Industry 4.1

Fan-Tien Cheng, PhD, is Director of the Intelligent Manufacturing Research Center at the National Cheng Kung University in Taiwan, ROC. He received his doctorate in Electrical Engineering from the Ohio State University in 1989. His research foci are on topics related to intelligent manufacturing and Industry 4.0.

• Editor Biography xvList of Contributors xviiPreface xixAcknowledgments xxiForeword xxiii1 Evolution of Automation and Development Strategy of Intelligent Manufacturing with Zero Defects 1Fan-Tien Cheng1.1 Introduction 11.2 Evolution of Automation 11.2.1 e-Manufacturing 11.2.1.1 Manufacturing Execution System (MES) 31.2.1.2 Supply Chain (SC) 61.2.1.3 Equipment Engineering System (EES) 71.2.1.4 Engineering Chain (EC) 91.2.2 Industry 4.0 101.2.2.1 Definition and Core Technologies of Industry 4.0 101.2.2.2 Migration from e-Manufacturing to Industry 4.0 121.2.2.3 Mass Customization 121.2.3 Zero Defects – Vision of Industry 4.1 131.2.3.1 Two Stages of Achieving Zero Defects 141.3 Development Strategy of Intelligent Manufacturing with Zero Defects 141.3.1 Five-Stage Strategy of Yield Enhancement and Zero-Defects Assurance 151.4 Conclusion 18Appendix 1.A – Abbreviation List 18References 202 Data Acquisition and Preprocessing 25Hao Tieng, Haw-Ching Yang, and Yu-Yong Li2.1 Introduction 252.2 Data Acquisition 262.2.1 Process Data Acquisition 262.2.1.1 Sensing Signals Acquisition 262.2.1.2 Manufacturing Parameters Acquisition 352.2.2 Metrology Data Acquisition 362.3 Data Preprocessing 372.3.1 Segmentation 372.3.2 Cleaning 382.3.2.1 Trend Removal 392.3.2.2 Wavelet Thresholding 412.3.3 Feature Extraction 432.3.3.1 Time Domain 432.3.3.2 Frequency Domain 472.3.3.3 Time–Frequency Domain 492.3.3.4 Autoencoder 522.4 Case Studies 532.4.1 Detrending of the Thermal Effect in Strain Gauge Data 532.4.2 Automated Segmentation of Signal Data 552.4.3 Tool State Diagnosis 572.4.4 Tool Diagnosis using Loading Data 612.5 Conclusion 64Appendix 2.A – Abbreviation List 64Appendix 2.B – List of Symbols in Equations 65References 673 Communication Standards 69Fan-Tien Cheng, Hao Tieng, and Yu-Chen Chiu3.1 Introduction 693.2 Communication Standards of the Semiconductor Equipment 693.2.1 Manufacturing Portion 693.2.1.1 SEMI Equipment Communication Standard I (SECS-I) (SEMI E4) 703.2.1.2 SEMI Equipment Communication Standard II (SECS-II) (SEMI E5) 753.2.1.3 Generic Model for Communications and Control of Manufacturing Equipment (GEM) (SEMI E30) 813.2.1.4 High-Speed SECS Message Services (HSMS) (SEMI E37) 843.2.2 Engineering Portion (Interface A) 913.2.2.1 Authentication & Authorization (A&A) (SEMI E132) 933.2.2.2 Common Equipment Model (CEM) (SEMI E120) 953.2.2.3 Equipment Self-Description (EqSD) (SEMI E125) 953.2.2.4 Equipment Data Acquisition (EDA) Common Metadata (ECM) (SEMI E164) 983.2.2.5 Data Collection Management (DCM) (SEMI E134) 1023.3 Communication Standards of the Industrial Devices and Systems 1073.3.1 Historical Roadmaps of Classic Open Platform Communications (OPC) and OPC Unified Architecture (OPC-UA) Protocols 1083.3.1.1 Classic OPC 1083.3.1.2 OPC-UA 1093.3.2 Fundamentals of OPC-UA 1103.3.2.1 Requirements 1103.3.2.2 Foundations 1113.3.2.3 Specifications 1123.3.2.4 System Architecture 1123.3.3 Example of Intelligent Manufacturing Hierarchy Applying OPC-UA Protocol 1193.3.3.1 Equipment Application Program (EAP) Server 1213.3.3.2 Use Cases of Data Manipulation 1223.3.3.3 Sequence Diagrams of Data Manipulation 1233.4 Conclusion 125Appendix 3.A – Abbreviation List 125References 1284 Cloud Computing, Internet of Things (IoT), Edge Computing, and Big Data Infrastructure 129Hung-Chang Hsiao, Min-Hsiung Hung, Chao-Chun Chen, and Yu-Chuan Lin4.1 Introduction 1294.2 Cloud Computing 1314.2.1 Essentials of Cloud Computing 1314.2.2 Cloud Service Models 1324.2.3 Cloud Deployment Models 1344.2.4 Cloud Computing Applications in Manufacturing 1374.2.5 Summary 1424.3 IoT and Edge Computing 1424.3.1 Essentials of IoT 1424.3.2 Essentials of Edge Computing 1464.3.3 Applications of IoT and Edge Computing in Manufacturing 1484.3.4 Summary 1504.4 Big Data Infrastructure 1504.4.1 Application Demands 1504.4.2 Core Software Stack Components 1524.4.3 Bridging the Gap between Core Software Stack Components and Applications 1534.4.3.1 Hadoop Data Service (HDS) 1534.4.3.2 Distributed R Language Computing Service (DRS) 1564.4.4 Summary 1594.5 Conclusion 159Appendix 4.A – Abbreviation List 160Appendix 4.B – List of Symbols in Equations 162References 1625 Docker and Kubernetes 169Chao-Chun Chen, Min-Hsiung Hung, Kuan-Chou Lai, and Yu-Chuan Lin5.1 Introduction 1695.2 Fundamentals of Docker 1735.2.1 Docker Architecture 1735.2.1.1 Docker Engine 1745.2.1.2 High-Level Docker Architecture 1745.2.1.3 Architecture of Linux Docker Host 1765.2.1.4 Architecture of Windows Docker Host 1775.2.1.5 Architecture of Windows Server Containers 1775.2.1.6 Architecture of Hyper-V Containers 1785.2.2 Docker Operational Principles 1785.2.2.1 Docker Image 1785.2.2.2 Dockerfile 1795.2.2.3 Docker Container 1835.2.2.4 Container Network Model 1845.2.2.5 Docker Networking 1855.2.3 Illustrative Applications of Docker 1875.2.3.1 Workflow of Building, Shipping, and Deploying a Containerized Application 1885.2.3.2 Deployment of a Docker Container Running a Linux Application 1895.2.3.3 Deployment of a Docker Container Running a Windows Application 1915.2.4 Summary 1945.3 Fundamentals of Kubernetes 1955.3.1 Kubernetes Architecture 1955.3.1.1 Kubernetes Control Plane Node 1955.3.1.2 Kubernetes Worker Nodes 1975.3.1.3 Kubernetes Objects 1995.3.2 Kubernetes Operational Principles 2005.3.2.1 Deployment 2005.3.2.2 High Availability and Self-Healing 2005.3.2.3 Ingress 2025.3.2.4 Replication 2045.3.2.5 Scheduler 2045.3.2.6 Autoscaling 2055.3.3 Illustrative Applications of Kubernetes 2055.3.4 Summary 2095.4 Conclusion 209Appendix 5.A – Abbreviation List 210References 2116 Intelligent Factory Automation (iFA) System Platform 215Fan-Tien Cheng6.1 Introduction 2156.2 Architecture Design of the Advanced Manufacturing Cloud of Things (AMCoT) Framework 2156.3 Brief Description of the Automatic Virtual Metrology (AVM) Server 2186.4 Brief Description of the Baseline Predictive Maintenance (BPM) Scheme in the Intelligent Prediction Maintenance (IPM) Server 2186.5 Brief Description of the Key-variable Search Algorithm (KSA) Scheme in the Intelligent Yield Management (IYM) Server 2196.6 The iFA System Platform 2206.6.1 Cloud-based iFA System Platform 2206.6.2 Server-based iFA System Platform 2216.7 Conclusion 222Appendix 6.A – Abbreviation List 222Appendix 6.B – List of Symbols 224References 2247 Advanced Manufacturing Cloud of Things (AMCoT) Framework 225Min-Hsiung Hung, Chao-Chun Chen, and Yu-Chuan Lin7.1 Introduction 2257.2 Key Components of AMCoT Framework 2277.2.1 Key Components of Cloud Part 2277.2.2 Key Components of Factory Part 2297.2.3 An Example Intelligent Manufacturing Platform Based on AMCoT Framework 2297.2.4 Summary 2317.3 Framework Design of Cyber-Physical Agent (CPA) 2317.3.1 Framework of CPA 2317.3.2 Framework of Containerized CPA (CPAC) 2327.3.3 Summary 2337.4 Rapid Construction Scheme of CPAs (RCSCPA) Based on Docker and Kubernetes 2347.4.1 Background and Motivation 2347.4.2 System Architecture of RCSCPA 2357.4.3 Core Functional Mechanisms of RCSCPA 2367.4.3.1 Horizontal Auto-Scaling Mechanism 2377.4.3.2 Load Balance Mechanism 2387.4.3.3 Failover Mechanism 2387.4.4 Industrial Case Study of RCSCPA 2397.4.4.1 Experimental Setup 2397.4.4.2 Testing Results 2397.4.5 Summary 2427.5 Big Data Analytics Application Platform 2427.5.1 Architecture of Big Data Analytics Application Platform 2427.5.2 Performance Evaluation of Processing Big Data 2437.5.3 Big Data Analytics Application in Manufacturing – Electrical Discharge Machining 2457.5.4 Summary 2477.6 Manufacturing Services Automated Construction Scheme (MSACS) 2487.6.1 Background and Motivation 2487.6.2 Design of Three-Phase Workflow of MSACS 2497.6.3 Architecture Design of MSACS 2517.6.4 Designs of Core Components 2527.6.4.1 Design of Key Information (KI) Extractor 2527.6.4.2 Design of Library Information (Lib. Info.) Template 2557.6.4.3 Design of Service Interface Information (SI Info.) Template 2567.6.4.4 Design of Web Service Package (WSP) Generator 2567.6.4.5 Design of Service Constructor 2617.6.5 Industrial Case Studies 2627.6.5.1 Web Graphical User Interface (GUI) of MSACS 2627.6.5.2 Case Study 1: Automated Construction of the AVM Cloud-based Manufacturing (CMfg) Service for Validating the Efficacy of MSACS 2627.6.5.3 Case Study 2: Performance Evaluation of MSACS 2647.6.6 Summary 2657.7 Containerized MSACS (MSACSC) 2667.8 Conclusion 268Appendix 7.A – Abbreviation List 269Appendix 7.B – Patents (AMCoT + CPA) 270References 2718 Automatic Virtual Metrology (AVM) 275Fan-Tien Cheng8.1 Introduction 2758.1.1 Survey of Virtual Metrology (VM)-Related Literature 2768.1.2 Necessity of Applying VM 2778.1.3 Benefits of VM 2788.2 Evolution of VM and Invention of AVM 2828.2.1 Invention of AVM 2838.3 Integrating AVM Functions into the Manufacturing Execution System (MES) 2878.3.1 Operating Scenarios among AVM, MES Components, and Run-to-Run (R2R) Controllers 2898.4 Applying AVM for Workpiece-to-Workpiece (W2W) Control 2928.4.1 Background Materials 2938.4.2 Fundamentals of Applying AVM for W2W Control 2958.4.3 R2R Control Utilizing VM with Reliance Index (RI) and Global Similarity Index (GSI) 2998.4.4 Illustrative Examples 3008.4.5 Summary 3138.5 AVM System Deployment 3138.5.1 Automation Levels of VM Systems 3138.5.2 Deployment of the AVM System 3158.6 Conclusion 318Appendix 8.A – Abbreviation List 319Appendix 8.B – List of Symbols in Equations 321Appendix 8.C – Patents (AVM) 323References 3269 Intelligent Predictive Maintenance (IPM) 331Yu-Chen Chiu, Yu-Ming Hsieh, Chin-Yi Lin, and Fan-Tien Cheng9.1 Introduction 3319.1.1 Necessity of Baseline Predictive Maintenance (BPM) 3329.1.2 Prediction Algorithms of Remaining Useful Life (RUL) 3339.1.3 Introducing the Factory-wide IPM System 3349.2 BPM 3349.2.1 Important Samples Needed for Creating Target-Device Baseline Model 3379.2.2 Samples Needed for Creating Baseline Individual Similarity Index (ISIB) Model 3389.2.3 Device-Health-Index (DHI) Module 3389.2.4 Baseline-Error-Index (BEI) Module 3399.2.5 Illustration of Fault-Detection-and-Classification (FDC) Logic 3409.2.6 Flow Chart of Baseline FDC Execution Procedure 3409.2.7 Exponential-Curve-Fitting (ECF) RUL Prediction Module 3409.3 Time-Series-Prediction (TSP) Algorithm for Calculating RUL 3449.3.1 ABPM Scheme 3459.3.2 Problems Encountered with the ECF Model 3469.3.3 Details of the TSP Algorithm 3469.3.3.1 AR Model 3489.3.3.2 MA Model 3499.3.3.3 ARMA and ARIMA Models 3499.3.3.4 TSP Algorithm 3499.3.3.5 Pre-Alarm Module 3529.3.3.6 Death Correlation Index 3539.4 Factory-Wide IPM Management Framework 3549.4.1 Management View and Equipment View of a Factory 3549.4.2 Health Index Hierarchy (HIH) 3559.4.3 Factory-wide IPM System Architecture 3569.5 IPM System Implementation Architecture 3599.5.1 Implementation Architecture of IPMC based on Docker and Kubernetes 3599.5.2 Construction and Implementation of the IPMC 3619.6 IPM System Deployment 3649.7 Conclusion 367Appendix 9.A – Abbreviation List 367Appendix 9.B – List of Symbols in Equations 370Appendix 9.C – Patents (IPM) 371References 37210 Intelligent Yield Management (IYM) 377Yu-Ming Hsieh, Chin-Yi Lin, and Fan-Tien Cheng10.1 Introduction 37710.1.1 Traditional Root-Cause Search Procedure of a Yield Loss 37910.1.2 IYM System 38010.1.3 Procedure for Finding the Root Causes of a Yield Loss by Applying the Key-variable Search Algorithm (KSA) Scheme 38010.2 KSA Scheme 38110.2.1 Data Preprocessing Module 38210.2.2 KSA Module 38210.2.2.1 Triple Phase Orthogonal Greedy Algorithm (TPOGA) 38210.2.2.2 Automated Least Absolute Shrinkage and Selection Operator (ALASSO) 38410.2.2.3 Reliance Index of KSA (RIK) Module 38510.2.3 Blind-stage Search Algorithm (BSA) Module 38610.2.3.1 Blind Cases 38710.2.3.2 Blind-stage Search Algorithm 39010.2.4 Interaction-Effect Search Algorithm (IESA) Module 39310.2.4.1 Interaction-Effect 39310.2.4.2 Interaction-Effect Search Algorithm 39610.3 IYM System Deployment 40110.4 Conclusion 402Appendix 10.A – Abbreviation List 402Appendix 10.B – List of Symbols in Equations 403Appendix 10.C – Patents (IYM) 405References 40611 Application Cases of Intelligent Manufacturing 409Fan-Tien Cheng, Yu-Chen Chiu, Yu-Ming Hsieh, Hao Tieng, Chin-Yi Lin, and Hsien-Cheng Huang11.1 Introduction 40911.2 Application Case I: Thin Film Transistor Liquid Crystal Display (TFT-LCD) Industry 40911.2.1 Automatic Virtual Metrology (AVM) Deployment Examples in the TFT-LCD Industry 40911.2.1.1 Introducing the TFT-LCD Production Tools and Manufacturing Processes for AVM Deployment 41011.2.1.2 AVM Deployment Types for TFT-LCD Manufacturing 41311.2.1.3 Illustrative Examples 41811.2.1.4 Summary 42511.2.2 Intelligent Yield Management (IYM) Deployment Examples in the TFT-LCD Industry 42511.2.2.1 Introducing the TFT-LCD Production Tools and Manufacturing Processes for IYM Deployment 42511.2.2.2 KSA Deployment Example 42611.2.2.3 Summary 43211.3 Application Case II: Solar Cell Industry 43211.3.1 Introducing the Solar Cell Manufacturing Process and Requirement Analysis of Intelligent Manufacturing 43311.3.2 T2T Control with AVM Deployment Examples 43411.3.2.1 T2T+VM Control Scheme with RI&GSI 43511.3.2.2 Illustrative Examples of T2T Control with AVM 43711.3.3 Factory-Wide Intelligent Predictive Maintenance (IPM) Deployment Examples 44411.3.3.1 Illustrative Examples of BPM and RUL Prediction 44411.3.3.2 Illustrative Example of Factory-Wide IPM System 45111.3.4 Summary 45311.4 Application Case III: Semiconductor Industry 45311.4.1 AVM Deployment Example in the Semiconductor Industry 45311.4.1.1 AVM Deployment Example of the Etching Process 45411.4.1.2 Summary 45611.4.2 IPM Deployment Examples in the Semiconductor Industry 45611.4.2.1 Introducing the Bumping Production Tools for IPM Deployment 45611.4.2.2 Illustrative Example 45611.4.2.3 Summary 46011.4.3 IYM Deployment Examples in the Semiconductor Industry 46011.4.3.1 Introducing the Bumping Process of Semiconductor Manufacturing for IYM Deployment 46011.4.3.2 Illustrative Example 46011.4.3.3 Summary 46411.5 Application Case IV: Automotive Industry 46411.5.1 AMCoT and AVM Deployment Examples in Wheel Machining Automation (WMA) 46411.5.1.1 Integrating GED-plus-AVM (GAVM) into WMA for Total Inspection 46411.5.1.2 Applying AMCoT to WMA 46611.5.1.3 Applying AVM in AMCoT to WMA 46911.5.1.4 Summary 47211.5.2 Mass Customization (MC) Example for WMA 47211.5.2.1 Requirements of MC Production for WMA 47211.5.2.2 Considerations for Applying AVM in MC-Production of WMA 47311.5.2.3 The AVM-plus-Target-Value-Adjustment (TVA) Scheme for MC 47311.5.2.4 AVM-plus-TVA Deployment Example for WMA 47711.5.2.5 Summary 47811.6 Application Case V: Aerospace Industry 47811.6.1 Introducing the Engine-Case (EC) Manufacturing Process 47911.6.1.1 Manufacturing Processes of an EC 47911.6.1.2 Inspection Processes of the Flange Holes 47911.6.1.3 Literature Reviews 48011.6.2 Integrating GAVM into EC Manufacturing for Total Inspection 48111.6.2.1 Considerations of Applying AVM in EC Manufacturing 48111.6.3 The DF Scheme for Estimating the Flange Deformation of an EC 48211.6.3.1 Probing Scenario 48211.6.3.2 Ellipse-like Deformation of an EC 48311.6.3.3 Position Error 48611.6.3.4 Integrating the On-Line Probing, the DF Scheme, and the AVM Prediction 48811.6.4 Illustrative Examples 48811.6.4.1 Diameter Prediction 49011.6.4.2 Position Prediction 49011.6.5 Summary 49211.7 Application Case VI: Chemical Industry 49211.7.1 Introducing the Carbon-Fiber Manufacturing Process 49211.7.2 Three Preconditions of Applying AVM 49311.7.3 Challenges of Applying AVM to Carbon-Fiber Manufacturing 49411.7.3.1 CPA+AVM (CPAVM) Scheme for Carbon-Fiber Manufacturing 49411.7.3.2 AMCoT for Carbon-Fiber Manufacturing 49811.7.4 Illustrative Example 49811.7.4.1 Production Data Traceback (PDT) Mechanism for Work-in-Process (WIP) Tracking 49911.7.4.2 AVM for Carbon-Fiber Manufacturing 50011.7.5 Summary 50111.8 Application Case VII: Bottle Industry 50211.8.1 Bottle Industry and Its Intelligent Manufacturing Requirements 50211.8.1.1 Introducing the Blow-Molding Manufacturing Process 50211.8.2 Applying AVM to Blow Molding Manufacturing Process 50211.8.3 AVM-Based Run-to-Run (R2R) Control for Blow Molding Manufacturing Process 50311.8.4 Illustrative Example 50411.8.5 Summary 507Appendix 11.A – Abbreviation List 508Appendix 11.B – List of Symbols in Equations 512References 516Index 521