

1199091

1199092













Trend (趨勢)



Randomness (隨機)




102

Σ

A

A1 A2

B

B1 B2

C

C1 C2

人

人




103





預測

良品不良品




Benefits




104



105

Dataset with

selected variable

Prediction

Classification

Model

PLS BPNN CNN


R-Squared

MSE

Confusion

Matrix

Model

Evaluation

BoostingDecision

TreeSVR

Random

Sampling

Data

Transformation

Imbalance

Categorical to

Dummy VarFeature

Extraction

Feature

Selection

hellip

Yes

No

Knowledge

Management (KM)

Documentation


Z-scores


iterative

process















Data Imbalance

106










107

helliphellip

Input

Layer

Hidden

Layer

Output

Layer

hellip

helliphellip

helliphellip

helliphellip

helliphellip

helliphellip

helliphellip

x1

x2

xm

ො1199101

ො1199102

ො119910n

y1

y2

yn

NN

Output

Desired

Output




108







109

Yie

ld

Pre

cis

ion

Metr

olo

gy V

alu

e

Lot

Real value







110

UCL

LCL

Yie

ld

Pre

cis

ion

Metr

olo

gy V

alu

e

Lot

Real value









TNTP

+++

+=Accuracy


預測類別


實際類別

類別1


FN (false negative)

(Type II error)

(miss)

類別2

(良品)

FP (false positive)

(Type I error)

(false alarm)

TN (true negative)

111











112

TPSensitivity

TP+FN=

TNSpecificity

TN+FP=

預測

類別1 類別2

實際

類別1 TP FN

類別2 FP TN




TP

Rate

= S

ensitiv

ity

Model A

Model B

Precision=TP






113

Testing


Model A 719 897 517 702

Model B 781 691 883 789

Model A預測

Bad Good

實際Bad 61 7

Good 29 31

Model B預測

Bad Good

實際Bad 47 21

Good 7 53


精度良率預測







114

Time

Y

UCL

LCL

Time

Y

UCL

LCL





double EWMA




EWMA Control


115


Liu et al (2018)



116


維修保養








117











118
























119




120


No 名稱 No 名稱




4 R扣環 12 風扇


6 S扣環 14 風罩






Vibration Dataset

121

Amplitude

Time

(Obs)



Lee et al (2019)





122


Inspection

zone

Preventive

replacement

zone

Corrective

replacement

zone

Failure level

Replacement level

Data collection RUL




123

(Lee et al 2014)















124





Feature Engineering

125

Peak-

to-

peak




Data

Collection

Data

Preprocessing



Feature

Extraction

Feature

Selection

Remove high



(VIF)



Important

Variables

Predict

Linear Regression

(OLS)


Prediction Result


Regression (PLS)

Prediction

Model

OLS


PLS


BPNN

MSE = 123456789

Feature Engineering

(製造資料)





127



Feature Engineering









129




29 Alarm

16 Prediction model

training

15 EWMA for Target

Baseline (TB)



24 Predicted

CUSUM out of

control

25 Pre-alarmYes

No

28 Actual

CUSUM out of

control

Yes

No


21 New sample

prediction



17 Model validation

34 Continuous

monitoring

11 Data collection

26 Engineering

Validation amp

Troubleshooting

31 Loss calculation


32 CUSUM

control chart

33 Loss

CUSUM out of

control

310 Add new samples


311 ILPM model


Yes

Off-line training

In-line prediction

Concept drift

Pre-alarm stage


correction

No

All good products

37 Bayesian

monitoring out

of control

35 Equipment



39 Update posterior


38 Alarm and

equipment

maintenance

Yes

Model misalignment


Equipment

misalignment


36 Lifetime

out of control

No

Yes


Engineering



















hellip

130
















hellip

131






ldquo機會rdquo


132




133


很多時候我們


134

事實上hellip


現場改善

資料科學

系統整合

資料品質確認


浪費與WIP

瓶頸站生產力

人機比

設施佈置

環境公安衛生


流程再造BPR

時間動作研究



浪費移除

產線平衡


IT基礎建設

Make-or-Buy

需求預測

產銷平衡

排程與交期

特徵選取

Troubleshooting

機台維修保養


預測方法


啟發式演算法

機器學習


系統開發

供應鏈平台JIT



製程能力優化

良率提升



組件剩餘壽命


資料不一致





Decision Science

New Business Model


Price Maintenance


Sustainability

資料分析確認

Lee and Chien

(2020)


可能會問hellip




136


資料科學






現場觀察


137


話說hellip


某廠區稼動率116200 = 58







138



139

魚骨圖

法



環境


少量多樣

溝通管道

其他

交班傳達不周

人

人力缺乏



等待人員操作

機

機台維修保養

模具更換


待料


料


在製品堆放

機台稼動率低


作業不熟練

需求變異

工程變更

政策法規改變

傳承關係





案例





eg (56+160+138 mins)(180+180+180 mins)

=656

140




案例





eg (56+160+138 mins)(180+180+180 mins)

=656

141


(分)作業

耗時

(分)作業

耗時

(分)作業

耗時

(分)




1427-1430 產品品質檢測 3

1430-1443 電腦資料輸入 13


1450-1454 電腦工程分析 4

1454-1500 領取原物料 6

1500-1515 休息 15

1515-1528 領取模具 13

1528-1533 產品品質檢測 5


1543-1548 換模具 5


1601-1610 領取模具 9

1610-1617 產品品質檢測 7

1617-1622 存放載具 5

1622-1631 產品品質檢測 9


1640-1647 產品品質檢測 7


1652-1655 領取原物料 3

1655-1700 電腦資料輸入 5

機器加工

(產品D)

機器加工

(產品C)

13

124


停機

等待換規格

換模

停機

待料

機器加工

(產品A)

機器加工

(產品B)

機器加工

(產品C)

43

140

20

88

42

50

機器加工

(產品B)







200 80 = 160 (台) 到 200 85 = 170 (台) 之間為理想機台運作數



142









=工作效率




=08

1minus0656= 233 (台)


143






缺點很花時間






144





A 全部hellip

現場rarr瓶頸站





目標的衝突


145

Strategic Level


Planning

Marketing

Planning

Make-or-Buy

Strategy

Tactical Level


Planning


Order Allocation

Master Production

Schedule

Resource Planning

Rough-Cut Capacity

Planning

Capacity Require

Planning

Material Require

Planning

Monthly Material

Planning

Capacity Planning

Productivity amp

Efficiency Analysis

Vendor Relationship

MgmtDemand Mgmt


Purchasing


Daily Assignment

Order Releasing


Scheduling



Production


Operational Level

Logistics Mgmt

Long Term

Mid Term

Short Term

Facility Layout






146




timeProduction


uptimeEquipment

timeProduction

timeTotal

uptimeEquipment

timeTotal


=

=

=

Nonscheduled

state

Unscheduled

down state

Scheduled

down state

Engineering

state

Standby

state

Productive

state

Equipment

uptime

Equipment

downtime

Operations

time

Production

time

Total

time



147

顧客訂單產品

交期變動插單

工程變更




操作員

人力不足

MO


人員配置


機台設備廠務





廠區間的Backup



停工待料


外包時程變異

進料品質變異

















148






優先順序

日期達交












衝突目標

Makespan


(TWET)

交期

利用率

庫存時間



排程應用範疇


機場飛機起降



電梯設定

微處理器系統

醫院排班

醫院復健排程

醫師手術排班




150




人工排程邏輯

訂單資料

依到期日排序


預估單

工作號賦予




Yes

No


No





優先順序法則

Dispatching










Rush 緊急事件

152




剩餘作業數




Performance Metrics

Mean Flow Time






119879119895 = max0 119871119895


N Jobs on 1 Machine


N Jobs on 1 Machine




Notations



119889119895 due date

154


1 11 61

2 29 45

3 31 31

4 1 33

5 2 32


N Jobs on 1 Machine

FCFS



Tardy Jobs 3

155


J1 11 11 61 0

J2 29 40 45 0

J3 31 71 31 40

J4 1 72 33 39

J5 2 74 32 42

Totals 74 268 121





N Jobs on 1 Machine

SPT



Tardy 1

156


J4 1 1 33 0

J5 2 3 32 0

J1 11 14 61 0

J2 29 43 45 0

J3 31 74 31 43

Totals 74 135 45


N Jobs on 1 Machine

EDD



Tardy 4

157


J3 31 31 31 0

J5 2 33 32 1

J4 1 34 33 1

J2 29 63 45 18

J1 11 74 61 13

Totals 74 235 33


N Jobs on 1 Machine






Compute


158

119862119877 =119863119906119890_119863119886119905119890 minus (119862119906119903_119879119894119898119890)

119875119903119900119888119890119904119904119894119899119892_119879119894119898119890


CR

N Jobs on 1 Machine

159

JOBPr

Time

D

DateCR

Current Time = 0

1 11 61 5546

2 29 45 1552

3 31 31 100

4 1 33 33

5 2 32 16

JOBPr

Time

D

DateCR

Current Time = 31

1 11 61 2727

2 29 45 483

4 1 33 2

5 2 32 05


N Jobs on 1 Machine

160

JOBPr

Time

D

DateCR

Current Time = 60

1 11 610091

do last

4 1 33 -27

5 2 32 -14

JOBC

Time

D

DateTardy

Summary

3 31 31 0

2 60 45 15

4 61 33 28

5 63 32 31

1 74 61 13

Total 289 87

Tie use SPT

CR

Mean F Time (289)5 = 578


Tardy 4



FCFS


SPT




EDD



CR


Sequencing Rules

due Time

FCFS

CRSPT

EDD


然而hellip








162



快速換模技術









163



快速換模技術









4改善內部換模

平行作業


5改善外部作業




164





NP-hard problem













Local optimum

Short running time

Global optimum

Long running time


Meta-heuristics






166

f(x)

x

Local optimum

Global

optimum

Meta-heuristics

ldquoJUMPrdquo

119909119905+1 larr 119909119905 + 120578120597119891

120597119909


120597119891

120597119909

119909119905 119909119905+1

120578



Basis











Neighborhood Search


promising regions








memory




go to step 3



















= 500




Due Date(119941119947)

Weights (119960119947)

1 10 4 14

2 10 2 12

3 13 1 1

4 4 12 12




(1243) (2413) and (2134)

119879 1243 = 480 119879 2413 = 436 and 119879 2134 = 652





(4213) (2143) TABU and (2431)

119879 4213 = 460 119879 2143 = 500 TABU and 119879 2431 = 608







(2413) TABU (4123) and (4231)

119879 2413 = 436 TABU 119879 4123 = 440 and 119879 4231 = 632





(1423) (4213) TABU and (4132)

119879 1423 = 408 119879 4213 = 460 TABU and 119879 4132 = 586





Metaheuristics


172

1199091


1199610


1199611 1199612



Global

optimum










exploration

exploitation

(Gen 2005)


If you hellip





175


Interfaces

1 Gantt Chart

2 Dispatch List

3 Capacity Buckets


Scenario

Management

System

Maintenance

Performance

Control

Algorithm

Generator

Interface

Algorithm

Generator

Scheduler amp

Dispatcher

Preprocessor

Scheduling amp

Rescheduling

Algorithms

Manufacturing

Execution

System (MES)

Enterprise

Resource

Planning (MRPII)

Production

Monitoring

System

Database

ImportExport

Synchronization


Algorithm

Library


Scheduling

Logic Unit

Order

Master

File

Shop-

Floor

Data



176







178

Capacity Buckets






改善的機會


講究的是synergy








179












180














Rescheduling

181








Hint WIP



182


Pull Strategy

High Uncertainty

Push Strategy

Low Uncertainty

WIP


Lateness









processing time



HVLV HV

HVHV HV

LVLV LV

LV LVHV

Process Variability

Inflow Variability


迷思










現場動態調整

184






185



再過一陣子





186



在製造業中





187









188







190


迷思


191


迷思

這是當然的


找出關鍵因子

建構因果關係




192



193

為什麼要預測


下一步為何


預測像hellip

194


預測像hellip

195




B2A1E9818B3F




196




197





198






瞭解這就hellip


199






200


其實hellip




201


決策的類型





202


小試身手hellip

天氣與決策

203

不帶傘帶傘





3 拿別人的傘

(良心不安)


小試身手hellip

204


神預測God2GO



小試身手hellip


205

機率02

機率08



方法一期望值







小試身手hellip


206

機率02

機率08





風險成本矩陣

不帶傘帶傘

晴天

成本 $0 成本 $100

(弄丟)

雨天

成本 $200

(感冒)

成本 $0

期望成本

02x0

+08x200

=160

02x100

+08x0

=20

決策帶傘


小試身手hellip


207



風險成本矩陣

不帶傘帶傘

晴天

成本 $0 成本 $100

(弄丟)

雨天

成本 $200

(感冒)

成本 $0

期望成本

02x0

+08x200

=160

02x100

+08x0

=20

決策帶傘

切記hellip


又或hellip



由此可知hellip




208

Lee (2019)


小試身手hellip


209

Based on your

Preference

Structure








210



併購公司A 42 21 8

購置機台 35 28 13

外包 28 25 23







211

天氣情境

方案景氣好

景氣持平

景氣差

Min

Return

併購公司A 42 21 8 8

購置機台 35 28 13 13

外包 28 25 23 23






212

天氣情境

方案景氣好

景氣持平

景氣差

Max

Return

併購公司A 42 21 8 42

購置機台 35 28 13 35

外包 28 25 23 28








213

悔惜矩陣

景氣好

景氣持平

景氣差

Max

Regret

0 7 15 15

7 0 10 10

14 3 0 14

天氣情境

方案景氣好

景氣持平

景氣差

併購公司A 42 21 8

購置機台 35 28 13

外包 28 25 23






214

天氣情境

方案景氣好

景氣持平

景氣差

併購公司A 42 21 8

購置機台 35 28 13

外包 28 25 23






215




Two Types of Risk



Time

Demand

Demand

A

B

C

大試身手hellip

0




Time

Demand

Demand


0

追高殺低


大試身手hellip






218






Scenario Simulator



Time

Demand

Marketing Forecast

Sales Forecast

大試身手hellip

0

Capacity Level






shortage


Linear Regression

Autoregression

Neural Network





220


Empirical Study




221

Capacity Regret

Assessment

CustomerInventory

Market

Share

Profit

Loss

Loss of

Falling Price

Inventory

Loss

Holding

CostReputation

Lower

Capacity

Level

Higher

Capacity

Level

ALTERNATIVE

OBJECTIVE

ATTRIBUTE

119877119904ℎ119900119903119905119886119892119890 缺貨風險119877119904119906119903119901119897119906119904 存貨風險



Empirical Study


222

119877119904ℎ119900119903119905119886119892119890 缺貨風險愈大產能水準向上拉

119877119904119906119903119901119897119906119904 存貨風險愈大產能水準向下壓

119863119898119886119909

119863119898119894119899

Capacity Decision


0

10000

20000

30000

Training

Dataset

Validation

Dataset

Technology

Node A

Time

Demand

Empirical Study

Data Source






223



Empirical Study

2-stage approach

Demand Forecast

Capacity Decision

VDGP


(Chang et al 2014)

224



Empirical Study




225

0

10000

20000

30000

Training

Dataset

Validation

Dataset

Technology

Node A

Time

Demand

Linear Regression

Autoregression

Neural Network


Empirical Study







119877119904ℎ119900119903119905119886119892119890 = 0521 and 119877119904119906119903119901119897119906119904 = 0479

226



MonthActual

Demand


EV MMR SP

Aug 2014 19499 20207 16941 17157 18922Sep 2014 18110 21305 17921 18306 19135Oct 2014 15059 22404 18536 19291 18885



Empirical Study


227

0

500

1000

1500

2000

0 300 600 900 1200

StandardDeviation

AverageRegret

Current

Policy

EVMMR

SP

Poor

Better

Better Poor




Min 119862119909 + 119864 119891 119909 ෩119863




119910+ 119910minus ge 0












228





229

Testing

Accuracy AUC

Model A 719 702

Model B 781 789

Model A預測

FAIL PASS

實際FAIL 61 7

PASS 29 31

Model B預測

FAIL PASS

實際FAIL 47 21

PASS 7 53



迷思


230


迷思

231

170cm

165cm 175cm

172cm



232















233



234



235











going on now






used here

236












237











238




1 1 0 4

2 0 2 12

3 3 2 18

Profit ($1000) $3 $5 0

1823

122

4 st

53

21

21

2

1

21

+

+=

xx

xx

x

x

xxZ


Graphical Solution


feasible region


0

1823

122

4 st

53

21

21

2

1

21

+

+=

xx

xx

x

x

xxZ


Graphical Solution




最佳化結果


6個產品2 (x2)


這就是處方~



遇到問題



提供solution


241



242

Domain Knowledge




243

處方性分析


DS in

MFG










為大於其細


方案評選


見

識

謀

斷


發想

收斂




執行對策

膽大心細

決策與行動

行




245

Descriptive

敘述性

Diagnostic

診斷性

Predictive

預測性

Prescriptive

處方性

Automating

自動性

見

What



Why



When


HowWho Where


戰情財報



(掌握趨勢)



(持續改善)

識謀斷行

U N I S O N


結語

Conclusion

246


迷思



247


迷思










248


迷思


249



Basic

interpretable

models

Post-hoc

Explanation

RegressionBased

Tree Based

DeepLearning

Linear Logistic

regression

Lasso Ridge

GLM GAM

Decision Tree

RF XGBoost

LightGBM

RF

DNN CNN RNN

helliphellip


(build-in)

DataFeature

EngineeringML

Models

Prediction Result

(build-in)

X

Post-hoc Methods


(plug-in)

FeatureImportance

洪紹嚴 (2019)



250

Yield

Time

Cost

Yield

New Tape-out (NTO)

研發導入

Device

optimization

during process

integration

Engineering

Parameter

Optimization

Design of

Experiments

成長期

Tool Matching

Benchmarking

Troubleshooting

Scheduling

Spec Setting SPC






成熟期

快速良率提升

Yield ramp

during pilot

production



during mass

production







機人


迷思




251








迷思

252







253




工業30





工業40








254














馬雲 (201704)








255


結語




However hellip









256


結語KPI Hierarchy

257


ROE

Profit

Margin

Asset

Turnover

Financial

Leveragetimes times

Profit

Sales

Assetsdivide divide

Cost minus Accounts


Sales

Price

Sales

Quantity

Effective

Outputs

Realized

Demand

times

minusmin

Price

Elasticity

Fixed

Cost

Variable

Cost+

Bottleneck

Throughput

Bottleneck

Utilization

Yield

times

Bottleneck

Capacity

times

Bottleneck

Machine

MTTR

MTBFMaintenance

Bottleneck

Availability

times

Demand

vs SupplyQuality

DL

Cost

IDL

Cost

Bui amp Fac

Depre

Equip

Cost

Variable

Unit Cost

times

Other

Assets+

ID Mater

Cost

D Mater

Cost

+ + + + +

Labor MaterialFloor

Space

Non-bottle

Machine

Fin

an

cia

l Ind

ex

Ma

nu

factu

ring In

de

xR

eso

urc

e

WIP Delivery

TAT

CVP CIP

Rework

Rate

Cycle

Time

times

Finished

Goods

+

SchedulingProduct-

mixLot Size

Man Machine

Ratio

Decis

ion




Line

Balancing



258

MFGcom

DATAcomINNOVATION

com

Technology

Migration

Analytics-oriented

- Prediction

- Troubleshooting

- Customer voice


Business-oriented






Analytics

Discussion

Implementation

Problem-oriented

- SOP and cost down




Data

(empirical)

Science

(critical)

Technology

(substantial)

Data Quality

(Internal data)

Data Analysis


Data Platform



Advanced training






戴勝益 (2014)


致謝

260

感謝



以及




謝謝大家~






2017 Modena Italy


1157ndash1182





















261

Contact Information


phone 02-33661206








5






Starting

material

Material in

processing

Processed

material

Value-added




7



Knowledge

詮釋的觀點

思辨的過程

科學的原理


迷思資料資訊



9





10

北南

Etu蔣居裕 (2013)


Experiencehellip


失敗的藝術

人生的歷練


知識與經驗之



Wisdom ishellip


Wisdom ishellip

13





13







智慧工廠



15

智慧工廠

智慧製造

製造智慧



(製造系統)

16


Value and Profit

Value




17

Price

Value

Cost

Consumer

Surplus

Producer

Surplus

Wikipedia (2016)


製造智慧決策

18



SPC APC VM RMS

Carbon

Emission

Water

Recycle


Energy



VRARAI

Cloud

Computing

Cyber-

Physical

System


RFIDSmart Labels



















Inventory



Inventory Reduction







Chien et al (2004)




22



23




24




















26





其實hellip


27

English Math

Student_A 80 76

Student_B 80 91

Student_C 80 83

Student_D 80 62

Student_E 80 88

Layer X Layer Y

Machine_A 81 76

Machine_B 80 91

Machine_C 79 83

Machine_D 80 62

Machine_E 82 88


來自於變異




MES

APC

FDC

SPC

VM

R2R

RMS



Yield Management

hellipetc

Demand Forecast



CapEx

Cost Structure

MPS amp MRP



Order Releasing

hellipetcQuality

Productivity

Cost Down

Cycle Time

28


CIM and Automation

29


ISBN 0-471-93450-X



Benefits

Reduce HR Cost

Reduce MO


Productivity




Benefits

Sustain EQ variance


Support RD




CIM and Automation





31



轉變hellip



一種改善過程

32





1 Transportation

2 Inventory

3 Motion

4 Waiting

5 Overproduction

6 Overprocessing

7 Defects

8 Eschewed Talents

Continuous flow

Line Balancing


Lean Manufacturing


33





CIM and Automation

34

AMHS

MES APC

FMEC



Big Data

Analytics


Data

Warehouse

Knowledge


Selection

Preprocessing

Target Data

Preprocessed

Data

Pattern

Transformed

Data

Data Mining

Transformation

Interpretation

Evaluation



IT Infrastructure

Pattern Extraction



35

Edge

Computing







Problems




製造現場



一言九鼎(頂)



Ask Why








38


生產線數據


39


Characteristic

Pure Feature-



(between features)











Color Images 3D

Scans and Videos



correlation







40



















特性與問題




Data Preprocessing

42

Data

Warehouse

Knowledge

Selection

Preprocessing

Target Data

Preprocessed

Data

Pattern

Transformed

Data

Transformation

Data Mining

Interpretation

Evaluation





Lot001 Lot001 Pass







Lot ID Pass or Fail

Lot001 Pass

Lot002 Pass

Lot003 Fail

Lot004 Pass


Lot001 Pass 20

Lot002 Pass 25

Lot003 Fail 10

Lot004 Pass 15

75 857


Lot002 hellip


Lot002_1

Lot002_2


Parallel Machine


Data Preparation

Missing Value

44


WS_A_Mach_2_Temp

Lot001 820 NA

Lot002 820 NA

Lot003 NA 840

Lot004 NA 840

Lot IDWS_A_Temp

WS_A_Mach_Type

Lot001 820 1

Lot002 820 1

Lot003 840 2

Lot004 840 2

WS_A_Mach_1

WS_A_Mach_2



Golden Machine


Missing Value

45


WS_A_Mach_2_Temp

Lot001 820 NA

Lot002 820 NA

Lot003 820 NA

Lot004 830 NA

Lot005 820 NA

Lot006 820 NA

Lot007 825 NA

Lot008 830 120

Lot009 820 130

Lot010 NA 120


WS_A_Mach_2_Temp

Mach_1 Mach_2

Lot001 820 Avg 1 0

Lot002 820 Avg 1 0

Lot003 820 Avg 1 0

Lot004 830 Avg 1 0

Lot005 820 Avg 1 0

Lot006 820 Avg 1 0

Lot007 825 Avg 1 0

Lot008 830 120 1 1

Lot009 820 130 1 1

Lot010 Avg 120 0 1






46


Lot001 PartsA

Lot002 PartsB

Lot003 PartsA

Lot004 PartsC

Lot005 PartsD

Lot006 PartsE

Lot007 PartsB

Lot008 PartsA

Lot009 PartsC

Lot010 PartsE


WS_A_Mach_1_PartsB

WS_A_Mach_1_PartsC

WS_A_Mach_1_PartsD

Lot001 1 0 0 0

Lot002 0 1 0 0

Lot003 1 0 0 0

Lot004 0 0 1 0

Lot005 0 0 0 1

Lot006 0 0 0 0

Lot007 0 1 0 0

Lot008 1 0 0 0

Lot009 0 0 1 0

Lot010 0 0 0 0






建議方式







沒有再現性

47



抽樣檢測

48




NO001 鋁 A 13723 7235

NO002 鋁 B NA NA

NO003 鋁 B 13728 7237

NO099 鋁 B NA NA

NO100 鋁 A 13726 7236

X Y (抽檢)

沒被抽檢

沒被抽檢

抽樣

填補遺漏值



3 Prediction Model








49









有母數GLMRandom


Learninghellip


換線換模






50

Machine A A A


Machine A B


B B B

A B A B









51

MachineI2

A A AMachine1

B B


A A A

Machine2

A A AMachine1

A A A

B

B




瓶頸 (bottleneck)







52


120

unitsday

140

unitsday

80

unitsday

120

unitsday

100

unitsday

瓶頸

80 unitsday



(勞工和幹部)



楊大和(2016)










53





54

IDProduct

TypeStage

Process

Time (hrs)

Start

Time

Lot1 A 1 1 20161226 1450

Lot1 A 2 1 20161226 1600

Lot1 A 3 05 20161226 1720

Lot1 A 4 1 20161226 1800

Lot1 A 5 05 20161226 2030







55


211 000000

211 010000

211 020000

211 230000


211 000629

211 001041

211 034109

211 231157




Data Merge

56









建議串接方法

Rolling Forward

Nearest time

Rolling Forward

Rolling Backward

Nearest time




Lee and Dong (2019)






產品的queue time



57

STA

GE

x_S

VID

x

0 5

10

1

5

2

0

2

5

0 200 400 600 800 1000Lot or

Time






58


Time Downcode


2017-05-07140528


2017-05-07161214


2017-05-07174130



2017-05-07192243


2017-05-07201817




19 22 43 minus (16 12 14)








10 vs 90 5 vs 95 or 1 vs 99



predictionhellip



59




Lot01 PASS

Lot02 PASS

Lot03 PASS

Lot04 PASS

Lot05 PASS

Lot06 PASS

Lot07 FAIL

Lot08 PASS

Lot09 PASS

Lot10 PASS

Lot11 PASS

Lot12 PASS





準確度可達 1112 = 917



迷思


61



62


資料整合













迷思補遺漏值


63

English Math

Student_A 80 76

Student_B 80 91

Student_C 80 83

Student_D 80 62

Student_E 80

Avg 80

Max 91

Min 62

Avg 78


迷思補遺漏值

64













64








B 男 51 $64000 Yes

C 男 52 $105000 Yes

D 女 33 $55000 Yes

E 男 45 $45000 No

F 女 45 $100000


65



66

K=3

K=5




迷思補遺漏值

67


1 00886 00886 00886 00886

2 00684 00684 00684 00684

3 03515 03515 03515 03515

4 09874 09874 09874 09874

5 04713 04713 04713 04713

6 06115 06115 06115 06115

7 02573 02573 02573 02573

8 02914 02914 02914 02914

9 01662 01662 01662 01662

10 044 044 044 044

11 06939 03731 06622

平均值 04023 03731 03731 03994

標準差 02785 02753 02612 02753

誤差值 03208 00317




數據品質

68






資料品質

Univariate





Multiple Column




數據品質



69



Automobile Company




digital materials







71















72






Feature Selection






74








75

材料

設計

光罩


測試

封裝

最後測試

加熱製程

微影製程

離子佈植


介電質沉積

晶圓


Over 1000 stages










and unreliable




76




77


Root Cause As-Is



To-Be

Data Science

Automation









78

K

C

H

E

A

G

I

J

F

L

OR

DS

BP M

N

Q






Rule Extraction




79

Good 68 68

Bad 32 32

Good - -

Bad 23 100

Good 68 88

Bad 9 12

Good - -

Bad 6 100

Good 68 96

Bad 3 4





OK

NG

NG

NG

NG

NG NG NG

OK

OK

OKOK OKOK

NG

YES NO

YES

YES YES

YESYES

YES

NO

NO

NO

NO NO

NO

80

Map clustering for

systematic defects

12 defect patterns

and build WBM bank





(Lee and Tsai 2019)



81




(Wang2012）





29 Alarm

16 Prediction model

training

15 EWMA for Target

Baseline (TB)



24 Predicted

CUSUM out of

control

25 Pre-alarmYes

No

28 Actual

CUSUM out of

control

Yes

No


21 New sample

prediction



17 Model validation

34 Continuous

monitoring

11 Data collection

26 Engineering

Validation amp

Troubleshooting

31 Loss calculation


32 CUSUM

control chart

33 Loss

CUSUM out of

control

310 Add new samples


311 ILPM model


Yes

Off-line training

In-line prediction

Concept drift

Pre-alarm stage


correction

No

All good products

37 Bayesian

monitoring out

of control

35 Equipment



39 Update posterior


38 Alarm and

equipment

maintenance

Yes

Model misalignment


Equipment

misalignment


36 Lifetime

out of control

No

Yes



82







83





Self-Priming

Centrifugal Pump



84




Feature Selection

Feature Engineering

85

Data

Warehouse

Knowledge

Selection

Preprocessing

Target Data

Preprocessed

Data

Pattern

Transformed

Data

Transformation

Data Mining

Interpretation

Evaluation




易於決策判斷









精度預測





86



Feature Selection



ie p gtgt n issue




87

An

p

Xn

k k ltlt p








Types









(PCA) etc

88







89

Lee and Chen (2018)



90

Prepared

Dataset

Feature

Selection

LASSO SVMStepwise

Regression

Voting


Pivot

Analysis

Engineering

Experience

Feature

Validation

BoostingRandom

ForestPCA Random

Sampling

Data

Reduction

(pgtgtn)

Imbalance

Correlation

Coefficient

Independence

Testhellip

Data

Preprocessing

hellip

Yes

No

Knowledge

Management (KM)

Documentation

Lee and Tsai (2019)

iterative

process






同理hellip

因果rarr相關







91








92

119910 = 120572 + 1205731199091 + 120576

119910 = 120572 + 1205731199092 + 120576

119910 = 120572 + 1205731199093 + 120576

119910 = 120572 + 1205731199094 + 120576

119910 = 120572 + 12057321199092 + 1205731199091 + 120576

119910 = 120572 + 12057321199092 + 1205731199093 + 120576

119910 = 120572 + 12057321199092 + 1205731199094 + 120576

119910 = 120572 + 12057321199092 + 12057341199094 + 1205731199091 + 120576

119910 = 120572 + 12057321199092 + 12057341199094 + 1205731199093 + 120576

統計顯著的變數1199092 and 1199094



መ120573119897119886119904119904119900 = argmin120573

σ119894=1119873 (119910119894 minus 1205730 minus σ119895=1

119875 119909119894119895120573119895)2

Subject to σ119895=1119875 120573119895 le 119905


1

2σ119894=1119873 (119910119894 minus 1205730 minus σ119895=1

119875 119909119894119895120573119895)2 + 120582σ119895=1

119875 120573119895

93


Penalty( 120582 ) x1 x2 x3 x4 x5 x6 x7

120582 = 0

120582 = 40

120582 = 418

120582 = 419

120582 = 42

120582 = 50





94


x12

x11

x10

x9

x8

x7

x6

x5

x4

x3

x2

x1

Feature Importance



Voting (投票法)



95



SVID_003 4

SVID_101 3

SVID_021 3

SVID_040 3

SVID_002 3

SVID_128 2

SVID_062 2

SVID_077 2






96

Test

Test

Test

Test


1st iter

2nd iter

3rd iter

10th iter

hellip

Error1

Error2

Error3

Error10

Minimize Error=1

10σ119894=110 Error119894



97


Undersampling



Example








SVIDVoting by

Undersampling

SVID_003 19

SVID_101 18

SVID_021 18

SVID_040 18

SVID_002 17

SVID_128 17

SVID_062 17

SVID_077 17

hellip hellip




98


SVID_003 09487 02583 11439

SVID_101 02078 05434 08934

SVID_021 04105 08377 06845

SVID_040 5208 7169 03170

SVID_002 27256 21025 02581

SVID_128 80523 85336 00580

SVID_062 09430 09747 00330

SVID_077 1569 1603 00216



Photo_06 12 384 00313

Etch_10 3 295 00102

Photo_32 10 1011 00099

Photo_17 4 410 00098

PVD_02 1 123 00081

CVD_14 9 3456 00026

Diff_09 1 495 00020

Etch_07 5 2769 00018



良品119886119907119892 minus不良品119886119907119892

119860119907119892

RATIO = FAIL TOTAL





99








迷思



100



Feature Engineering









119903 = 11990912 + 1199092

2

120579 = arctan11990921199091


101


119903

120579

1199091

1199092













Trend (趨勢)



Randomness (隨機)




102

Σ

A

A1 A2

B

B1 B2

C

C1 C2

人

人




103





預測

良品不良品




Benefits




104



105

Dataset with

selected variable

Prediction

Classification

Model

PLS BPNN CNN


R-Squared

MSE

Confusion

Matrix

Model

Evaluation

BoostingDecision

TreeSVR

Random

Sampling

Data

Transformation

Imbalance

Categorical to

Dummy VarFeature

Extraction

Feature

Selection

hellip

Yes

No

Knowledge

Management (KM)

Documentation


Z-scores


iterative

process















Data Imbalance

106










107

helliphellip

Input

Layer

Hidden

Layer

Output

Layer

hellip

helliphellip

helliphellip

helliphellip

helliphellip

helliphellip

helliphellip

x1

x2

xm

ො1199101

ො1199102

ො119910n

y1

y2

yn

NN

Output

Desired

Output




108







109

Yie

ld

Pre

cis

ion

Metr

olo

gy V

alu

e

Lot

Real value







110

UCL

LCL

Yie

ld

Pre

cis

ion

Metr

olo

gy V

alu

e

Lot

Real value









TNTP

+++

+=Accuracy


預測類別


實際類別

類別1


FN (false negative)

(Type II error)

(miss)

類別2

(良品)

FP (false positive)

(Type I error)

(false alarm)

TN (true negative)

111











112

TPSensitivity

TP+FN=

TNSpecificity

TN+FP=

預測

類別1 類別2

實際

類別1 TP FN

類別2 FP TN




TP

Rate

= S

ensitiv

ity

Model A

Model B

Precision=TP






113

Testing


Model A 719 897 517 702

Model B 781 691 883 789

Model A預測

Bad Good

實際Bad 61 7

Good 29 31

Model B預測

Bad Good

實際Bad 47 21

Good 7 53


精度良率預測







114

Time

Y

UCL

LCL

Time

Y

UCL

LCL





double EWMA




EWMA Control


115


Liu et al (2018)



116


維修保養








117











118
























119




120


No 名稱 No 名稱




4 R扣環 12 風扇


6 S扣環 14 風罩






Vibration Dataset

121

Amplitude

Time

(Obs)



Lee et al (2019)





122


Inspection

zone

Preventive

replacement

zone

Corrective

replacement

zone

Failure level

Replacement level

Data collection RUL




123

(Lee et al 2014)















124





Feature Engineering

125

Peak-

to-

peak




Data

Collection

Data

Preprocessing



Feature

Extraction

Feature

Selection

Remove high



(VIF)



Important

Variables

Predict

Linear Regression

(OLS)


Prediction Result


Regression (PLS)

Prediction

Model

OLS


PLS


BPNN

MSE = 123456789

Feature Engineering

(製造資料)





127



Feature Engineering









129




29 Alarm

16 Prediction model

training

15 EWMA for Target

Baseline (TB)



24 Predicted

CUSUM out of

control

25 Pre-alarmYes

No

28 Actual

CUSUM out of

control

Yes

No


21 New sample

prediction



17 Model validation

34 Continuous

monitoring

11 Data collection

26 Engineering

Validation amp

Troubleshooting

31 Loss calculation


32 CUSUM

control chart

33 Loss

CUSUM out of

control

310 Add new samples


311 ILPM model


Yes

Off-line training

In-line prediction

Concept drift

Pre-alarm stage


correction

No

All good products

37 Bayesian

monitoring out

of control

35 Equipment



39 Update posterior


38 Alarm and

equipment

maintenance

Yes

Model misalignment


Equipment

misalignment


36 Lifetime

out of control

No

Yes


Engineering



















hellip

130
















hellip

131






ldquo機會rdquo


132




133


很多時候我們


134

事實上hellip


現場改善

資料科學

系統整合

資料品質確認


浪費與WIP

瓶頸站生產力

人機比

設施佈置

環境公安衛生


流程再造BPR

時間動作研究



浪費移除

產線平衡


IT基礎建設

Make-or-Buy

需求預測

產銷平衡

排程與交期

特徵選取

Troubleshooting

機台維修保養


預測方法


啟發式演算法

機器學習


系統開發

供應鏈平台JIT



製程能力優化

良率提升



組件剩餘壽命


資料不一致





Decision Science

New Business Model


Price Maintenance


Sustainability

資料分析確認

Lee and Chien

(2020)


可能會問hellip




136


資料科學






現場觀察


137


話說hellip


某廠區稼動率116200 = 58







138



139

魚骨圖

法



環境


少量多樣

溝通管道

其他

交班傳達不周

人

人力缺乏



等待人員操作

機

機台維修保養

模具更換


待料


料


在製品堆放

機台稼動率低


作業不熟練

需求變異

工程變更

政策法規改變

傳承關係





案例





eg (56+160+138 mins)(180+180+180 mins)

=656

140




案例





eg (56+160+138 mins)(180+180+180 mins)

=656

141


(分)作業

耗時

(分)作業

耗時

(分)作業

耗時

(分)




1427-1430 產品品質檢測 3

1430-1443 電腦資料輸入 13


1450-1454 電腦工程分析 4

1454-1500 領取原物料 6

1500-1515 休息 15

1515-1528 領取模具 13

1528-1533 產品品質檢測 5


1543-1548 換模具 5


1601-1610 領取模具 9

1610-1617 產品品質檢測 7

1617-1622 存放載具 5

1622-1631 產品品質檢測 9


1640-1647 產品品質檢測 7


1652-1655 領取原物料 3

1655-1700 電腦資料輸入 5

機器加工

(產品D)

機器加工

(產品C)

13

124


停機

等待換規格

換模

停機

待料

機器加工

(產品A)

機器加工

(產品B)

機器加工

(產品C)

43

140

20

88

42

50

機器加工

(產品B)







200 80 = 160 (台) 到 200 85 = 170 (台) 之間為理想機台運作數



142









=工作效率




=08

1minus0656= 233 (台)


143






缺點很花時間






144





A 全部hellip

現場rarr瓶頸站





目標的衝突


145

Strategic Level


Planning

Marketing

Planning

Make-or-Buy

Strategy

Tactical Level


Planning


Order Allocation

Master Production

Schedule

Resource Planning

Rough-Cut Capacity

Planning

Capacity Require

Planning

Material Require

Planning

Monthly Material

Planning

Capacity Planning

Productivity amp

Efficiency Analysis

Vendor Relationship

MgmtDemand Mgmt


Purchasing


Daily Assignment

Order Releasing


Scheduling



Production


Operational Level

Logistics Mgmt

Long Term

Mid Term

Short Term

Facility Layout






146




timeProduction


uptimeEquipment

timeProduction

timeTotal

uptimeEquipment

timeTotal


=

=

=

Nonscheduled

state

Unscheduled

down state

Scheduled

down state

Engineering

state

Standby

state

Productive

state

Equipment

uptime

Equipment

downtime

Operations

time

Production

time

Total

time



147

顧客訂單產品

交期變動插單

工程變更




操作員

人力不足

MO


人員配置


機台設備廠務





廠區間的Backup



停工待料


外包時程變異

進料品質變異

















148






優先順序

日期達交












衝突目標

Makespan


(TWET)

交期

利用率

庫存時間



排程應用範疇


機場飛機起降



電梯設定

微處理器系統

醫院排班

醫院復健排程

醫師手術排班




150




人工排程邏輯

訂單資料

依到期日排序


預估單

工作號賦予




Yes

No


No





優先順序法則

Dispatching










Rush 緊急事件

152




剩餘作業數




Performance Metrics

Mean Flow Time






119879119895 = max0 119871119895


N Jobs on 1 Machine


N Jobs on 1 Machine




Notations



119889119895 due date

154


1 11 61

2 29 45

3 31 31

4 1 33

5 2 32


N Jobs on 1 Machine

FCFS



Tardy Jobs 3

155


J1 11 11 61 0

J2 29 40 45 0

J3 31 71 31 40

J4 1 72 33 39

J5 2 74 32 42

Totals 74 268 121





N Jobs on 1 Machine

SPT



Tardy 1

156


J4 1 1 33 0

J5 2 3 32 0

J1 11 14 61 0

J2 29 43 45 0

J3 31 74 31 43

Totals 74 135 45


N Jobs on 1 Machine

EDD



Tardy 4

157


J3 31 31 31 0

J5 2 33 32 1

J4 1 34 33 1

J2 29 63 45 18

J1 11 74 61 13

Totals 74 235 33


N Jobs on 1 Machine






Compute


158

119862119877 =119863119906119890_119863119886119905119890 minus (119862119906119903_119879119894119898119890)

119875119903119900119888119890119904119904119894119899119892_119879119894119898119890


CR

N Jobs on 1 Machine

159

JOBPr

Time

D

DateCR

Current Time = 0

1 11 61 5546

2 29 45 1552

3 31 31 100

4 1 33 33

5 2 32 16

JOBPr

Time

D

DateCR

Current Time = 31

1 11 61 2727

2 29 45 483

4 1 33 2

5 2 32 05


N Jobs on 1 Machine

160

JOBPr

Time

D

DateCR

Current Time = 60

1 11 610091

do last

4 1 33 -27

5 2 32 -14

JOBC

Time

D

DateTardy

Summary

3 31 31 0

2 60 45 15

4 61 33 28

5 63 32 31

1 74 61 13

Total 289 87

Tie use SPT

CR

Mean F Time (289)5 = 578


Tardy 4



FCFS


SPT




EDD



CR


Sequencing Rules

due Time

FCFS

CRSPT

EDD


然而hellip








162



快速換模技術









163



快速換模技術









4改善內部換模

平行作業


5改善外部作業




164





NP-hard problem













Local optimum

Short running time

Global optimum

Long running time


Meta-heuristics






166

f(x)

x

Local optimum

Global

optimum

Meta-heuristics

ldquoJUMPrdquo

119909119905+1 larr 119909119905 + 120578120597119891

120597119909


120597119891

120597119909

119909119905 119909119905+1

120578



Basis











Neighborhood Search


promising regions








memory




go to step 3



















= 500




Due Date(119941119947)

Weights (119960119947)

1 10 4 14

2 10 2 12

3 13 1 1

4 4 12 12




(1243) (2413) and (2134)

119879 1243 = 480 119879 2413 = 436 and 119879 2134 = 652





(4213) (2143) TABU and (2431)

119879 4213 = 460 119879 2143 = 500 TABU and 119879 2431 = 608







(2413) TABU (4123) and (4231)

119879 2413 = 436 TABU 119879 4123 = 440 and 119879 4231 = 632





(1423) (4213) TABU and (4132)

119879 1423 = 408 119879 4213 = 460 TABU and 119879 4132 = 586





Metaheuristics


172

1199091


1199610


1199611 1199612



Global

optimum










exploration

exploitation

(Gen 2005)


If you hellip





175


Interfaces

1 Gantt Chart

2 Dispatch List

3 Capacity Buckets


Scenario

Management

System

Maintenance

Performance

Control

Algorithm

Generator

Interface

Algorithm

Generator

Scheduler amp

Dispatcher

Preprocessor

Scheduling amp

Rescheduling

Algorithms

Manufacturing

Execution

System (MES)

Enterprise

Resource

Planning (MRPII)

Production

Monitoring

System

Database

ImportExport

Synchronization


Algorithm

Library


Scheduling

Logic Unit

Order

Master

File

Shop-

Floor

Data



176







178

Capacity Buckets






改善的機會


講究的是synergy








179












180














Rescheduling

181








Hint WIP



182


Pull Strategy

High Uncertainty

Push Strategy

Low Uncertainty

WIP


Lateness









processing time



HVLV HV

HVHV HV

LVLV LV

LV LVHV

Process Variability

Inflow Variability


迷思










現場動態調整

184






185



再過一陣子





186



在製造業中





187









188







190


迷思


191


迷思

這是當然的


找出關鍵因子

建構因果關係




192



193

為什麼要預測


下一步為何


預測像hellip

194


預測像hellip

195




B2A1E9818B3F




196




197





198






瞭解這就hellip


199






200


其實hellip




201


決策的類型





202


小試身手hellip

天氣與決策

203

不帶傘帶傘





3 拿別人的傘

(良心不安)


小試身手hellip

204


神預測God2GO



小試身手hellip


205

機率02

機率08



方法一期望值







小試身手hellip


206

機率02

機率08





風險成本矩陣

不帶傘帶傘

晴天

成本 $0 成本 $100

(弄丟)

雨天

成本 $200

(感冒)

成本 $0

期望成本

02x0

+08x200

=160

02x100

+08x0

=20

決策帶傘


小試身手hellip


207



風險成本矩陣

不帶傘帶傘

晴天

成本 $0 成本 $100

(弄丟)

雨天

成本 $200

(感冒)

成本 $0

期望成本

02x0

+08x200

=160

02x100

+08x0

=20

決策帶傘

切記hellip


又或hellip



由此可知hellip




208

Lee (2019)


小試身手hellip


209

Based on your

Preference

Structure








210



併購公司A 42 21 8

購置機台 35 28 13

外包 28 25 23







211

天氣情境

方案景氣好

景氣持平

景氣差

Min

Return

併購公司A 42 21 8 8

購置機台 35 28 13 13

外包 28 25 23 23






212

天氣情境

方案景氣好

景氣持平

景氣差

Max

Return

併購公司A 42 21 8 42

購置機台 35 28 13 35

外包 28 25 23 28








213

悔惜矩陣

景氣好

景氣持平

景氣差

Max

Regret

0 7 15 15

7 0 10 10

14 3 0 14

天氣情境

方案景氣好

景氣持平

景氣差

併購公司A 42 21 8

購置機台 35 28 13

外包 28 25 23






214

天氣情境

方案景氣好

景氣持平

景氣差

併購公司A 42 21 8

購置機台 35 28 13

外包 28 25 23






215




Two Types of Risk



Time

Demand

Demand

A

B

C

大試身手hellip

0




Time

Demand

Demand


0

追高殺低


大試身手hellip






218






Scenario Simulator



Time

Demand

Marketing Forecast

Sales Forecast

大試身手hellip

0

Capacity Level






shortage


Linear Regression

Autoregression

Neural Network





220


Empirical Study




221

Capacity Regret

Assessment

CustomerInventory

Market

Share

Profit

Loss

Loss of

Falling Price

Inventory

Loss

Holding

CostReputation

Lower

Capacity

Level

Higher

Capacity

Level

ALTERNATIVE

OBJECTIVE

ATTRIBUTE

119877119904ℎ119900119903119905119886119892119890 缺貨風險119877119904119906119903119901119897119906119904 存貨風險



Empirical Study


222

119877119904ℎ119900119903119905119886119892119890 缺貨風險愈大產能水準向上拉

119877119904119906119903119901119897119906119904 存貨風險愈大產能水準向下壓

119863119898119886119909

119863119898119894119899

Capacity Decision


0

10000

20000

30000

Training

Dataset

Validation

Dataset

Technology

Node A

Time

Demand

Empirical Study

Data Source






223



Empirical Study

2-stage approach

Demand Forecast

Capacity Decision

VDGP


(Chang et al 2014)

224



Empirical Study




225

0

10000

20000

30000

Training

Dataset

Validation

Dataset

Technology

Node A

Time

Demand

Linear Regression

Autoregression

Neural Network


Empirical Study







119877119904ℎ119900119903119905119886119892119890 = 0521 and 119877119904119906119903119901119897119906119904 = 0479

226



MonthActual

Demand


EV MMR SP

Aug 2014 19499 20207 16941 17157 18922Sep 2014 18110 21305 17921 18306 19135Oct 2014 15059 22404 18536 19291 18885



Empirical Study


227

0

500

1000

1500

2000

0 300 600 900 1200

StandardDeviation

AverageRegret

Current

Policy

EVMMR

SP

Poor

Better

Better Poor




Min 119862119909 + 119864 119891 119909 ෩119863




119910+ 119910minus ge 0












228





229

Testing

Accuracy AUC

Model A 719 702

Model B 781 789

Model A預測

FAIL PASS

實際FAIL 61 7

PASS 29 31

Model B預測

FAIL PASS

實際FAIL 47 21

PASS 7 53



迷思


230


迷思

231

170cm

165cm 175cm

172cm



232















233



234



235











going on now






used here

236












237











238




1 1 0 4

2 0 2 12

3 3 2 18

Profit ($1000) $3 $5 0

1823

122

4 st

53

21

21

2

1

21

+

+=

xx

xx

x

x

xxZ


Graphical Solution


feasible region


0

1823

122

4 st

53

21

21

2

1

21

+

+=

xx

xx

x

x

xxZ


Graphical Solution




最佳化結果


6個產品2 (x2)


這就是處方~



遇到問題



提供solution


241



242

Domain Knowledge




243

處方性分析


DS in

MFG










為大於其細


方案評選


見

識

謀

斷


發想

收斂




執行對策

膽大心細

決策與行動

行




245

Descriptive

敘述性

Diagnostic

診斷性

Predictive

預測性

Prescriptive

處方性

Automating

自動性

見

What



Why



When


HowWho Where


戰情財報



(掌握趨勢)



(持續改善)

識謀斷行

U N I S O N


結語

Conclusion

246


迷思



247


迷思










248


迷思


249



Basic

interpretable

models

Post-hoc

Explanation

RegressionBased

Tree Based

DeepLearning

Linear Logistic

regression

Lasso Ridge

GLM GAM

Decision Tree

RF XGBoost

LightGBM

RF

DNN CNN RNN

helliphellip


(build-in)

DataFeature

EngineeringML

Models

Prediction Result

(build-in)

X

Post-hoc Methods


(plug-in)

FeatureImportance

洪紹嚴 (2019)



250

Yield

Time

Cost

Yield

New Tape-out (NTO)

研發導入

Device

optimization

during process

integration

Engineering

Parameter

Optimization

Design of

Experiments

成長期

Tool Matching

Benchmarking

Troubleshooting

Scheduling

Spec Setting SPC






成熟期

快速良率提升

Yield ramp

during pilot

production



during mass

production







機人


迷思




251








迷思

252







253




工業30





工業40








254














馬雲 (201704)








255


結語




However hellip









256


結語KPI Hierarchy

257


ROE

Profit

Margin

Asset

Turnover

Financial

Leveragetimes times

Profit

Sales

Assetsdivide divide

Cost minus Accounts


Sales

Price

Sales

Quantity

Effective

Outputs

Realized

Demand

times

minusmin

Price

Elasticity

Fixed

Cost

Variable

Cost+

Bottleneck

Throughput

Bottleneck

Utilization

Yield

times

Bottleneck

Capacity

times

Bottleneck

Machine

MTTR

MTBFMaintenance

Bottleneck

Availability

times

Demand

vs SupplyQuality

DL

Cost

IDL

Cost

Bui amp Fac

Depre

Equip

Cost

Variable

Unit Cost

times

Other

Assets+

ID Mater

Cost

D Mater

Cost

+ + + + +

Labor MaterialFloor

Space

Non-bottle

Machine

Fin

an

cia

l Ind

ex

Ma

nu

factu

ring In

de

xR

eso

urc

e

WIP Delivery

TAT

CVP CIP

Rework

Rate

Cycle

Time

times

Finished

Goods

+

SchedulingProduct-

mixLot Size

Man Machine

Ratio

Decis

ion




Line

Balancing



258

MFGcom

DATAcomINNOVATION

com

Technology

Migration

Analytics-oriented

- Prediction

- Troubleshooting

- Customer voice


Business-oriented






Analytics

Discussion

Implementation

Problem-oriented

- SOP and cost down




Data

(empirical)

Science

(critical)

Technology

(substantial)

Data Quality

(Internal data)

Data Analysis


Data Platform



Advanced training






戴勝益 (2014)


致謝

260

感謝



以及




謝謝大家~






2017 Modena Italy


1157ndash1182





















261

Contact Information


phone 02-33661206











Starting

material

Material in

processing

Processed

material

Value-added




7



Knowledge

詮釋的觀點

思辨的過程

科學的原理


迷思資料資訊



9





10

北南

Etu蔣居裕 (2013)


Experiencehellip


失敗的藝術

人生的歷練


知識與經驗之



Wisdom ishellip


Wisdom ishellip

13





13







智慧工廠



15

智慧工廠

智慧製造

製造智慧



(製造系統)

16


Value and Profit

Value




17

Price

Value

Cost

Consumer

Surplus

Producer

Surplus

Wikipedia (2016)


製造智慧決策

18



SPC APC VM RMS

Carbon

Emission

Water

Recycle


Energy



VRARAI

Cloud

Computing

Cyber-

Physical

System


RFIDSmart Labels



















Inventory



Inventory Reduction







Chien et al (2004)




22



23




24




















26





其實hellip


27

English Math

Student_A 80 76

Student_B 80 91

Student_C 80 83

Student_D 80 62

Student_E 80 88

Layer X Layer Y

Machine_A 81 76

Machine_B 80 91

Machine_C 79 83

Machine_D 80 62

Machine_E 82 88


來自於變異




MES

APC

FDC

SPC

VM

R2R

RMS



Yield Management

hellipetc

Demand Forecast



CapEx

Cost Structure

MPS amp MRP



Order Releasing

hellipetcQuality

Productivity

Cost Down

Cycle Time

28


CIM and Automation

29


ISBN 0-471-93450-X



Benefits

Reduce HR Cost

Reduce MO


Productivity




Benefits

Sustain EQ variance


Support RD




CIM and Automation





31



轉變hellip



一種改善過程

32





1 Transportation

2 Inventory

3 Motion

4 Waiting

5 Overproduction

6 Overprocessing

7 Defects

8 Eschewed Talents

Continuous flow

Line Balancing


Lean Manufacturing


33





CIM and Automation

34

AMHS

MES APC

FMEC



Big Data

Analytics


Data

Warehouse

Knowledge


Selection

Preprocessing

Target Data

Preprocessed

Data

Pattern

Transformed

Data

Data Mining

Transformation

Interpretation

Evaluation



IT Infrastructure

Pattern Extraction



35

Edge

Computing







Problems




製造現場



一言九鼎(頂)



Ask Why








38


生產線數據


39


Characteristic

Pure Feature-



(between features)











Color Images 3D

Scans and Videos



correlation







40



















特性與問題




Data Preprocessing

42

Data

Warehouse

Knowledge

Selection

Preprocessing

Target Data

Preprocessed

Data

Pattern

Transformed

Data

Transformation

Data Mining

Interpretation

Evaluation





Lot001 Lot001 Pass







Lot ID Pass or Fail

Lot001 Pass

Lot002 Pass

Lot003 Fail

Lot004 Pass


Lot001 Pass 20

Lot002 Pass 25

Lot003 Fail 10

Lot004 Pass 15

75 857


Lot002 hellip


Lot002_1

Lot002_2


Parallel Machine


Data Preparation

Missing Value

44


WS_A_Mach_2_Temp

Lot001 820 NA

Lot002 820 NA

Lot003 NA 840

Lot004 NA 840

Lot IDWS_A_Temp

WS_A_Mach_Type

Lot001 820 1

Lot002 820 1

Lot003 840 2

Lot004 840 2

WS_A_Mach_1

WS_A_Mach_2



Golden Machine


Missing Value

45


WS_A_Mach_2_Temp

Lot001 820 NA

Lot002 820 NA

Lot003 820 NA

Lot004 830 NA

Lot005 820 NA

Lot006 820 NA

Lot007 825 NA

Lot008 830 120

Lot009 820 130

Lot010 NA 120


WS_A_Mach_2_Temp

Mach_1 Mach_2

Lot001 820 Avg 1 0

Lot002 820 Avg 1 0

Lot003 820 Avg 1 0

Lot004 830 Avg 1 0

Lot005 820 Avg 1 0

Lot006 820 Avg 1 0

Lot007 825 Avg 1 0

Lot008 830 120 1 1

Lot009 820 130 1 1

Lot010 Avg 120 0 1






46


Lot001 PartsA

Lot002 PartsB

Lot003 PartsA

Lot004 PartsC

Lot005 PartsD

Lot006 PartsE

Lot007 PartsB

Lot008 PartsA

Lot009 PartsC

Lot010 PartsE


WS_A_Mach_1_PartsB

WS_A_Mach_1_PartsC

WS_A_Mach_1_PartsD

Lot001 1 0 0 0

Lot002 0 1 0 0

Lot003 1 0 0 0

Lot004 0 0 1 0

Lot005 0 0 0 1

Lot006 0 0 0 0

Lot007 0 1 0 0

Lot008 1 0 0 0

Lot009 0 0 1 0

Lot010 0 0 0 0






建議方式







沒有再現性

47



抽樣檢測

48




NO001 鋁 A 13723 7235

NO002 鋁 B NA NA

NO003 鋁 B 13728 7237

NO099 鋁 B NA NA

NO100 鋁 A 13726 7236

X Y (抽檢)

沒被抽檢

沒被抽檢

抽樣

填補遺漏值



3 Prediction Model








49









有母數GLMRandom


Learninghellip


換線換模






50

Machine A A A


Machine A B


B B B

A B A B









51

MachineI2

A A AMachine1

B B


A A A

Machine2

A A AMachine1

A A A

B

B




瓶頸 (bottleneck)







52


120

unitsday

140

unitsday

80

unitsday

120

unitsday

100

unitsday

瓶頸

80 unitsday



(勞工和幹部)



楊大和(2016)










53





54

IDProduct

TypeStage

Process

Time (hrs)

Start

Time

Lot1 A 1 1 20161226 1450

Lot1 A 2 1 20161226 1600

Lot1 A 3 05 20161226 1720

Lot1 A 4 1 20161226 1800

Lot1 A 5 05 20161226 2030







55


211 000000

211 010000

211 020000

211 230000


211 000629

211 001041

211 034109

211 231157




Data Merge

56









建議串接方法

Rolling Forward

Nearest time

Rolling Forward

Rolling Backward

Nearest time




Lee and Dong (2019)






產品的queue time



57

STA

GE

x_S

VID

x

0 5

10

1

5

2

0

2

5

0 200 400 600 800 1000Lot or

Time






58


Time Downcode


2017-05-07140528


2017-05-07161214


2017-05-07174130



2017-05-07192243


2017-05-07201817




19 22 43 minus (16 12 14)








10 vs 90 5 vs 95 or 1 vs 99



predictionhellip



59




Lot01 PASS

Lot02 PASS

Lot03 PASS

Lot04 PASS

Lot05 PASS

Lot06 PASS

Lot07 FAIL

Lot08 PASS

Lot09 PASS

Lot10 PASS

Lot11 PASS

Lot12 PASS





準確度可達 1112 = 917



迷思


61



62


資料整合













迷思補遺漏值


63

English Math

Student_A 80 76

Student_B 80 91

Student_C 80 83

Student_D 80 62

Student_E 80

Avg 80

Max 91

Min 62

Avg 78


迷思補遺漏值

64













64








B 男 51 $64000 Yes

C 男 52 $105000 Yes

D 女 33 $55000 Yes

E 男 45 $45000 No

F 女 45 $100000


65



66

K=3

K=5




迷思補遺漏值

67


1 00886 00886 00886 00886

2 00684 00684 00684 00684

3 03515 03515 03515 03515

4 09874 09874 09874 09874

5 04713 04713 04713 04713

6 06115 06115 06115 06115

7 02573 02573 02573 02573

8 02914 02914 02914 02914

9 01662 01662 01662 01662

10 044 044 044 044

11 06939 03731 06622

平均值 04023 03731 03731 03994

標準差 02785 02753 02612 02753

誤差值 03208 00317




數據品質

68






資料品質

Univariate





Multiple Column




數據品質



69



Automobile Company




digital materials







71















72






Feature Selection






74








75

材料

設計

光罩


測試

封裝

最後測試

加熱製程

微影製程

離子佈植


介電質沉積

晶圓


Over 1000 stages










and unreliable




76




77


Root Cause As-Is



To-Be

Data Science

Automation









78

K

C

H

E

A

G

I

J

F

L

OR

DS

BP M

N

Q






Rule Extraction




79

Good 68 68

Bad 32 32

Good - -

Bad 23 100

Good 68 88

Bad 9 12

Good - -

Bad 6 100

Good 68 96

Bad 3 4





OK

NG

NG

NG

NG

NG NG NG

OK

OK

OKOK OKOK

NG

YES NO

YES

YES YES

YESYES

YES

NO

NO

NO

NO NO

NO

80

Map clustering for

systematic defects

12 defect patterns

and build WBM bank





(Lee and Tsai 2019)



81




(Wang2012）





29 Alarm

16 Prediction model

training

15 EWMA for Target

Baseline (TB)



24 Predicted

CUSUM out of

control

25 Pre-alarmYes

No

28 Actual

CUSUM out of

control

Yes

No


21 New sample

prediction



17 Model validation

34 Continuous

monitoring

11 Data collection

26 Engineering

Validation amp

Troubleshooting

31 Loss calculation


32 CUSUM

control chart

33 Loss

CUSUM out of

control

310 Add new samples


311 ILPM model


Yes

Off-line training

In-line prediction

Concept drift

Pre-alarm stage


correction

No

All good products

37 Bayesian

monitoring out

of control

35 Equipment



39 Update posterior


38 Alarm and

equipment

maintenance

Yes

Model misalignment


Equipment

misalignment


36 Lifetime

out of control

No

Yes



82







83





Self-Priming

Centrifugal Pump



84




Feature Selection

Feature Engineering

85

Data

Warehouse

Knowledge

Selection

Preprocessing

Target Data

Preprocessed

Data

Pattern

Transformed

Data

Transformation

Data Mining

Interpretation

Evaluation




易於決策判斷









精度預測





86



Feature Selection



ie p gtgt n issue




87

An

p

Xn

k k ltlt p








Types









(PCA) etc

88







89

Lee and Chen (2018)



90

Prepared

Dataset

Feature

Selection

LASSO SVMStepwise

Regression

Voting


Pivot

Analysis

Engineering

Experience

Feature

Validation

BoostingRandom

ForestPCA Random

Sampling

Data

Reduction

(pgtgtn)

Imbalance

Correlation

Coefficient

Independence

Testhellip

Data

Preprocessing

hellip

Yes

No

Knowledge

Management (KM)

Documentation

Lee and Tsai (2019)

iterative

process






同理hellip

因果rarr相關







91








92

119910 = 120572 + 1205731199091 + 120576

119910 = 120572 + 1205731199092 + 120576

119910 = 120572 + 1205731199093 + 120576

119910 = 120572 + 1205731199094 + 120576

119910 = 120572 + 12057321199092 + 1205731199091 + 120576

119910 = 120572 + 12057321199092 + 1205731199093 + 120576

119910 = 120572 + 12057321199092 + 1205731199094 + 120576

119910 = 120572 + 12057321199092 + 12057341199094 + 1205731199091 + 120576

119910 = 120572 + 12057321199092 + 12057341199094 + 1205731199093 + 120576

統計顯著的變數1199092 and 1199094



መ120573119897119886119904119904119900 = argmin120573

σ119894=1119873 (119910119894 minus 1205730 minus σ119895=1

119875 119909119894119895120573119895)2

Subject to σ119895=1119875 120573119895 le 119905


1

2σ119894=1119873 (119910119894 minus 1205730 minus σ119895=1

119875 119909119894119895120573119895)2 + 120582σ119895=1

119875 120573119895

93


Penalty( 120582 ) x1 x2 x3 x4 x5 x6 x7

120582 = 0

120582 = 40

120582 = 418

120582 = 419

120582 = 42

120582 = 50





94


x12

x11

x10

x9

x8

x7

x6

x5

x4

x3

x2

x1

Feature Importance



Voting (投票法)



95



SVID_003 4

SVID_101 3

SVID_021 3

SVID_040 3

SVID_002 3

SVID_128 2

SVID_062 2

SVID_077 2






96

Test

Test

Test

Test


1st iter

2nd iter

3rd iter

10th iter

hellip

Error1

Error2

Error3

Error10

Minimize Error=1

10σ119894=110 Error119894



97


Undersampling



Example








SVIDVoting by

Undersampling

SVID_003 19

SVID_101 18

SVID_021 18

SVID_040 18

SVID_002 17

SVID_128 17

SVID_062 17

SVID_077 17

hellip hellip




98


SVID_003 09487 02583 11439

SVID_101 02078 05434 08934

SVID_021 04105 08377 06845

SVID_040 5208 7169 03170

SVID_002 27256 21025 02581

SVID_128 80523 85336 00580

SVID_062 09430 09747 00330

SVID_077 1569 1603 00216



Photo_06 12 384 00313

Etch_10 3 295 00102

Photo_32 10 1011 00099

Photo_17 4 410 00098

PVD_02 1 123 00081

CVD_14 9 3456 00026

Diff_09 1 495 00020

Etch_07 5 2769 00018



良品119886119907119892 minus不良品119886119907119892

119860119907119892

RATIO = FAIL TOTAL





99








迷思



100



Feature Engineering









119903 = 11990912 + 1199092

2

120579 = arctan11990921199091


101


119903

120579

1199091

1199092













Trend (趨勢)



Randomness (隨機)




102

Σ

A

A1 A2

B

B1 B2

C

C1 C2

人

人




103





預測

良品不良品




Benefits




104



105

Dataset with

selected variable

Prediction

Classification

Model

PLS BPNN CNN


R-Squared

MSE

Confusion

Matrix

Model

Evaluation

BoostingDecision

TreeSVR

Random

Sampling

Data

Transformation

Imbalance

Categorical to

Dummy VarFeature

Extraction

Feature

Selection

hellip

Yes

No

Knowledge

Management (KM)

Documentation


Z-scores


iterative

process















Data Imbalance

106










107

helliphellip

Input

Layer

Hidden

Layer

Output

Layer

hellip

helliphellip

helliphellip

helliphellip

helliphellip

helliphellip

helliphellip

x1

x2

xm

ො1199101

ො1199102

ො119910n

y1

y2

yn

NN

Output

Desired

Output




108







109

Yie

ld

Pre

cis

ion

Metr

olo

gy V

alu

e

Lot

Real value







110

UCL

LCL

Yie

ld

Pre

cis

ion

Metr

olo

gy V

alu

e

Lot

Real value









TNTP

+++

+=Accuracy


預測類別


實際類別

類別1


FN (false negative)

(Type II error)

(miss)

類別2

(良品)

FP (false positive)

(Type I error)

(false alarm)

TN (true negative)

111











112

TPSensitivity

TP+FN=

TNSpecificity

TN+FP=

預測

類別1 類別2

實際

類別1 TP FN

類別2 FP TN




TP

Rate

= S

ensitiv

ity

Model A

Model B

Precision=TP






113

Testing


Model A 719 897 517 702

Model B 781 691 883 789

Model A預測

Bad Good

實際Bad 61 7

Good 29 31

Model B預測

Bad Good

實際Bad 47 21

Good 7 53


精度良率預測







114

Time

Y

UCL

LCL

Time

Y

UCL

LCL





double EWMA




EWMA Control


115


Liu et al (2018)



116


維修保養








117











118
























119




120


No 名稱 No 名稱




4 R扣環 12 風扇


6 S扣環 14 風罩






Vibration Dataset

121

Amplitude

Time

(Obs)



Lee et al (2019)





122


Inspection

zone

Preventive

replacement

zone

Corrective

replacement

zone

Failure level

Replacement level

Data collection RUL




123

(Lee et al 2014)















124





Feature Engineering

125

Peak-

to-

peak




Data

Collection

Data

Preprocessing



Feature

Extraction

Feature

Selection

Remove high



(VIF)



Important

Variables

Predict

Linear Regression

(OLS)


Prediction Result


Regression (PLS)

Prediction

Model

OLS


PLS


BPNN

MSE = 123456789

Feature Engineering

(製造資料)





127



Feature Engineering









129




29 Alarm

16 Prediction model

training

15 EWMA for Target

Baseline (TB)



24 Predicted

CUSUM out of

control

25 Pre-alarmYes

No

28 Actual

CUSUM out of

control

Yes

No


21 New sample

prediction



17 Model validation

34 Continuous

monitoring

11 Data collection

26 Engineering

Validation amp

Troubleshooting

31 Loss calculation


32 CUSUM

control chart

33 Loss

CUSUM out of

control

310 Add new samples


311 ILPM model


Yes

Off-line training

In-line prediction

Concept drift

Pre-alarm stage


correction

No

All good products

37 Bayesian

monitoring out

of control

35 Equipment



39 Update posterior


38 Alarm and

equipment

maintenance

Yes

Model misalignment


Equipment

misalignment


36 Lifetime

out of control

No

Yes


Engineering



















hellip

130
















hellip

131






ldquo機會rdquo


132




133


很多時候我們


134

事實上hellip


現場改善

資料科學

系統整合

資料品質確認


浪費與WIP

瓶頸站生產力

人機比

設施佈置

環境公安衛生


流程再造BPR

時間動作研究



浪費移除

產線平衡


IT基礎建設

Make-or-Buy

需求預測

產銷平衡

排程與交期

特徵選取

Troubleshooting

機台維修保養


預測方法


啟發式演算法

機器學習


系統開發

供應鏈平台JIT



製程能力優化

良率提升



組件剩餘壽命


資料不一致





Decision Science

New Business Model


Price Maintenance


Sustainability

資料分析確認

Lee and Chien

(2020)


可能會問hellip




136


資料科學






現場觀察


137


話說hellip


某廠區稼動率116200 = 58







138



139

魚骨圖

法



環境


少量多樣

溝通管道

其他

交班傳達不周

人

人力缺乏



等待人員操作

機

機台維修保養

模具更換


待料


料


在製品堆放

機台稼動率低


作業不熟練

需求變異

工程變更

政策法規改變

傳承關係





案例





eg (56+160+138 mins)(180+180+180 mins)

=656

140




案例





eg (56+160+138 mins)(180+180+180 mins)

=656

141


(分)作業

耗時

(分)作業

耗時

(分)作業

耗時

(分)




1427-1430 產品品質檢測 3

1430-1443 電腦資料輸入 13


1450-1454 電腦工程分析 4

1454-1500 領取原物料 6

1500-1515 休息 15

1515-1528 領取模具 13

1528-1533 產品品質檢測 5


1543-1548 換模具 5


1601-1610 領取模具 9

1610-1617 產品品質檢測 7

1617-1622 存放載具 5

1622-1631 產品品質檢測 9


1640-1647 產品品質檢測 7


1652-1655 領取原物料 3

1655-1700 電腦資料輸入 5

機器加工

(產品D)

機器加工

(產品C)

13

124


停機

等待換規格

換模

停機

待料

機器加工

(產品A)

機器加工

(產品B)

機器加工

(產品C)

43

140

20

88

42

50

機器加工

(產品B)







200 80 = 160 (台) 到 200 85 = 170 (台) 之間為理想機台運作數



142









=工作效率




=08

1minus0656= 233 (台)


143






缺點很花時間






144





A 全部hellip

現場rarr瓶頸站





目標的衝突


145

Strategic Level


Planning

Marketing

Planning

Make-or-Buy

Strategy

Tactical Level


Planning


Order Allocation

Master Production

Schedule

Resource Planning

Rough-Cut Capacity

Planning

Capacity Require

Planning

Material Require

Planning

Monthly Material

Planning

Capacity Planning

Productivity amp

Efficiency Analysis

Vendor Relationship

MgmtDemand Mgmt


Purchasing


Daily Assignment

Order Releasing


Scheduling



Production


Operational Level

Logistics Mgmt

Long Term

Mid Term

Short Term

Facility Layout






146




timeProduction


uptimeEquipment

timeProduction

timeTotal

uptimeEquipment

timeTotal


=

=

=

Nonscheduled

state

Unscheduled

down state

Scheduled

down state

Engineering

state

Standby

state

Productive

state

Equipment

uptime

Equipment

downtime

Operations

time

Production

time

Total

time



147

顧客訂單產品

交期變動插單

工程變更




操作員

人力不足

MO


人員配置


機台設備廠務





廠區間的Backup



停工待料


外包時程變異

進料品質變異

















148






優先順序

日期達交












衝突目標

Makespan


(TWET)

交期

利用率

庫存時間



排程應用範疇


機場飛機起降



電梯設定

微處理器系統

醫院排班

醫院復健排程

醫師手術排班




150




人工排程邏輯

訂單資料

依到期日排序


預估單

工作號賦予




Yes

No


No





優先順序法則

Dispatching










Rush 緊急事件

152




剩餘作業數




Performance Metrics

Mean Flow Time






119879119895 = max0 119871119895


N Jobs on 1 Machine


N Jobs on 1 Machine




Notations



119889119895 due date

154


1 11 61

2 29 45

3 31 31

4 1 33

5 2 32


N Jobs on 1 Machine

FCFS



Tardy Jobs 3

155


J1 11 11 61 0

J2 29 40 45 0

J3 31 71 31 40

J4 1 72 33 39

J5 2 74 32 42

Totals 74 268 121





N Jobs on 1 Machine

SPT



Tardy 1

156


J4 1 1 33 0

J5 2 3 32 0

J1 11 14 61 0

J2 29 43 45 0

J3 31 74 31 43

Totals 74 135 45


N Jobs on 1 Machine

EDD



Tardy 4

157


J3 31 31 31 0

J5 2 33 32 1

J4 1 34 33 1

J2 29 63 45 18

J1 11 74 61 13

Totals 74 235 33


N Jobs on 1 Machine






Compute


158

119862119877 =119863119906119890_119863119886119905119890 minus (119862119906119903_119879119894119898119890)

119875119903119900119888119890119904119904119894119899119892_119879119894119898119890


CR

N Jobs on 1 Machine

159

JOBPr

Time

D

DateCR

Current Time = 0

1 11 61 5546

2 29 45 1552

3 31 31 100

4 1 33 33

5 2 32 16

JOBPr

Time

D

DateCR

Current Time = 31

1 11 61 2727

2 29 45 483

4 1 33 2

5 2 32 05


N Jobs on 1 Machine

160

JOBPr

Time

D

DateCR

Current Time = 60

1 11 610091

do last

4 1 33 -27

5 2 32 -14

JOBC

Time

D

DateTardy

Summary

3 31 31 0

2 60 45 15

4 61 33 28

5 63 32 31

1 74 61 13

Total 289 87

Tie use SPT

CR

Mean F Time (289)5 = 578


Tardy 4



FCFS


SPT




EDD



CR


Sequencing Rules

due Time

FCFS

CRSPT

EDD


然而hellip








162



快速換模技術









163



快速換模技術









4改善內部換模

平行作業


5改善外部作業




164





NP-hard problem













Local optimum

Short running time

Global optimum

Long running time


Meta-heuristics






166

f(x)

x

Local optimum

Global

optimum

Meta-heuristics

ldquoJUMPrdquo

119909119905+1 larr 119909119905 + 120578120597119891

120597119909


120597119891

120597119909

119909119905 119909119905+1

120578



Basis











Neighborhood Search


promising regions








memory




go to step 3



















= 500




Due Date(119941119947)

Weights (119960119947)

1 10 4 14

2 10 2 12

3 13 1 1

4 4 12 12




(1243) (2413) and (2134)

119879 1243 = 480 119879 2413 = 436 and 119879 2134 = 652





(4213) (2143) TABU and (2431)

119879 4213 = 460 119879 2143 = 500 TABU and 119879 2431 = 608







(2413) TABU (4123) and (4231)

119879 2413 = 436 TABU 119879 4123 = 440 and 119879 4231 = 632





(1423) (4213) TABU and (4132)

119879 1423 = 408 119879 4213 = 460 TABU and 119879 4132 = 586





Metaheuristics


172

1199091


1199610


1199611 1199612



Global

optimum










exploration

exploitation

(Gen 2005)


If you hellip





175


Interfaces

1 Gantt Chart

2 Dispatch List

3 Capacity Buckets


Scenario

Management

System

Maintenance

Performance

Control

Algorithm

Generator

Interface

Algorithm

Generator

Scheduler amp

Dispatcher

Preprocessor

Scheduling amp

Rescheduling

Algorithms

Manufacturing

Execution

System (MES)

Enterprise

Resource

Planning (MRPII)

Production

Monitoring

System

Database

ImportExport

Synchronization


Algorithm

Library


Scheduling

Logic Unit

Order

Master

File

Shop-

Floor

Data



176







178

Capacity Buckets






改善的機會


講究的是synergy








179












180














Rescheduling

181








Hint WIP



182


Pull Strategy

High Uncertainty

Push Strategy

Low Uncertainty

WIP


Lateness









processing time



HVLV HV

HVHV HV

LVLV LV

LV LVHV

Process Variability

Inflow Variability


迷思










現場動態調整

184






185



再過一陣子





186



在製造業中





187









188







190


迷思


191


迷思

這是當然的


找出關鍵因子

建構因果關係




192



193

為什麼要預測


下一步為何


預測像hellip

194


預測像hellip

195




B2A1E9818B3F




196




197





198






瞭解這就hellip


199






200


其實hellip




201


決策的類型





202


小試身手hellip

天氣與決策

203

不帶傘帶傘





3 拿別人的傘

(良心不安)


小試身手hellip

204


神預測God2GO



小試身手hellip


205

機率02

機率08



方法一期望值







小試身手hellip


206

機率02

機率08





風險成本矩陣

不帶傘帶傘

晴天

成本 $0 成本 $100

(弄丟)

雨天

成本 $200

(感冒)

成本 $0

期望成本

02x0

+08x200

=160

02x100

+08x0

=20

決策帶傘


小試身手hellip


207



風險成本矩陣

不帶傘帶傘

晴天

成本 $0 成本 $100

(弄丟)

雨天

成本 $200

(感冒)

成本 $0

期望成本

02x0

+08x200

=160

02x100

+08x0

=20

決策帶傘

切記hellip


又或hellip



由此可知hellip




208

Lee (2019)


小試身手hellip


209

Based on your

Preference

Structure








210



併購公司A 42 21 8

購置機台 35 28 13

外包 28 25 23







211

天氣情境

方案景氣好

景氣持平

景氣差

Min

Return

併購公司A 42 21 8 8

購置機台 35 28 13 13

外包 28 25 23 23






212

天氣情境

方案景氣好

景氣持平

景氣差

Max

Return

併購公司A 42 21 8 42

購置機台 35 28 13 35

外包 28 25 23 28








213

悔惜矩陣

景氣好

景氣持平

景氣差

Max

Regret

0 7 15 15

7 0 10 10

14 3 0 14

天氣情境

方案景氣好

景氣持平

景氣差

併購公司A 42 21 8

購置機台 35 28 13

外包 28 25 23






214

天氣情境

方案景氣好

景氣持平

景氣差

併購公司A 42 21 8

購置機台 35 28 13

外包 28 25 23






215




Two Types of Risk



Time

Demand

Demand

A

B

C

大試身手hellip

0




Time

Demand

Demand


0

追高殺低


大試身手hellip






218






Scenario Simulator



Time

Demand

Marketing Forecast

Sales Forecast

大試身手hellip

0

Capacity Level






shortage


Linear Regression

Autoregression

Neural Network





220


Empirical Study




221

Capacity Regret

Assessment

CustomerInventory

Market

Share

Profit

Loss

Loss of

Falling Price

Inventory

Loss

Holding

CostReputation

Lower

Capacity

Level

Higher

Capacity

Level

ALTERNATIVE

OBJECTIVE

ATTRIBUTE

119877119904ℎ119900119903119905119886119892119890 缺貨風險119877119904119906119903119901119897119906119904 存貨風險



Empirical Study


222

119877119904ℎ119900119903119905119886119892119890 缺貨風險愈大產能水準向上拉

119877119904119906119903119901119897119906119904 存貨風險愈大產能水準向下壓

119863119898119886119909

119863119898119894119899

Capacity Decision


0

10000

20000

30000

Training

Dataset

Validation

Dataset

Technology

Node A

Time

Demand

Empirical Study

Data Source






223



Empirical Study

2-stage approach

Demand Forecast

Capacity Decision

VDGP


(Chang et al 2014)

224



Empirical Study




225

0

10000

20000

30000

Training

Dataset

Validation

Dataset

Technology

Node A

Time

Demand

Linear Regression

Autoregression

Neural Network


Empirical Study







119877119904ℎ119900119903119905119886119892119890 = 0521 and 119877119904119906119903119901119897119906119904 = 0479

226



MonthActual

Demand


EV MMR SP

Aug 2014 19499 20207 16941 17157 18922Sep 2014 18110 21305 17921 18306 19135Oct 2014 15059 22404 18536 19291 18885



Empirical Study


227

0

500

1000

1500

2000

0 300 600 900 1200

StandardDeviation

AverageRegret

Current

Policy

EVMMR

SP

Poor

Better

Better Poor




Min 119862119909 + 119864 119891 119909 ෩119863




119910+ 119910minus ge 0












228





229

Testing

Accuracy AUC

Model A 719 702

Model B 781 789

Model A預測

FAIL PASS

實際FAIL 61 7

PASS 29 31

Model B預測

FAIL PASS

實際FAIL 47 21

PASS 7 53



迷思


230


迷思

231

170cm

165cm 175cm

172cm



232















233



234



235











going on now






used here

236












237











238




1 1 0 4

2 0 2 12

3 3 2 18

Profit ($1000) $3 $5 0

1823

122

4 st

53

21

21

2

1

21

+

+=

xx

xx

x

x

xxZ


Graphical Solution


feasible region


0

1823

122

4 st

53

21

21

2

1

21

+

+=

xx

xx

x

x

xxZ


Graphical Solution




最佳化結果


6個產品2 (x2)


這就是處方~



遇到問題



提供solution


241



242

Domain Knowledge




243

處方性分析


DS in

MFG










為大於其細


方案評選


見

識

謀

斷


發想

收斂




執行對策

膽大心細

決策與行動

行




245

Descriptive

敘述性

Diagnostic

診斷性

Predictive

預測性

Prescriptive

處方性

Automating

自動性

見

What



Why



When


HowWho Where


戰情財報



(掌握趨勢)



(持續改善)

識謀斷行

U N I S O N


結語

Conclusion

246


迷思



247


迷思










248


迷思


249



Basic

interpretable

models

Post-hoc

Explanation

RegressionBased

Tree Based

DeepLearning

Linear Logistic

regression

Lasso Ridge

GLM GAM

Decision Tree

RF XGBoost

LightGBM

RF

DNN CNN RNN

helliphellip


(build-in)

DataFeature

EngineeringML

Models

Prediction Result

(build-in)

X

Post-hoc Methods


(plug-in)

FeatureImportance

洪紹嚴 (2019)



250

Yield

Time

Cost

Yield

New Tape-out (NTO)

研發導入

Device

optimization

during process

integration

Engineering

Parameter

Optimization

Design of

Experiments

成長期

Tool Matching

Benchmarking

Troubleshooting

Scheduling

Spec Setting SPC






成熟期

快速良率提升

Yield ramp

during pilot

production



during mass

production







機人


迷思




251








迷思

252







253




工業30





工業40








254














馬雲 (201704)








255


結語




However hellip









256


結語KPI Hierarchy

257


ROE

Profit

Margin

Asset

Turnover

Financial

Leveragetimes times

Profit

Sales

Assetsdivide divide

Cost minus Accounts


Sales

Price

Sales

Quantity

Effective

Outputs

Realized

Demand

times

minusmin

Price

Elasticity

Fixed

Cost

Variable

Cost+

Bottleneck

Throughput

Bottleneck

Utilization

Yield

times

Bottleneck

Capacity

times

Bottleneck

Machine

MTTR

MTBFMaintenance

Bottleneck

Availability

times

Demand

vs SupplyQuality

DL

Cost

IDL

Cost

Bui amp Fac

Depre

Equip

Cost

Variable

Unit Cost

times

Other

Assets+

ID Mater

Cost

D Mater

Cost

+ + + + +

Labor MaterialFloor

Space

Non-bottle

Machine

Fin

an

cia

l Ind

ex

Ma

nu

factu

ring In

de

xR

eso

urc

e

WIP Delivery

TAT

CVP CIP

Rework

Rate

Cycle

Time

times

Finished

Goods

+

SchedulingProduct-

mixLot Size

Man Machine

Ratio

Decis

ion




Line

Balancing



258

MFGcom

DATAcomINNOVATION

com

Technology

Migration

Analytics-oriented

- Prediction

- Troubleshooting

- Customer voice


Business-oriented






Analytics

Discussion

Implementation

Problem-oriented

- SOP and cost down




Data

(empirical)

Science

(critical)

Technology

(substantial)

Data Quality

(Internal data)

Data Analysis


Data Platform



Advanced training






戴勝益 (2014)


致謝

260

感謝



以及




謝謝大家~






2017 Modena Italy


1157ndash1182





















261

Contact Information


phone 02-33661206








7



Knowledge

詮釋的觀點

思辨的過程

科學的原理


迷思資料資訊



9





10

北南

Etu蔣居裕 (2013)


Experiencehellip


失敗的藝術

人生的歷練


知識與經驗之



Wisdom ishellip


Wisdom ishellip

13





13







智慧工廠



15

智慧工廠

智慧製造

製造智慧



(製造系統)

16


Value and Profit

Value




17

Price

Value

Cost

Consumer

Surplus

Producer

Surplus

Wikipedia (2016)


製造智慧決策

18



SPC APC VM RMS

Carbon

Emission

Water

Recycle


Energy



VRARAI

Cloud

Computing

Cyber-

Physical

System


RFIDSmart Labels



















Inventory



Inventory Reduction







Chien et al (2004)




22



23




24




















26





其實hellip


27

English Math

Student_A 80 76

Student_B 80 91

Student_C 80 83

Student_D 80 62

Student_E 80 88

Layer X Layer Y

Machine_A 81 76

Machine_B 80 91

Machine_C 79 83

Machine_D 80 62

Machine_E 82 88


來自於變異




MES

APC

FDC

SPC

VM

R2R

RMS



Yield Management

hellipetc

Demand Forecast



CapEx

Cost Structure

MPS amp MRP



Order Releasing

hellipetcQuality

Productivity

Cost Down

Cycle Time

28


CIM and Automation

29


ISBN 0-471-93450-X



Benefits

Reduce HR Cost

Reduce MO


Productivity




Benefits

Sustain EQ variance


Support RD




CIM and Automation





31



轉變hellip



一種改善過程

32





1 Transportation

2 Inventory

3 Motion

4 Waiting

5 Overproduction

6 Overprocessing

7 Defects

8 Eschewed Talents

Continuous flow

Line Balancing


Lean Manufacturing


33





CIM and Automation

34

AMHS

MES APC

FMEC



Big Data

Analytics


Data

Warehouse

Knowledge


Selection

Preprocessing

Target Data

Preprocessed

Data

Pattern

Transformed

Data

Data Mining

Transformation

Interpretation

Evaluation



IT Infrastructure

Pattern Extraction



35

Edge

Computing







Problems




製造現場



一言九鼎(頂)



Ask Why








38


生產線數據


39


Characteristic

Pure Feature-



(between features)











Color Images 3D

Scans and Videos



correlation







40



















特性與問題




Data Preprocessing

42

Data

Warehouse

Knowledge

Selection

Preprocessing

Target Data

Preprocessed

Data

Pattern

Transformed

Data

Transformation

Data Mining

Interpretation

Evaluation





Lot001 Lot001 Pass







Lot ID Pass or Fail

Lot001 Pass

Lot002 Pass

Lot003 Fail

Lot004 Pass


Lot001 Pass 20

Lot002 Pass 25

Lot003 Fail 10

Lot004 Pass 15

75 857


Lot002 hellip


Lot002_1

Lot002_2


Parallel Machine


Data Preparation

Missing Value

44


WS_A_Mach_2_Temp

Lot001 820 NA

Lot002 820 NA

Lot003 NA 840

Lot004 NA 840

Lot IDWS_A_Temp

WS_A_Mach_Type

Lot001 820 1

Lot002 820 1

Lot003 840 2

Lot004 840 2

WS_A_Mach_1

WS_A_Mach_2



Golden Machine


Missing Value

45


WS_A_Mach_2_Temp

Lot001 820 NA

Lot002 820 NA

Lot003 820 NA

Lot004 830 NA

Lot005 820 NA

Lot006 820 NA

Lot007 825 NA

Lot008 830 120

Lot009 820 130

Lot010 NA 120


WS_A_Mach_2_Temp

Mach_1 Mach_2

Lot001 820 Avg 1 0

Lot002 820 Avg 1 0

Lot003 820 Avg 1 0

Lot004 830 Avg 1 0

Lot005 820 Avg 1 0

Lot006 820 Avg 1 0

Lot007 825 Avg 1 0

Lot008 830 120 1 1

Lot009 820 130 1 1

Lot010 Avg 120 0 1






46


Lot001 PartsA

Lot002 PartsB

Lot003 PartsA

Lot004 PartsC

Lot005 PartsD

Lot006 PartsE

Lot007 PartsB

Lot008 PartsA

Lot009 PartsC

Lot010 PartsE


WS_A_Mach_1_PartsB

WS_A_Mach_1_PartsC

WS_A_Mach_1_PartsD

Lot001 1 0 0 0

Lot002 0 1 0 0

Lot003 1 0 0 0

Lot004 0 0 1 0

Lot005 0 0 0 1

Lot006 0 0 0 0

Lot007 0 1 0 0

Lot008 1 0 0 0

Lot009 0 0 1 0

Lot010 0 0 0 0






建議方式







沒有再現性

47



抽樣檢測

48




NO001 鋁 A 13723 7235

NO002 鋁 B NA NA

NO003 鋁 B 13728 7237

NO099 鋁 B NA NA

NO100 鋁 A 13726 7236

X Y (抽檢)

沒被抽檢

沒被抽檢

抽樣

填補遺漏值



3 Prediction Model








49









有母數GLMRandom


Learninghellip


換線換模






50

Machine A A A


Machine A B


B B B

A B A B









51

MachineI2

A A AMachine1

B B


A A A

Machine2

A A AMachine1

A A A

B

B




瓶頸 (bottleneck)







52


120

unitsday

140

unitsday

80

unitsday

120

unitsday

100

unitsday

瓶頸

80 unitsday



(勞工和幹部)



楊大和(2016)










53





54

IDProduct

TypeStage

Process

Time (hrs)

Start

Time

Lot1 A 1 1 20161226 1450

Lot1 A 2 1 20161226 1600

Lot1 A 3 05 20161226 1720

Lot1 A 4 1 20161226 1800

Lot1 A 5 05 20161226 2030







55


211 000000

211 010000

211 020000

211 230000


211 000629

211 001041

211 034109

211 231157




Data Merge

56









建議串接方法

Rolling Forward

Nearest time

Rolling Forward

Rolling Backward

Nearest time




Lee and Dong (2019)






產品的queue time



57

STA

GE

x_S

VID

x

0 5

10

1

5

2

0

2

5

0 200 400 600 800 1000Lot or

Time






58


Time Downcode


2017-05-07140528


2017-05-07161214


2017-05-07174130



2017-05-07192243


2017-05-07201817




19 22 43 minus (16 12 14)








10 vs 90 5 vs 95 or 1 vs 99



predictionhellip



59




Lot01 PASS

Lot02 PASS

Lot03 PASS

Lot04 PASS

Lot05 PASS

Lot06 PASS

Lot07 FAIL

Lot08 PASS

Lot09 PASS

Lot10 PASS

Lot11 PASS

Lot12 PASS





準確度可達 1112 = 917



迷思


61



62


資料整合













迷思補遺漏值


63

English Math

Student_A 80 76

Student_B 80 91

Student_C 80 83

Student_D 80 62

Student_E 80

Avg 80

Max 91

Min 62

Avg 78


迷思補遺漏值

64













64








B 男 51 $64000 Yes

C 男 52 $105000 Yes

D 女 33 $55000 Yes

E 男 45 $45000 No

F 女 45 $100000


65



66

K=3

K=5




迷思補遺漏值

67


1 00886 00886 00886 00886

2 00684 00684 00684 00684

3 03515 03515 03515 03515

4 09874 09874 09874 09874

5 04713 04713 04713 04713

6 06115 06115 06115 06115

7 02573 02573 02573 02573

8 02914 02914 02914 02914

9 01662 01662 01662 01662

10 044 044 044 044

11 06939 03731 06622

平均值 04023 03731 03731 03994

標準差 02785 02753 02612 02753

誤差值 03208 00317




數據品質

68






資料品質

Univariate





Multiple Column




數據品質



69



Automobile Company




digital materials







71















72






Feature Selection






74








75

材料

設計

光罩


測試

封裝

最後測試

加熱製程

微影製程

離子佈植


介電質沉積

晶圓


Over 1000 stages










and unreliable




76




77


Root Cause As-Is



To-Be

Data Science

Automation









78

K

C

H

E

A

G

I

J

F

L

OR

DS

BP M

N

Q






Rule Extraction




79

Good 68 68

Bad 32 32

Good - -

Bad 23 100

Good 68 88

Bad 9 12

Good - -

Bad 6 100

Good 68 96

Bad 3 4





OK

NG

NG

NG

NG

NG NG NG

OK

OK

OKOK OKOK

NG

YES NO

YES

YES YES

YESYES

YES

NO

NO

NO

NO NO

NO

80

Map clustering for

systematic defects

12 defect patterns

and build WBM bank





(Lee and Tsai 2019)



81




(Wang2012）





29 Alarm

16 Prediction model

training

15 EWMA for Target

Baseline (TB)



24 Predicted

CUSUM out of

control

25 Pre-alarmYes

No

28 Actual

CUSUM out of

control

Yes

No


21 New sample

prediction



17 Model validation

34 Continuous

monitoring

11 Data collection

26 Engineering

Validation amp

Troubleshooting

31 Loss calculation


32 CUSUM

control chart

33 Loss

CUSUM out of

control

310 Add new samples


311 ILPM model


Yes

Off-line training

In-line prediction

Concept drift

Pre-alarm stage


correction

No

All good products

37 Bayesian

monitoring out

of control

35 Equipment



39 Update posterior


38 Alarm and

equipment

maintenance

Yes

Model misalignment


Equipment

misalignment


36 Lifetime

out of control

No

Yes



82







83





Self-Priming

Centrifugal Pump



84




Feature Selection

Feature Engineering

85

Data

Warehouse

Knowledge

Selection

Preprocessing

Target Data

Preprocessed

Data

Pattern

Transformed

Data

Transformation

Data Mining

Interpretation

Evaluation




易於決策判斷









精度預測





86



Feature Selection



ie p gtgt n issue




87

An

p

Xn

k k ltlt p








Types









(PCA) etc

88







89

Lee and Chen (2018)



90

Prepared

Dataset

Feature

Selection

LASSO SVMStepwise

Regression

Voting


Pivot

Analysis

Engineering

Experience

Feature

Validation

BoostingRandom

ForestPCA Random

Sampling

Data

Reduction

(pgtgtn)

Imbalance

Correlation

Coefficient

Independence

Testhellip

Data

Preprocessing

hellip

Yes

No

Knowledge

Management (KM)

Documentation

Lee and Tsai (2019)

iterative

process






同理hellip

因果rarr相關







91








92

119910 = 120572 + 1205731199091 + 120576

119910 = 120572 + 1205731199092 + 120576

119910 = 120572 + 1205731199093 + 120576

119910 = 120572 + 1205731199094 + 120576

119910 = 120572 + 12057321199092 + 1205731199091 + 120576

119910 = 120572 + 12057321199092 + 1205731199093 + 120576

119910 = 120572 + 12057321199092 + 1205731199094 + 120576

119910 = 120572 + 12057321199092 + 12057341199094 + 1205731199091 + 120576

119910 = 120572 + 12057321199092 + 12057341199094 + 1205731199093 + 120576

統計顯著的變數1199092 and 1199094



መ120573119897119886119904119904119900 = argmin120573

σ119894=1119873 (119910119894 minus 1205730 minus σ119895=1

119875 119909119894119895120573119895)2

Subject to σ119895=1119875 120573119895 le 119905


1

2σ119894=1119873 (119910119894 minus 1205730 minus σ119895=1

119875 119909119894119895120573119895)2 + 120582σ119895=1

119875 120573119895

93


Penalty( 120582 ) x1 x2 x3 x4 x5 x6 x7

120582 = 0

120582 = 40

120582 = 418

120582 = 419

120582 = 42

120582 = 50





94


x12

x11

x10

x9

x8

x7

x6

x5

x4

x3

x2

x1

Feature Importance



Voting (投票法)



95



SVID_003 4

SVID_101 3

SVID_021 3

SVID_040 3

SVID_002 3

SVID_128 2

SVID_062 2

SVID_077 2






96

Test

Test

Test

Test


1st iter

2nd iter

3rd iter

10th iter

hellip

Error1

Error2

Error3

Error10

Minimize Error=1

10σ119894=110 Error119894



97


Undersampling



Example








SVIDVoting by

Undersampling

SVID_003 19

SVID_101 18

SVID_021 18

SVID_040 18

SVID_002 17

SVID_128 17

SVID_062 17

SVID_077 17

hellip hellip




98


SVID_003 09487 02583 11439

SVID_101 02078 05434 08934

SVID_021 04105 08377 06845

SVID_040 5208 7169 03170

SVID_002 27256 21025 02581

SVID_128 80523 85336 00580

SVID_062 09430 09747 00330

SVID_077 1569 1603 00216



Photo_06 12 384 00313

Etch_10 3 295 00102

Photo_32 10 1011 00099

Photo_17 4 410 00098

PVD_02 1 123 00081

CVD_14 9 3456 00026

Diff_09 1 495 00020

Etch_07 5 2769 00018



良品119886119907119892 minus不良品119886119907119892

119860119907119892

RATIO = FAIL TOTAL





99








迷思



100



Feature Engineering









119903 = 11990912 + 1199092

2

120579 = arctan11990921199091


101


119903

120579

1199091

1199092













Trend (趨勢)



Randomness (隨機)




102

Σ

A

A1 A2

B

B1 B2

C

C1 C2

人

人




103





預測

良品不良品




Benefits




104



105

Dataset with

selected variable

Prediction

Classification

Model

PLS BPNN CNN


R-Squared

MSE

Confusion

Matrix

Model

Evaluation

BoostingDecision

TreeSVR

Random

Sampling

Data

Transformation

Imbalance

Categorical to

Dummy VarFeature

Extraction

Feature

Selection

hellip

Yes

No

Knowledge

Management (KM)

Documentation


Z-scores


iterative

process















Data Imbalance

106










107

helliphellip

Input

Layer

Hidden

Layer

Output

Layer

hellip

helliphellip

helliphellip

helliphellip

helliphellip

helliphellip

helliphellip

x1

x2

xm

ො1199101

ො1199102

ො119910n

y1

y2

yn

NN

Output

Desired

Output




108







109

Yie

ld

Pre

cis

ion

Metr

olo

gy V

alu

e

Lot

Real value







110

UCL

LCL

Yie

ld

Pre

cis

ion

Metr

olo

gy V

alu

e

Lot

Real value









TNTP

+++

+=Accuracy


預測類別


實際類別

類別1


FN (false negative)

(Type II error)

(miss)

類別2

(良品)

FP (false positive)

(Type I error)

(false alarm)

TN (true negative)

111











112

TPSensitivity

TP+FN=

TNSpecificity

TN+FP=

預測

類別1 類別2

實際

類別1 TP FN

類別2 FP TN




TP

Rate

= S

ensitiv

ity

Model A

Model B

Precision=TP






113

Testing


Model A 719 897 517 702

Model B 781 691 883 789

Model A預測

Bad Good

實際Bad 61 7

Good 29 31

Model B預測

Bad Good

實際Bad 47 21

Good 7 53


精度良率預測







114

Time

Y

UCL

LCL

Time

Y

UCL

LCL





double EWMA




EWMA Control


115


Liu et al (2018)



116


維修保養








117











118
























119




120


No 名稱 No 名稱




4 R扣環 12 風扇


6 S扣環 14 風罩






Vibration Dataset

121

Amplitude

Time

(Obs)



Lee et al (2019)





122


Inspection

zone

Preventive

replacement

zone

Corrective

replacement

zone

Failure level

Replacement level

Data collection RUL




123

(Lee et al 2014)















124





Feature Engineering

125

Peak-

to-

peak




Data

Collection

Data

Preprocessing



Feature

Extraction

Feature

Selection

Remove high



(VIF)



Important

Variables

Predict

Linear Regression

(OLS)


Prediction Result


Regression (PLS)

Prediction

Model

OLS


PLS


BPNN

MSE = 123456789

Feature Engineering

(製造資料)





127



Feature Engineering









129




29 Alarm

16 Prediction model

training

15 EWMA for Target

Baseline (TB)



24 Predicted

CUSUM out of

control

25 Pre-alarmYes

No

28 Actual

CUSUM out of

control

Yes

No


21 New sample

prediction



17 Model validation

34 Continuous

monitoring

11 Data collection

26 Engineering

Validation amp

Troubleshooting

31 Loss calculation


32 CUSUM

control chart

33 Loss

CUSUM out of

control

310 Add new samples


311 ILPM model


Yes

Off-line training

In-line prediction

Concept drift

Pre-alarm stage


correction

No

All good products

37 Bayesian

monitoring out

of control

35 Equipment



39 Update posterior


38 Alarm and

equipment

maintenance

Yes

Model misalignment


Equipment

misalignment


36 Lifetime

out of control

No

Yes


Engineering



















hellip

130
















hellip

131






ldquo機會rdquo


132




133


很多時候我們


134

事實上hellip


現場改善

資料科學

系統整合

資料品質確認


浪費與WIP

瓶頸站生產力

人機比

設施佈置

環境公安衛生


流程再造BPR

時間動作研究



浪費移除

產線平衡


IT基礎建設

Make-or-Buy

需求預測

產銷平衡

排程與交期

特徵選取

Troubleshooting

機台維修保養


預測方法


啟發式演算法

機器學習


系統開發

供應鏈平台JIT



製程能力優化

良率提升



組件剩餘壽命


資料不一致





Decision Science

New Business Model


Price Maintenance


Sustainability

資料分析確認

Lee and Chien

(2020)


可能會問hellip




136


資料科學






現場觀察


137


話說hellip


某廠區稼動率116200 = 58







138



139

魚骨圖

法



環境


少量多樣

溝通管道

其他

交班傳達不周

人

人力缺乏



等待人員操作

機

機台維修保養

模具更換


待料


料


在製品堆放

機台稼動率低


作業不熟練

需求變異

工程變更

政策法規改變

傳承關係





案例





eg (56+160+138 mins)(180+180+180 mins)

=656

140




案例





eg (56+160+138 mins)(180+180+180 mins)

=656

141


(分)作業

耗時

(分)作業

耗時

(分)作業

耗時

(分)




1427-1430 產品品質檢測 3

1430-1443 電腦資料輸入 13


1450-1454 電腦工程分析 4

1454-1500 領取原物料 6

1500-1515 休息 15

1515-1528 領取模具 13

1528-1533 產品品質檢測 5


1543-1548 換模具 5


1601-1610 領取模具 9

1610-1617 產品品質檢測 7

1617-1622 存放載具 5

1622-1631 產品品質檢測 9


1640-1647 產品品質檢測 7


1652-1655 領取原物料 3

1655-1700 電腦資料輸入 5

機器加工

(產品D)

機器加工

(產品C)

13

124


停機

等待換規格

換模

停機

待料

機器加工

(產品A)

機器加工

(產品B)

機器加工

(產品C)

43

140

20

88

42

50

機器加工

(產品B)







200 80 = 160 (台) 到 200 85 = 170 (台) 之間為理想機台運作數



142









=工作效率




=08

1minus0656= 233 (台)


143






缺點很花時間






144





A 全部hellip

現場rarr瓶頸站





目標的衝突


145

Strategic Level


Planning

Marketing

Planning

Make-or-Buy

Strategy

Tactical Level


Planning


Order Allocation

Master Production

Schedule

Resource Planning

Rough-Cut Capacity

Planning

Capacity Require

Planning

Material Require

Planning

Monthly Material

Planning

Capacity Planning

Productivity amp

Efficiency Analysis

Vendor Relationship

MgmtDemand Mgmt


Purchasing


Daily Assignment

Order Releasing


Scheduling



Production


Operational Level

Logistics Mgmt

Long Term

Mid Term

Short Term

Facility Layout






146




timeProduction


uptimeEquipment

timeProduction

timeTotal

uptimeEquipment

timeTotal


=

=

=

Nonscheduled

state

Unscheduled

down state

Scheduled

down state

Engineering

state

Standby

state

Productive

state

Equipment

uptime

Equipment

downtime

Operations

time

Production

time

Total

time



147

顧客訂單產品

交期變動插單

工程變更




操作員

人力不足

MO


人員配置


機台設備廠務





廠區間的Backup



停工待料


外包時程變異

進料品質變異

















148






優先順序

日期達交












衝突目標

Makespan


(TWET)

交期

利用率

庫存時間



排程應用範疇


機場飛機起降



電梯設定

微處理器系統

醫院排班

醫院復健排程

醫師手術排班




150




人工排程邏輯

訂單資料

依到期日排序


預估單

工作號賦予




Yes

No


No





優先順序法則

Dispatching










Rush 緊急事件

152




剩餘作業數




Performance Metrics

Mean Flow Time






119879119895 = max0 119871119895


N Jobs on 1 Machine


N Jobs on 1 Machine




Notations



119889119895 due date

154


1 11 61

2 29 45

3 31 31

4 1 33

5 2 32


N Jobs on 1 Machine

FCFS



Tardy Jobs 3

155


J1 11 11 61 0

J2 29 40 45 0

J3 31 71 31 40

J4 1 72 33 39

J5 2 74 32 42

Totals 74 268 121





N Jobs on 1 Machine

SPT



Tardy 1

156


J4 1 1 33 0

J5 2 3 32 0

J1 11 14 61 0

J2 29 43 45 0

J3 31 74 31 43

Totals 74 135 45


N Jobs on 1 Machine

EDD



Tardy 4

157


J3 31 31 31 0

J5 2 33 32 1

J4 1 34 33 1

J2 29 63 45 18

J1 11 74 61 13

Totals 74 235 33


N Jobs on 1 Machine






Compute


158

119862119877 =119863119906119890_119863119886119905119890 minus (119862119906119903_119879119894119898119890)

119875119903119900119888119890119904119904119894119899119892_119879119894119898119890


CR

N Jobs on 1 Machine

159

JOBPr

Time

D

DateCR

Current Time = 0

1 11 61 5546

2 29 45 1552

3 31 31 100

4 1 33 33

5 2 32 16

JOBPr

Time

D

DateCR

Current Time = 31

1 11 61 2727

2 29 45 483

4 1 33 2

5 2 32 05


N Jobs on 1 Machine

160

JOBPr

Time

D

DateCR

Current Time = 60

1 11 610091

do last

4 1 33 -27

5 2 32 -14

JOBC

Time

D

DateTardy

Summary

3 31 31 0

2 60 45 15

4 61 33 28

5 63 32 31

1 74 61 13

Total 289 87

Tie use SPT

CR

Mean F Time (289)5 = 578


Tardy 4



FCFS


SPT




EDD



CR


Sequencing Rules

due Time

FCFS

CRSPT

EDD


然而hellip








162



快速換模技術









163



快速換模技術









4改善內部換模

平行作業


5改善外部作業




164





NP-hard problem













Local optimum

Short running time

Global optimum

Long running time


Meta-heuristics






166

f(x)

x

Local optimum

Global

optimum

Meta-heuristics

ldquoJUMPrdquo

119909119905+1 larr 119909119905 + 120578120597119891

120597119909


120597119891

120597119909

119909119905 119909119905+1

120578



Basis











Neighborhood Search


promising regions








memory




go to step 3



















= 500




Due Date(119941119947)

Weights (119960119947)

1 10 4 14

2 10 2 12

3 13 1 1

4 4 12 12




(1243) (2413) and (2134)

119879 1243 = 480 119879 2413 = 436 and 119879 2134 = 652





(4213) (2143) TABU and (2431)

119879 4213 = 460 119879 2143 = 500 TABU and 119879 2431 = 608







(2413) TABU (4123) and (4231)

119879 2413 = 436 TABU 119879 4123 = 440 and 119879 4231 = 632





(1423) (4213) TABU and (4132)

119879 1423 = 408 119879 4213 = 460 TABU and 119879 4132 = 586





Metaheuristics


172

1199091


1199610


1199611 1199612



Global

optimum










exploration

exploitation

(Gen 2005)


If you hellip





175


Interfaces

1 Gantt Chart

2 Dispatch List

3 Capacity Buckets


Scenario

Management

System

Maintenance

Performance

Control

Algorithm

Generator

Interface

Algorithm

Generator

Scheduler amp

Dispatcher

Preprocessor

Scheduling amp

Rescheduling

Algorithms

Manufacturing

Execution

System (MES)

Enterprise

Resource

Planning (MRPII)

Production

Monitoring

System

Database

ImportExport

Synchronization


Algorithm

Library


Scheduling

Logic Unit

Order

Master

File

Shop-

Floor

Data



176







178

Capacity Buckets






改善的機會


講究的是synergy








179












180














Rescheduling

181








Hint WIP



182


Pull Strategy

High Uncertainty

Push Strategy

Low Uncertainty

WIP


Lateness









processing time



HVLV HV

HVHV HV

LVLV LV

LV LVHV

Process Variability

Inflow Variability


迷思










現場動態調整

184






185



再過一陣子





186



在製造業中





187









188







190


迷思


191


迷思

這是當然的


找出關鍵因子

建構因果關係




192



193

為什麼要預測


下一步為何


預測像hellip

194


預測像hellip

195




B2A1E9818B3F




196




197





198






瞭解這就hellip


199






200


其實hellip




201


決策的類型





202


小試身手hellip

天氣與決策

203

不帶傘帶傘





3 拿別人的傘

(良心不安)


小試身手hellip

204


神預測God2GO



小試身手hellip


205

機率02

機率08



方法一期望值







小試身手hellip


206

機率02

機率08





風險成本矩陣

不帶傘帶傘

晴天

成本 $0 成本 $100

(弄丟)

雨天

成本 $200

(感冒)

成本 $0

期望成本

02x0

+08x200

=160

02x100

+08x0

=20

決策帶傘


小試身手hellip


207



風險成本矩陣

不帶傘帶傘

晴天

成本 $0 成本 $100

(弄丟)

雨天

成本 $200

(感冒)

成本 $0

期望成本

02x0

+08x200

=160

02x100

+08x0

=20

決策帶傘

切記hellip


又或hellip



由此可知hellip




208

Lee (2019)


小試身手hellip


209

Based on your

Preference

Structure








210



併購公司A 42 21 8

購置機台 35 28 13

外包 28 25 23







211

天氣情境

方案景氣好

景氣持平

景氣差

Min

Return

併購公司A 42 21 8 8

購置機台 35 28 13 13

外包 28 25 23 23






212

天氣情境

方案景氣好

景氣持平

景氣差

Max

Return

併購公司A 42 21 8 42

購置機台 35 28 13 35

外包 28 25 23 28








213

悔惜矩陣

景氣好

景氣持平

景氣差

Max

Regret

0 7 15 15

7 0 10 10

14 3 0 14

天氣情境

方案景氣好

景氣持平

景氣差

併購公司A 42 21 8

購置機台 35 28 13

外包 28 25 23






214

天氣情境

方案景氣好

景氣持平

景氣差

併購公司A 42 21 8

購置機台 35 28 13

外包 28 25 23






215




Two Types of Risk



Time

Demand

Demand

A

B

C

大試身手hellip

0




Time

Demand

Demand


0

追高殺低


大試身手hellip






218






Scenario Simulator



Time

Demand

Marketing Forecast

Sales Forecast

大試身手hellip

0

Capacity Level






shortage


Linear Regression

Autoregression

Neural Network





220


Empirical Study




221

Capacity Regret

Assessment

CustomerInventory

Market

Share

Profit

Loss

Loss of

Falling Price

Inventory

Loss

Holding

CostReputation

Lower

Capacity

Level

Higher

Capacity

Level

ALTERNATIVE

OBJECTIVE

ATTRIBUTE

119877119904ℎ119900119903119905119886119892119890 缺貨風險119877119904119906119903119901119897119906119904 存貨風險



Empirical Study


222

119877119904ℎ119900119903119905119886119892119890 缺貨風險愈大產能水準向上拉

119877119904119906119903119901119897119906119904 存貨風險愈大產能水準向下壓

119863119898119886119909

119863119898119894119899

Capacity Decision


0

10000

20000

30000

Training

Dataset

Validation

Dataset

Technology

Node A

Time

Demand

Empirical Study

Data Source






223



Empirical Study

2-stage approach

Demand Forecast

Capacity Decision

VDGP


(Chang et al 2014)

224



Empirical Study




225

0

10000

20000

30000

Training

Dataset

Validation

Dataset

Technology

Node A

Time

Demand

Linear Regression

Autoregression

Neural Network


Empirical Study







119877119904ℎ119900119903119905119886119892119890 = 0521 and 119877119904119906119903119901119897119906119904 = 0479

226



MonthActual

Demand


EV MMR SP

Aug 2014 19499 20207 16941 17157 18922Sep 2014 18110 21305 17921 18306 19135Oct 2014 15059 22404 18536 19291 18885



Empirical Study


227

0

500

1000

1500

2000

0 300 600 900 1200

StandardDeviation

AverageRegret

Current

Policy

EVMMR

SP

Poor

Better

Better Poor




Min 119862119909 + 119864 119891 119909 ෩119863




119910+ 119910minus ge 0












228





229

Testing

Accuracy AUC

Model A 719 702

Model B 781 789

Model A預測

FAIL PASS

實際FAIL 61 7

PASS 29 31

Model B預測

FAIL PASS

實際FAIL 47 21

PASS 7 53



迷思


230


迷思

231

170cm

165cm 175cm

172cm



232















233



234



235











going on now






used here

236












237











238




1 1 0 4

2 0 2 12

3 3 2 18

Profit ($1000) $3 $5 0

1823

122

4 st

53

21

21

2

1

21

+

+=

xx

xx

x

x

xxZ


Graphical Solution


feasible region


0

1823

122

4 st

53

21

21

2

1

21

+

+=

xx

xx

x

x

xxZ


Graphical Solution




最佳化結果


6個產品2 (x2)


這就是處方~



遇到問題



提供solution


241



242

Domain Knowledge




243

處方性分析


DS in

MFG










為大於其細


方案評選


見

識

謀

斷


發想

收斂




執行對策

膽大心細

決策與行動

行




245

Descriptive

敘述性

Diagnostic

診斷性

Predictive

預測性

Prescriptive

處方性

Automating

自動性

見

What



Why



When


HowWho Where


戰情財報



(掌握趨勢)



(持續改善)

識謀斷行

U N I S O N


結語

Conclusion

246


迷思



247


迷思










248


迷思


249



Basic

interpretable

models

Post-hoc

Explanation

RegressionBased

Tree Based

DeepLearning

Linear Logistic

regression

Lasso Ridge

GLM GAM

Decision Tree

RF XGBoost

LightGBM

RF

DNN CNN RNN

helliphellip


(build-in)

DataFeature

EngineeringML

Models

Prediction Result

(build-in)

X

Post-hoc Methods


(plug-in)

FeatureImportance

洪紹嚴 (2019)



250

Yield

Time

Cost

Yield

New Tape-out (NTO)

研發導入

Device

optimization

during process

integration

Engineering

Parameter

Optimization

Design of

Experiments

成長期

Tool Matching

Benchmarking

Troubleshooting

Scheduling

Spec Setting SPC






成熟期

快速良率提升

Yield ramp

during pilot

production



during mass

production







機人


迷思




251








迷思

252







253




工業30





工業40








254














馬雲 (201704)








255


結語




However hellip









256


結語KPI Hierarchy

257


ROE

Profit

Margin

Asset

Turnover

Financial

Leveragetimes times

Profit

Sales

Assetsdivide divide

Cost minus Accounts


Sales

Price

Sales

Quantity

Effective

Outputs

Realized

Demand

times

minusmin

Price

Elasticity

Fixed

Cost

Variable

Cost+

Bottleneck

Throughput

Bottleneck

Utilization

Yield

times

Bottleneck

Capacity

times

Bottleneck

Machine

MTTR

MTBFMaintenance

Bottleneck

Availability

times

Demand

vs SupplyQuality

DL

Cost

IDL

Cost

Bui amp Fac

Depre

Equip

Cost

Variable

Unit Cost

times

Other

Assets+

ID Mater

Cost

D Mater

Cost

+ + + + +

Labor MaterialFloor

Space

Non-bottle

Machine

Fin

an

cia

l Ind

ex

Ma

nu

factu

ring In

de

xR

eso

urc

e

WIP Delivery

TAT

CVP CIP

Rework

Rate

Cycle

Time

times

Finished

Goods

+

SchedulingProduct-

mixLot Size

Man Machine

Ratio

Decis

ion




Line

Balancing



258

MFGcom

DATAcomINNOVATION

com

Technology

Migration

Analytics-oriented

- Prediction

- Troubleshooting

- Customer voice


Business-oriented






Analytics

Discussion

Implementation

Problem-oriented

- SOP and cost down




Data

(empirical)

Science

(critical)

Technology

(substantial)

Data Quality

(Internal data)

Data Analysis


Data Platform



Advanced training






戴勝益 (2014)


致謝

260

感謝



以及




謝謝大家~






2017 Modena Italy


1157ndash1182





















261

Contact Information


phone 02-33661206







Knowledge

詮釋的觀點

思辨的過程

科學的原理


迷思資料資訊



9





10

北南

Etu蔣居裕 (2013)


Experiencehellip


失敗的藝術

人生的歷練


知識與經驗之



Wisdom ishellip


Wisdom ishellip

13





13







智慧工廠



15

智慧工廠

智慧製造

製造智慧



(製造系統)

16


Value and Profit

Value




17

Price

Value

Cost

Consumer

Surplus

Producer

Surplus

Wikipedia (2016)


製造智慧決策

18



SPC APC VM RMS

Carbon

Emission

Water

Recycle


Energy



VRARAI

Cloud

Computing

Cyber-

Physical

System


RFIDSmart Labels



















Inventory



Inventory Reduction







Chien et al (2004)




22



23




24




















26





其實hellip


27

English Math

Student_A 80 76

Student_B 80 91

Student_C 80 83

Student_D 80 62

Student_E 80 88

Layer X Layer Y

Machine_A 81 76

Machine_B 80 91

Machine_C 79 83

Machine_D 80 62

Machine_E 82 88


來自於變異




MES

APC

FDC

SPC

VM

R2R

RMS



Yield Management

hellipetc

Demand Forecast



CapEx

Cost Structure

MPS amp MRP



Order Releasing

hellipetcQuality

Productivity

Cost Down

Cycle Time

28


CIM and Automation

29


ISBN 0-471-93450-X



Benefits

Reduce HR Cost

Reduce MO


Productivity




Benefits

Sustain EQ variance


Support RD




CIM and Automation





31



轉變hellip



一種改善過程

32





1 Transportation

2 Inventory

3 Motion

4 Waiting

5 Overproduction

6 Overprocessing

7 Defects

8 Eschewed Talents

Continuous flow

Line Balancing


Lean Manufacturing


33





CIM and Automation

34

AMHS

MES APC

FMEC



Big Data

Analytics


Data

Warehouse

Knowledge


Selection

Preprocessing

Target Data

Preprocessed

Data

Pattern

Transformed

Data

Data Mining

Transformation

Interpretation

Evaluation



IT Infrastructure

Pattern Extraction



35

Edge

Computing







Problems




製造現場



一言九鼎(頂)



Ask Why








38


生產線數據


39


Characteristic

Pure Feature-



(between features)











Color Images 3D

Scans and Videos



correlation







40



















特性與問題




Data Preprocessing

42

Data

Warehouse

Knowledge

Selection

Preprocessing

Target Data

Preprocessed

Data

Pattern

Transformed

Data

Transformation

Data Mining

Interpretation

Evaluation





Lot001 Lot001 Pass







Lot ID Pass or Fail

Lot001 Pass

Lot002 Pass

Lot003 Fail

Lot004 Pass


Lot001 Pass 20

Lot002 Pass 25

Lot003 Fail 10

Lot004 Pass 15

75 857


Lot002 hellip


Lot002_1

Lot002_2


Parallel Machine


Data Preparation

Missing Value

44


WS_A_Mach_2_Temp

Lot001 820 NA

Lot002 820 NA

Lot003 NA 840

Lot004 NA 840

Lot IDWS_A_Temp

WS_A_Mach_Type

Lot001 820 1

Lot002 820 1

Lot003 840 2

Lot004 840 2

WS_A_Mach_1

WS_A_Mach_2



Golden Machine


Missing Value

45


WS_A_Mach_2_Temp

Lot001 820 NA

Lot002 820 NA

Lot003 820 NA

Lot004 830 NA

Lot005 820 NA

Lot006 820 NA

Lot007 825 NA

Lot008 830 120

Lot009 820 130

Lot010 NA 120


WS_A_Mach_2_Temp

Mach_1 Mach_2

Lot001 820 Avg 1 0

Lot002 820 Avg 1 0

Lot003 820 Avg 1 0

Lot004 830 Avg 1 0

Lot005 820 Avg 1 0

Lot006 820 Avg 1 0

Lot007 825 Avg 1 0

Lot008 830 120 1 1

Lot009 820 130 1 1

Lot010 Avg 120 0 1






46


Lot001 PartsA

Lot002 PartsB

Lot003 PartsA

Lot004 PartsC

Lot005 PartsD

Lot006 PartsE

Lot007 PartsB

Lot008 PartsA

Lot009 PartsC

Lot010 PartsE


WS_A_Mach_1_PartsB

WS_A_Mach_1_PartsC

WS_A_Mach_1_PartsD

Lot001 1 0 0 0

Lot002 0 1 0 0

Lot003 1 0 0 0

Lot004 0 0 1 0

Lot005 0 0 0 1

Lot006 0 0 0 0

Lot007 0 1 0 0

Lot008 1 0 0 0

Lot009 0 0 1 0

Lot010 0 0 0 0






建議方式







沒有再現性

47



抽樣檢測

48




NO001 鋁 A 13723 7235

NO002 鋁 B NA NA

NO003 鋁 B 13728 7237

NO099 鋁 B NA NA

NO100 鋁 A 13726 7236

X Y (抽檢)

沒被抽檢

沒被抽檢

抽樣

填補遺漏值



3 Prediction Model








49









有母數GLMRandom


Learninghellip


換線換模






50

Machine A A A


Machine A B


B B B

A B A B









51

MachineI2

A A AMachine1

B B


A A A

Machine2

A A AMachine1

A A A

B

B




瓶頸 (bottleneck)







52


120

unitsday

140

unitsday

80

unitsday

120

unitsday

100

unitsday

瓶頸

80 unitsday



(勞工和幹部)



楊大和(2016)










53





54

IDProduct

TypeStage

Process

Time (hrs)

Start

Time

Lot1 A 1 1 20161226 1450

Lot1 A 2 1 20161226 1600

Lot1 A 3 05 20161226 1720

Lot1 A 4 1 20161226 1800

Lot1 A 5 05 20161226 2030







55


211 000000

211 010000

211 020000

211 230000


211 000629

211 001041

211 034109

211 231157




Data Merge

56









建議串接方法

Rolling Forward

Nearest time

Rolling Forward

Rolling Backward

Nearest time




Lee and Dong (2019)






產品的queue time



57

STA

GE

x_S

VID

x

0 5

10

1

5

2

0

2

5

0 200 400 600 800 1000Lot or

Time






58


Time Downcode


2017-05-07140528


2017-05-07161214


2017-05-07174130



2017-05-07192243


2017-05-07201817




19 22 43 minus (16 12 14)








10 vs 90 5 vs 95 or 1 vs 99



predictionhellip



59




Lot01 PASS

Lot02 PASS

Lot03 PASS

Lot04 PASS

Lot05 PASS

Lot06 PASS

Lot07 FAIL

Lot08 PASS

Lot09 PASS

Lot10 PASS

Lot11 PASS

Lot12 PASS





準確度可達 1112 = 917



迷思


61



62


資料整合













迷思補遺漏值


63

English Math

Student_A 80 76

Student_B 80 91

Student_C 80 83

Student_D 80 62

Student_E 80

Avg 80

Max 91

Min 62

Avg 78


迷思補遺漏值

64













64








B 男 51 $64000 Yes

C 男 52 $105000 Yes

D 女 33 $55000 Yes

E 男 45 $45000 No

F 女 45 $100000


65



66

K=3

K=5




迷思補遺漏值

67


1 00886 00886 00886 00886

2 00684 00684 00684 00684

3 03515 03515 03515 03515

4 09874 09874 09874 09874

5 04713 04713 04713 04713

6 06115 06115 06115 06115

7 02573 02573 02573 02573

8 02914 02914 02914 02914

9 01662 01662 01662 01662

10 044 044 044 044

11 06939 03731 06622

平均值 04023 03731 03731 03994

標準差 02785 02753 02612 02753

誤差值 03208 00317




數據品質

68






資料品質

Univariate





Multiple Column




數據品質



69



Automobile Company




digital materials







71















72






Feature Selection






74








75

材料

設計

光罩


測試

封裝

最後測試

加熱製程

微影製程

離子佈植


介電質沉積

晶圓


Over 1000 stages










and unreliable




76




77


Root Cause As-Is



To-Be

Data Science

Automation









78

K

C

H

E

A

G

I

J

F

L

OR

DS

BP M

N

Q






Rule Extraction




79

Good 68 68

Bad 32 32

Good - -

Bad 23 100

Good 68 88

Bad 9 12

Good - -

Bad 6 100

Good 68 96

Bad 3 4





OK

NG

NG

NG

NG

NG NG NG

OK

OK

OKOK OKOK

NG

YES NO

YES

YES YES

YESYES

YES

NO

NO

NO

NO NO

NO

80

Map clustering for

systematic defects

12 defect patterns

and build WBM bank





(Lee and Tsai 2019)



81




(Wang2012）





29 Alarm

16 Prediction model

training

15 EWMA for Target

Baseline (TB)



24 Predicted

CUSUM out of

control

25 Pre-alarmYes

No

28 Actual

CUSUM out of

control

Yes

No


21 New sample

prediction



17 Model validation

34 Continuous

monitoring

11 Data collection

26 Engineering

Validation amp

Troubleshooting

31 Loss calculation


32 CUSUM

control chart

33 Loss

CUSUM out of

control

310 Add new samples


311 ILPM model


Yes

Off-line training

In-line prediction

Concept drift

Pre-alarm stage


correction

No

All good products

37 Bayesian

monitoring out

of control

35 Equipment



39 Update posterior


38 Alarm and

equipment

maintenance

Yes

Model misalignment


Equipment

misalignment


36 Lifetime

out of control

No

Yes



82







83





Self-Priming

Centrifugal Pump



84




Feature Selection

Feature Engineering

85

Data

Warehouse

Knowledge

Selection

Preprocessing

Target Data

Preprocessed

Data

Pattern

Transformed

Data

Transformation

Data Mining

Interpretation

Evaluation




易於決策判斷









精度預測





86



Feature Selection



ie p gtgt n issue




87

An

p

Xn

k k ltlt p








Types









(PCA) etc

88







89

Lee and Chen (2018)



90

Prepared

Dataset

Feature

Selection

LASSO SVMStepwise

Regression

Voting


Pivot

Analysis

Engineering

Experience

Feature

Validation

BoostingRandom

ForestPCA Random

Sampling

Data

Reduction

(pgtgtn)

Imbalance

Correlation

Coefficient

Independence

Testhellip

Data

Preprocessing

hellip

Yes

No

Knowledge

Management (KM)

Documentation

Lee and Tsai (2019)

iterative

process






同理hellip

因果rarr相關







91








92

119910 = 120572 + 1205731199091 + 120576

119910 = 120572 + 1205731199092 + 120576

119910 = 120572 + 1205731199093 + 120576

119910 = 120572 + 1205731199094 + 120576

119910 = 120572 + 12057321199092 + 1205731199091 + 120576

119910 = 120572 + 12057321199092 + 1205731199093 + 120576

119910 = 120572 + 12057321199092 + 1205731199094 + 120576

119910 = 120572 + 12057321199092 + 12057341199094 + 1205731199091 + 120576

119910 = 120572 + 12057321199092 + 12057341199094 + 1205731199093 + 120576

統計顯著的變數1199092 and 1199094



መ120573119897119886119904119904119900 = argmin120573

σ119894=1119873 (119910119894 minus 1205730 minus σ119895=1

119875 119909119894119895120573119895)2

Subject to σ119895=1119875 120573119895 le 119905


1

2σ119894=1119873 (119910119894 minus 1205730 minus σ119895=1

119875 119909119894119895120573119895)2 + 120582σ119895=1

119875 120573119895

93


Penalty( 120582 ) x1 x2 x3 x4 x5 x6 x7

120582 = 0

120582 = 40

120582 = 418

120582 = 419

120582 = 42

120582 = 50





94


x12

x11

x10

x9

x8

x7

x6

x5

x4

x3

x2

x1

Feature Importance



Voting (投票法)



95



SVID_003 4

SVID_101 3

SVID_021 3

SVID_040 3

SVID_002 3

SVID_128 2

SVID_062 2

SVID_077 2






96

Test

Test

Test

Test


1st iter

2nd iter

3rd iter

10th iter

hellip

Error1

Error2

Error3

Error10

Minimize Error=1

10σ119894=110 Error119894



97


Undersampling



Example








SVIDVoting by

Undersampling

SVID_003 19

SVID_101 18

SVID_021 18

SVID_040 18

SVID_002 17

SVID_128 17

SVID_062 17

SVID_077 17

hellip hellip




98


SVID_003 09487 02583 11439

SVID_101 02078 05434 08934

SVID_021 04105 08377 06845

SVID_040 5208 7169 03170

SVID_002 27256 21025 02581

SVID_128 80523 85336 00580

SVID_062 09430 09747 00330

SVID_077 1569 1603 00216



Photo_06 12 384 00313

Etch_10 3 295 00102

Photo_32 10 1011 00099

Photo_17 4 410 00098

PVD_02 1 123 00081

CVD_14 9 3456 00026

Diff_09 1 495 00020

Etch_07 5 2769 00018



良品119886119907119892 minus不良品119886119907119892

119860119907119892

RATIO = FAIL TOTAL





99








迷思



100



Feature Engineering









119903 = 11990912 + 1199092

2

120579 = arctan11990921199091


101


119903

120579

1199091

1199092













Trend (趨勢)



Randomness (隨機)




102

Σ

A

A1 A2

B

B1 B2

C

C1 C2

人

人




103





預測

良品不良品




Benefits




104



105

Dataset with

selected variable

Prediction

Classification

Model

PLS BPNN CNN


R-Squared

MSE

Confusion

Matrix

Model

Evaluation

BoostingDecision

TreeSVR

Random

Sampling

Data

Transformation

Imbalance

Categorical to

Dummy VarFeature

Extraction

Feature

Selection

hellip

Yes

No

Knowledge

Management (KM)

Documentation


Z-scores


iterative

process















Data Imbalance

106










107

helliphellip

Input

Layer

Hidden

Layer

Output

Layer

hellip

helliphellip

helliphellip

helliphellip

helliphellip

helliphellip

helliphellip

x1

x2

xm

ො1199101

ො1199102

ො119910n

y1

y2

yn

NN

Output

Desired

Output




108







109

Yie

ld

Pre

cis

ion

Metr

olo

gy V

alu

e

Lot

Real value







110

UCL

LCL

Yie

ld

Pre

cis

ion

Metr

olo

gy V

alu

e

Lot

Real value









TNTP

+++

+=Accuracy


預測類別


實際類別

類別1


FN (false negative)

(Type II error)

(miss)

類別2

(良品)

FP (false positive)

(Type I error)

(false alarm)

TN (true negative)

111











112

TPSensitivity

TP+FN=

TNSpecificity

TN+FP=

預測

類別1 類別2

實際

類別1 TP FN

類別2 FP TN




TP

Rate

= S

ensitiv

ity

Model A

Model B

Precision=TP






113

Testing


Model A 719 897 517 702

Model B 781 691 883 789

Model A預測

Bad Good

實際Bad 61 7

Good 29 31

Model B預測

Bad Good

實際Bad 47 21

Good 7 53


精度良率預測







114

Time

Y

UCL

LCL

Time

Y

UCL

LCL





double EWMA




EWMA Control


115


Liu et al (2018)



116


維修保養








117











118
























119




120


No 名稱 No 名稱




4 R扣環 12 風扇


6 S扣環 14 風罩






Vibration Dataset

121

Amplitude

Time

(Obs)



Lee et al (2019)





122


Inspection

zone

Preventive

replacement

zone

Corrective

replacement

zone

Failure level

Replacement level

Data collection RUL




123

(Lee et al 2014)















124





Feature Engineering

125

Peak-

to-

peak




Data

Collection

Data

Preprocessing



Feature

Extraction

Feature

Selection

Remove high



(VIF)



Important

Variables

Predict

Linear Regression

(OLS)


Prediction Result


Regression (PLS)

Prediction

Model

OLS


PLS


BPNN

MSE = 123456789

Feature Engineering

(製造資料)





127



Feature Engineering









129




29 Alarm

16 Prediction model

training

15 EWMA for Target

Baseline (TB)



24 Predicted

CUSUM out of

control

25 Pre-alarmYes

No

28 Actual

CUSUM out of

control

Yes

No


21 New sample

prediction



17 Model validation

34 Continuous

monitoring

11 Data collection

26 Engineering

Validation amp

Troubleshooting

31 Loss calculation


32 CUSUM

control chart

33 Loss

CUSUM out of

control

310 Add new samples


311 ILPM model


Yes

Off-line training

In-line prediction

Concept drift

Pre-alarm stage


correction

No

All good products

37 Bayesian

monitoring out

of control

35 Equipment



39 Update posterior


38 Alarm and

equipment

maintenance

Yes

Model misalignment


Equipment

misalignment


36 Lifetime

out of control

No

Yes


Engineering



















hellip

130
















hellip

131






ldquo機會rdquo


132




133


很多時候我們


134

事實上hellip


現場改善

資料科學

系統整合

資料品質確認


浪費與WIP

瓶頸站生產力

人機比

設施佈置

環境公安衛生


流程再造BPR

時間動作研究



浪費移除

產線平衡


IT基礎建設

Make-or-Buy

需求預測

產銷平衡

排程與交期

特徵選取

Troubleshooting

機台維修保養


預測方法


啟發式演算法

機器學習


系統開發

供應鏈平台JIT



製程能力優化

良率提升



組件剩餘壽命


資料不一致





Decision Science

New Business Model


Price Maintenance


Sustainability

資料分析確認

Lee and Chien

(2020)


可能會問hellip




136


資料科學






現場觀察


137


話說hellip


某廠區稼動率116200 = 58







138



139

魚骨圖

法



環境


少量多樣

溝通管道

其他

交班傳達不周

人

人力缺乏



等待人員操作

機

機台維修保養

模具更換


待料


料


在製品堆放

機台稼動率低


作業不熟練

需求變異

工程變更

政策法規改變

傳承關係





案例





eg (56+160+138 mins)(180+180+180 mins)

=656

140




案例





eg (56+160+138 mins)(180+180+180 mins)

=656

141


(分)作業

耗時

(分)作業

耗時

(分)作業

耗時

(分)




1427-1430 產品品質檢測 3

1430-1443 電腦資料輸入 13


1450-1454 電腦工程分析 4

1454-1500 領取原物料 6

1500-1515 休息 15

1515-1528 領取模具 13

1528-1533 產品品質檢測 5


1543-1548 換模具 5


1601-1610 領取模具 9

1610-1617 產品品質檢測 7

1617-1622 存放載具 5

1622-1631 產品品質檢測 9


1640-1647 產品品質檢測 7


1652-1655 領取原物料 3

1655-1700 電腦資料輸入 5

機器加工

(產品D)

機器加工

(產品C)

13

124


停機

等待換規格

換模

停機

待料

機器加工

(產品A)

機器加工

(產品B)

機器加工

(產品C)

43

140

20

88

42

50

機器加工

(產品B)







200 80 = 160 (台) 到 200 85 = 170 (台) 之間為理想機台運作數



142









=工作效率




=08

1minus0656= 233 (台)


143






缺點很花時間






144





A 全部hellip

現場rarr瓶頸站





目標的衝突


145

Strategic Level


Planning

Marketing

Planning

Make-or-Buy

Strategy

Tactical Level


Planning


Order Allocation

Master Production

Schedule

Resource Planning

Rough-Cut Capacity

Planning

Capacity Require

Planning

Material Require

Planning

Monthly Material

Planning

Capacity Planning

Productivity amp

Efficiency Analysis

Vendor Relationship

MgmtDemand Mgmt


Purchasing


Daily Assignment

Order Releasing


Scheduling



Production


Operational Level

Logistics Mgmt

Long Term

Mid Term

Short Term

Facility Layout






146




timeProduction


uptimeEquipment

timeProduction

timeTotal

uptimeEquipment

timeTotal


=

=

=

Nonscheduled

state

Unscheduled

down state

Scheduled

down state

Engineering

state

Standby

state

Productive

state

Equipment

uptime

Equipment

downtime

Operations

time

Production

time

Total

time



147

顧客訂單產品

交期變動插單

工程變更




操作員

人力不足

MO


人員配置


機台設備廠務





廠區間的Backup



停工待料


外包時程變異

進料品質變異

















148






優先順序

日期達交












衝突目標

Makespan


(TWET)

交期

利用率

庫存時間



排程應用範疇


機場飛機起降



電梯設定

微處理器系統

醫院排班

醫院復健排程

醫師手術排班




150




人工排程邏輯

訂單資料

依到期日排序


預估單

工作號賦予




Yes

No


No





優先順序法則

Dispatching










Rush 緊急事件

152




剩餘作業數




Performance Metrics

Mean Flow Time






119879119895 = max0 119871119895


N Jobs on 1 Machine


N Jobs on 1 Machine




Notations



119889119895 due date

154


1 11 61

2 29 45

3 31 31

4 1 33

5 2 32


N Jobs on 1 Machine

FCFS



Tardy Jobs 3

155


J1 11 11 61 0

J2 29 40 45 0

J3 31 71 31 40

J4 1 72 33 39

J5 2 74 32 42

Totals 74 268 121





N Jobs on 1 Machine

SPT



Tardy 1

156


J4 1 1 33 0

J5 2 3 32 0

J1 11 14 61 0

J2 29 43 45 0

J3 31 74 31 43

Totals 74 135 45


N Jobs on 1 Machine

EDD



Tardy 4

157


J3 31 31 31 0

J5 2 33 32 1

J4 1 34 33 1

J2 29 63 45 18

J1 11 74 61 13

Totals 74 235 33


N Jobs on 1 Machine






Compute


158

119862119877 =119863119906119890_119863119886119905119890 minus (119862119906119903_119879119894119898119890)

119875119903119900119888119890119904119904119894119899119892_119879119894119898119890


CR

N Jobs on 1 Machine

159

JOBPr

Time

D

DateCR

Current Time = 0

1 11 61 5546

2 29 45 1552

3 31 31 100

4 1 33 33

5 2 32 16

JOBPr

Time

D

DateCR

Current Time = 31

1 11 61 2727

2 29 45 483

4 1 33 2

5 2 32 05


N Jobs on 1 Machine

160

JOBPr

Time

D

DateCR

Current Time = 60

1 11 610091

do last

4 1 33 -27

5 2 32 -14

JOBC

Time

D

DateTardy

Summary

3 31 31 0

2 60 45 15

4 61 33 28

5 63 32 31

1 74 61 13

Total 289 87

Tie use SPT

CR

Mean F Time (289)5 = 578


Tardy 4



FCFS


SPT




EDD



CR


Sequencing Rules

due Time

FCFS

CRSPT

EDD


然而hellip








162



快速換模技術









163



快速換模技術









4改善內部換模

平行作業


5改善外部作業




164





NP-hard problem













Local optimum

Short running time

Global optimum

Long running time


Meta-heuristics






166

f(x)

x

Local optimum

Global

optimum

Meta-heuristics

ldquoJUMPrdquo

119909119905+1 larr 119909119905 + 120578120597119891

120597119909


120597119891

120597119909

119909119905 119909119905+1

120578



Basis











Neighborhood Search


promising regions








memory




go to step 3



















= 500




Due Date(119941119947)

Weights (119960119947)

1 10 4 14

2 10 2 12

3 13 1 1

4 4 12 12




(1243) (2413) and (2134)

119879 1243 = 480 119879 2413 = 436 and 119879 2134 = 652





(4213) (2143) TABU and (2431)

119879 4213 = 460 119879 2143 = 500 TABU and 119879 2431 = 608







(2413) TABU (4123) and (4231)

119879 2413 = 436 TABU 119879 4123 = 440 and 119879 4231 = 632





(1423) (4213) TABU and (4132)

119879 1423 = 408 119879 4213 = 460 TABU and 119879 4132 = 586





Metaheuristics


172

1199091


1199610


1199611 1199612



Global

optimum










exploration

exploitation

(Gen 2005)


If you hellip





175


Interfaces

1 Gantt Chart

2 Dispatch List

3 Capacity Buckets


Scenario

Management

System

Maintenance

Performance

Control

Algorithm

Generator

Interface

Algorithm

Generator

Scheduler amp

Dispatcher

Preprocessor

Scheduling amp

Rescheduling

Algorithms

Manufacturing

Execution

System (MES)

Enterprise

Resource

Planning (MRPII)

Production

Monitoring

System

Database

ImportExport

Synchronization


Algorithm

Library


Scheduling

Logic Unit

Order

Master

File

Shop-

Floor

Data



176







178

Capacity Buckets






改善的機會


講究的是synergy








179












180














Rescheduling

181








Hint WIP



182


Pull Strategy

High Uncertainty

Push Strategy

Low Uncertainty

WIP


Lateness









processing time



HVLV HV

HVHV HV

LVLV LV

LV LVHV

Process Variability

Inflow Variability


迷思










現場動態調整

184






185



再過一陣子





186



在製造業中





187









188







190


迷思


191


迷思

這是當然的


找出關鍵因子

建構因果關係




192



193

為什麼要預測


下一步為何


預測像hellip

194


預測像hellip

195




B2A1E9818B3F




196




197





198






瞭解這就hellip


199






200


其實hellip




201


決策的類型





202


小試身手hellip

天氣與決策

203

不帶傘帶傘





3 拿別人的傘

(良心不安)


小試身手hellip

204


神預測God2GO



小試身手hellip


205

機率02

機率08



方法一期望值







小試身手hellip


206

機率02

機率08





風險成本矩陣

不帶傘帶傘

晴天

成本 $0 成本 $100

(弄丟)

雨天

成本 $200

(感冒)

成本 $0

期望成本

02x0

+08x200

=160

02x100

+08x0

=20

決策帶傘


小試身手hellip


207



風險成本矩陣

不帶傘帶傘

晴天

成本 $0 成本 $100

(弄丟)

雨天

成本 $200

(感冒)

成本 $0

期望成本

02x0

+08x200

=160

02x100

+08x0

=20

決策帶傘

切記hellip


又或hellip



由此可知hellip




208

Lee (2019)


小試身手hellip


209

Based on your

Preference

Structure








210



併購公司A 42 21 8

購置機台 35 28 13

外包 28 25 23







211

天氣情境

方案景氣好

景氣持平

景氣差

Min

Return

併購公司A 42 21 8 8

購置機台 35 28 13 13

外包 28 25 23 23






212

天氣情境

方案景氣好

景氣持平

景氣差

Max

Return

併購公司A 42 21 8 42

購置機台 35 28 13 35

外包 28 25 23 28








213

悔惜矩陣

景氣好

景氣持平

景氣差

Max

Regret

0 7 15 15

7 0 10 10

14 3 0 14

天氣情境

方案景氣好

景氣持平

景氣差

併購公司A 42 21 8

購置機台 35 28 13

外包 28 25 23






214

天氣情境

方案景氣好

景氣持平

景氣差

併購公司A 42 21 8

購置機台 35 28 13

外包 28 25 23






215




Two Types of Risk



Time

Demand

Demand

A

B

C

大試身手hellip

0




Time

Demand

Demand


0

追高殺低


大試身手hellip






218






Scenario Simulator



Time

Demand

Marketing Forecast

Sales Forecast

大試身手hellip

0

Capacity Level






shortage


Linear Regression

Autoregression

Neural Network





220


Empirical Study




221

Capacity Regret

Assessment

CustomerInventory

Market

Share

Profit

Loss

Loss of

Falling Price

Inventory

Loss

Holding

CostReputation

Lower

Capacity

Level

Higher

Capacity

Level

ALTERNATIVE

OBJECTIVE

ATTRIBUTE

119877119904ℎ119900119903119905119886119892119890 缺貨風險119877119904119906119903119901119897119906119904 存貨風險



Empirical Study


222

119877119904ℎ119900119903119905119886119892119890 缺貨風險愈大產能水準向上拉

119877119904119906119903119901119897119906119904 存貨風險愈大產能水準向下壓

119863119898119886119909

119863119898119894119899

Capacity Decision


0

10000

20000

30000

Training

Dataset

Validation

Dataset

Technology

Node A

Time

Demand

Empirical Study

Data Source






223



Empirical Study

2-stage approach

Demand Forecast

Capacity Decision

VDGP


(Chang et al 2014)

224



Empirical Study




225

0

10000

20000

30000

Training

Dataset

Validation

Dataset

Technology

Node A

Time

Demand

Linear Regression

Autoregression

Neural Network


Empirical Study







119877119904ℎ119900119903119905119886119892119890 = 0521 and 119877119904119906119903119901119897119906119904 = 0479

226



MonthActual

Demand


EV MMR SP

Aug 2014 19499 20207 16941 17157 18922Sep 2014 18110 21305 17921 18306 19135Oct 2014 15059 22404 18536 19291 18885



Empirical Study


227

0

500

1000

1500

2000

0 300 600 900 1200

StandardDeviation

AverageRegret

Current

Policy

EVMMR

SP

Poor

Better

Better Poor




Min 119862119909 + 119864 119891 119909 ෩119863




119910+ 119910minus ge 0












228





229

Testing

Accuracy AUC

Model A 719 702

Model B 781 789

Model A預測

FAIL PASS

實際FAIL 61 7

PASS 29 31

Model B預測

FAIL PASS

實際FAIL 47 21

PASS 7 53



迷思


230


迷思

231

170cm

165cm 175cm

172cm



232















233



234



235











going on now






used here

236












237











238




1 1 0 4

2 0 2 12

3 3 2 18

Profit ($1000) $3 $5 0

1823

122

4 st

53

21

21

2

1

21

+

+=

xx

xx

x

x

xxZ


Graphical Solution


feasible region


0

1823

122

4 st

53

21

21

2

1

21

+

+=

xx

xx

x

x

xxZ


Graphical Solution




最佳化結果


6個產品2 (x2)


這就是處方~



遇到問題



提供solution


241



242

Domain Knowledge




243

處方性分析


DS in

MFG










為大於其細


方案評選


見

識

謀

斷


發想

收斂




執行對策

膽大心細

決策與行動

行




245

Descriptive

敘述性

Diagnostic

診斷性

Predictive

預測性

Prescriptive

處方性

Automating

自動性

見

What



Why



When


HowWho Where


戰情財報



(掌握趨勢)



(持續改善)

識謀斷行

U N I S O N


結語

Conclusion

246


迷思



247


迷思










248


迷思


249



Basic

interpretable

models

Post-hoc

Explanation

RegressionBased

Tree Based

DeepLearning

Linear Logistic

regression

Lasso Ridge

GLM GAM

Decision Tree

RF XGBoost

LightGBM

RF

DNN CNN RNN

helliphellip


(build-in)

DataFeature

EngineeringML

Models

Prediction Result

(build-in)

X

Post-hoc Methods


(plug-in)

FeatureImportance

洪紹嚴 (2019)



250

Yield

Time

Cost

Yield

New Tape-out (NTO)

研發導入

Device

optimization

during process

integration

Engineering

Parameter

Optimization

Design of

Experiments

成長期

Tool Matching

Benchmarking

Troubleshooting

Scheduling

Spec Setting SPC






成熟期

快速良率提升

Yield ramp

during pilot

production



during mass

production







機人


迷思




251








迷思

252







253




工業30





工業40








254














馬雲 (201704)








255


結語




However hellip









256


結語KPI Hierarchy

257


ROE

Profit

Margin

Asset

Turnover

Financial

Leveragetimes times

Profit

Sales

Assetsdivide divide

Cost minus Accounts


Sales

Price

Sales

Quantity

Effective

Outputs

Realized

Demand

times

minusmin

Price

Elasticity

Fixed

Cost

Variable

Cost+

Bottleneck

Throughput

Bottleneck

Utilization

Yield

times

Bottleneck

Capacity

times

Bottleneck

Machine

MTTR

MTBFMaintenance

Bottleneck

Availability

times

Demand

vs SupplyQuality

DL

Cost

IDL

Cost

Bui amp Fac

Depre

Equip

Cost

Variable

Unit Cost

times

Other

Assets+

ID Mater

Cost

D Mater

Cost

+ + + + +

Labor MaterialFloor

Space

Non-bottle

Machine

Fin

an

cia

l Ind

ex

Ma

nu

factu

ring In

de

xR

eso

urc

e

WIP Delivery

TAT

CVP CIP

Rework

Rate

Cycle

Time

times

Finished

Goods

+

SchedulingProduct-

mixLot Size

Man Machine

Ratio

Decis

ion




Line

Balancing



258

MFGcom

DATAcomINNOVATION

com

Technology

Migration

Analytics-oriented

- Prediction

- Troubleshooting

- Customer voice


Business-oriented






Analytics

Discussion

Implementation

Problem-oriented

- SOP and cost down




Data

(empirical)

Science

(critical)

Technology

(substantial)

Data Quality

(Internal data)

Data Analysis


Data Platform



Advanced training






戴勝益 (2014)


致謝

260

感謝



以及




謝謝大家~






2017 Modena Italy


1157ndash1182





















261

Contact Information


phone 02-33661206







迷思資料資訊



9





10

北南

Etu蔣居裕 (2013)


Experiencehellip


失敗的藝術

人生的歷練


知識與經驗之



Wisdom ishellip


Wisdom ishellip

13





13







智慧工廠



15

智慧工廠

智慧製造

製造智慧



(製造系統)

16


Value and Profit

Value




17

Price

Value

Cost

Consumer

Surplus

Producer

Surplus

Wikipedia (2016)


製造智慧決策

18



SPC APC VM RMS

Carbon

Emission

Water

Recycle


Energy



VRARAI

Cloud

Computing

Cyber-

Physical

System


RFIDSmart Labels



















Inventory



Inventory Reduction







Chien et al (2004)




22



23




24




















26





其實hellip


27

English Math

Student_A 80 76

Student_B 80 91

Student_C 80 83

Student_D 80 62

Student_E 80 88

Layer X Layer Y

Machine_A 81 76

Machine_B 80 91

Machine_C 79 83

Machine_D 80 62

Machine_E 82 88


來自於變異




MES

APC

FDC

SPC

VM

R2R

RMS



Yield Management

hellipetc

Demand Forecast



CapEx

Cost Structure

MPS amp MRP



Order Releasing

hellipetcQuality

Productivity

Cost Down

Cycle Time

28


CIM and Automation

29


ISBN 0-471-93450-X



Benefits

Reduce HR Cost

Reduce MO


Productivity




Benefits

Sustain EQ variance


Support RD




CIM and Automation





31



轉變hellip



一種改善過程

32





1 Transportation

2 Inventory

3 Motion

4 Waiting

5 Overproduction

6 Overprocessing

7 Defects

8 Eschewed Talents

Continuous flow

Line Balancing


Lean Manufacturing


33





CIM and Automation

34

AMHS

MES APC

FMEC



Big Data

Analytics


Data

Warehouse

Knowledge


Selection

Preprocessing

Target Data

Preprocessed

Data

Pattern

Transformed

Data

Data Mining

Transformation

Interpretation

Evaluation



IT Infrastructure

Pattern Extraction



35

Edge

Computing







Problems




製造現場



一言九鼎(頂)



Ask Why








38


生產線數據


39


Characteristic

Pure Feature-



(between features)











Color Images 3D

Scans and Videos



correlation







40



















特性與問題




Data Preprocessing

42

Data

Warehouse

Knowledge

Selection

Preprocessing

Target Data

Preprocessed

Data

Pattern

Transformed

Data

Transformation

Data Mining

Interpretation

Evaluation





Lot001 Lot001 Pass







Lot ID Pass or Fail

Lot001 Pass

Lot002 Pass

Lot003 Fail

Lot004 Pass


Lot001 Pass 20

Lot002 Pass 25

Lot003 Fail 10

Lot004 Pass 15

75 857


Lot002 hellip


Lot002_1

Lot002_2


Parallel Machine


Data Preparation

Missing Value

44


WS_A_Mach_2_Temp

Lot001 820 NA

Lot002 820 NA

Lot003 NA 840

Lot004 NA 840

Lot IDWS_A_Temp

WS_A_Mach_Type

Lot001 820 1

Lot002 820 1

Lot003 840 2

Lot004 840 2

WS_A_Mach_1

WS_A_Mach_2



Golden Machine


Missing Value

45


WS_A_Mach_2_Temp

Lot001 820 NA

Lot002 820 NA

Lot003 820 NA

Lot004 830 NA

Lot005 820 NA

Lot006 820 NA

Lot007 825 NA

Lot008 830 120

Lot009 820 130

Lot010 NA 120


WS_A_Mach_2_Temp

Mach_1 Mach_2

Lot001 820 Avg 1 0

Lot002 820 Avg 1 0

Lot003 820 Avg 1 0

Lot004 830 Avg 1 0

Lot005 820 Avg 1 0

Lot006 820 Avg 1 0

Lot007 825 Avg 1 0

Lot008 830 120 1 1

Lot009 820 130 1 1

Lot010 Avg 120 0 1






46


Lot001 PartsA

Lot002 PartsB

Lot003 PartsA

Lot004 PartsC

Lot005 PartsD

Lot006 PartsE

Lot007 PartsB

Lot008 PartsA

Lot009 PartsC

Lot010 PartsE


WS_A_Mach_1_PartsB

WS_A_Mach_1_PartsC

WS_A_Mach_1_PartsD

Lot001 1 0 0 0

Lot002 0 1 0 0

Lot003 1 0 0 0

Lot004 0 0 1 0

Lot005 0 0 0 1

Lot006 0 0 0 0

Lot007 0 1 0 0

Lot008 1 0 0 0

Lot009 0 0 1 0

Lot010 0 0 0 0






建議方式







沒有再現性

47



抽樣檢測

48




NO001 鋁 A 13723 7235

NO002 鋁 B NA NA

NO003 鋁 B 13728 7237

NO099 鋁 B NA NA

NO100 鋁 A 13726 7236

X Y (抽檢)

沒被抽檢

沒被抽檢

抽樣

填補遺漏值



3 Prediction Model








49









有母數GLMRandom


Learninghellip


換線換模






50

Machine A A A


Machine A B


B B B

A B A B









51

MachineI2

A A AMachine1

B B


A A A

Machine2

A A AMachine1

A A A

B

B




瓶頸 (bottleneck)







52


120

unitsday

140

unitsday

80

unitsday

120

unitsday

100

unitsday

瓶頸

80 unitsday



(勞工和幹部)



楊大和(2016)










53





54

IDProduct

TypeStage

Process

Time (hrs)

Start

Time

Lot1 A 1 1 20161226 1450

Lot1 A 2 1 20161226 1600

Lot1 A 3 05 20161226 1720

Lot1 A 4 1 20161226 1800

Lot1 A 5 05 20161226 2030







55


211 000000

211 010000

211 020000

211 230000


211 000629

211 001041

211 034109

211 231157




Data Merge

56









建議串接方法

Rolling Forward

Nearest time

Rolling Forward

Rolling Backward

Nearest time




Lee and Dong (2019)






產品的queue time



57

STA

GE

x_S

VID

x

0 5

10

1

5

2

0

2

5

0 200 400 600 800 1000Lot or

Time






58


Time Downcode


2017-05-07140528


2017-05-07161214


2017-05-07174130



2017-05-07192243


2017-05-07201817




19 22 43 minus (16 12 14)








10 vs 90 5 vs 95 or 1 vs 99



predictionhellip



59




Lot01 PASS

Lot02 PASS

Lot03 PASS

Lot04 PASS

Lot05 PASS

Lot06 PASS

Lot07 FAIL

Lot08 PASS

Lot09 PASS

Lot10 PASS

Lot11 PASS

Lot12 PASS





準確度可達 1112 = 917



迷思


61



62


資料整合













迷思補遺漏值


63

English Math

Student_A 80 76

Student_B 80 91

Student_C 80 83

Student_D 80 62

Student_E 80

Avg 80

Max 91

Min 62

Avg 78


迷思補遺漏值

64













64








B 男 51 $64000 Yes

C 男 52 $105000 Yes

D 女 33 $55000 Yes

E 男 45 $45000 No

F 女 45 $100000


65



66

K=3

K=5




迷思補遺漏值

67


1 00886 00886 00886 00886

2 00684 00684 00684 00684

3 03515 03515 03515 03515

4 09874 09874 09874 09874

5 04713 04713 04713 04713

6 06115 06115 06115 06115

7 02573 02573 02573 02573

8 02914 02914 02914 02914

9 01662 01662 01662 01662

10 044 044 044 044

11 06939 03731 06622

平均值 04023 03731 03731 03994

標準差 02785 02753 02612 02753

誤差值 03208 00317




數據品質

68






資料品質

Univariate





Multiple Column




數據品質



69



Automobile Company




digital materials







71















72






Feature Selection






74








75

材料

設計

光罩


測試

封裝

最後測試

加熱製程

微影製程

離子佈植


介電質沉積

晶圓


Over 1000 stages










and unreliable




76




77


Root Cause As-Is



To-Be

Data Science

Automation









78

K

C

H

E

A

G

I

J

F

L

OR

DS

BP M

N

Q






Rule Extraction




79

Good 68 68

Bad 32 32

Good - -

Bad 23 100

Good 68 88

Bad 9 12

Good - -

Bad 6 100

Good 68 96

Bad 3 4





OK

NG

NG

NG

NG

NG NG NG

OK

OK

OKOK OKOK

NG

YES NO

YES

YES YES

YESYES

YES

NO

NO

NO

NO NO

NO

80

Map clustering for

systematic defects

12 defect patterns

and build WBM bank





(Lee and Tsai 2019)



81




(Wang2012）





29 Alarm

16 Prediction model

training

15 EWMA for Target

Baseline (TB)



24 Predicted

CUSUM out of

control

25 Pre-alarmYes

No

28 Actual

CUSUM out of

control

Yes

No


21 New sample

prediction



17 Model validation

34 Continuous

monitoring

11 Data collection

26 Engineering

Validation amp

Troubleshooting

31 Loss calculation


32 CUSUM

control chart

33 Loss

CUSUM out of

control

310 Add new samples


311 ILPM model


Yes

Off-line training

In-line prediction

Concept drift

Pre-alarm stage


correction

No

All good products

37 Bayesian

monitoring out

of control

35 Equipment



39 Update posterior


38 Alarm and

equipment

maintenance

Yes

Model misalignment


Equipment

misalignment


36 Lifetime

out of control

No

Yes



82







83





Self-Priming

Centrifugal Pump



84




Feature Selection

Feature Engineering

85

Data

Warehouse

Knowledge

Selection

Preprocessing

Target Data

Preprocessed

Data

Pattern

Transformed

Data

Transformation

Data Mining

Interpretation

Evaluation




易於決策判斷









精度預測





86



Feature Selection



ie p gtgt n issue




87

An

p

Xn

k k ltlt p








Types









(PCA) etc

88







89

Lee and Chen (2018)



90

Prepared

Dataset

Feature

Selection

LASSO SVMStepwise

Regression

Voting


Pivot

Analysis

Engineering

Experience

Feature

Validation

BoostingRandom

ForestPCA Random

Sampling

Data

Reduction

(pgtgtn)

Imbalance

Correlation

Coefficient

Independence

Testhellip

Data

Preprocessing

hellip

Yes

No

Knowledge

Management (KM)

Documentation

Lee and Tsai (2019)

iterative

process






同理hellip

因果rarr相關







91








92

119910 = 120572 + 1205731199091 + 120576

119910 = 120572 + 1205731199092 + 120576

119910 = 120572 + 1205731199093 + 120576

119910 = 120572 + 1205731199094 + 120576

119910 = 120572 + 12057321199092 + 1205731199091 + 120576

119910 = 120572 + 12057321199092 + 1205731199093 + 120576

119910 = 120572 + 12057321199092 + 1205731199094 + 120576

119910 = 120572 + 12057321199092 + 12057341199094 + 1205731199091 + 120576

119910 = 120572 + 12057321199092 + 12057341199094 + 1205731199093 + 120576

統計顯著的變數1199092 and 1199094



መ120573119897119886119904119904119900 = argmin120573

σ119894=1119873 (119910119894 minus 1205730 minus σ119895=1

119875 119909119894119895120573119895)2

Subject to σ119895=1119875 120573119895 le 119905


1

2σ119894=1119873 (119910119894 minus 1205730 minus σ119895=1

119875 119909119894119895120573119895)2 + 120582σ119895=1

119875 120573119895

93


Penalty( 120582 ) x1 x2 x3 x4 x5 x6 x7

120582 = 0

120582 = 40

120582 = 418

120582 = 419

120582 = 42

120582 = 50





94


x12

x11

x10

x9

x8

x7

x6

x5

x4

x3

x2

x1

Feature Importance



Voting (投票法)



95



SVID_003 4

SVID_101 3

SVID_021 3

SVID_040 3

SVID_002 3

SVID_128 2

SVID_062 2

SVID_077 2






96

Test

Test

Test

Test


1st iter

2nd iter

3rd iter

10th iter

hellip

Error1

Error2

Error3

Error10

Minimize Error=1

10σ119894=110 Error119894



97


Undersampling



Example








SVIDVoting by

Undersampling

SVID_003 19

SVID_101 18

SVID_021 18

SVID_040 18

SVID_002 17

SVID_128 17

SVID_062 17

SVID_077 17

hellip hellip




98


SVID_003 09487 02583 11439

SVID_101 02078 05434 08934

SVID_021 04105 08377 06845

SVID_040 5208 7169 03170

SVID_002 27256 21025 02581

SVID_128 80523 85336 00580

SVID_062 09430 09747 00330

SVID_077 1569 1603 00216



Photo_06 12 384 00313

Etch_10 3 295 00102

Photo_32 10 1011 00099

Photo_17 4 410 00098

PVD_02 1 123 00081

CVD_14 9 3456 00026

Diff_09 1 495 00020

Etch_07 5 2769 00018



良品119886119907119892 minus不良品119886119907119892

119860119907119892

RATIO = FAIL TOTAL





99








迷思



100



Feature Engineering









119903 = 11990912 + 1199092

2

120579 = arctan11990921199091


101


119903

120579

1199091

1199092













Trend (趨勢)



Randomness (隨機)




102

Σ

A

A1 A2

B

B1 B2

C

C1 C2

人

人




103





預測

良品不良品




Benefits




104



105

Dataset with

selected variable

Prediction

Classification

Model

PLS BPNN CNN


R-Squared

MSE

Confusion

Matrix

Model

Evaluation

BoostingDecision

TreeSVR

Random

Sampling

Data

Transformation

Imbalance

Categorical to

Dummy VarFeature

Extraction

Feature

Selection

hellip

Yes

No

Knowledge

Management (KM)

Documentation


Z-scores


iterative

process















Data Imbalance

106










107

helliphellip

Input

Layer

Hidden

Layer

Output

Layer

hellip

helliphellip

helliphellip

helliphellip

helliphellip

helliphellip

helliphellip

x1

x2

xm

ො1199101

ො1199102

ො119910n

y1

y2

yn

NN

Output

Desired

Output




108







109

Yie

ld

Pre

cis

ion

Metr

olo

gy V

alu

e

Lot

Real value







110

UCL

LCL

Yie

ld

Pre

cis

ion

Metr

olo

gy V

alu

e

Lot

Real value









TNTP

+++

+=Accuracy


預測類別


實際類別

類別1


FN (false negative)

(Type II error)

(miss)

類別2

(良品)

FP (false positive)

(Type I error)

(false alarm)

TN (true negative)

111











112

TPSensitivity

TP+FN=

TNSpecificity

TN+FP=

預測

類別1 類別2

實際

類別1 TP FN

類別2 FP TN




TP

Rate

= S

ensitiv

ity

Model A

Model B

Precision=TP






113

Testing


Model A 719 897 517 702

Model B 781 691 883 789

Model A預測

Bad Good

實際Bad 61 7

Good 29 31

Model B預測

Bad Good

實際Bad 47 21

Good 7 53


精度良率預測







114

Time

Y

UCL

LCL

Time

Y

UCL

LCL





double EWMA




EWMA Control


115


Liu et al (2018)



116


維修保養








117











118
























119




120


No 名稱 No 名稱




4 R扣環 12 風扇


6 S扣環 14 風罩






Vibration Dataset

121

Amplitude

Time

(Obs)



Lee et al (2019)





122


Inspection

zone

Preventive

replacement

zone

Corrective

replacement

zone

Failure level

Replacement level

Data collection RUL




123

(Lee et al 2014)















124





Feature Engineering

125

Peak-

to-

peak




Data

Collection

Data

Preprocessing



Feature

Extraction

Feature

Selection

Remove high



(VIF)



Important

Variables

Predict

Linear Regression

(OLS)


Prediction Result


Regression (PLS)

Prediction

Model

OLS


PLS


BPNN

MSE = 123456789

Feature Engineering

(製造資料)





127



Feature Engineering









129




29 Alarm

16 Prediction model

training

15 EWMA for Target

Baseline (TB)



24 Predicted

CUSUM out of

control

25 Pre-alarmYes

No

28 Actual

CUSUM out of

control

Yes

No


21 New sample

prediction



17 Model validation

34 Continuous

monitoring

11 Data collection

26 Engineering

Validation amp

Troubleshooting

31 Loss calculation


32 CUSUM

control chart

33 Loss

CUSUM out of

control

310 Add new samples


311 ILPM model


Yes

Off-line training

In-line prediction

Concept drift

Pre-alarm stage


correction

No

All good products

37 Bayesian

monitoring out

of control

35 Equipment



39 Update posterior


38 Alarm and

equipment

maintenance

Yes

Model misalignment


Equipment

misalignment


36 Lifetime

out of control

No

Yes


Engineering



















hellip

130
















hellip

131






ldquo機會rdquo


132




133


很多時候我們


134

事實上hellip


現場改善

資料科學

系統整合

資料品質確認


浪費與WIP

瓶頸站生產力

人機比

設施佈置

環境公安衛生


流程再造BPR

時間動作研究



浪費移除

產線平衡


IT基礎建設

Make-or-Buy

需求預測

產銷平衡

排程與交期

特徵選取

Troubleshooting

機台維修保養


預測方法


啟發式演算法

機器學習


系統開發

供應鏈平台JIT



製程能力優化

良率提升



組件剩餘壽命


資料不一致





Decision Science

New Business Model


Price Maintenance


Sustainability

資料分析確認

Lee and Chien

(2020)


可能會問hellip




136


資料科學






現場觀察


137


話說hellip


某廠區稼動率116200 = 58







138



139

魚骨圖

法



環境


少量多樣

溝通管道

其他

交班傳達不周

人

人力缺乏



等待人員操作

機

機台維修保養

模具更換


待料


料


在製品堆放

機台稼動率低


作業不熟練

需求變異

工程變更

政策法規改變

傳承關係





案例





eg (56+160+138 mins)(180+180+180 mins)

=656

140




案例





eg (56+160+138 mins)(180+180+180 mins)

=656

141


(分)作業

耗時

(分)作業

耗時

(分)作業

耗時

(分)




1427-1430 產品品質檢測 3

1430-1443 電腦資料輸入 13


1450-1454 電腦工程分析 4

1454-1500 領取原物料 6

1500-1515 休息 15

1515-1528 領取模具 13

1528-1533 產品品質檢測 5


1543-1548 換模具 5


1601-1610 領取模具 9

1610-1617 產品品質檢測 7

1617-1622 存放載具 5

1622-1631 產品品質檢測 9


1640-1647 產品品質檢測 7


1652-1655 領取原物料 3

1655-1700 電腦資料輸入 5

機器加工

(產品D)

機器加工

(產品C)

13

124


停機

等待換規格

換模

停機

待料

機器加工

(產品A)

機器加工

(產品B)

機器加工

(產品C)

43

140

20

88

42

50

機器加工

(產品B)







200 80 = 160 (台) 到 200 85 = 170 (台) 之間為理想機台運作數



142









=工作效率




=08

1minus0656= 233 (台)


143






缺點很花時間






144





A 全部hellip

現場rarr瓶頸站





目標的衝突


145

Strategic Level


Planning

Marketing

Planning

Make-or-Buy

Strategy

Tactical Level


Planning


Order Allocation

Master Production

Schedule

Resource Planning

Rough-Cut Capacity

Planning

Capacity Require

Planning

Material Require

Planning

Monthly Material

Planning

Capacity Planning

Productivity amp

Efficiency Analysis

Vendor Relationship

MgmtDemand Mgmt


Purchasing


Daily Assignment

Order Releasing


Scheduling



Production


Operational Level

Logistics Mgmt

Long Term

Mid Term

Short Term

Facility Layout






146




timeProduction


uptimeEquipment

timeProduction

timeTotal

uptimeEquipment

timeTotal


=

=

=

Nonscheduled

state

Unscheduled

down state

Scheduled

down state

Engineering

state

Standby

state

Productive

state

Equipment

uptime

Equipment

downtime

Operations

time

Production

time

Total

time



147

顧客訂單產品

交期變動插單

工程變更




操作員

人力不足

MO


人員配置


機台設備廠務





廠區間的Backup



停工待料


外包時程變異

進料品質變異

















148






優先順序

日期達交












衝突目標

Makespan


(TWET)

交期

利用率

庫存時間



排程應用範疇


機場飛機起降



電梯設定

微處理器系統

醫院排班

醫院復健排程

醫師手術排班




150




人工排程邏輯

訂單資料

依到期日排序


預估單

工作號賦予




Yes

No


No





優先順序法則

Dispatching










Rush 緊急事件

152




剩餘作業數




Performance Metrics

Mean Flow Time






119879119895 = max0 119871119895


N Jobs on 1 Machine


N Jobs on 1 Machine




Notations



119889119895 due date

154


1 11 61

2 29 45

3 31 31

4 1 33

5 2 32


N Jobs on 1 Machine

FCFS



Tardy Jobs 3

155


J1 11 11 61 0

J2 29 40 45 0

J3 31 71 31 40

J4 1 72 33 39

J5 2 74 32 42

Totals 74 268 121





N Jobs on 1 Machine

SPT



Tardy 1

156


J4 1 1 33 0

J5 2 3 32 0

J1 11 14 61 0

J2 29 43 45 0

J3 31 74 31 43

Totals 74 135 45


N Jobs on 1 Machine

EDD



Tardy 4

157


J3 31 31 31 0

J5 2 33 32 1

J4 1 34 33 1

J2 29 63 45 18

J1 11 74 61 13

Totals 74 235 33


N Jobs on 1 Machine






Compute


158

119862119877 =119863119906119890_119863119886119905119890 minus (119862119906119903_119879119894119898119890)

119875119903119900119888119890119904119904119894119899119892_119879119894119898119890


CR

N Jobs on 1 Machine

159

JOBPr

Time

D

DateCR

Current Time = 0

1 11 61 5546

2 29 45 1552

3 31 31 100

4 1 33 33

5 2 32 16

JOBPr

Time

D

DateCR

Current Time = 31

1 11 61 2727

2 29 45 483

4 1 33 2

5 2 32 05


N Jobs on 1 Machine

160

JOBPr

Time

D

DateCR

Current Time = 60

1 11 610091

do last

4 1 33 -27

5 2 32 -14

JOBC

Time

D

DateTardy

Summary

3 31 31 0

2 60 45 15

4 61 33 28

5 63 32 31

1 74 61 13

Total 289 87

Tie use SPT

CR

Mean F Time (289)5 = 578


Tardy 4



FCFS


SPT




EDD



CR


Sequencing Rules

due Time

FCFS

CRSPT

EDD


然而hellip








162



快速換模技術









163



快速換模技術









4改善內部換模

平行作業


5改善外部作業




164





NP-hard problem













Local optimum

Short running time

Global optimum

Long running time


Meta-heuristics






166

f(x)

x

Local optimum

Global

optimum

Meta-heuristics

ldquoJUMPrdquo

119909119905+1 larr 119909119905 + 120578120597119891

120597119909


120597119891

120597119909

119909119905 119909119905+1

120578



Basis











Neighborhood Search


promising regions








memory




go to step 3



















= 500




Due Date(119941119947)

Weights (119960119947)

1 10 4 14

2 10 2 12

3 13 1 1

4 4 12 12




(1243) (2413) and (2134)

119879 1243 = 480 119879 2413 = 436 and 119879 2134 = 652





(4213) (2143) TABU and (2431)

119879 4213 = 460 119879 2143 = 500 TABU and 119879 2431 = 608







(2413) TABU (4123) and (4231)

119879 2413 = 436 TABU 119879 4123 = 440 and 119879 4231 = 632





(1423) (4213) TABU and (4132)

119879 1423 = 408 119879 4213 = 460 TABU and 119879 4132 = 586





Metaheuristics


172

1199091


1199610


1199611 1199612



Global

optimum










exploration

exploitation

(Gen 2005)


If you hellip





175


Interfaces

1 Gantt Chart

2 Dispatch List

3 Capacity Buckets


Scenario

Management

System

Maintenance

Performance

Control

Algorithm

Generator

Interface

Algorithm

Generator

Scheduler amp

Dispatcher

Preprocessor

Scheduling amp

Rescheduling

Algorithms

Manufacturing

Execution

System (MES)

Enterprise

Resource

Planning (MRPII)

Production

Monitoring

System

Database

ImportExport

Synchronization


Algorithm

Library


Scheduling

Logic Unit

Order

Master

File

Shop-

Floor

Data



176







178

Capacity Buckets






改善的機會


講究的是synergy








179












180














Rescheduling

181








Hint WIP



182


Pull Strategy

High Uncertainty

Push Strategy

Low Uncertainty

WIP


Lateness









processing time



HVLV HV

HVHV HV

LVLV LV

LV LVHV

Process Variability

Inflow Variability


迷思










現場動態調整

184






185



再過一陣子





186



在製造業中





187









188







190


迷思


191


迷思

這是當然的


找出關鍵因子

建構因果關係




192



193

為什麼要預測


下一步為何


預測像hellip

194


預測像hellip

195




B2A1E9818B3F




196




197





198






瞭解這就hellip


199






200


其實hellip




201


決策的類型





202


小試身手hellip

天氣與決策

203

不帶傘帶傘





3 拿別人的傘

(良心不安)


小試身手hellip

204


神預測God2GO



小試身手hellip


205

機率02

機率08



方法一期望值







小試身手hellip


206

機率02

機率08





風險成本矩陣

不帶傘帶傘

晴天

成本 $0 成本 $100

(弄丟)

雨天

成本 $200

(感冒)

成本 $0

期望成本

02x0

+08x200

=160

02x100

+08x0

=20

決策帶傘


小試身手hellip


207



風險成本矩陣

不帶傘帶傘

晴天

成本 $0 成本 $100

(弄丟)

雨天

成本 $200

(感冒)

成本 $0

期望成本

02x0

+08x200

=160

02x100

+08x0

=20

決策帶傘

切記hellip


又或hellip



由此可知hellip




208

Lee (2019)


小試身手hellip


209

Based on your

Preference

Structure








210



併購公司A 42 21 8

購置機台 35 28 13

外包 28 25 23







211

天氣情境

方案景氣好

景氣持平

景氣差

Min

Return

併購公司A 42 21 8 8

購置機台 35 28 13 13

外包 28 25 23 23






212

天氣情境

方案景氣好

景氣持平

景氣差

Max

Return

併購公司A 42 21 8 42

購置機台 35 28 13 35

外包 28 25 23 28








213

悔惜矩陣

景氣好

景氣持平

景氣差

Max

Regret

0 7 15 15

7 0 10 10

14 3 0 14

天氣情境

方案景氣好

景氣持平

景氣差

併購公司A 42 21 8

購置機台 35 28 13

外包 28 25 23






214

天氣情境

方案景氣好

景氣持平

景氣差

併購公司A 42 21 8

購置機台 35 28 13

外包 28 25 23






215




Two Types of Risk



Time

Demand

Demand

A

B

C

大試身手hellip

0




Time

Demand

Demand


0

追高殺低


大試身手hellip






218






Scenario Simulator



Time

Demand

Marketing Forecast

Sales Forecast

大試身手hellip

0

Capacity Level






shortage


Linear Regression

Autoregression

Neural Network





220


Empirical Study




221

Capacity Regret

Assessment

CustomerInventory

Market

Share

Profit

Loss

Loss of

Falling Price

Inventory

Loss

Holding

CostReputation

Lower

Capacity

Level

Higher

Capacity

Level

ALTERNATIVE

OBJECTIVE

ATTRIBUTE

119877119904ℎ119900119903119905119886119892119890 缺貨風險119877119904119906119903119901119897119906119904 存貨風險



Empirical Study


222

119877119904ℎ119900119903119905119886119892119890 缺貨風險愈大產能水準向上拉

119877119904119906119903119901119897119906119904 存貨風險愈大產能水準向下壓

119863119898119886119909

119863119898119894119899

Capacity Decision


0

10000

20000

30000

Training

Dataset

Validation

Dataset

Technology

Node A

Time

Demand

Empirical Study

Data Source






223



Empirical Study

2-stage approach

Demand Forecast

Capacity Decision

VDGP


(Chang et al 2014)

224



Empirical Study




225

0

10000

20000

30000

Training

Dataset

Validation

Dataset

Technology

Node A

Time

Demand

Linear Regression

Autoregression

Neural Network


Empirical Study







119877119904ℎ119900119903119905119886119892119890 = 0521 and 119877119904119906119903119901119897119906119904 = 0479

226



MonthActual

Demand


EV MMR SP

Aug 2014 19499 20207 16941 17157 18922Sep 2014 18110 21305 17921 18306 19135Oct 2014 15059 22404 18536 19291 18885



Empirical Study


227

0

500

1000

1500

2000

0 300 600 900 1200

StandardDeviation

AverageRegret

Current

Policy

EVMMR

SP

Poor

Better

Better Poor




Min 119862119909 + 119864 119891 119909 ෩119863




119910+ 119910minus ge 0












228





229

Testing

Accuracy AUC

Model A 719 702

Model B 781 789

Model A預測

FAIL PASS

實際FAIL 61 7

PASS 29 31

Model B預測

FAIL PASS

實際FAIL 47 21

PASS 7 53



迷思


230


迷思

231

170cm

165cm 175cm

172cm



232















233



234



235











going on now






used here

236












237











238




1 1 0 4

2 0 2 12

3 3 2 18

Profit ($1000) $3 $5 0

1823

122

4 st

53

21

21

2

1

21

+

+=

xx

xx

x

x

xxZ


Graphical Solution


feasible region


0

1823

122

4 st

53

21

21

2

1

21

+

+=

xx

xx

x

x

xxZ


Graphical Solution




最佳化結果


6個產品2 (x2)


這就是處方~



遇到問題



提供solution


241



242

Domain Knowledge




243

處方性分析


DS in

MFG










為大於其細


方案評選


見

識

謀

斷


發想

收斂




執行對策

膽大心細

決策與行動

行




245

Descriptive

敘述性

Diagnostic

診斷性

Predictive

預測性

Prescriptive

處方性

Automating

自動性

見

What



Why



When


HowWho Where


戰情財報



(掌握趨勢)



(持續改善)

識謀斷行

U N I S O N


結語

Conclusion

246


迷思



247


迷思










248


迷思


249



Basic

interpretable

models

Post-hoc

Explanation

RegressionBased

Tree Based

DeepLearning

Linear Logistic

regression

Lasso Ridge

GLM GAM

Decision Tree

RF XGBoost

LightGBM

RF

DNN CNN RNN

helliphellip


(build-in)

DataFeature

EngineeringML

Models

Prediction Result

(build-in)

X

Post-hoc Methods


(plug-in)

FeatureImportance

洪紹嚴 (2019)



250

Yield

Time

Cost

Yield

New Tape-out (NTO)

研發導入

Device

optimization

during process

integration

Engineering

Parameter

Optimization

Design of

Experiments

成長期

Tool Matching

Benchmarking

Troubleshooting

Scheduling

Spec Setting SPC






成熟期

快速良率提升

Yield ramp

during pilot

production



during mass

production







機人


迷思




251








迷思

252







253




工業30





工業40








254














馬雲 (201704)








255


結語




However hellip









256


結語KPI Hierarchy

257


ROE

Profit

Margin

Asset

Turnover

Financial

Leveragetimes times

Profit

Sales

Assetsdivide divide

Cost minus Accounts


Sales

Price

Sales

Quantity

Effective

Outputs

Realized

Demand

times

minusmin

Price

Elasticity

Fixed

Cost

Variable

Cost+

Bottleneck

Throughput

Bottleneck

Utilization

Yield

times

Bottleneck

Capacity

times

Bottleneck

Machine

MTTR

MTBFMaintenance

Bottleneck

Availability

times

Demand

vs SupplyQuality

DL

Cost

IDL

Cost

Bui amp Fac

Depre

Equip

Cost

Variable

Unit Cost

times

Other

Assets+

ID Mater

Cost

D Mater

Cost

+ + + + +

Labor MaterialFloor

Space

Non-bottle

Machine

Fin

an

cia

l Ind

ex

Ma

nu

factu

ring In

de

xR

eso

urc

e

WIP Delivery

TAT

CVP CIP

Rework

Rate

Cycle

Time

times

Finished

Goods

+

SchedulingProduct-

mixLot Size

Man Machine

Ratio

Decis

ion




Line

Balancing



258

MFGcom

DATAcomINNOVATION

com

Technology

Migration

Analytics-oriented

- Prediction

- Troubleshooting

- Customer voice


Business-oriented






Analytics

Discussion

Implementation

Problem-oriented

- SOP and cost down




Data

(empirical)

Science

(critical)

Technology

(substantial)

Data Quality

(Internal data)

Data Analysis


Data Platform



Advanced training






戴勝益 (2014)


致謝

260

感謝



以及




謝謝大家~






2017 Modena Italy


1157ndash1182





















261

Contact Information


phone 02-33661206








10

北南

Etu蔣居裕 (2013)


Experiencehellip


失敗的藝術

人生的歷練


知識與經驗之



Wisdom ishellip


Wisdom ishellip

13





13







智慧工廠



15

智慧工廠

智慧製造

製造智慧



(製造系統)

16


Value and Profit

Value




17

Price

Value

Cost

Consumer

Surplus

Producer

Surplus

Wikipedia (2016)


製造智慧決策

18



SPC APC VM RMS

Carbon

Emission

Water

Recycle


Energy



VRARAI

Cloud

Computing

Cyber-

Physical

System


RFIDSmart Labels



















Inventory



Inventory Reduction







Chien et al (2004)




22



23




24




















26





其實hellip


27

English Math

Student_A 80 76

Student_B 80 91

Student_C 80 83

Student_D 80 62

Student_E 80 88

Layer X Layer Y

Machine_A 81 76

Machine_B 80 91

Machine_C 79 83

Machine_D 80 62

Machine_E 82 88


來自於變異




MES

APC

FDC

SPC

VM

R2R

RMS



Yield Management

hellipetc

Demand Forecast



CapEx

Cost Structure

MPS amp MRP



Order Releasing

hellipetcQuality

Productivity

Cost Down

Cycle Time

28


CIM and Automation

29


ISBN 0-471-93450-X



Benefits

Reduce HR Cost

Reduce MO


Productivity




Benefits

Sustain EQ variance


Support RD




CIM and Automation





31



轉變hellip



一種改善過程

32





1 Transportation

2 Inventory

3 Motion

4 Waiting

5 Overproduction

6 Overprocessing

7 Defects

8 Eschewed Talents

Continuous flow

Line Balancing


Lean Manufacturing


33





CIM and Automation

34

AMHS

MES APC

FMEC



Big Data

Analytics


Data

Warehouse

Knowledge


Selection

Preprocessing

Target Data

Preprocessed

Data

Pattern

Transformed

Data

Data Mining

Transformation

Interpretation

Evaluation



IT Infrastructure

Pattern Extraction



35

Edge

Computing







Problems




製造現場



一言九鼎(頂)



Ask Why








38


生產線數據


39


Characteristic

Pure Feature-



(between features)











Color Images 3D

Scans and Videos



correlation







40



















特性與問題




Data Preprocessing

42

Data

Warehouse

Knowledge

Selection

Preprocessing

Target Data

Preprocessed

Data

Pattern

Transformed

Data

Transformation

Data Mining

Interpretation

Evaluation





Lot001 Lot001 Pass







Lot ID Pass or Fail

Lot001 Pass

Lot002 Pass

Lot003 Fail

Lot004 Pass


Lot001 Pass 20

Lot002 Pass 25

Lot003 Fail 10

Lot004 Pass 15

75 857


Lot002 hellip


Lot002_1

Lot002_2


Parallel Machine


Data Preparation

Missing Value

44


WS_A_Mach_2_Temp

Lot001 820 NA

Lot002 820 NA

Lot003 NA 840

Lot004 NA 840

Lot IDWS_A_Temp

WS_A_Mach_Type

Lot001 820 1

Lot002 820 1

Lot003 840 2

Lot004 840 2

WS_A_Mach_1

WS_A_Mach_2



Golden Machine


Missing Value

45


WS_A_Mach_2_Temp

Lot001 820 NA

Lot002 820 NA

Lot003 820 NA

Lot004 830 NA

Lot005 820 NA

Lot006 820 NA

Lot007 825 NA

Lot008 830 120

Lot009 820 130

Lot010 NA 120


WS_A_Mach_2_Temp

Mach_1 Mach_2

Lot001 820 Avg 1 0

Lot002 820 Avg 1 0

Lot003 820 Avg 1 0

Lot004 830 Avg 1 0

Lot005 820 Avg 1 0

Lot006 820 Avg 1 0

Lot007 825 Avg 1 0

Lot008 830 120 1 1

Lot009 820 130 1 1

Lot010 Avg 120 0 1






46


Lot001 PartsA

Lot002 PartsB

Lot003 PartsA

Lot004 PartsC

Lot005 PartsD

Lot006 PartsE

Lot007 PartsB

Lot008 PartsA

Lot009 PartsC

Lot010 PartsE


WS_A_Mach_1_PartsB

WS_A_Mach_1_PartsC

WS_A_Mach_1_PartsD

Lot001 1 0 0 0

Lot002 0 1 0 0

Lot003 1 0 0 0

Lot004 0 0 1 0

Lot005 0 0 0 1

Lot006 0 0 0 0

Lot007 0 1 0 0

Lot008 1 0 0 0

Lot009 0 0 1 0

Lot010 0 0 0 0






建議方式







沒有再現性

47



抽樣檢測

48




NO001 鋁 A 13723 7235

NO002 鋁 B NA NA

NO003 鋁 B 13728 7237

NO099 鋁 B NA NA

NO100 鋁 A 13726 7236

X Y (抽檢)

沒被抽檢

沒被抽檢

抽樣

填補遺漏值



3 Prediction Model








49









有母數GLMRandom


Learninghellip


換線換模






50

Machine A A A


Machine A B


B B B

A B A B









51

MachineI2

A A AMachine1

B B


A A A

Machine2

A A AMachine1

A A A

B

B




瓶頸 (bottleneck)







52


120

unitsday

140

unitsday

80

unitsday

120

unitsday

100

unitsday

瓶頸

80 unitsday



(勞工和幹部)



楊大和(2016)










53





54

IDProduct

TypeStage

Process

Time (hrs)

Start

Time

Lot1 A 1 1 20161226 1450

Lot1 A 2 1 20161226 1600

Lot1 A 3 05 20161226 1720

Lot1 A 4 1 20161226 1800

Lot1 A 5 05 20161226 2030







55


211 000000

211 010000

211 020000

211 230000


211 000629

211 001041

211 034109

211 231157




Data Merge

56









建議串接方法

Rolling Forward

Nearest time

Rolling Forward

Rolling Backward

Nearest time




Lee and Dong (2019)






產品的queue time



57

STA

GE

x_S

VID

x

0 5

10

1

5

2

0

2

5

0 200 400 600 800 1000Lot or

Time






58


Time Downcode


2017-05-07140528


2017-05-07161214


2017-05-07174130



2017-05-07192243


2017-05-07201817




19 22 43 minus (16 12 14)








10 vs 90 5 vs 95 or 1 vs 99



predictionhellip



59




Lot01 PASS

Lot02 PASS

Lot03 PASS

Lot04 PASS

Lot05 PASS

Lot06 PASS

Lot07 FAIL

Lot08 PASS

Lot09 PASS

Lot10 PASS

Lot11 PASS

Lot12 PASS





準確度可達 1112 = 917



迷思


61



62


資料整合













迷思補遺漏值


63

English Math

Student_A 80 76

Student_B 80 91

Student_C 80 83

Student_D 80 62

Student_E 80

Avg 80

Max 91

Min 62

Avg 78


迷思補遺漏值

64













64








B 男 51 $64000 Yes

C 男 52 $105000 Yes

D 女 33 $55000 Yes

E 男 45 $45000 No

F 女 45 $100000


65



66

K=3

K=5




迷思補遺漏值

67


1 00886 00886 00886 00886

2 00684 00684 00684 00684

3 03515 03515 03515 03515

4 09874 09874 09874 09874

5 04713 04713 04713 04713

6 06115 06115 06115 06115

7 02573 02573 02573 02573

8 02914 02914 02914 02914

9 01662 01662 01662 01662

10 044 044 044 044

11 06939 03731 06622

平均值 04023 03731 03731 03994

標準差 02785 02753 02612 02753

誤差值 03208 00317




數據品質

68






資料品質

Univariate





Multiple Column




數據品質



69



Automobile Company




digital materials







71















72






Feature Selection






74








75

材料

設計

光罩


測試

封裝

最後測試

加熱製程

微影製程

離子佈植


介電質沉積

晶圓


Over 1000 stages










and unreliable




76




77


Root Cause As-Is



To-Be

Data Science

Automation









78

K

C

H

E

A

G

I

J

F

L

OR

DS

BP M

N

Q






Rule Extraction




79

Good 68 68

Bad 32 32

Good - -

Bad 23 100

Good 68 88

Bad 9 12

Good - -

Bad 6 100

Good 68 96

Bad 3 4





OK

NG

NG

NG

NG

NG NG NG

OK

OK

OKOK OKOK

NG

YES NO

YES

YES YES

YESYES

YES

NO

NO

NO

NO NO

NO

80

Map clustering for

systematic defects

12 defect patterns

and build WBM bank





(Lee and Tsai 2019)



81




(Wang2012）





29 Alarm

16 Prediction model

training

15 EWMA for Target

Baseline (TB)



24 Predicted

CUSUM out of

control

25 Pre-alarmYes

No

28 Actual

CUSUM out of

control

Yes

No


21 New sample

prediction



17 Model validation

34 Continuous

monitoring

11 Data collection

26 Engineering

Validation amp

Troubleshooting

31 Loss calculation


32 CUSUM

control chart

33 Loss

CUSUM out of

control

310 Add new samples


311 ILPM model


Yes

Off-line training

In-line prediction

Concept drift

Pre-alarm stage


correction

No

All good products

37 Bayesian

monitoring out

of control

35 Equipment



39 Update posterior


38 Alarm and

equipment

maintenance

Yes

Model misalignment


Equipment

misalignment


36 Lifetime

out of control

No

Yes



82







83





Self-Priming

Centrifugal Pump



84




Feature Selection

Feature Engineering

85

Data

Warehouse

Knowledge

Selection

Preprocessing

Target Data

Preprocessed

Data

Pattern

Transformed

Data

Transformation

Data Mining

Interpretation

Evaluation




易於決策判斷









精度預測





86



Feature Selection



ie p gtgt n issue




87

An

p

Xn

k k ltlt p








Types









(PCA) etc

88







89

Lee and Chen (2018)



90

Prepared

Dataset

Feature

Selection

LASSO SVMStepwise

Regression

Voting


Pivot

Analysis

Engineering

Experience

Feature

Validation

BoostingRandom

ForestPCA Random

Sampling

Data

Reduction

(pgtgtn)

Imbalance

Correlation

Coefficient

Independence

Testhellip

Data

Preprocessing

hellip

Yes

No

Knowledge

Management (KM)

Documentation

Lee and Tsai (2019)

iterative

process






同理hellip

因果rarr相關







91








92

119910 = 120572 + 1205731199091 + 120576

119910 = 120572 + 1205731199092 + 120576

119910 = 120572 + 1205731199093 + 120576

119910 = 120572 + 1205731199094 + 120576

119910 = 120572 + 12057321199092 + 1205731199091 + 120576

119910 = 120572 + 12057321199092 + 1205731199093 + 120576

119910 = 120572 + 12057321199092 + 1205731199094 + 120576

119910 = 120572 + 12057321199092 + 12057341199094 + 1205731199091 + 120576

119910 = 120572 + 12057321199092 + 12057341199094 + 1205731199093 + 120576

統計顯著的變數1199092 and 1199094



መ120573119897119886119904119904119900 = argmin120573

σ119894=1119873 (119910119894 minus 1205730 minus σ119895=1

119875 119909119894119895120573119895)2

Subject to σ119895=1119875 120573119895 le 119905


1

2σ119894=1119873 (119910119894 minus 1205730 minus σ119895=1

119875 119909119894119895120573119895)2 + 120582σ119895=1

119875 120573119895

93


Penalty( 120582 ) x1 x2 x3 x4 x5 x6 x7

120582 = 0

120582 = 40

120582 = 418

120582 = 419

120582 = 42

120582 = 50





94


x12

x11

x10

x9

x8

x7

x6

x5

x4

x3

x2

x1

Feature Importance



Voting (投票法)



95



SVID_003 4

SVID_101 3

SVID_021 3

SVID_040 3

SVID_002 3

SVID_128 2

SVID_062 2

SVID_077 2






96

Test

Test

Test

Test


1st iter

2nd iter

3rd iter

10th iter

hellip

Error1

Error2

Error3

Error10

Minimize Error=1

10σ119894=110 Error119894



97


Undersampling



Example








SVIDVoting by

Undersampling

SVID_003 19

SVID_101 18

SVID_021 18

SVID_040 18

SVID_002 17

SVID_128 17

SVID_062 17

SVID_077 17

hellip hellip




98


SVID_003 09487 02583 11439

SVID_101 02078 05434 08934

SVID_021 04105 08377 06845

SVID_040 5208 7169 03170

SVID_002 27256 21025 02581

SVID_128 80523 85336 00580

SVID_062 09430 09747 00330

SVID_077 1569 1603 00216



Photo_06 12 384 00313

Etch_10 3 295 00102

Photo_32 10 1011 00099

Photo_17 4 410 00098

PVD_02 1 123 00081

CVD_14 9 3456 00026

Diff_09 1 495 00020

Etch_07 5 2769 00018



良品119886119907119892 minus不良品119886119907119892

119860119907119892

RATIO = FAIL TOTAL





99








迷思



100



Feature Engineering









119903 = 11990912 + 1199092

2

120579 = arctan11990921199091


101


119903

120579

1199091

1199092













Trend (趨勢)



Randomness (隨機)




102

Σ

A

A1 A2

B

B1 B2

C

C1 C2

人

人




103





預測

良品不良品




Benefits




104



105

Dataset with

selected variable

Prediction

Classification

Model

PLS BPNN CNN


R-Squared

MSE

Confusion

Matrix

Model

Evaluation

BoostingDecision

TreeSVR

Random

Sampling

Data

Transformation

Imbalance

Categorical to

Dummy VarFeature

Extraction

Feature

Selection

hellip

Yes

No

Knowledge

Management (KM)

Documentation


Z-scores


iterative

process















Data Imbalance

106










107

helliphellip

Input

Layer

Hidden

Layer

Output

Layer

hellip

helliphellip

helliphellip

helliphellip

helliphellip

helliphellip

helliphellip

x1

x2

xm

ො1199101

ො1199102

ො119910n

y1

y2

yn

NN

Output

Desired

Output




108







109

Yie

ld

Pre

cis

ion

Metr

olo

gy V

alu

e

Lot

Real value







110

UCL

LCL

Yie

ld

Pre

cis

ion

Metr

olo

gy V

alu

e

Lot

Real value









TNTP

+++

+=Accuracy


預測類別


實際類別

類別1


FN (false negative)

(Type II error)

(miss)

類別2

(良品)

FP (false positive)

(Type I error)

(false alarm)

TN (true negative)

111











112

TPSensitivity

TP+FN=

TNSpecificity

TN+FP=

預測

類別1 類別2

實際

類別1 TP FN

類別2 FP TN




TP

Rate

= S

ensitiv

ity

Model A

Model B

Precision=TP






113

Testing


Model A 719 897 517 702

Model B 781 691 883 789

Model A預測

Bad Good

實際Bad 61 7

Good 29 31

Model B預測

Bad Good

實際Bad 47 21

Good 7 53


精度良率預測







114

Time

Y

UCL

LCL

Time

Y

UCL

LCL





double EWMA




EWMA Control


115


Liu et al (2018)



116


維修保養








117











118
























119




120


No 名稱 No 名稱




4 R扣環 12 風扇


6 S扣環 14 風罩






Vibration Dataset

121

Amplitude

Time

(Obs)



Lee et al (2019)





122


Inspection

zone

Preventive

replacement

zone

Corrective

replacement

zone

Failure level

Replacement level

Data collection RUL




123

(Lee et al 2014)















124





Feature Engineering

125

Peak-

to-

peak




Data

Collection

Data

Preprocessing



Feature

Extraction

Feature

Selection

Remove high



(VIF)



Important

Variables

Predict

Linear Regression

(OLS)


Prediction Result


Regression (PLS)

Prediction

Model

OLS


PLS


BPNN

MSE = 123456789

Feature Engineering

(製造資料)





127



Feature Engineering









129




29 Alarm

16 Prediction model

training

15 EWMA for Target

Baseline (TB)



24 Predicted

CUSUM out of

control

25 Pre-alarmYes

No

28 Actual

CUSUM out of

control

Yes

No


21 New sample

prediction



17 Model validation

34 Continuous

monitoring

11 Data collection

26 Engineering

Validation amp

Troubleshooting

31 Loss calculation


32 CUSUM

control chart

33 Loss

CUSUM out of

control

310 Add new samples


311 ILPM model


Yes

Off-line training

In-line prediction

Concept drift

Pre-alarm stage


correction

No

All good products

37 Bayesian

monitoring out

of control

35 Equipment



39 Update posterior


38 Alarm and

equipment

maintenance

Yes

Model misalignment


Equipment

misalignment


36 Lifetime

out of control

No

Yes


Engineering



















hellip

130
















hellip

131






ldquo機會rdquo


132




133


很多時候我們


134

事實上hellip


現場改善

資料科學

系統整合

資料品質確認


浪費與WIP

瓶頸站生產力

人機比

設施佈置

環境公安衛生


流程再造BPR

時間動作研究



浪費移除

產線平衡


IT基礎建設

Make-or-Buy

需求預測

產銷平衡

排程與交期

特徵選取

Troubleshooting

機台維修保養


預測方法


啟發式演算法

機器學習


系統開發

供應鏈平台JIT



製程能力優化

良率提升



組件剩餘壽命


資料不一致





Decision Science

New Business Model


Price Maintenance


Sustainability

資料分析確認

Lee and Chien

(2020)


可能會問hellip




136


資料科學






現場觀察


137


話說hellip


某廠區稼動率116200 = 58







138



139

魚骨圖

法



環境


少量多樣

溝通管道

其他

交班傳達不周

人

人力缺乏



等待人員操作

機

機台維修保養

模具更換


待料


料


在製品堆放

機台稼動率低


作業不熟練

需求變異

工程變更

政策法規改變

傳承關係





案例





eg (56+160+138 mins)(180+180+180 mins)

=656

140




案例





eg (56+160+138 mins)(180+180+180 mins)

=656

141


(分)作業

耗時

(分)作業

耗時

(分)作業

耗時

(分)




1427-1430 產品品質檢測 3

1430-1443 電腦資料輸入 13


1450-1454 電腦工程分析 4

1454-1500 領取原物料 6

1500-1515 休息 15

1515-1528 領取模具 13

1528-1533 產品品質檢測 5


1543-1548 換模具 5


1601-1610 領取模具 9

1610-1617 產品品質檢測 7

1617-1622 存放載具 5

1622-1631 產品品質檢測 9


1640-1647 產品品質檢測 7


1652-1655 領取原物料 3

1655-1700 電腦資料輸入 5

機器加工

(產品D)

機器加工

(產品C)

13

124


停機

等待換規格

換模

停機

待料

機器加工

(產品A)

機器加工

(產品B)

機器加工

(產品C)

43

140

20

88

42

50

機器加工

(產品B)







200 80 = 160 (台) 到 200 85 = 170 (台) 之間為理想機台運作數



142









=工作效率




=08

1minus0656= 233 (台)


143






缺點很花時間






144





A 全部hellip

現場rarr瓶頸站





目標的衝突


145

Strategic Level


Planning

Marketing

Planning

Make-or-Buy

Strategy

Tactical Level


Planning


Order Allocation

Master Production

Schedule

Resource Planning

Rough-Cut Capacity

Planning

Capacity Require

Planning

Material Require

Planning

Monthly Material

Planning

Capacity Planning

Productivity amp

Efficiency Analysis

Vendor Relationship

MgmtDemand Mgmt


Purchasing


Daily Assignment

Order Releasing


Scheduling



Production


Operational Level

Logistics Mgmt

Long Term

Mid Term

Short Term

Facility Layout






146




timeProduction


uptimeEquipment

timeProduction

timeTotal

uptimeEquipment

timeTotal


=

=

=

Nonscheduled

state

Unscheduled

down state

Scheduled

down state

Engineering

state

Standby

state

Productive

state

Equipment

uptime

Equipment

downtime

Operations

time

Production

time

Total

time



147

顧客訂單產品

交期變動插單

工程變更




操作員

人力不足

MO


人員配置


機台設備廠務





廠區間的Backup



停工待料


外包時程變異

進料品質變異

















148






優先順序

日期達交












衝突目標

Makespan


(TWET)

交期

利用率

庫存時間



排程應用範疇


機場飛機起降



電梯設定

微處理器系統

醫院排班

醫院復健排程

醫師手術排班




150




人工排程邏輯

訂單資料

依到期日排序


預估單

工作號賦予




Yes

No


No





優先順序法則

Dispatching










Rush 緊急事件

152




剩餘作業數




Performance Metrics

Mean Flow Time






119879119895 = max0 119871119895


N Jobs on 1 Machine


N Jobs on 1 Machine




Notations



119889119895 due date

154


1 11 61

2 29 45

3 31 31

4 1 33

5 2 32


N Jobs on 1 Machine

FCFS



Tardy Jobs 3

155


J1 11 11 61 0

J2 29 40 45 0

J3 31 71 31 40

J4 1 72 33 39

J5 2 74 32 42

Totals 74 268 121





N Jobs on 1 Machine

SPT



Tardy 1

156


J4 1 1 33 0

J5 2 3 32 0

J1 11 14 61 0

J2 29 43 45 0

J3 31 74 31 43

Totals 74 135 45


N Jobs on 1 Machine

EDD



Tardy 4

157


J3 31 31 31 0

J5 2 33 32 1

J4 1 34 33 1

J2 29 63 45 18

J1 11 74 61 13

Totals 74 235 33


N Jobs on 1 Machine






Compute


158

119862119877 =119863119906119890_119863119886119905119890 minus (119862119906119903_119879119894119898119890)

119875119903119900119888119890119904119904119894119899119892_119879119894119898119890


CR

N Jobs on 1 Machine

159

JOBPr

Time

D

DateCR

Current Time = 0

1 11 61 5546

2 29 45 1552

3 31 31 100

4 1 33 33

5 2 32 16

JOBPr

Time

D

DateCR

Current Time = 31

1 11 61 2727

2 29 45 483

4 1 33 2

5 2 32 05


N Jobs on 1 Machine

160

JOBPr

Time

D

DateCR

Current Time = 60

1 11 610091

do last

4 1 33 -27

5 2 32 -14

JOBC

Time

D

DateTardy

Summary

3 31 31 0

2 60 45 15

4 61 33 28

5 63 32 31

1 74 61 13

Total 289 87

Tie use SPT

CR

Mean F Time (289)5 = 578


Tardy 4



FCFS


SPT




EDD



CR


Sequencing Rules

due Time

FCFS

CRSPT

EDD


然而hellip








162



快速換模技術









163



快速換模技術









4改善內部換模

平行作業


5改善外部作業




164





NP-hard problem













Local optimum

Short running time

Global optimum

Long running time


Meta-heuristics






166

f(x)

x

Local optimum

Global

optimum

Meta-heuristics

ldquoJUMPrdquo

119909119905+1 larr 119909119905 + 120578120597119891

120597119909


120597119891

120597119909

119909119905 119909119905+1

120578



Basis











Neighborhood Search


promising regions








memory




go to step 3



















= 500




Due Date(119941119947)

Weights (119960119947)

1 10 4 14

2 10 2 12

3 13 1 1

4 4 12 12




(1243) (2413) and (2134)

119879 1243 = 480 119879 2413 = 436 and 119879 2134 = 652





(4213) (2143) TABU and (2431)

119879 4213 = 460 119879 2143 = 500 TABU and 119879 2431 = 608







(2413) TABU (4123) and (4231)

119879 2413 = 436 TABU 119879 4123 = 440 and 119879 4231 = 632





(1423) (4213) TABU and (4132)

119879 1423 = 408 119879 4213 = 460 TABU and 119879 4132 = 586





Metaheuristics


172

1199091


1199610


1199611 1199612



Global

optimum










exploration

exploitation

(Gen 2005)


If you hellip





175


Interfaces

1 Gantt Chart

2 Dispatch List

3 Capacity Buckets


Scenario

Management

System

Maintenance

Performance

Control

Algorithm

Generator

Interface

Algorithm

Generator

Scheduler amp

Dispatcher

Preprocessor

Scheduling amp

Rescheduling

Algorithms

Manufacturing

Execution

System (MES)

Enterprise

Resource

Planning (MRPII)

Production

Monitoring

System

Database

ImportExport

Synchronization


Algorithm

Library


Scheduling

Logic Unit

Order

Master

File

Shop-

Floor

Data



176







178

Capacity Buckets






改善的機會


講究的是synergy








179












180














Rescheduling

181








Hint WIP



182


Pull Strategy

High Uncertainty

Push Strategy

Low Uncertainty

WIP


Lateness









processing time



HVLV HV

HVHV HV

LVLV LV

LV LVHV

Process Variability

Inflow Variability


迷思










現場動態調整

184






185



再過一陣子





186



在製造業中





187









188







190


迷思


191


迷思

這是當然的


找出關鍵因子

建構因果關係




192



193

為什麼要預測


下一步為何


預測像hellip

194


預測像hellip

195




B2A1E9818B3F




196




197





198






瞭解這就hellip


199






200


其實hellip




201


決策的類型





202


小試身手hellip

天氣與決策

203

不帶傘帶傘





3 拿別人的傘

(良心不安)


小試身手hellip

204


神預測God2GO



小試身手hellip


205

機率02

機率08



方法一期望值







小試身手hellip


206

機率02

機率08





風險成本矩陣

不帶傘帶傘

晴天

成本 $0 成本 $100

(弄丟)

雨天

成本 $200

(感冒)

成本 $0

期望成本

02x0

+08x200

=160

02x100

+08x0

=20

決策帶傘


小試身手hellip


207



風險成本矩陣

不帶傘帶傘

晴天

成本 $0 成本 $100

(弄丟)

雨天

成本 $200

(感冒)

成本 $0

期望成本

02x0

+08x200

=160

02x100

+08x0

=20

決策帶傘

切記hellip


又或hellip



由此可知hellip




208

Lee (2019)


小試身手hellip


209

Based on your

Preference

Structure








210



併購公司A 42 21 8

購置機台 35 28 13

外包 28 25 23







211

天氣情境

方案景氣好

景氣持平

景氣差

Min

Return

併購公司A 42 21 8 8

購置機台 35 28 13 13

外包 28 25 23 23






212

天氣情境

方案景氣好

景氣持平

景氣差

Max

Return

併購公司A 42 21 8 42

購置機台 35 28 13 35

外包 28 25 23 28








213

悔惜矩陣

景氣好

景氣持平

景氣差

Max

Regret

0 7 15 15

7 0 10 10

14 3 0 14

天氣情境

方案景氣好

景氣持平

景氣差

併購公司A 42 21 8

購置機台 35 28 13

外包 28 25 23






214

天氣情境

方案景氣好

景氣持平

景氣差

併購公司A 42 21 8

購置機台 35 28 13

外包 28 25 23






215




Two Types of Risk



Time

Demand

Demand

A

B

C

大試身手hellip

0




Time

Demand

Demand


0

追高殺低


大試身手hellip






218






Scenario Simulator



Time

Demand

Marketing Forecast

Sales Forecast

大試身手hellip

0

Capacity Level






shortage


Linear Regression

Autoregression

Neural Network





220


Empirical Study




221

Capacity Regret

Assessment

CustomerInventory

Market

Share

Profit

Loss

Loss of

Falling Price

Inventory

Loss

Holding

CostReputation

Lower

Capacity

Level

Higher

Capacity

Level

ALTERNATIVE

OBJECTIVE

ATTRIBUTE

119877119904ℎ119900119903119905119886119892119890 缺貨風險119877119904119906119903119901119897119906119904 存貨風險



Empirical Study


222

119877119904ℎ119900119903119905119886119892119890 缺貨風險愈大產能水準向上拉

119877119904119906119903119901119897119906119904 存貨風險愈大產能水準向下壓

119863119898119886119909

119863119898119894119899

Capacity Decision


0

10000

20000

30000

Training

Dataset

Validation

Dataset

Technology

Node A

Time

Demand

Empirical Study

Data Source






223



Empirical Study

2-stage approach

Demand Forecast

Capacity Decision

VDGP


(Chang et al 2014)

224



Empirical Study




225

0

10000

20000

30000

Training

Dataset

Validation

Dataset

Technology

Node A

Time

Demand

Linear Regression

Autoregression

Neural Network


Empirical Study







119877119904ℎ119900119903119905119886119892119890 = 0521 and 119877119904119906119903119901119897119906119904 = 0479

226



MonthActual

Demand


EV MMR SP

Aug 2014 19499 20207 16941 17157 18922Sep 2014 18110 21305 17921 18306 19135Oct 2014 15059 22404 18536 19291 18885



Empirical Study


227

0

500

1000

1500

2000

0 300 600 900 1200

StandardDeviation

AverageRegret

Current

Policy

EVMMR

SP

Poor

Better

Better Poor




Min 119862119909 + 119864 119891 119909 ෩119863




119910+ 119910minus ge 0












228





229

Testing

Accuracy AUC

Model A 719 702

Model B 781 789

Model A預測

FAIL PASS

實際FAIL 61 7

PASS 29 31

Model B預測

FAIL PASS

實際FAIL 47 21

PASS 7 53



迷思


230


迷思

231

170cm

165cm 175cm

172cm



232















233



234



235











going on now






used here

236












237











238




1 1 0 4

2 0 2 12

3 3 2 18

Profit ($1000) $3 $5 0

1823

122

4 st

53

21

21

2

1

21

+

+=

xx

xx

x

x

xxZ


Graphical Solution


feasible region


0

1823

122

4 st

53

21

21

2

1

21

+

+=

xx

xx

x

x

xxZ


Graphical Solution




最佳化結果


6個產品2 (x2)


這就是處方~



遇到問題



提供solution


241



242

Domain Knowledge




243

處方性分析


DS in

MFG










為大於其細


方案評選


見

識

謀

斷


發想

收斂




執行對策

膽大心細

決策與行動

行




245

Descriptive

敘述性

Diagnostic

診斷性

Predictive

預測性

Prescriptive

處方性

Automating

自動性

見

What



Why



When


HowWho Where


戰情財報



(掌握趨勢)



(持續改善)

識謀斷行

U N I S O N


結語

Conclusion

246


迷思



247


迷思










248


迷思


249



Basic

interpretable

models

Post-hoc

Explanation

RegressionBased

Tree Based

DeepLearning

Linear Logistic

regression

Lasso Ridge

GLM GAM

Decision Tree

RF XGBoost

LightGBM

RF

DNN CNN RNN

helliphellip


(build-in)

DataFeature

EngineeringML

Models

Prediction Result

(build-in)

X

Post-hoc Methods


(plug-in)

FeatureImportance

洪紹嚴 (2019)



250

Yield

Time

Cost

Yield

New Tape-out (NTO)

研發導入

Device

optimization

during process

integration

Engineering

Parameter

Optimization

Design of

Experiments

成長期

Tool Matching

Benchmarking

Troubleshooting

Scheduling

Spec Setting SPC






成熟期

快速良率提升

Yield ramp

during pilot

production



during mass

production







機人


迷思




251








迷思

252







253




工業30





工業40








254














馬雲 (201704)








255


結語




However hellip









256


結語KPI Hierarchy

257


ROE

Profit

Margin

Asset

Turnover

Financial

Leveragetimes times

Profit

Sales

Assetsdivide divide

Cost minus Accounts


Sales

Price

Sales

Quantity

Effective

Outputs

Realized

Demand

times

minusmin

Price

Elasticity

Fixed

Cost

Variable

Cost+

Bottleneck

Throughput

Bottleneck

Utilization

Yield

times

Bottleneck

Capacity

times

Bottleneck

Machine

MTTR

MTBFMaintenance

Bottleneck

Availability

times

Demand

vs SupplyQuality

DL

Cost

IDL

Cost

Bui amp Fac

Depre

Equip

Cost

Variable

Unit Cost

times

Other

Assets+

ID Mater

Cost

D Mater

Cost

+ + + + +

Labor MaterialFloor

Space

Non-bottle

Machine

Fin

an

cia

l Ind

ex

Ma

nu

factu

ring In

de

xR

eso

urc

e

WIP Delivery

TAT

CVP CIP

Rework

Rate

Cycle

Time

times

Finished

Goods

+

SchedulingProduct-

mixLot Size

Man Machine

Ratio

Decis

ion




Line

Balancing



258

MFGcom

DATAcomINNOVATION

com

Technology

Migration

Analytics-oriented

- Prediction

- Troubleshooting

- Customer voice


Business-oriented






Analytics

Discussion

Implementation

Problem-oriented

- SOP and cost down




Data

(empirical)

Science

(critical)

Technology

(substantial)

Data Quality

(Internal data)

Data Analysis


Data Platform



Advanced training






戴勝益 (2014)


致謝

260

感謝



以及




謝謝大家~






2017 Modena Italy


1157ndash1182





















261

Contact Information


phone 02-33661206







Experiencehellip


失敗的藝術

人生的歷練


知識與經驗之



Wisdom ishellip


Wisdom ishellip

13





13







智慧工廠



15

智慧工廠

智慧製造

製造智慧



(製造系統)

16


Value and Profit

Value




17

Price

Value

Cost

Consumer

Surplus

Producer

Surplus

Wikipedia (2016)


製造智慧決策

18



SPC APC VM RMS

Carbon

Emission

Water

Recycle


Energy



VRARAI

Cloud

Computing

Cyber-

Physical

System


RFIDSmart Labels



















Inventory



Inventory Reduction







Chien et al (2004)




22



23




24




















26





其實hellip


27

English Math

Student_A 80 76

Student_B 80 91

Student_C 80 83

Student_D 80 62

Student_E 80 88

Layer X Layer Y

Machine_A 81 76

Machine_B 80 91

Machine_C 79 83

Machine_D 80 62

Machine_E 82 88


來自於變異




MES

APC

FDC

SPC

VM

R2R

RMS



Yield Management

hellipetc

Demand Forecast



CapEx

Cost Structure

MPS amp MRP



Order Releasing

hellipetcQuality

Productivity

Cost Down

Cycle Time

28


CIM and Automation

29


ISBN 0-471-93450-X



Benefits

Reduce HR Cost

Reduce MO


Productivity




Benefits

Sustain EQ variance


Support RD




CIM and Automation





31



轉變hellip



一種改善過程

32





1 Transportation

2 Inventory

3 Motion

4 Waiting

5 Overproduction

6 Overprocessing

7 Defects

8 Eschewed Talents

Continuous flow

Line Balancing


Lean Manufacturing


33





CIM and Automation

34

AMHS

MES APC

FMEC



Big Data

Analytics


Data

Warehouse

Knowledge


Selection

Preprocessing

Target Data

Preprocessed

Data

Pattern

Transformed

Data

Data Mining

Transformation

Interpretation

Evaluation



IT Infrastructure

Pattern Extraction



35

Edge

Computing







Problems




製造現場



一言九鼎(頂)



Ask Why








38


生產線數據


39


Characteristic

Pure Feature-



(between features)











Color Images 3D

Scans and Videos



correlation







40



















特性與問題




Data Preprocessing

42

Data

Warehouse

Knowledge

Selection

Preprocessing

Target Data

Preprocessed

Data

Pattern

Transformed

Data

Transformation

Data Mining

Interpretation

Evaluation





Lot001 Lot001 Pass







Lot ID Pass or Fail

Lot001 Pass

Lot002 Pass

Lot003 Fail

Lot004 Pass


Lot001 Pass 20

Lot002 Pass 25

Lot003 Fail 10

Lot004 Pass 15

75 857


Lot002 hellip


Lot002_1

Lot002_2


Parallel Machine


Data Preparation

Missing Value

44


WS_A_Mach_2_Temp

Lot001 820 NA

Lot002 820 NA

Lot003 NA 840

Lot004 NA 840

Lot IDWS_A_Temp

WS_A_Mach_Type

Lot001 820 1

Lot002 820 1

Lot003 840 2

Lot004 840 2

WS_A_Mach_1

WS_A_Mach_2



Golden Machine


Missing Value

45


WS_A_Mach_2_Temp

Lot001 820 NA

Lot002 820 NA

Lot003 820 NA

Lot004 830 NA

Lot005 820 NA

Lot006 820 NA

Lot007 825 NA

Lot008 830 120

Lot009 820 130

Lot010 NA 120


WS_A_Mach_2_Temp

Mach_1 Mach_2

Lot001 820 Avg 1 0

Lot002 820 Avg 1 0

Lot003 820 Avg 1 0

Lot004 830 Avg 1 0

Lot005 820 Avg 1 0

Lot006 820 Avg 1 0

Lot007 825 Avg 1 0

Lot008 830 120 1 1

Lot009 820 130 1 1

Lot010 Avg 120 0 1






46


Lot001 PartsA

Lot002 PartsB

Lot003 PartsA

Lot004 PartsC

Lot005 PartsD

Lot006 PartsE

Lot007 PartsB

Lot008 PartsA

Lot009 PartsC

Lot010 PartsE


WS_A_Mach_1_PartsB

WS_A_Mach_1_PartsC

WS_A_Mach_1_PartsD

Lot001 1 0 0 0

Lot002 0 1 0 0

Lot003 1 0 0 0

Lot004 0 0 1 0

Lot005 0 0 0 1

Lot006 0 0 0 0

Lot007 0 1 0 0

Lot008 1 0 0 0

Lot009 0 0 1 0

Lot010 0 0 0 0






建議方式







沒有再現性

47



抽樣檢測

48




NO001 鋁 A 13723 7235

NO002 鋁 B NA NA

NO003 鋁 B 13728 7237

NO099 鋁 B NA NA

NO100 鋁 A 13726 7236

X Y (抽檢)

沒被抽檢

沒被抽檢

抽樣

填補遺漏值



3 Prediction Model








49









有母數GLMRandom


Learninghellip


換線換模






50

Machine A A A


Machine A B


B B B

A B A B









51

MachineI2

A A AMachine1

B B


A A A

Machine2

A A AMachine1

A A A

B

B




瓶頸 (bottleneck)







52


120

unitsday

140

unitsday

80

unitsday

120

unitsday

100

unitsday

瓶頸

80 unitsday



(勞工和幹部)



楊大和(2016)










53





54

IDProduct

TypeStage

Process

Time (hrs)

Start

Time

Lot1 A 1 1 20161226 1450

Lot1 A 2 1 20161226 1600

Lot1 A 3 05 20161226 1720

Lot1 A 4 1 20161226 1800

Lot1 A 5 05 20161226 2030







55


211 000000

211 010000

211 020000

211 230000


211 000629

211 001041

211 034109

211 231157




Data Merge

56









建議串接方法

Rolling Forward

Nearest time

Rolling Forward

Rolling Backward

Nearest time




Lee and Dong (2019)






產品的queue time



57

STA

GE

x_S

VID

x

0 5

10

1

5

2

0

2

5

0 200 400 600 800 1000Lot or

Time






58


Time Downcode


2017-05-07140528


2017-05-07161214


2017-05-07174130



2017-05-07192243


2017-05-07201817




19 22 43 minus (16 12 14)








10 vs 90 5 vs 95 or 1 vs 99



predictionhellip



59




Lot01 PASS

Lot02 PASS

Lot03 PASS

Lot04 PASS

Lot05 PASS

Lot06 PASS

Lot07 FAIL

Lot08 PASS

Lot09 PASS

Lot10 PASS

Lot11 PASS

Lot12 PASS





準確度可達 1112 = 917



迷思


61



62


資料整合













迷思補遺漏值


63

English Math

Student_A 80 76

Student_B 80 91

Student_C 80 83

Student_D 80 62

Student_E 80

Avg 80

Max 91

Min 62

Avg 78


迷思補遺漏值

64













64








B 男 51 $64000 Yes

C 男 52 $105000 Yes

D 女 33 $55000 Yes

E 男 45 $45000 No

F 女 45 $100000


65



66

K=3

K=5




迷思補遺漏值

67


1 00886 00886 00886 00886

2 00684 00684 00684 00684

3 03515 03515 03515 03515

4 09874 09874 09874 09874

5 04713 04713 04713 04713

6 06115 06115 06115 06115

7 02573 02573 02573 02573

8 02914 02914 02914 02914

9 01662 01662 01662 01662

10 044 044 044 044

11 06939 03731 06622

平均值 04023 03731 03731 03994

標準差 02785 02753 02612 02753

誤差值 03208 00317




數據品質

68






資料品質

Univariate





Multiple Column




數據品質



69



Automobile Company




digital materials







71















72






Feature Selection






74








75

材料

設計

光罩


測試

封裝

最後測試

加熱製程

微影製程

離子佈植


介電質沉積

晶圓


Over 1000 stages










and unreliable




76




77


Root Cause As-Is



To-Be

Data Science

Automation









78

K

C

H

E

A

G

I

J

F

L

OR

DS

BP M

N

Q






Rule Extraction




79

Good 68 68

Bad 32 32

Good - -

Bad 23 100

Good 68 88

Bad 9 12

Good - -

Bad 6 100

Good 68 96

Bad 3 4





OK

NG

NG

NG

NG

NG NG NG

OK

OK

OKOK OKOK

NG

YES NO

YES

YES YES

YESYES

YES

NO

NO

NO

NO NO

NO

80

Map clustering for

systematic defects

12 defect patterns

and build WBM bank





(Lee and Tsai 2019)



81




(Wang2012）





29 Alarm

16 Prediction model

training

15 EWMA for Target

Baseline (TB)



24 Predicted

CUSUM out of

control

25 Pre-alarmYes

No

28 Actual

CUSUM out of

control

Yes

No


21 New sample

prediction



17 Model validation

34 Continuous

monitoring

11 Data collection

26 Engineering

Validation amp

Troubleshooting

31 Loss calculation


32 CUSUM

control chart

33 Loss

CUSUM out of

control

310 Add new samples


311 ILPM model


Yes

Off-line training

In-line prediction

Concept drift

Pre-alarm stage


correction

No

All good products

37 Bayesian

monitoring out

of control

35 Equipment



39 Update posterior


38 Alarm and

equipment

maintenance

Yes

Model misalignment


Equipment

misalignment


36 Lifetime

out of control

No

Yes



82







83





Self-Priming

Centrifugal Pump



84




Feature Selection

Feature Engineering

85

Data

Warehouse

Knowledge

Selection

Preprocessing

Target Data

Preprocessed

Data

Pattern

Transformed

Data

Transformation

Data Mining

Interpretation

Evaluation




易於決策判斷









精度預測





86



Feature Selection



ie p gtgt n issue




87

An

p

Xn

k k ltlt p








Types









(PCA) etc

88







89

Lee and Chen (2018)



90

Prepared

Dataset

Feature

Selection

LASSO SVMStepwise

Regression

Voting


Pivot

Analysis

Engineering

Experience

Feature

Validation

BoostingRandom

ForestPCA Random

Sampling

Data

Reduction

(pgtgtn)

Imbalance

Correlation

Coefficient

Independence

Testhellip

Data

Preprocessing

hellip

Yes

No

Knowledge

Management (KM)

Documentation

Lee and Tsai (2019)

iterative

process






同理hellip

因果rarr相關







91








92

119910 = 120572 + 1205731199091 + 120576

119910 = 120572 + 1205731199092 + 120576

119910 = 120572 + 1205731199093 + 120576

119910 = 120572 + 1205731199094 + 120576

119910 = 120572 + 12057321199092 + 1205731199091 + 120576

119910 = 120572 + 12057321199092 + 1205731199093 + 120576

119910 = 120572 + 12057321199092 + 1205731199094 + 120576

119910 = 120572 + 12057321199092 + 12057341199094 + 1205731199091 + 120576

119910 = 120572 + 12057321199092 + 12057341199094 + 1205731199093 + 120576

統計顯著的變數1199092 and 1199094



መ120573119897119886119904119904119900 = argmin120573

σ119894=1119873 (119910119894 minus 1205730 minus σ119895=1

119875 119909119894119895120573119895)2

Subject to σ119895=1119875 120573119895 le 119905


1

2σ119894=1119873 (119910119894 minus 1205730 minus σ119895=1

119875 119909119894119895120573119895)2 + 120582σ119895=1

119875 120573119895

93


Penalty( 120582 ) x1 x2 x3 x4 x5 x6 x7

120582 = 0

120582 = 40

120582 = 418

120582 = 419

120582 = 42

120582 = 50





94


x12

x11

x10

x9

x8

x7

x6

x5

x4

x3

x2

x1

Feature Importance



Voting (投票法)



95



SVID_003 4

SVID_101 3

SVID_021 3

SVID_040 3

SVID_002 3

SVID_128 2

SVID_062 2

SVID_077 2






96

Test

Test

Test

Test


1st iter

2nd iter

3rd iter

10th iter

hellip

Error1

Error2

Error3

Error10

Minimize Error=1

10σ119894=110 Error119894



97


Undersampling



Example








SVIDVoting by

Undersampling

SVID_003 19

SVID_101 18

SVID_021 18

SVID_040 18

SVID_002 17

SVID_128 17

SVID_062 17

SVID_077 17

hellip hellip




98


SVID_003 09487 02583 11439

SVID_101 02078 05434 08934

SVID_021 04105 08377 06845

SVID_040 5208 7169 03170

SVID_002 27256 21025 02581

SVID_128 80523 85336 00580

SVID_062 09430 09747 00330

SVID_077 1569 1603 00216



Photo_06 12 384 00313

Etch_10 3 295 00102

Photo_32 10 1011 00099

Photo_17 4 410 00098

PVD_02 1 123 00081

CVD_14 9 3456 00026

Diff_09 1 495 00020

Etch_07 5 2769 00018



良品119886119907119892 minus不良品119886119907119892

119860119907119892

RATIO = FAIL TOTAL





99








迷思



100



Feature Engineering









119903 = 11990912 + 1199092

2

120579 = arctan11990921199091


101


119903

120579

1199091

1199092













Trend (趨勢)



Randomness (隨機)




102

Σ

A

A1 A2

B

B1 B2

C

C1 C2

人

人




103





預測

良品不良品




Benefits




104



105

Dataset with

selected variable

Prediction

Classification

Model

PLS BPNN CNN


R-Squared

MSE

Confusion

Matrix

Model

Evaluation

BoostingDecision

TreeSVR

Random

Sampling

Data

Transformation

Imbalance

Categorical to

Dummy VarFeature

Extraction

Feature

Selection

hellip

Yes

No

Knowledge

Management (KM)

Documentation


Z-scores


iterative

process















Data Imbalance

106










107

helliphellip

Input

Layer

Hidden

Layer

Output

Layer

hellip

helliphellip

helliphellip

helliphellip

helliphellip

helliphellip

helliphellip

x1

x2

xm

ො1199101

ො1199102

ො119910n

y1

y2

yn

NN

Output

Desired

Output




108







109

Yie

ld

Pre

cis

ion

Metr

olo

gy V

alu

e

Lot

Real value







110

UCL

LCL

Yie

ld

Pre

cis

ion

Metr

olo

gy V

alu

e

Lot

Real value









TNTP

+++

+=Accuracy


預測類別


實際類別

類別1


FN (false negative)

(Type II error)

(miss)

類別2

(良品)

FP (false positive)

(Type I error)

(false alarm)

TN (true negative)

111











112

TPSensitivity

TP+FN=

TNSpecificity

TN+FP=

預測

類別1 類別2

實際

類別1 TP FN

類別2 FP TN




TP

Rate

= S

ensitiv

ity

Model A

Model B

Precision=TP






113

Testing


Model A 719 897 517 702

Model B 781 691 883 789

Model A預測

Bad Good

實際Bad 61 7

Good 29 31

Model B預測

Bad Good

實際Bad 47 21

Good 7 53


精度良率預測







114

Time

Y

UCL

LCL

Time

Y

UCL

LCL





double EWMA




EWMA Control


115


Liu et al (2018)



116


維修保養








117











118
























119




120


No 名稱 No 名稱




4 R扣環 12 風扇


6 S扣環 14 風罩






Vibration Dataset

121

Amplitude

Time

(Obs)



Lee et al (2019)





122


Inspection

zone

Preventive

replacement

zone

Corrective

replacement

zone

Failure level

Replacement level

Data collection RUL




123

(Lee et al 2014)















124





Feature Engineering

125

Peak-

to-

peak




Data

Collection

Data

Preprocessing



Feature

Extraction

Feature

Selection

Remove high



(VIF)



Important

Variables

Predict

Linear Regression

(OLS)


Prediction Result


Regression (PLS)

Prediction

Model

OLS


PLS


BPNN

MSE = 123456789

Feature Engineering

(製造資料)





127



Feature Engineering









129




29 Alarm

16 Prediction model

training

15 EWMA for Target

Baseline (TB)



24 Predicted

CUSUM out of

control

25 Pre-alarmYes

No

28 Actual

CUSUM out of

control

Yes

No


21 New sample

prediction



17 Model validation

34 Continuous

monitoring

11 Data collection

26 Engineering

Validation amp

Troubleshooting

31 Loss calculation


32 CUSUM

control chart

33 Loss

CUSUM out of

control

310 Add new samples


311 ILPM model


Yes

Off-line training

In-line prediction

Concept drift

Pre-alarm stage


correction

No

All good products

37 Bayesian

monitoring out

of control

35 Equipment



39 Update posterior


38 Alarm and

equipment

maintenance

Yes

Model misalignment


Equipment

misalignment


36 Lifetime

out of control

No

Yes


Engineering



















hellip

130
















hellip

131






ldquo機會rdquo


132




133


很多時候我們


134

事實上hellip


現場改善

資料科學

系統整合

資料品質確認


浪費與WIP

瓶頸站生產力

人機比

設施佈置

環境公安衛生


流程再造BPR

時間動作研究



浪費移除

產線平衡


IT基礎建設

Make-or-Buy

需求預測

產銷平衡

排程與交期

特徵選取

Troubleshooting

機台維修保養


預測方法


啟發式演算法

機器學習


系統開發

供應鏈平台JIT



製程能力優化

良率提升



組件剩餘壽命


資料不一致





Decision Science

New Business Model


Price Maintenance


Sustainability

資料分析確認

Lee and Chien

(2020)


可能會問hellip




136


資料科學






現場觀察


137


話說hellip


某廠區稼動率116200 = 58







138



139

魚骨圖

法



環境


少量多樣

溝通管道

其他

交班傳達不周

人

人力缺乏



等待人員操作

機

機台維修保養

模具更換


待料


料


在製品堆放

機台稼動率低


作業不熟練

需求變異

工程變更

政策法規改變

傳承關係





案例





eg (56+160+138 mins)(180+180+180 mins)

=656

140




案例





eg (56+160+138 mins)(180+180+180 mins)

=656

141


(分)作業

耗時

(分)作業

耗時

(分)作業

耗時

(分)




1427-1430 產品品質檢測 3

1430-1443 電腦資料輸入 13


1450-1454 電腦工程分析 4

1454-1500 領取原物料 6

1500-1515 休息 15

1515-1528 領取模具 13

1528-1533 產品品質檢測 5


1543-1548 換模具 5


1601-1610 領取模具 9

1610-1617 產品品質檢測 7

1617-1622 存放載具 5

1622-1631 產品品質檢測 9


1640-1647 產品品質檢測 7


1652-1655 領取原物料 3

1655-1700 電腦資料輸入 5

機器加工

(產品D)

機器加工

(產品C)

13

124


停機

等待換規格

換模

停機

待料

機器加工

(產品A)

機器加工

(產品B)

機器加工

(產品C)

43

140

20

88

42

50

機器加工

(產品B)







200 80 = 160 (台) 到 200 85 = 170 (台) 之間為理想機台運作數



142









=工作效率




=08

1minus0656= 233 (台)


143






缺點很花時間






144





A 全部hellip

現場rarr瓶頸站





目標的衝突


145

Strategic Level


Planning

Marketing

Planning

Make-or-Buy

Strategy

Tactical Level


Planning


Order Allocation

Master Production

Schedule

Resource Planning

Rough-Cut Capacity

Planning

Capacity Require

Planning

Material Require

Planning

Monthly Material

Planning

Capacity Planning

Productivity amp

Efficiency Analysis

Vendor Relationship

MgmtDemand Mgmt


Purchasing


Daily Assignment

Order Releasing


Scheduling



Production


Operational Level

Logistics Mgmt

Long Term

Mid Term

Short Term

Facility Layout






146




timeProduction


uptimeEquipment

timeProduction

timeTotal

uptimeEquipment

timeTotal


=

=

=

Nonscheduled

state

Unscheduled

down state

Scheduled

down state

Engineering

state

Standby

state

Productive

state

Equipment

uptime

Equipment

downtime

Operations

time

Production

time

Total

time



147

顧客訂單產品

交期變動插單

工程變更




操作員

人力不足

MO


人員配置


機台設備廠務





廠區間的Backup



停工待料


外包時程變異

進料品質變異

















148






優先順序

日期達交












衝突目標

Makespan


(TWET)

交期

利用率

庫存時間



排程應用範疇


機場飛機起降



電梯設定

微處理器系統

醫院排班

醫院復健排程

醫師手術排班




150




人工排程邏輯

訂單資料

依到期日排序


預估單

工作號賦予




Yes

No


No





優先順序法則

Dispatching










Rush 緊急事件

152




剩餘作業數




Performance Metrics

Mean Flow Time






119879119895 = max0 119871119895


N Jobs on 1 Machine


N Jobs on 1 Machine




Notations



119889119895 due date

154


1 11 61

2 29 45

3 31 31

4 1 33

5 2 32


N Jobs on 1 Machine

FCFS



Tardy Jobs 3

155


J1 11 11 61 0

J2 29 40 45 0

J3 31 71 31 40

J4 1 72 33 39

J5 2 74 32 42

Totals 74 268 121





N Jobs on 1 Machine

SPT



Tardy 1

156


J4 1 1 33 0

J5 2 3 32 0

J1 11 14 61 0

J2 29 43 45 0

J3 31 74 31 43

Totals 74 135 45


N Jobs on 1 Machine

EDD



Tardy 4

157


J3 31 31 31 0

J5 2 33 32 1

J4 1 34 33 1

J2 29 63 45 18

J1 11 74 61 13

Totals 74 235 33


N Jobs on 1 Machine






Compute


158

119862119877 =119863119906119890_119863119886119905119890 minus (119862119906119903_119879119894119898119890)

119875119903119900119888119890119904119904119894119899119892_119879119894119898119890


CR

N Jobs on 1 Machine

159

JOBPr

Time

D

DateCR

Current Time = 0

1 11 61 5546

2 29 45 1552

3 31 31 100

4 1 33 33

5 2 32 16

JOBPr

Time

D

DateCR

Current Time = 31

1 11 61 2727

2 29 45 483

4 1 33 2

5 2 32 05


N Jobs on 1 Machine

160

JOBPr

Time

D

DateCR

Current Time = 60

1 11 610091

do last

4 1 33 -27

5 2 32 -14

JOBC

Time

D

DateTardy

Summary

3 31 31 0

2 60 45 15

4 61 33 28

5 63 32 31

1 74 61 13

Total 289 87

Tie use SPT

CR

Mean F Time (289)5 = 578


Tardy 4



FCFS


SPT




EDD



CR


Sequencing Rules

due Time

FCFS

CRSPT

EDD


然而hellip








162



快速換模技術









163



快速換模技術









4改善內部換模

平行作業


5改善外部作業




164





NP-hard problem













Local optimum

Short running time

Global optimum

Long running time


Meta-heuristics






166

f(x)

x

Local optimum

Global

optimum

Meta-heuristics

ldquoJUMPrdquo

119909119905+1 larr 119909119905 + 120578120597119891

120597119909


120597119891

120597119909

119909119905 119909119905+1

120578



Basis











Neighborhood Search


promising regions








memory




go to step 3



















= 500




Due Date(119941119947)

Weights (119960119947)

1 10 4 14

2 10 2 12

3 13 1 1

4 4 12 12




(1243) (2413) and (2134)

119879 1243 = 480 119879 2413 = 436 and 119879 2134 = 652





(4213) (2143) TABU and (2431)

119879 4213 = 460 119879 2143 = 500 TABU and 119879 2431 = 608







(2413) TABU (4123) and (4231)

119879 2413 = 436 TABU 119879 4123 = 440 and 119879 4231 = 632





(1423) (4213) TABU and (4132)

119879 1423 = 408 119879 4213 = 460 TABU and 119879 4132 = 586





Metaheuristics


172

1199091


1199610


1199611 1199612



Global

optimum










exploration

exploitation

(Gen 2005)


If you hellip





175


Interfaces

1 Gantt Chart

2 Dispatch List

3 Capacity Buckets


Scenario

Management

System

Maintenance

Performance

Control

Algorithm

Generator

Interface

Algorithm

Generator

Scheduler amp

Dispatcher

Preprocessor

Scheduling amp

Rescheduling

Algorithms

Manufacturing

Execution

System (MES)

Enterprise

Resource

Planning (MRPII)

Production

Monitoring

System

Database

ImportExport

Synchronization


Algorithm

Library


Scheduling

Logic Unit

Order

Master

File

Shop-

Floor

Data



176







178

Capacity Buckets






改善的機會


講究的是synergy








179












180














Rescheduling

181








Hint WIP



182


Pull Strategy

High Uncertainty

Push Strategy

Low Uncertainty

WIP


Lateness









processing time



HVLV HV

HVHV HV

LVLV LV

LV LVHV

Process Variability

Inflow Variability


迷思










現場動態調整

184






185



再過一陣子





186



在製造業中





187









188







190


迷思


191


迷思

這是當然的


找出關鍵因子

建構因果關係




192



193

為什麼要預測


下一步為何


預測像hellip

194


預測像hellip

195




B2A1E9818B3F




196




197





198






瞭解這就hellip


199






200


其實hellip




201


決策的類型





202


小試身手hellip

天氣與決策

203

不帶傘帶傘





3 拿別人的傘

(良心不安)


小試身手hellip

204


神預測God2GO



小試身手hellip


205

機率02

機率08



方法一期望值







小試身手hellip


206

機率02

機率08





風險成本矩陣

不帶傘帶傘

晴天

成本 $0 成本 $100

(弄丟)

雨天

成本 $200

(感冒)

成本 $0

期望成本

02x0

+08x200

=160

02x100

+08x0

=20

決策帶傘


小試身手hellip


207



風險成本矩陣

不帶傘帶傘

晴天

成本 $0 成本 $100

(弄丟)

雨天

成本 $200

(感冒)

成本 $0

期望成本

02x0

+08x200

=160

02x100

+08x0

=20

決策帶傘

切記hellip


又或hellip



由此可知hellip




208

Lee (2019)


小試身手hellip


209

Based on your

Preference

Structure








210



併購公司A 42 21 8

購置機台 35 28 13

外包 28 25 23







211

天氣情境

方案景氣好

景氣持平

景氣差

Min

Return

併購公司A 42 21 8 8

購置機台 35 28 13 13

外包 28 25 23 23






212

天氣情境

方案景氣好

景氣持平

景氣差

Max

Return

併購公司A 42 21 8 42

購置機台 35 28 13 35

外包 28 25 23 28








213

悔惜矩陣

景氣好

景氣持平

景氣差

Max

Regret

0 7 15 15

7 0 10 10

14 3 0 14

天氣情境

方案景氣好

景氣持平

景氣差

併購公司A 42 21 8

購置機台 35 28 13

外包 28 25 23






214

天氣情境

方案景氣好

景氣持平

景氣差

併購公司A 42 21 8

購置機台 35 28 13

外包 28 25 23






215




Two Types of Risk



Time

Demand

Demand

A

B

C

大試身手hellip

0




Time

Demand

Demand


0

追高殺低


大試身手hellip






218






Scenario Simulator



Time

Demand

Marketing Forecast

Sales Forecast

大試身手hellip

0

Capacity Level






shortage


Linear Regression

Autoregression

Neural Network





220


Empirical Study




221

Capacity Regret

Assessment

CustomerInventory

Market

Share

Profit

Loss

Loss of

Falling Price

Inventory

Loss

Holding

CostReputation

Lower

Capacity

Level

Higher

Capacity

Level

ALTERNATIVE

OBJECTIVE

ATTRIBUTE

119877119904ℎ119900119903119905119886119892119890 缺貨風險119877119904119906119903119901119897119906119904 存貨風險



Empirical Study


222

119877119904ℎ119900119903119905119886119892119890 缺貨風險愈大產能水準向上拉

119877119904119906119903119901119897119906119904 存貨風險愈大產能水準向下壓

119863119898119886119909

119863119898119894119899

Capacity Decision


0

10000

20000

30000

Training

Dataset

Validation

Dataset

Technology

Node A

Time

Demand

Empirical Study

Data Source






223



Empirical Study

2-stage approach

Demand Forecast

Capacity Decision

VDGP


(Chang et al 2014)

224



Empirical Study




225

0

10000

20000

30000

Training

Dataset

Validation

Dataset

Technology

Node A

Time

Demand

Linear Regression

Autoregression

Neural Network


Empirical Study







119877119904ℎ119900119903119905119886119892119890 = 0521 and 119877119904119906119903119901119897119906119904 = 0479

226



MonthActual

Demand


EV MMR SP

Aug 2014 19499 20207 16941 17157 18922Sep 2014 18110 21305 17921 18306 19135Oct 2014 15059 22404 18536 19291 18885



Empirical Study


227

0

500

1000

1500

2000

0 300 600 900 1200

StandardDeviation

AverageRegret

Current

Policy

EVMMR

SP

Poor

Better

Better Poor




Min 119862119909 + 119864 119891 119909 ෩119863




119910+ 119910minus ge 0












228





229

Testing

Accuracy AUC

Model A 719 702

Model B 781 789

Model A預測

FAIL PASS

實際FAIL 61 7

PASS 29 31

Model B預測

FAIL PASS

實際FAIL 47 21

PASS 7 53



迷思


230


迷思

231

170cm

165cm 175cm

172cm



232















233



234



235











going on now






used here

236












237











238




1 1 0 4

2 0 2 12

3 3 2 18

Profit ($1000) $3 $5 0

1823

122

4 st

53

21

21

2

1

21

+

+=

xx

xx

x

x

xxZ


Graphical Solution


feasible region


0

1823

122

4 st

53

21

21

2

1

21

+

+=

xx

xx

x

x

xxZ


Graphical Solution




最佳化結果


6個產品2 (x2)


這就是處方~



遇到問題



提供solution


241



242

Domain Knowledge




243

處方性分析


DS in

MFG










為大於其細


方案評選


見

識

謀

斷


發想

收斂




執行對策

膽大心細

決策與行動

行




245

Descriptive

敘述性

Diagnostic

診斷性

Predictive

預測性

Prescriptive

處方性

Automating

自動性

見

What



Why



When


HowWho Where


戰情財報



(掌握趨勢)



(持續改善)

識謀斷行

U N I S O N


結語

Conclusion

246


迷思



247


迷思










248


迷思


249



Basic

interpretable

models

Post-hoc

Explanation

RegressionBased

Tree Based

DeepLearning

Linear Logistic

regression

Lasso Ridge

GLM GAM

Decision Tree

RF XGBoost

LightGBM

RF

DNN CNN RNN

helliphellip


(build-in)

DataFeature

EngineeringML

Models

Prediction Result

(build-in)

X

Post-hoc Methods


(plug-in)

FeatureImportance

洪紹嚴 (2019)



250

Yield

Time

Cost

Yield

New Tape-out (NTO)

研發導入

Device

optimization

during process

integration

Engineering

Parameter

Optimization

Design of

Experiments

成長期

Tool Matching

Benchmarking

Troubleshooting

Scheduling

Spec Setting SPC






成熟期

快速良率提升

Yield ramp

during pilot

production



during mass

production







機人


迷思




251








迷思

252







253




工業30





工業40








254














馬雲 (201704)








255


結語




However hellip









256


結語KPI Hierarchy

257


ROE

Profit

Margin

Asset

Turnover

Financial

Leveragetimes times

Profit

Sales

Assetsdivide divide

Cost minus Accounts


Sales

Price

Sales

Quantity

Effective

Outputs

Realized

Demand

times

minusmin

Price

Elasticity

Fixed

Cost

Variable

Cost+

Bottleneck

Throughput

Bottleneck

Utilization

Yield

times

Bottleneck

Capacity

times

Bottleneck

Machine

MTTR

MTBFMaintenance

Bottleneck

Availability

times

Demand

vs SupplyQuality

DL

Cost

IDL

Cost

Bui amp Fac

Depre

Equip

Cost

Variable

Unit Cost

times

Other

Assets+

ID Mater

Cost

D Mater

Cost

+ + + + +

Labor MaterialFloor

Space

Non-bottle

Machine

Fin

an

cia

l Ind

ex

Ma

nu

factu

ring In

de

xR

eso

urc

e

WIP Delivery

TAT

CVP CIP

Rework

Rate

Cycle

Time

times

Finished

Goods

+

SchedulingProduct-

mixLot Size

Man Machine

Ratio

Decis

ion




Line

Balancing



258

MFGcom

DATAcomINNOVATION

com

Technology

Migration

Analytics-oriented

- Prediction

- Troubleshooting

- Customer voice


Business-oriented






Analytics

Discussion

Implementation

Problem-oriented

- SOP and cost down




Data

(empirical)

Science

(critical)

Technology

(substantial)

Data Quality

(Internal data)

Data Analysis


Data Platform



Advanced training






戴勝益 (2014)


致謝

260

感謝



以及




謝謝大家~






2017 Modena Italy


1157ndash1182





















261

Contact Information


phone 02-33661206







知識與經驗之



Wisdom ishellip


Wisdom ishellip

13





13







智慧工廠



15

智慧工廠

智慧製造

製造智慧



(製造系統)

16


Value and Profit

Value




17

Price

Value

Cost

Consumer

Surplus

Producer

Surplus

Wikipedia (2016)


製造智慧決策

18



SPC APC VM RMS

Carbon

Emission

Water

Recycle


Energy



VRARAI

Cloud

Computing

Cyber-

Physical

System


RFIDSmart Labels



















Inventory



Inventory Reduction







Chien et al (2004)




22



23




24




















26





其實hellip


27

English Math

Student_A 80 76

Student_B 80 91

Student_C 80 83

Student_D 80 62

Student_E 80 88

Layer X Layer Y

Machine_A 81 76

Machine_B 80 91

Machine_C 79 83

Machine_D 80 62

Machine_E 82 88


來自於變異




MES

APC

FDC

SPC

VM

R2R

RMS



Yield Management

hellipetc

Demand Forecast



CapEx

Cost Structure

MPS amp MRP



Order Releasing

hellipetcQuality

Productivity

Cost Down

Cycle Time

28


CIM and Automation

29


ISBN 0-471-93450-X



Benefits

Reduce HR Cost

Reduce MO


Productivity




Benefits

Sustain EQ variance


Support RD




CIM and Automation





31



轉變hellip



一種改善過程

32





1 Transportation

2 Inventory

3 Motion

4 Waiting

5 Overproduction

6 Overprocessing

7 Defects

8 Eschewed Talents

Continuous flow

Line Balancing


Lean Manufacturing


33





CIM and Automation

34

AMHS

MES APC

FMEC



Big Data

Analytics


Data

Warehouse

Knowledge


Selection

Preprocessing

Target Data

Preprocessed

Data

Pattern

Transformed

Data

Data Mining

Transformation

Interpretation

Evaluation



IT Infrastructure

Pattern Extraction



35

Edge

Computing







Problems




製造現場



一言九鼎(頂)



Ask Why








38


生產線數據


39


Characteristic

Pure Feature-



(between features)











Color Images 3D

Scans and Videos



correlation







40



















特性與問題




Data Preprocessing

42

Data

Warehouse

Knowledge

Selection

Preprocessing

Target Data

Preprocessed

Data

Pattern

Transformed

Data

Transformation

Data Mining

Interpretation

Evaluation





Lot001 Lot001 Pass







Lot ID Pass or Fail

Lot001 Pass

Lot002 Pass

Lot003 Fail

Lot004 Pass


Lot001 Pass 20

Lot002 Pass 25

Lot003 Fail 10

Lot004 Pass 15

75 857


Lot002 hellip


Lot002_1

Lot002_2


Parallel Machine


Data Preparation

Missing Value

44


WS_A_Mach_2_Temp

Lot001 820 NA

Lot002 820 NA

Lot003 NA 840

Lot004 NA 840

Lot IDWS_A_Temp

WS_A_Mach_Type

Lot001 820 1

Lot002 820 1

Lot003 840 2

Lot004 840 2

WS_A_Mach_1

WS_A_Mach_2



Golden Machine


Missing Value

45


WS_A_Mach_2_Temp

Lot001 820 NA

Lot002 820 NA

Lot003 820 NA

Lot004 830 NA

Lot005 820 NA

Lot006 820 NA

Lot007 825 NA

Lot008 830 120

Lot009 820 130

Lot010 NA 120


WS_A_Mach_2_Temp

Mach_1 Mach_2

Lot001 820 Avg 1 0

Lot002 820 Avg 1 0

Lot003 820 Avg 1 0

Lot004 830 Avg 1 0

Lot005 820 Avg 1 0

Lot006 820 Avg 1 0

Lot007 825 Avg 1 0

Lot008 830 120 1 1

Lot009 820 130 1 1

Lot010 Avg 120 0 1






46


Lot001 PartsA

Lot002 PartsB

Lot003 PartsA

Lot004 PartsC

Lot005 PartsD

Lot006 PartsE

Lot007 PartsB

Lot008 PartsA

Lot009 PartsC

Lot010 PartsE


WS_A_Mach_1_PartsB

WS_A_Mach_1_PartsC

WS_A_Mach_1_PartsD

Lot001 1 0 0 0

Lot002 0 1 0 0

Lot003 1 0 0 0

Lot004 0 0 1 0

Lot005 0 0 0 1

Lot006 0 0 0 0

Lot007 0 1 0 0

Lot008 1 0 0 0

Lot009 0 0 1 0

Lot010 0 0 0 0






建議方式







沒有再現性

47



抽樣檢測

48




NO001 鋁 A 13723 7235

NO002 鋁 B NA NA

NO003 鋁 B 13728 7237

NO099 鋁 B NA NA

NO100 鋁 A 13726 7236

X Y (抽檢)

沒被抽檢

沒被抽檢

抽樣

填補遺漏值



3 Prediction Model








49









有母數GLMRandom


Learninghellip


換線換模






50

Machine A A A


Machine A B


B B B

A B A B









51

MachineI2

A A AMachine1

B B


A A A

Machine2

A A AMachine1

A A A

B

B




瓶頸 (bottleneck)







52


120

unitsday

140

unitsday

80

unitsday

120

unitsday

100

unitsday

瓶頸

80 unitsday



(勞工和幹部)



楊大和(2016)










53





54

IDProduct

TypeStage

Process

Time (hrs)

Start

Time

Lot1 A 1 1 20161226 1450

Lot1 A 2 1 20161226 1600

Lot1 A 3 05 20161226 1720

Lot1 A 4 1 20161226 1800

Lot1 A 5 05 20161226 2030







55


211 000000

211 010000

211 020000

211 230000


211 000629

211 001041

211 034109

211 231157




Data Merge

56









建議串接方法

Rolling Forward

Nearest time

Rolling Forward

Rolling Backward

Nearest time




Lee and Dong (2019)






產品的queue time



57

STA

GE

x_S

VID

x

0 5

10

1

5

2

0

2

5

0 200 400 600 800 1000Lot or

Time






58


Time Downcode


2017-05-07140528


2017-05-07161214


2017-05-07174130



2017-05-07192243


2017-05-07201817




19 22 43 minus (16 12 14)








10 vs 90 5 vs 95 or 1 vs 99



predictionhellip



59




Lot01 PASS

Lot02 PASS

Lot03 PASS

Lot04 PASS

Lot05 PASS

Lot06 PASS

Lot07 FAIL

Lot08 PASS

Lot09 PASS

Lot10 PASS

Lot11 PASS

Lot12 PASS





準確度可達 1112 = 917



迷思


61



62


資料整合













迷思補遺漏值


63

English Math

Student_A 80 76

Student_B 80 91

Student_C 80 83

Student_D 80 62

Student_E 80

Avg 80

Max 91

Min 62

Avg 78


迷思補遺漏值

64













64








B 男 51 $64000 Yes

C 男 52 $105000 Yes

D 女 33 $55000 Yes

E 男 45 $45000 No

F 女 45 $100000


65



66

K=3

K=5




迷思補遺漏值

67


1 00886 00886 00886 00886

2 00684 00684 00684 00684

3 03515 03515 03515 03515

4 09874 09874 09874 09874

5 04713 04713 04713 04713

6 06115 06115 06115 06115

7 02573 02573 02573 02573

8 02914 02914 02914 02914

9 01662 01662 01662 01662

10 044 044 044 044

11 06939 03731 06622

平均值 04023 03731 03731 03994

標準差 02785 02753 02612 02753

誤差值 03208 00317




數據品質

68






資料品質

Univariate





Multiple Column




數據品質



69



Automobile Company




digital materials







71















72






Feature Selection






74








75

材料

設計

光罩


測試

封裝

最後測試

加熱製程

微影製程

離子佈植


介電質沉積

晶圓


Over 1000 stages










and unreliable




76




77


Root Cause As-Is



To-Be

Data Science

Automation









78

K

C

H

E

A

G

I

J

F

L

OR

DS

BP M

N

Q






Rule Extraction




79

Good 68 68

Bad 32 32

Good - -

Bad 23 100

Good 68 88

Bad 9 12

Good - -

Bad 6 100

Good 68 96

Bad 3 4





OK

NG

NG

NG

NG

NG NG NG

OK

OK

OKOK OKOK

NG

YES NO

YES

YES YES

YESYES

YES

NO

NO

NO

NO NO

NO

80

Map clustering for

systematic defects

12 defect patterns

and build WBM bank





(Lee and Tsai 2019)



81




(Wang2012）





29 Alarm

16 Prediction model

training

15 EWMA for Target

Baseline (TB)



24 Predicted

CUSUM out of

control

25 Pre-alarmYes

No

28 Actual

CUSUM out of

control

Yes

No


21 New sample

prediction



17 Model validation

34 Continuous

monitoring

11 Data collection

26 Engineering

Validation amp

Troubleshooting

31 Loss calculation


32 CUSUM

control chart

33 Loss

CUSUM out of

control

310 Add new samples


311 ILPM model


Yes

Off-line training

In-line prediction

Concept drift

Pre-alarm stage


correction

No

All good products

37 Bayesian

monitoring out

of control

35 Equipment



39 Update posterior


38 Alarm and

equipment

maintenance

Yes

Model misalignment


Equipment

misalignment


36 Lifetime

out of control

No

Yes



82







83





Self-Priming

Centrifugal Pump



84




Feature Selection

Feature Engineering

85

Data

Warehouse

Knowledge

Selection

Preprocessing

Target Data

Preprocessed

Data

Pattern

Transformed

Data

Transformation

Data Mining

Interpretation

Evaluation




易於決策判斷









精度預測





86



Feature Selection



ie p gtgt n issue




87

An

p

Xn

k k ltlt p








Types









(PCA) etc

88







89

Lee and Chen (2018)



90

Prepared

Dataset

Feature

Selection

LASSO SVMStepwise

Regression

Voting


Pivot

Analysis

Engineering

Experience

Feature

Validation

BoostingRandom

ForestPCA Random

Sampling

Data

Reduction

(pgtgtn)

Imbalance

Correlation

Coefficient

Independence

Testhellip

Data

Preprocessing

hellip

Yes

No

Knowledge

Management (KM)

Documentation

Lee and Tsai (2019)

iterative

process






同理hellip

因果rarr相關







91








92

119910 = 120572 + 1205731199091 + 120576

119910 = 120572 + 1205731199092 + 120576

119910 = 120572 + 1205731199093 + 120576

119910 = 120572 + 1205731199094 + 120576

119910 = 120572 + 12057321199092 + 1205731199091 + 120576

119910 = 120572 + 12057321199092 + 1205731199093 + 120576

119910 = 120572 + 12057321199092 + 1205731199094 + 120576

119910 = 120572 + 12057321199092 + 12057341199094 + 1205731199091 + 120576

119910 = 120572 + 12057321199092 + 12057341199094 + 1205731199093 + 120576

統計顯著的變數1199092 and 1199094



መ120573119897119886119904119904119900 = argmin120573

σ119894=1119873 (119910119894 minus 1205730 minus σ119895=1

119875 119909119894119895120573119895)2

Subject to σ119895=1119875 120573119895 le 119905


1

2σ119894=1119873 (119910119894 minus 1205730 minus σ119895=1

119875 119909119894119895120573119895)2 + 120582σ119895=1

119875 120573119895

93


Penalty( 120582 ) x1 x2 x3 x4 x5 x6 x7

120582 = 0

120582 = 40

120582 = 418

120582 = 419

120582 = 42

120582 = 50





94


x12

x11

x10

x9

x8

x7

x6

x5

x4

x3

x2

x1

Feature Importance



Voting (投票法)



95



SVID_003 4

SVID_101 3

SVID_021 3

SVID_040 3

SVID_002 3

SVID_128 2

SVID_062 2

SVID_077 2






96

Test

Test

Test

Test


1st iter

2nd iter

3rd iter

10th iter

hellip

Error1

Error2

Error3

Error10

Minimize Error=1

10σ119894=110 Error119894



97


Undersampling



Example








SVIDVoting by

Undersampling

SVID_003 19

SVID_101 18

SVID_021 18

SVID_040 18

SVID_002 17

SVID_128 17

SVID_062 17

SVID_077 17

hellip hellip




98


SVID_003 09487 02583 11439

SVID_101 02078 05434 08934

SVID_021 04105 08377 06845

SVID_040 5208 7169 03170

SVID_002 27256 21025 02581

SVID_128 80523 85336 00580

SVID_062 09430 09747 00330

SVID_077 1569 1603 00216



Photo_06 12 384 00313

Etch_10 3 295 00102

Photo_32 10 1011 00099

Photo_17 4 410 00098

PVD_02 1 123 00081

CVD_14 9 3456 00026

Diff_09 1 495 00020

Etch_07 5 2769 00018



良品119886119907119892 minus不良品119886119907119892

119860119907119892

RATIO = FAIL TOTAL





99








迷思



100



Feature Engineering









119903 = 11990912 + 1199092

2

120579 = arctan11990921199091


101


119903

120579

1199091

1199092













Trend (趨勢)



Randomness (隨機)




102

Σ

A

A1 A2

B

B1 B2

C

C1 C2

人

人




103





預測

良品不良品




Benefits




104



105

Dataset with

selected variable

Prediction

Classification

Model

PLS BPNN CNN


R-Squared

MSE

Confusion

Matrix

Model

Evaluation

BoostingDecision

TreeSVR

Random

Sampling

Data

Transformation

Imbalance

Categorical to

Dummy VarFeature

Extraction

Feature

Selection

hellip

Yes

No

Knowledge

Management (KM)

Documentation


Z-scores


iterative

process















Data Imbalance

106










107

helliphellip

Input

Layer

Hidden

Layer

Output

Layer

hellip

helliphellip

helliphellip

helliphellip

helliphellip

helliphellip

helliphellip

x1

x2

xm

ො1199101

ො1199102

ො119910n

y1

y2

yn

NN

Output

Desired

Output




108







109

Yie

ld

Pre

cis

ion

Metr

olo

gy V

alu

e

Lot

Real value







110

UCL

LCL

Yie

ld

Pre

cis

ion

Metr

olo

gy V

alu

e

Lot

Real value









TNTP

+++

+=Accuracy


預測類別


實際類別

類別1


FN (false negative)

(Type II error)

(miss)

類別2

(良品)

FP (false positive)

(Type I error)

(false alarm)

TN (true negative)

111











112

TPSensitivity

TP+FN=

TNSpecificity

TN+FP=

預測

類別1 類別2

實際

類別1 TP FN

類別2 FP TN




TP

Rate

= S

ensitiv

ity

Model A

Model B

Precision=TP






113

Testing


Model A 719 897 517 702

Model B 781 691 883 789

Model A預測

Bad Good

實際Bad 61 7

Good 29 31

Model B預測

Bad Good

實際Bad 47 21

Good 7 53


精度良率預測







114

Time

Y

UCL

LCL

Time

Y

UCL

LCL





double EWMA




EWMA Control


115


Liu et al (2018)



116


維修保養








117











118
























119




120


No 名稱 No 名稱




4 R扣環 12 風扇


6 S扣環 14 風罩






Vibration Dataset

121

Amplitude

Time

(Obs)



Lee et al (2019)





122


Inspection

zone

Preventive

replacement

zone

Corrective

replacement

zone

Failure level

Replacement level

Data collection RUL




123

(Lee et al 2014)















124





Feature Engineering

125

Peak-

to-

peak




Data

Collection

Data

Preprocessing



Feature

Extraction

Feature

Selection

Remove high



(VIF)



Important

Variables

Predict

Linear Regression

(OLS)


Prediction Result


Regression (PLS)

Prediction

Model

OLS


PLS


BPNN

MSE = 123456789

Feature Engineering

(製造資料)





127



Feature Engineering









129




29 Alarm

16 Prediction model

training

15 EWMA for Target

Baseline (TB)



24 Predicted

CUSUM out of

control

25 Pre-alarmYes

No

28 Actual

CUSUM out of

control

Yes

No


21 New sample

prediction



17 Model validation

34 Continuous

monitoring

11 Data collection

26 Engineering

Validation amp

Troubleshooting

31 Loss calculation


32 CUSUM

control chart

33 Loss

CUSUM out of

control

310 Add new samples


311 ILPM model


Yes

Off-line training

In-line prediction

Concept drift

Pre-alarm stage


correction

No

All good products

37 Bayesian

monitoring out

of control

35 Equipment



39 Update posterior


38 Alarm and

equipment

maintenance

Yes

Model misalignment


Equipment

misalignment


36 Lifetime

out of control

No

Yes


Engineering



















hellip

130
















hellip

131






ldquo機會rdquo


132




133


很多時候我們


134

事實上hellip


現場改善

資料科學

系統整合

資料品質確認


浪費與WIP

瓶頸站生產力

人機比

設施佈置

環境公安衛生


流程再造BPR

時間動作研究



浪費移除

產線平衡


IT基礎建設

Make-or-Buy

需求預測

產銷平衡

排程與交期

特徵選取

Troubleshooting

機台維修保養


預測方法


啟發式演算法

機器學習


系統開發

供應鏈平台JIT



製程能力優化

良率提升



組件剩餘壽命


資料不一致





Decision Science

New Business Model


Price Maintenance


Sustainability

資料分析確認

Lee and Chien

(2020)


可能會問hellip




136


資料科學






現場觀察


137


話說hellip


某廠區稼動率116200 = 58







138



139

魚骨圖

法



環境


少量多樣

溝通管道

其他

交班傳達不周

人

人力缺乏



等待人員操作

機

機台維修保養

模具更換


待料


料


在製品堆放

機台稼動率低


作業不熟練

需求變異

工程變更

政策法規改變

傳承關係





案例





eg (56+160+138 mins)(180+180+180 mins)

=656

140




案例





eg (56+160+138 mins)(180+180+180 mins)

=656

141


(分)作業

耗時

(分)作業

耗時

(分)作業

耗時

(分)




1427-1430 產品品質檢測 3

1430-1443 電腦資料輸入 13


1450-1454 電腦工程分析 4

1454-1500 領取原物料 6

1500-1515 休息 15

1515-1528 領取模具 13

1528-1533 產品品質檢測 5


1543-1548 換模具 5


1601-1610 領取模具 9

1610-1617 產品品質檢測 7

1617-1622 存放載具 5

1622-1631 產品品質檢測 9


1640-1647 產品品質檢測 7


1652-1655 領取原物料 3

1655-1700 電腦資料輸入 5

機器加工

(產品D)

機器加工

(產品C)

13

124


停機

等待換規格

換模

停機

待料

機器加工

(產品A)

機器加工

(產品B)

機器加工

(產品C)

43

140

20

88

42

50

機器加工

(產品B)







200 80 = 160 (台) 到 200 85 = 170 (台) 之間為理想機台運作數



142









=工作效率




=08

1minus0656= 233 (台)


143






缺點很花時間






144





A 全部hellip

現場rarr瓶頸站





目標的衝突


145

Strategic Level


Planning

Marketing

Planning

Make-or-Buy

Strategy

Tactical Level


Planning


Order Allocation

Master Production

Schedule

Resource Planning

Rough-Cut Capacity

Planning

Capacity Require

Planning

Material Require

Planning

Monthly Material

Planning

Capacity Planning

Productivity amp

Efficiency Analysis

Vendor Relationship

MgmtDemand Mgmt


Purchasing


Daily Assignment

Order Releasing


Scheduling



Production


Operational Level

Logistics Mgmt

Long Term

Mid Term

Short Term

Facility Layout






146




timeProduction


uptimeEquipment

timeProduction

timeTotal

uptimeEquipment

timeTotal


=

=

=

Nonscheduled

state

Unscheduled

down state

Scheduled

down state

Engineering

state

Standby

state

Productive

state

Equipment

uptime

Equipment

downtime

Operations

time

Production

time

Total

time



147

顧客訂單產品

交期變動插單

工程變更




操作員

人力不足

MO


人員配置


機台設備廠務





廠區間的Backup



停工待料


外包時程變異

進料品質變異

















148






優先順序

日期達交












衝突目標

Makespan


(TWET)

交期

利用率

庫存時間



排程應用範疇


機場飛機起降



電梯設定

微處理器系統

醫院排班

醫院復健排程

醫師手術排班




150




人工排程邏輯

訂單資料

依到期日排序


預估單

工作號賦予




Yes

No


No





優先順序法則

Dispatching










Rush 緊急事件

152




剩餘作業數




Performance Metrics

Mean Flow Time






119879119895 = max0 119871119895


N Jobs on 1 Machine


N Jobs on 1 Machine




Notations



119889119895 due date

154


1 11 61

2 29 45

3 31 31

4 1 33

5 2 32


N Jobs on 1 Machine

FCFS



Tardy Jobs 3

155


J1 11 11 61 0

J2 29 40 45 0

J3 31 71 31 40

J4 1 72 33 39

J5 2 74 32 42

Totals 74 268 121





N Jobs on 1 Machine

SPT



Tardy 1

156


J4 1 1 33 0

J5 2 3 32 0

J1 11 14 61 0

J2 29 43 45 0

J3 31 74 31 43

Totals 74 135 45


N Jobs on 1 Machine

EDD



Tardy 4

157


J3 31 31 31 0

J5 2 33 32 1

J4 1 34 33 1

J2 29 63 45 18

J1 11 74 61 13

Totals 74 235 33


N Jobs on 1 Machine






Compute


158

119862119877 =119863119906119890_119863119886119905119890 minus (119862119906119903_119879119894119898119890)

119875119903119900119888119890119904119904119894119899119892_119879119894119898119890


CR

N Jobs on 1 Machine

159

JOBPr

Time

D

DateCR

Current Time = 0

1 11 61 5546

2 29 45 1552

3 31 31 100

4 1 33 33

5 2 32 16

JOBPr

Time

D

DateCR

Current Time = 31

1 11 61 2727

2 29 45 483

4 1 33 2

5 2 32 05


N Jobs on 1 Machine

160

JOBPr

Time

D

DateCR

Current Time = 60

1 11 610091

do last

4 1 33 -27

5 2 32 -14

JOBC

Time

D

DateTardy

Summary

3 31 31 0

2 60 45 15

4 61 33 28

5 63 32 31

1 74 61 13

Total 289 87

Tie use SPT

CR

Mean F Time (289)5 = 578


Tardy 4



FCFS


SPT




EDD



CR


Sequencing Rules

due Time

FCFS

CRSPT

EDD


然而hellip








162



快速換模技術









163



快速換模技術









4改善內部換模

平行作業


5改善外部作業




164





NP-hard problem













Local optimum

Short running time

Global optimum

Long running time


Meta-heuristics






166

f(x)

x

Local optimum

Global

optimum

Meta-heuristics

ldquoJUMPrdquo

119909119905+1 larr 119909119905 + 120578120597119891

120597119909


120597119891

120597119909

119909119905 119909119905+1

120578



Basis











Neighborhood Search


promising regions








memory




go to step 3



















= 500




Due Date(119941119947)

Weights (119960119947)

1 10 4 14

2 10 2 12

3 13 1 1

4 4 12 12




(1243) (2413) and (2134)

119879 1243 = 480 119879 2413 = 436 and 119879 2134 = 652





(4213) (2143) TABU and (2431)

119879 4213 = 460 119879 2143 = 500 TABU and 119879 2431 = 608







(2413) TABU (4123) and (4231)

119879 2413 = 436 TABU 119879 4123 = 440 and 119879 4231 = 632





(1423) (4213) TABU and (4132)

119879 1423 = 408 119879 4213 = 460 TABU and 119879 4132 = 586





Metaheuristics


172

1199091


1199610


1199611 1199612



Global

optimum










exploration

exploitation

(Gen 2005)


If you hellip





175


Interfaces

1 Gantt Chart

2 Dispatch List

3 Capacity Buckets


Scenario

Management

System

Maintenance

Performance

Control

Algorithm

Generator

Interface

Algorithm

Generator

Scheduler amp

Dispatcher

Preprocessor

Scheduling amp

Rescheduling

Algorithms

Manufacturing

Execution

System (MES)

Enterprise

Resource

Planning (MRPII)

Production

Monitoring

System

Database

ImportExport

Synchronization


Algorithm

Library


Scheduling

Logic Unit

Order

Master

File

Shop-

Floor

Data



176







178

Capacity Buckets






改善的機會


講究的是synergy








179












180














Rescheduling

181








Hint WIP



182


Pull Strategy

High Uncertainty

Push Strategy

Low Uncertainty

WIP


Lateness









processing time



HVLV HV

HVHV HV

LVLV LV

LV LVHV

Process Variability

Inflow Variability


迷思










現場動態調整

184






185



再過一陣子





186



在製造業中





187









188







190


迷思


191


迷思

這是當然的


找出關鍵因子

建構因果關係




192



193

為什麼要預測


下一步為何


預測像hellip

194


預測像hellip

195




B2A1E9818B3F




196




197





198






瞭解這就hellip


199






200


其實hellip




201


決策的類型





202


小試身手hellip

天氣與決策

203

不帶傘帶傘





3 拿別人的傘

(良心不安)


小試身手hellip

204


神預測God2GO



小試身手hellip


205

機率02

機率08



方法一期望值







小試身手hellip


206

機率02

機率08





風險成本矩陣

不帶傘帶傘

晴天

成本 $0 成本 $100

(弄丟)

雨天

成本 $200

(感冒)

成本 $0

期望成本

02x0

+08x200

=160

02x100

+08x0

=20

決策帶傘


小試身手hellip


207



風險成本矩陣

不帶傘帶傘

晴天

成本 $0 成本 $100

(弄丟)

雨天

成本 $200

(感冒)

成本 $0

期望成本

02x0

+08x200

=160

02x100

+08x0

=20

決策帶傘

切記hellip


又或hellip



由此可知hellip




208

Lee (2019)


小試身手hellip


209

Based on your

Preference

Structure








210



併購公司A 42 21 8

購置機台 35 28 13

外包 28 25 23







211

天氣情境

方案景氣好

景氣持平

景氣差

Min

Return

併購公司A 42 21 8 8

購置機台 35 28 13 13

外包 28 25 23 23






212

天氣情境

方案景氣好

景氣持平

景氣差

Max

Return

併購公司A 42 21 8 42

購置機台 35 28 13 35

外包 28 25 23 28








213

悔惜矩陣

景氣好

景氣持平

景氣差

Max

Regret

0 7 15 15

7 0 10 10

14 3 0 14

天氣情境

方案景氣好

景氣持平

景氣差

併購公司A 42 21 8

購置機台 35 28 13

外包 28 25 23






214

天氣情境

方案景氣好

景氣持平

景氣差

併購公司A 42 21 8

購置機台 35 28 13

外包 28 25 23






215




Two Types of Risk



Time

Demand

Demand

A

B

C

大試身手hellip

0




Time

Demand

Demand


0

追高殺低


大試身手hellip






218






Scenario Simulator



Time

Demand

Marketing Forecast

Sales Forecast

大試身手hellip

0

Capacity Level






shortage


Linear Regression

Autoregression

Neural Network





220


Empirical Study




221

Capacity Regret

Assessment

CustomerInventory

Market

Share

Profit

Loss

Loss of

Falling Price

Inventory

Loss

Holding

CostReputation

Lower

Capacity

Level

Higher

Capacity

Level

ALTERNATIVE

OBJECTIVE

ATTRIBUTE

119877119904ℎ119900119903119905119886119892119890 缺貨風險119877119904119906119903119901119897119906119904 存貨風險



Empirical Study


222

119877119904ℎ119900119903119905119886119892119890 缺貨風險愈大產能水準向上拉

119877119904119906119903119901119897119906119904 存貨風險愈大產能水準向下壓

119863119898119886119909

119863119898119894119899

Capacity Decision


0

10000

20000

30000

Training

Dataset

Validation

Dataset

Technology

Node A

Time

Demand

Empirical Study

Data Source






223



Empirical Study

2-stage approach

Demand Forecast

Capacity Decision

VDGP


(Chang et al 2014)

224



Empirical Study




225

0

10000

20000

30000

Training

Dataset

Validation

Dataset

Technology

Node A

Time

Demand

Linear Regression

Autoregression

Neural Network


Empirical Study







119877119904ℎ119900119903119905119886119892119890 = 0521 and 119877119904119906119903119901119897119906119904 = 0479

226



MonthActual

Demand


EV MMR SP

Aug 2014 19499 20207 16941 17157 18922Sep 2014 18110 21305 17921 18306 19135Oct 2014 15059 22404 18536 19291 18885



Empirical Study


227

0

500

1000

1500

2000

0 300 600 900 1200

StandardDeviation

AverageRegret

Current

Policy

EVMMR

SP

Poor

Better

Better Poor




Min 119862119909 + 119864 119891 119909 ෩119863




119910+ 119910minus ge 0












228





229

Testing

Accuracy AUC

Model A 719 702

Model B 781 789

Model A預測

FAIL PASS

實際FAIL 61 7

PASS 29 31

Model B預測

FAIL PASS

實際FAIL 47 21

PASS 7 53



迷思


230


迷思

231

170cm

165cm 175cm

172cm



232















233



234



235











going on now






used here

236












237











238




1 1 0 4

2 0 2 12

3 3 2 18

Profit ($1000) $3 $5 0

1823

122

4 st

53

21

21

2

1

21

+

+=

xx

xx

x

x

xxZ


Graphical Solution


feasible region


0

1823

122

4 st

53

21

21

2

1

21

+

+=

xx

xx

x

x

xxZ


Graphical Solution




最佳化結果


6個產品2 (x2)


這就是處方~



遇到問題



提供solution


241



242

Domain Knowledge




243

處方性分析


DS in

MFG










為大於其細


方案評選


見

識

謀

斷


發想

收斂




執行對策

膽大心細

決策與行動

行




245

Descriptive

敘述性

Diagnostic

診斷性

Predictive

預測性

Prescriptive

處方性

Automating

自動性

見

What



Why



When


HowWho Where


戰情財報



(掌握趨勢)



(持續改善)

識謀斷行

U N I S O N


結語

Conclusion

246


迷思



247


迷思










248


迷思


249



Basic

interpretable

models

Post-hoc

Explanation

RegressionBased

Tree Based

DeepLearning

Linear Logistic

regression

Lasso Ridge

GLM GAM

Decision Tree

RF XGBoost

LightGBM

RF

DNN CNN RNN

helliphellip


(build-in)

DataFeature

EngineeringML

Models

Prediction Result

(build-in)

X

Post-hoc Methods


(plug-in)

FeatureImportance

洪紹嚴 (2019)



250

Yield

Time

Cost

Yield

New Tape-out (NTO)

研發導入

Device

optimization

during process

integration

Engineering

Parameter

Optimization

Design of

Experiments

成長期

Tool Matching

Benchmarking

Troubleshooting

Scheduling

Spec Setting SPC






成熟期

快速良率提升

Yield ramp

during pilot

production



during mass

production







機人


迷思




251








迷思

252







253




工業30





工業40








254














馬雲 (201704)








255


結語




However hellip









256


結語KPI Hierarchy

257


ROE

Profit

Margin

Asset

Turnover

Financial

Leveragetimes times

Profit

Sales

Assetsdivide divide

Cost minus Accounts


Sales

Price

Sales

Quantity

Effective

Outputs

Realized

Demand

times

minusmin

Price

Elasticity

Fixed

Cost

Variable

Cost+

Bottleneck

Throughput

Bottleneck

Utilization

Yield

times

Bottleneck

Capacity

times

Bottleneck

Machine

MTTR

MTBFMaintenance

Bottleneck

Availability

times

Demand

vs SupplyQuality

DL

Cost

IDL

Cost

Bui amp Fac

Depre

Equip

Cost

Variable

Unit Cost

times

Other

Assets+

ID Mater

Cost

D Mater

Cost

+ + + + +

Labor MaterialFloor

Space

Non-bottle

Machine

Fin

an

cia

l Ind

ex

Ma

nu

factu

ring In

de

xR

eso

urc

e

WIP Delivery

TAT

CVP CIP

Rework

Rate

Cycle

Time

times

Finished

Goods

+

SchedulingProduct-

mixLot Size

Man Machine

Ratio

Decis

ion




Line

Balancing



258

MFGcom

DATAcomINNOVATION

com

Technology

Migration

Analytics-oriented

- Prediction

- Troubleshooting

- Customer voice


Business-oriented






Analytics

Discussion

Implementation

Problem-oriented

- SOP and cost down




Data

(empirical)

Science

(critical)

Technology

(substantial)

Data Quality

(Internal data)

Data Analysis


Data Platform



Advanced training






戴勝益 (2014)


致謝

260

感謝



以及




謝謝大家~






2017 Modena Italy


1157ndash1182





















261

Contact Information


phone 02-33661206






智慧製造與生產線上的數據科學polab.im.ntu.edu.tw/talk/data_science_in_manufacturing.pdf智慧製造與生產線上的數據科學...

Documents