Industry 4.1
Description
Discover the future of manufacturing with this comprehensive introduction to Industry 4.0 technologies from a celebrated expert in the field
Industry 4.1: Intelligent Manufacturing with Zero Defects delivers an in-depth exploration of the functions of intelligent manufacturing and its applications and implementations through the Intelligent Factory Automation (iFA) System Platform. The book's distinguished editor offers readers a broad range of resources that educate and enlighten on topics as diverse as the Internet of Things, edge computing, cloud computing, and cyber-physical systems.
You'll learn about three different advanced prediction technologies: Automatic Virtual Metrology (AVM), Intelligent Yield Management (IYM), and Intelligent Predictive Maintenance (IPM). Different use cases in a variety of manufacturing industries are covered, including both high-tech and traditional areas.
In addition to providing a broad view of intelligent manufacturing and covering fundamental technologies like sensors, communication standards, and container technologies, the book offers access to experimental data through the IEEE DataPort. Finally, it shows readers how to build an intelligent manufacturing platform called an Advanced Manufacturing Cloud of Things (AMCoT).
Readers will also learn from:
* An introduction to the evolution of automation and development strategy of intelligent manufacturing
* A comprehensive discussion of foundational concepts in sensors, communication standards, and container technologies
* An exploration of the applications of the Internet of Things, edge computing, and cloud computing
* The Intelligent Factory Automation (iFA) System Platform and its applications and implementations
* A variety of use cases of intelligent manufacturing, from industries like flat-panel, semiconductor, solar cell, automotive, aerospace, chemical, and blow molding machine
Perfect for researchers, engineers, scientists, professionals, and students who are interested in the ongoing evolution of Industry 4.0 and beyond, Industry 4.1: Intelligent Manufacturing with Zero Defects will also win a place in the library of laypersons interested in intelligent manufacturing applications and concepts. Completely unique, this book shows readers how Industry 4.0 technologies can be applied to achieve the goal of Zero Defects for all product
More details
Other editions
Additional editions
Person
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.
Content
Editor Biography xv
List of Contributors xvii
Preface xix
Acknowledgments xxi
Foreword xxiii
1 Evolution of Automation and Development Strategy of Intelligent Manufacturing with Zero Defects 1
Fan-Tien Cheng
1.1 Introduction 1
1.2 Evolution of Automation 1
1.2.1 e-Manufacturing 1
1.2.1.1 Manufacturing Execution System (MES) 3
1.2.1.2 Supply Chain (SC) 6
1.2.1.3 Equipment Engineering System (EES) 7
1.2.1.4 Engineering Chain (EC) 9
1.2.2 Industry 4.0 10
1.2.2.1 Definition and Core Technologies of Industry 4.0 10
1.2.2.2 Migration from e-Manufacturing to Industry 4.0 12
1.2.2.3 Mass Customization 12
1.2.3 Zero Defects - Vision of Industry 4.1 13
1.2.3.1 Two Stages of Achieving Zero Defects 14
1.3 Development Strategy of Intelligent Manufacturing with Zero Defects 14
1.3.1 Five-Stage Strategy of Yield Enhancement and Zero-Defects Assurance 15
1.4 Conclusion 18
Appendix 1.A - Abbreviation List 18
References 20
2 Data Acquisition and Preprocessing 25
Hao Tieng, Haw-Ching Yang, and Yu-Yong Li
2.1 Introduction 25
2.2 Data Acquisition 26
2.2.1 Process Data Acquisition 26
2.2.1.1 Sensing Signals Acquisition 26
2.2.1.2 Manufacturing Parameters Acquisition 35
2.2.2 Metrology Data Acquisition 36
2.3 Data Preprocessing 37
2.3.1 Segmentation 37
2.3.2 Cleaning 38
2.3.2.1 Trend Removal 39
2.3.2.2 Wavelet Thresholding 41
2.3.3 Feature Extraction 43
2.3.3.1 Time Domain 43
2.3.3.2 Frequency Domain 47
2.3.3.3 Time-Frequency Domain 49
2.3.3.4 Autoencoder 52
2.4 Case Studies 53
2.4.1 Detrending of the Thermal Effect in Strain Gauge Data 53
2.4.2 Automated Segmentation of Signal Data 55
2.4.3 Tool State Diagnosis 57
2.4.4 Tool Diagnosis using Loading Data 61
2.5 Conclusion 64
Appendix 2.A - Abbreviation List 64
Appendix 2.B - List of Symbols in Equations 65
References 67
3 Communication Standards 69
Fan-Tien Cheng, Hao Tieng, and Yu-Chen Chiu
3.1 Introduction 69
3.2 Communication Standards of the Semiconductor Equipment 69
3.2.1 Manufacturing Portion 69
3.2.1.1 SEMI Equipment Communication Standard I (SECS-I) (SEMI E4) 70
3.2.1.2 SEMI Equipment Communication Standard II (SECS-II) (SEMI E5) 75
3.2.1.3 Generic Model for Communications and Control of Manufacturing Equipment (GEM) (SEMI E30) 81
3.2.1.4 High-Speed SECS Message Services (HSMS) (SEMI E37) 84
3.2.2 Engineering Portion (Interface A) 91
3.2.2.1 Authentication & Authorization (A&A) (SEMI E132) 93
3.2.2.2 Common Equipment Model (CEM) (SEMI E120) 95
3.2.2.3 Equipment Self-Description (EqSD) (SEMI E125) 95
3.2.2.4 Equipment Data Acquisition (EDA) Common Metadata (ECM) (SEMI E164) 98
3.2.2.5 Data Collection Management (DCM) (SEMI E134) 102
3.3 Communication Standards of the Industrial Devices and Systems 107
3.3.1 Historical Roadmaps of Classic Open Platform Communications (OPC) and OPC Unified Architecture (OPC-UA) Protocols 108
3.3.1.1 Classic OPC 108
3.3.1.2 OPC-UA 109
3.3.2 Fundamentals of OPC-UA 110
3.3.2.1 Requirements 110
3.3.2.2 Foundations 111
3.3.2.3 Specifications 112
3.3.2.4 System Architecture 112
3.3.3 Example of Intelligent Manufacturing Hierarchy Applying OPC-UA Protocol 119
3.3.3.1 Equipment Application Program (EAP) Server 121
3.3.3.2 Use Cases of Data Manipulation 122
3.3.3.3 Sequence Diagrams of Data Manipulation 123
3.4 Conclusion 125
Appendix 3.A - Abbreviation List 125
References 128
4 Cloud Computing, Internet of Things (IoT), Edge Computing, and Big Data Infrastructure 129
Hung-Chang Hsiao, Min-Hsiung Hung, Chao-Chun Chen, and Yu-Chuan Lin
4.1 Introduction 129
4.2 Cloud Computing 131
4.2.1 Essentials of Cloud Computing 131
4.2.2 Cloud Service Models 132
4.2.3 Cloud Deployment Models 134
4.2.4 Cloud Computing Applications in Manufacturing 137
4.2.5 Summary 142
4.3 IoT and Edge Computing 142
4.3.1 Essentials of IoT 142
4.3.2 Essentials of Edge Computing 146
4.3.3 Applications of IoT and Edge Computing in Manufacturing 148
4.3.4 Summary 150
4.4 Big Data Infrastructure 150
4.4.1 Application Demands 150
4.4.2 Core Software Stack Components 152
4.4.3 Bridging the Gap between Core Software Stack Components and Applications 153
4.4.3.1 Hadoop Data Service (HDS) 153
4.4.3.2 Distributed R Language Computing Service (DRS) 156
4.4.4 Summary 159
4.5 Conclusion 159
Appendix 4.A - Abbreviation List 160
Appendix 4.B - List of Symbols in Equations 162
References 162
5 Docker and Kubernetes 169
Chao-Chun Chen, Min-Hsiung Hung, Kuan-Chou Lai, and Yu-Chuan Lin
5.1 Introduction 169
5.2 Fundamentals of Docker 173
5.2.1 Docker Architecture 173
5.2.1.1 Docker Engine 174
5.2.1.2 High-Level Docker Architecture 174
5.2.1.3 Architecture of Linux Docker Host 176
5.2.1.4 Architecture of Windows Docker Host 177
5.2.1.5 Architecture of Windows Server Containers 177
5.2.1.6 Architecture of Hyper-V Containers 178
5.2.2 Docker Operational Principles 178
5.2.2.1 Docker Image 178
5.2.2.2 Dockerfile 179
5.2.2.3 Docker Container 183
5.2.2.4 Container Network Model 184
5.2.2.5 Docker Networking 185
5.2.3 Illustrative Applications of Docker 187
5.2.3.1 Workflow of Building, Shipping, and Deploying a Containerized Application 188
5.2.3.2 Deployment of a Docker Container Running a Linux Application 189
5.2.3.3 Deployment of a Docker Container Running a Windows Application 191
5.2.4 Summary 194
5.3 Fundamentals of Kubernetes 195
5.3.1 Kubernetes Architecture 195
5.3.1.1 Kubernetes Control Plane Node 195
5.3.1.2 Kubernetes Worker Nodes 197
5.3.1.3 Kubernetes Objects 199
5.3.2 Kubernetes Operational Principles 200
5.3.2.1 Deployment 200
5.3.2.2 High Availability and Self-Healing 200
5.3.2.3 Ingress 202
5.3.2.4 Replication 204
5.3.2.5 Scheduler 204
5.3.2.6 Autoscaling 205
5.3.3 Illustrative Applications of Kubernetes 205
5.3.4 Summary 209
5.4 Conclusion 209
Appendix 5.A - Abbreviation List 210
References 211
6 Intelligent Factory Automation (iFA) System Platform 215
Fan-Tien Cheng
6.1 Introduction 215
6.2 Architecture Design of the Advanced Manufacturing Cloud of Things (AMCoT) Framework 215
6.3 Brief Description of the Automatic Virtual Metrology (AVM) Server 218
6.4 Brief Description of the Baseline Predictive Maintenance (BPM) Scheme in the Intelligent Prediction Maintenance (IPM) Server 218
6.5 Brief Description of the Key-variable Search Algorithm (KSA) Scheme in the Intelligent Yield Management (IYM) Server 219
6.6 The iFA System Platform 220
6.6.1 Cloud-based iFA System Platform 220
6.6.2 Server-based iFA System Platform 221
6.7 Conclusion 222
Appendix 6.A - Abbreviation List 222
Appendix 6.B - List of Symbols 224
References 224
7 Advanced Manufacturing Cloud of Things (AMCoT) Framework 225
Min-Hsiung Hung, Chao-Chun Chen, and Yu-Chuan Lin
7.1 Introduction 225
7.2 Key Components of AMCoT Framework 227
7.2.1 Key Components of Cloud Part 227
7.2.2 Key Components of Factory Part 229
7.2.3 An Example Intelligent Manufacturing Platform Based on AMCoT Framework 229
7.2.4 Summary 231
7.3 Framework Design of Cyber-Physical Agent (CPA) 231
7.3.1 Framework of CPA 231
7.3.2 Framework of Containerized CPA (CPAC) 232
7.3.3 Summary 233
7.4 Rapid Construction Scheme of CPAs (RCSCPA) Based on Docker and Kubernetes 234
7.4.1 Background and Motivation 234
7.4.2 System Architecture of RCSCPA 235
7.4.3 Core Functional Mechanisms of RCSCPA 236
7.4.3.1 Horizontal Auto-Scaling Mechanism 237
7.4.3.2 Load Balance Mechanism 238
7.4.3.3 Failover Mechanism 238
7.4.4 Industrial Case Study of RCSCPA 239
7.4.4.1 Experimental Setup 239
7.4.4.2 Testing Results 239
7.4.5 Summary 242
7.5 Big Data Analytics Application Platform 242
7.5.1 Architecture of Big Data Analytics Application Platform 242
7.5.2 Performance Evaluation of Processing Big Data 243
7.5.3 Big Data Analytics Application in Manufacturing - Electrical Discharge Machining 245
7.5.4 Summary 247
7.6 Manufacturing Services Automated Construction Scheme (MSACS) 248
7.6.1 Background and Motivation 248
7.6.2 Design of Three-Phase Workflow of MSACS 249
7.6.3 Architecture Design of MSACS 251
7.6.4 Designs of Core Components 252
7.6.4.1 Design of Key Information (KI) Extractor 252
7.6.4.2 Design of Library Information (Lib. Info.) Template 255
7.6.4.3 Design of Service Interface Information (SI Info.) Template 256
7.6.4.4 Design of Web Service Package (WSP) Generator 256
7.6.4.5 Design of Service Constructor 261
7.6.5 Industrial Case Studies 262
7.6.5.1 Web Graphical User Interface (GUI) of MSACS 262
7.6.5.2 Case Study 1: Automated Construction of the AVM Cloud-based Manufacturing (CMfg) Service for Validating the Efficacy of MSACS 262
7.6.5.3 Case Study 2: Performance Evaluation of MSACS 264
7.6.6 Summary 265
7.7 Containerized MSACS (MSACSC) 266
7.8 Conclusion 268
Appendix 7.A - Abbreviation List 269
Appendix 7.B - Patents (AMCoT + CPA) 270
References 271
8 Automatic Virtual Metrology (AVM) 275
Fan-Tien Cheng
8.1 Introduction 275
8.1.1 Survey of Virtual Metrology (VM)-Related Literature 276
8.1.2 Necessity of Applying VM 277
8.1.3 Benefits of VM 278
8.2 Evolution of VM and Invention of AVM 282
8.2.1 Invention of AVM 283
8.3 Integrating AVM Functions into the Manufacturing Execution System (MES) 287
8.3.1 Operating Scenarios among AVM, MES Components, and Run-to-Run (R2R) Controllers 289
8.4 Applying AVM for Workpiece-to-Workpiece (W2W) Control 292
8.4.1 Background Materials 293
8.4.2 Fundamentals of Applying AVM for W2W Control 295
8.4.3 R2R Control Utilizing VM with Reliance Index (RI) and Global Similarity Index (GSI) 299
8.4.4 Illustrative Examples 300
8.4.5 Summary 313
8.5 AVM System Deployment 313
8.5.1 Automation Levels of VM Systems 313
8.5.2 Deployment of the AVM System 315
8.6 Conclusion 318
Appendix 8.A - Abbreviation List 319
Appendix 8.B - List of Symbols in Equations 321
Appendix 8.C - Patents (AVM) 323
References 326
9 Intelligent Predictive Maintenance (IPM) 331
Yu-Chen Chiu, Yu-Ming Hsieh, Chin-Yi Lin, and Fan-Tien Cheng
9.1 Introduction 331
9.1.1 Necessity of Baseline Predictive Maintenance (BPM) 332
9.1.2 Prediction Algorithms of Remaining Useful Life (RUL) 333
9.1.3 Introducing the Factory-wide IPM System 334
9.2 BPM 334
9.2.1 Important Samples Needed for Creating Target-Device Baseline Model 337
9.2.2 Samples Needed for Creating Baseline Individual Similarity Index (ISIB) Model 338
9.2.3 Device-Health-Index (DHI) Module 338
9.2.4 Baseline-Error-Index (BEI) Module 339
9.2.5 Illustration of Fault-Detection-and-Classification (FDC) Logic 340
9.2.6 Flow Chart of Baseline FDC Execution Procedure 340
9.2.7 Exponential-Curve-Fitting (ECF) RUL Prediction Module 340
9.3 Time-Series-Prediction (TSP) Algorithm for Calculating RUL 344
9.3.1 ABPM Scheme 345
9.3.2 Problems Encountered with the ECF Model 346
9.3.3 Details of the TSP Algorithm 346
9.3.3.1 AR Model 348
9.3.3.2 MA Model 349
9.3.3.3 ARMA and ARIMA Models 349
9.3.3.4 TSP Algorithm 349
9.3.3.5 Pre-Alarm Module 352
9.3.3.6 Death Correlation Index 353
9.4 Factory-Wide IPM Management Framework 354
9.4.1 Management View and Equipment View of a Factory 354
9.4.2 Health Index Hierarchy (HIH) 355
9.4.3 Factory-wide IPM System Architecture 356
9.5 IPM System Implementation Architecture 359
9.5.1 Implementation Architecture of IPMC based on Docker and Kubernetes 359
9.5.2 Construction and Implementation of the IPMC 361
9.6 IPM System Deployment 364
9.7 Conclusion 367
Appendix 9.A - Abbreviation List 367
Appendix 9.B - List of Symbols in Equations 370
Appendix 9.C - Patents (IPM) 371
References 372
10 Intelligent Yield Management (IYM) 377
Yu-Ming Hsieh, Chin-Yi Lin, and Fan-Tien Cheng
10.1 Introduction 377
10.1.1 Traditional Root-Cause Search Procedure of a Yield Loss 379
10.1.2 IYM System 380
10.1.3 Procedure for Finding the Root Causes of a Yield Loss by Applying the Key-variable Search Algorithm (KSA) Scheme 380
10.2 KSA Scheme 381
10.2.1 Data Preprocessing Module 382
10.2.2 KSA Module 382
10.2.2.1 Triple Phase Orthogonal Greedy Algorithm (TPOGA) 382
10.2.2.2 Automated Least Absolute Shrinkage and Selection Operator (ALASSO) 384
10.2.2.3 Reliance Index of KSA (RIK) Module 385
10.2.3 Blind-stage Search Algorithm (BSA) Module 386
10.2.3.1 Blind Cases 387
10.2.3.2 Blind-stage Search Algorithm 390
10.2.4 Interaction-Effect Search Algorithm (IESA) Module 393
10.2.4.1 Interaction-Effect 393
10.2.4.2 Interaction-Effect Search Algorithm 396
10.3 IYM System Deployment 401
10.4 Conclusion 402
Appendix 10.A - Abbreviation List 402
Appendix 10.B - List of Symbols in Equations 403
Appendix 10.C - Patents (IYM) 405
References 406
11 Application Cases of Intelligent Manufacturing 409
Fan-Tien Cheng, Yu-Chen Chiu, Yu-Ming Hsieh, Hao Tieng, Chin-Yi Lin, and Hsien-Cheng Huang
11.1 Introduction 409
11.2 Application Case I: Thin Film Transistor Liquid Crystal Display (TFT-LCD) Industry 409
11.2.1 Automatic Virtual Metrology (AVM) Deployment Examples in the TFT-LCD Industry 409
11.2.1.1 Introducing the TFT-LCD Production Tools and Manufacturing Processes for AVM Deployment 410
11.2.1.2 AVM Deployment Types for TFT-LCD Manufacturing 413
11.2.1.3 Illustrative Examples 418
11.2.1.4 Summary 425
11.2.2 Intelligent Yield Management (IYM) Deployment Examples in the TFT-LCD Industry 425
11.2.2.1 Introducing the TFT-LCD Production Tools and Manufacturing Processes for IYM Deployment 425
11.2.2.2 KSA Deployment Example 426
11.2.2.3 Summary 432
11.3 Application Case II: Solar Cell Industry 432
11.3.1 Introducing the Solar Cell Manufacturing Process and Requirement Analysis of Intelligent Manufacturing 433
11.3.2 T2T Control with AVM Deployment Examples 434
11.3.2.1 T2T+VM Control Scheme with RI&GSI 435
11.3.2.2 Illustrative Examples of T2T Control with AVM 437
11.3.3 Factory-Wide Intelligent Predictive Maintenance (IPM) Deployment Examples 444
11.3.3.1 Illustrative Examples of BPM and RUL Prediction 444
11.3.3.2 Illustrative Example of Factory-Wide IPM System 451
11.3.4 Summary 453
11.4 Application Case III: Semiconductor Industry 453
11.4.1 AVM Deployment Example in the Semiconductor Industry 453
11.4.1.1 AVM Deployment Example of the Etching Process 454
11.4.1.2 Summary 456
11.4.2 IPM Deployment Examples in the Semiconductor Industry 456
11.4.2.1 Introducing the Bumping Production Tools for IPM Deployment 456
11.4.2.2 Illustrative Example 456
11.4.2.3 Summary 460
11.4.3 IYM Deployment Examples in the Semiconductor Industry 460
11.4.3.1 Introducing the Bumping Process of Semiconductor Manufacturing for IYM Deployment 460
11.4.3.2 Illustrative Example 460
11.4.3.3 Summary 464
11.5 Application Case IV: Automotive Industry 464
11.5.1 AMCoT and AVM Deployment Examples in Wheel Machining Automation (WMA) 464
11.5.1.1 Integrating GED-plus-AVM (GAVM) into WMA for Total Inspection 464
11.5.1.2 Applying AMCoT to WMA 466
11.5.1.3 Applying AVM in AMCoT to WMA 469
11.5.1.4 Summary 472
11.5.2 Mass Customization (MC) Example for WMA 472
11.5.2.1 Requirements of MC Production for WMA 472
11.5.2.2 Considerations for Applying AVM in MC-Production of WMA 473
11.5.2.3 The AVM-plus-Target-Value-Adjustment (TVA) Scheme for MC 473
11.5.2.4 AVM-plus-TVA Deployment Example for WMA 477
11.5.2.5 Summary 478
11.6 Application Case V: Aerospace Industry 478
11.6.1 Introducing the Engine-Case (EC) Manufacturing Process 479
11.6.1.1 Manufacturing Processes of an EC 479
11.6.1.2 Inspection Processes of the Flange Holes 479
11.6.1.3 Literature Reviews 480
11.6.2 Integrating GAVM into EC Manufacturing for Total Inspection 481
11.6.2.1 Considerations of Applying AVM in EC Manufacturing 481
11.6.3 The DF Scheme for Estimating the Flange Deformation of an EC 482
11.6.3.1 Probing Scenario 482
11.6.3.2 Ellipse-like Deformation of an EC 483
11.6.3.3 Position Error 486
11.6.3.4 Integrating the On-Line Probing, the DF Scheme, and the AVM Prediction 488
11.6.4 Illustrative Examples 488
11.6.4.1 Diameter Prediction 490
11.6.4.2 Position Prediction 490
11.6.5 Summary 492
11.7 Application Case VI: Chemical Industry 492
11.7.1 Introducing the Carbon-Fiber Manufacturing Process 492
11.7.2 Three Preconditions of Applying AVM 493
11.7.3 Challenges of Applying AVM to Carbon-Fiber Manufacturing 494
11.7.3.1 CPA+AVM (CPAVM) Scheme for Carbon-Fiber Manufacturing 494
11.7.3.2 AMCoT for Carbon-Fiber Manufacturing 498
11.7.4 Illustrative Example 498
11.7.4.1 Production Data Traceback (PDT) Mechanism for Work-in-Process (WIP) Tracking 499
11.7.4.2 AVM for Carbon-Fiber Manufacturing 500
11.7.5 Summary 501
11.8 Application Case VII: Bottle Industry 502
11.8.1 Bottle Industry and Its Intelligent Manufacturing Requirements 502
11.8.1.1 Introducing the Blow-Molding Manufacturing Process 502
11.8.2 Applying AVM to Blow Molding Manufacturing Process 502
11.8.3 AVM-Based Run-to-Run (R2R) Control for Blow Molding Manufacturing Process 503
11.8.4 Illustrative Example 504
11.8.5 Summary 507
Appendix 11.A - Abbreviation List 508
Appendix 11.B - List of Symbols in Equations 512
References 516
Index 521
Foreword
Since the term "Industry 4.0" was coined in Germany in 2011, industries worldwide have been investing in the development of smart factories that are more efficient and better adaptive to digital transformation to enhance their service-oriented and customized-supply capabilities.
To take Industry 4.0 a step further, Professor Fan-Tien Cheng proposed the upgraded version of Industry 4.1, core to which is the realization of Zero Defects, a solution taking advantage of the newly developed Intelligent Factory Automation (iFA) System Platform to address the production quality issue that has received relatively scant attention in Industry 4.0. To put into practice Zero Defects as well as in response to the Intelligent Manufacturing Industry Innovation policy of the Taiwan, ROC government, he further established the Intelligent Manufacturing Research Center (iMRC) at National Cheng Kung University (NCKU) in 2018.
As NCKU's President, I always take great pride in the achievements of all my colleagues and students. In the latest Times Higher Education (THE) Impact Rankings 2020, NCKU is ranked first in Taiwan, ROC, second in the Asia region, and 38th globally. It excels especially in "Industry, Innovations, and Infrastructure," one of United Nation's 17 Sustainable Development Goals (SDGs), and earns the 10th place worldwide. Professor Cheng's innovative research has played a critical role in this intense competition because, as I understand it, his Industry 4.1 and Intelligent Manufacturing are key to NCKU's success in the SDG of "Industry, Innovations, and Infrastructure" and NCKU's continuous leadership in the Engineering field.
As NCKU is accelerating its research momentum, especially in disciplines of traditional strengths like Intelligent Manufacturing and Engineering, I am glad that Professor Cheng is willing to share his valuable research and industry-university cooperation experiences in this book, one that will become an important reference not only for students but professors and researchers alike, and not only at NCKU but in industries and higher education worldwide whose focus is Intelligent Manufacturing.
This book not only details the essentials that have paved the way from Industry 4.0 to Industry 4.1 but also provides numerous practical industrial application cases in different manufacturing industries. It thus offers readers a comprehensive perspective of what they are and will be facing in the industry. I am sure this book is fundamental - a must-have indeed - for researchers, engineers, and focused students in the fields of, among others, Intelligent Manufacturing and Industry 4.1.
Huey-Jen Su
President, National Cheng Kung University (NCKU)
Industry 4.0 is a confluence of trends and technologies for the fourth industrial revolution. It has been "pushed" by the digital revolution over the past many decades and the recent Internet of Things (IoT); and "pulled" by demand from customers for high quality and customized products at reasonable prices and lead times. With (i) the ubiquitous connection and interaction of machines, things, and people; (ii) the integration of cyber and physical systems; and (iii) the emerging of disruptive technologies such as big data, machine learning, artificial intelligence, 3D printing and robotics, the ways we design and manufacture products and provide services are undergoing fundamental changes.
Although much R&D progress has been made, industries have been slow to develop effective holistic Industry 4.0 strategies. From a recent survey of 2000 C-suite executives by Deloitte (https://www2.deloitte.com/content/dam/insights/us/articles/us32959-industry-4-0/DI_Industry4.0.pdf), only 10% of the executives surveyed indicated they had long-range strategies to leverage new technologies that reach across their organizations. This is not surprising since creating and implementing holistic Industry 4.0 strategies are complicated, and require deep understanding, sharp vision, inspirational leadership, and resolute persistence. Among those with comprehensive Industry 4.0 strategies, the results have been impressive: 73% of those with a strategy report success in protecting their businesses from disruption, versus 12% of those with more scattershot approaches; 61% of those with Industry 4.0 strategies report that they have developed innovative products and services, versus 12% of those lacking strategies; and 60% of those with Industry 4.0 strategies report that they have found growth opportunities for existing products and services, versus 8% of those lacking strategies. Those companies with strategies also are growing more financially, and making more progress investing in technologies that have a positive societal impact.
Consider specifically a key area of Industry 4.0, the quality of products and processes. It is well-known that a host of methods and processes such as Statistical Process Control (SPC), Zero Defect Manufacturing (ZDM), Six Sigma Methodologies, Preventive Maintenance (PM), Continuous Improvement (Kaizen), Total Quality Management (TQM), etc., have been around for years and are contributing to the quality of products and processes. Integrating the digital revolution, the Internet of Things, big data, machine learning, and artificial intelligence to raise the quality of products and processes to a new level and with practical and scalable implementations, however, remains a major challenge for scholars, practitioners, and C-suite executives alike.
This book "Industry 4.1 - Intelligent Manufacturing with Zero Defects" focuses on improving the quality of products and processes, and is the culmination of the brilliant but down-to-the-earth efforts of the team led by Professor Fan-Tien Cheng over the past many years. The efforts started with Virtual Metrology. In view of the incompatible paces of fast production and slow metrology, 100% inspection is impossible, and sample inspection has been the practice. With the advancements in sensing, metrology, analytics and Industry 4.0 technologies, the team innovatively integrated physical metrology with its cyber counterparts, Virtual Metrology (VM). The resulting Automatic Virtual Metrology (AVM) system presented in this book is capable of predicting the quality of a product based on machine parameters, sensor data in the production equipment, and off-line sampling measurements. It also provides on-line and real-time total inspection of all work pieces to timely detect abnormalities during production. As a result, the sampling rate of real measurements can be cut down, the production costs can be reduced, and the goal of nearly zero defects of deliverables can be achieved.
Effective implementation of Automatic Virtual Metrology, however, is not easy, especially if we want it to be scalable to large factories and transferrable to other companies and other industries. Major infrastructure needs to be established efficiently and flexibly. Based on the team's successful research, development, implementation, and redeployment at many factories and across multiple industries, this book methodically presents the essential infrastructure components. The content includes data collection and management and feature extraction; communication standards; computation infrastructure of cloud, edge, Internet of Things and big data; container-related software development, deployment, and management technologies of Docker and Kubernetes; the overall architecture of the advanced manufacturing "Cloud of Things" framework, and the specific design and implementation of key components such as cyber-physical agents, big data analytics application platform, the automated construction scheme for manufacturing services, and AVM and other servers.
Extending the ideas, methods, and infrastructure presented above, the book then focuses on Intelligent Predictive Maintenance (IPM). Predictive maintenance, sometimes known as "condition-based maintenance," is to monitor the performance and conditions of equipment during operations to predict when equipment performance is deteriorating and when equipment is going to fail, followed by scheduled or corrective maintenance. Intelligent Predictive Maintenance presented in this book detects the abnormality of key components of manufacturing tools based on advanced fault detection and classification techniques and predicts their Remaining Useful Lives (RUL) using time series prediction algorithms. Factory-wide implementation is then discussed to improve tool availability and prevent unscheduled down of manufacturing tools.
Since modern manufacturing facilities are generally capital intensive, it is critical to have consistently high yields to justify the investment and to have a positive bottom line. Intelligent Yield Management (IYM) presented in this book is a closely related cousin of Intelligent Predictive Maintenance, with the purpose to effectively detect root causes that affect the yield. It consists of data collection and management; statistical, big data, and machine learning tools for defect and yield analysis; and timely resolution of issues discovered while maintaining the requisite quality and reliability standards. The kernel of the above is the "Key-variable Search Algorithm" (KSA), which includes new root-cause search methods for solving the high-dimensional variable...
