Intelligent Manufacturing Management Systems

Kamalakanta Muduli, PhD, is an associate professor in the Department of Mechanical Engineering, Papua New Guinea University of Technology, Papua New Guinea. He has over 15 years of academic and research experience and has published 40 papers in peer-reviewed international journals. V. P. Kommula, PhD, is an associate professor in the Department of Mechanical Engineering, University of Botswana. He has over 21 years of teaching experience and served in various positions with different universities in many countries. Kommula’s research is in the area of lean manufacturing and productivity improvement by adopting digital technologies. He has published 42 research articles in peer-reviewed international journals. Devendra K. Yadav, PhD, is an assistant professor in the Department of Mechanical Engineering, National Institute of Technology Calicut, Kerala, India. His current research interests include supply chain management, logistics performance measurement, and Industry 4.0 applications in supply chain domains. Chithirai Pon Selvan, PhD, is an associate professor at Curtin University, Dubai. He has over 21 years of experience in teaching and has published more than 100 research articles in journals. His research interests are in the areas of machine design, optimization techniques, and manufacturing practices. Jayakrishna Kandasamy, PhD, is an associate professor in the School of Mechanical Engineering, Vellore Institute of Technology University, India. He has published 47 journal articles in leading SCI journals, 22 book chapters, 85 contributions to refereed conference proceedings, and one edited book. Dr. Jayakrishna’s research is focused on the design and management of manufacturing systems and supply chains to enhance efficiency, productivity, and sustainability performance.

Preface xvii

Part I: Smart Technologies in Manufacturing 1

1 Smart Manufacturing Systems for Industry 4.0 3
Gaijinliu Gangmei and Polash Pratim Dutta

Abbreviations 3

1.1 Introduction 4

1.2 Research Methodology 5

1.3 Pillars of Smart Manufacturing 6

1.3.1 Manufacturing Technology and Processes 6

1.3.2 Materials 7

1.3.3 Data 8

1.3.4 Sustainability 8

1.3.5 Resource Sharing and Networking 9

1.3.6 Predictive Engineering 9

1.3.7 Stakeholders 10

1.3.8 Standardization 10

1.4 Enablers and Their Applications 11

1.4.1 Smart Design 12

1.4.2 Smart Machining 12

1.4.3 Smart Monitoring 13

1.4.4 Smart Control 13

1.4.5 Smart Scheduling 14

1.5 Assessment of Smart Manufacturing Systems 14

1.6 Challenges in Implementation of Smart Manufacturing Systems 15

1.6.1 Technological Issue 16

1.6.2 Methodological Issue 16

1.7 Implications of the Study for Academicians and Practitioners 17

1.8 Conclusion 17

References 18

2 Smart Manufacturing Technologies in Industry 4.0: Challenges and Opportunities 23
S. Deepak Kumar, G. Arun Manohar, R. Surya Teja, P. S. V. Ramana Rao, A. Mandal, Ajit Behera and P. Srinivasa Rao

Abbreviations 24

2.1 Introduction to Smart Manufacturing 24

2.1.1 Background of SM 24

2.1.2 Traditional Manufacturing versus Smart Manufacturing 25

2.1.3 Concept and Evolution of Industry 4.0 25

2.1.4 Motivations for Research in Smart Manufacturing 28

2.1.5 Objectives and Need of Industry 4.0 29

2.1.6 Research Methodology 30

2.1.7 Principles of I4. 0 30

2.1.8 Benefits/Advantages of Industry 4.0 31

2.2 Technology Pillars of Industry 4.0 31

2.2.1 Automation in Industry 4.0 33

2.2.1.1 Need of Automation 33

2.2.1.2 Components of Automation 33

2.2.1.3 Applications of Automation 34

2.2.2 Robots in Industry 4.0 34

2.2.2.1 Need of Robots 35

2.2.2.2 Advantages of Robots 35

2.2.2.3 Applications of Robots 37

2.2.2.4 Advances Robotics 37

2.2.3 Additive Manufacturing (AM) 38

2.2.3.1 Additive Manufacturing’s Potential Applications 39

2.2.4 Big Data Analytics 40

2.2.5 Cloud Computing 41

2.2.6 Cyber Security 43

2.2.6.1 Cyber-Security Challenges in Industry 4.0 43

2.2.7 Augmented Reality and Virtual Reality 44

2.2.8 Simulation 46

2.2.8.1 Need of Simulation in Smart Manufacturing 46

2.2.8.2 Advantages of Simulation 47

2.2.8.3 Simulation and Digital Twin 47

2.2.9 Digital Twins 47

2.2.9.1 Integration of Horizontal and Vertical Systems 48

2.2.10 IoT and IIoT in Industry 4.0 48

2.2.11 Artificial Intelligence in Industry 4.0 49

2.2.12 Implications of the Study for Academicians and Practitioners 51

2.3 Summary and Conclusions 51

2.3.1 Benefits of Industry 4.0 51

2.3.2 Challenges in Industry 4.0 52

2.3.3 Future Directions 52

Acknowledgement 53

References 53

3 IoT-Based Intelligent Manufacturing System: A Review 59
Hiranmoy Samanta, Pradip Kumar Talapatra, Kamal Golui and Pritam Chakraborty

3.1 Introduction 60

3.2 Literature Review 60

3.3 Research Procedure 64

3.3.1 The Beginning and Advancement of SM/IM 64

3.3.2 Beginning of SM/IM 64

3.3.3 Defining SM/IM 65

3.3.4 Potential of SM/IM 66

3.3.5 Statistical Analysis of SM/IM 68

3.3.6 Future Endeavour of SM/IM 68

3.3.7 Necessary Components of IoT Framework 69

3.3.8 Proposed System Based on IoT 71

3.3.9 Development of IoT in Industry 4.0 72

3.4 Smart Manufacturing 73

3.4.1 Re-Configurability Manufacturing System 73

3.4.2 RMS Framework Based Upon IoT 75

3.4.3 Machine Control 76

3.4.4 Machine Intelligence 77

3.4.5 Innovation and the IIoT 78

3.4.6 Wireless Technology 78

3.4.7 IP Mobility 78

3.4.8 Network Functionality Virtualization (NFV) 79

3.5 Academia Industry Collaboration 79

3.6 Conclusions 80

References 81

4 3D Printing Technology in Smart Manufacturing Systems for Efficient Production Process 85
Kali Charan Rath, Prasenjit Chatterjee, Pankajkumar Munibara Patro, Polaiah Bojja, Amaresh Kumar and Rashmi Prava Das

Abbreviations 86

4.1 Introduction and Literature Reviews 86

4.1.1 Motivation Behind the Study 88

4.1.2 Objective of the Chapter 89

4.2 Network in Smart Manufacturing System 89

4.2.1 Challenges for Smart Manufacturing Industries 90

4.2.2 Smart Manufacturing Current Market Scenario 93

4.3 Data Drives in Smart Manufacturing 93

4.3.1 Benefits of Data-Driven Manufacturing 94

4.4 Manufacturing of Product Through 3D Printing Process 97

4.4.1 3D Printing Technology 99

4.4.2 3D Printing Technologies Classification 100

4.4.3 3D Printer Parameters 101

4.4.4 Significance of Honeycomb Structure 102

4.4.5 Acrylonitrile Butadiene Styrene (ABS) Thermoplastic Polymer Used for Honeycomb Structures Model 103

4.4.6 3D Printing Parameters and Their Descriptions 107

4.5 Conclusion 107

References 109

5 Smart Inventory Control: Proposed Framework on Basis of IoT, RFID, and Supply Chain Management 113
Hiranmoy Samanta and Kamal Golui

5.1 Introduction 114

5.2 Objectives 114

5.3 Research Methodology 114

5.4 Literature Review 115

5.5 Components of SIM 116

5.5.1 Supply Chain Management (SCM) 116

5.5.2 Inventory Management System (IMS) 117

5.5.3 Internet of Things (IoT) 120

5.5.4 RFID System 121

5.5.5 Maintenance, Repair, and Operations 123

5.5.6 Deep Reinforcement Learning 125

5.6 Framework 127

5.7 Optimization 130

5.7.1 Inventory Optimization 130

5.8 Results and Discussion 131

5.9 A Mirror to Researchers and Managers 132

5.10 Conclusions 133

5.11 Future Scope 133

References 134

6 Application of Machine Learning in the Machining Processes: Future Perspective Towards Industry 4.0 141
Bikash Chandra Behera, Bikash Ranjan Moharana, Matruprasad Rout and Kishore Debnath

6.1 Introduction 142

6.2 Machine Learning 143

6.3 Smart Factory 146

6.4 Intelligent Machining 148

6.5 Machine Learning Processes Used in Machining Process 150

6.6 Performance Improvement of Machine Structure Using Machine Learning 152

6.7 Conclusions 153

References 153

7 Intelligent Machine Learning and Deep Learning Techniques for Bearings Fault Detection and Decision-Making Strategies 157
Jagadeesha T., Thutupalli Srinivasa Advaith, Choppala Sarath Wesley, Grandhi Sri Sai Charith and Doppalapudi Manohar

Abbreviations 158

7.1 Introduction 158

7.2 Literature Review 159

7.3 Methodology 161

7.3.1 Dataset Preparation 161

7.3.2 CWRU Dataset 161

7.3.3 Methodology Flow Chart 161

7.3.4 Data Pre-Processing 162

7.3.5 Models Deployed 163

7.3.6 Training and Testing 163

7.4 Analysis 164

7.4.1 Datasets 164

7.4.2 Feature Extraction 168

7.4.3 Splitting of Data into Samples 168

7.4.4 Algorithms Used 169

7.4.4.1 Multinomial Logistic Regression 169

7.4.4.2 K-Nearest Neighbors 170

7.4.4.3 Decision Tree 172

7.4.4.4 Support Vector Machine (SVM) 173

7.4.4.5 Random Forest 175

7.5 Results and Discussion 177

7.5.1 Importance of Classification Reports 177

7.5.2 Importance of Confusion Matrices 177

7.5.3 Decision Tree 178

7.5.4 Random Forest 180

7.5.5 K-Nearest Neighbors 182

7.5.6 Logistic Regression 185

7.5.7 Support Vector Machine 185

7.5.8 Comparison of the Algorithms 188

7.5.8.1 Accuracies 188

7.5.8.2 Precision and Recall 188

7.6 Conclusions 191

7.7 Scope of Future Work 191

References 192

8 Smart Vision-Based Sensing and Monitoring of Power Plants for a Clean Environment 195
K. Sujatha, R. Krishnakumar, N.P.G. Bhavani, U. Jayalatsumi, V. Srividhya, C. Kamatchi and R. Vani

8.1 Introduction 196

8.1.1 Color Image Processing 197

8.1.2 Motivation 199

8.1.3 Objectives 199

8.2 Literature Review 200

8.2.1 Gas Turbine Power Plants 200

8.2.2 Artificial Intelligent Methods 201

8.3 Materials and Methods 202

8.3.1 Feature Extraction 202

8.3.2 Classification 203

8.4 Results and Discussion 204

8.4.1 Fisher’s Linear Discriminant Function (FLDA) and Curvelet 204

8.5 Conclusion 219

8.5.1 Future Scope of Work 220

References 221

9 Implementation of FEM and Machine Learning Algorithms in the Design and Manufacturing of Laminated Composite Plate 223
Sidharth Patro, Trupti Ranjan Mahapatra, Romeo S. Fono Tamo, Allu Vikram Kishore Murty, Soumya Ranjan Parimanik and Debadutta Mishra

Abbreviations 224

9.1 Introduction 224

9.2 Numerical Experimentation Program 227

9.3 Discussion of the Results 239

9.4 Conclusion 244

Acknowledgements 245

References 245

Part II: Integration of Digital Technologies to Operations 249

10 Edge Computing-Based Conditional Monitoring 251
Granville Embia, Aezeden Mohamed, Bikash Ranjan Moharana and Kamalakanta Muduli

10.1 Introduction 252

10.1.1 Problem Statement 252

10.2 Literature Review 253

10.3 Edge Computing 257

10.4 Methodology 259

10.5 Discussion 263

10.5.1 Predictive Maintenance 263

10.5.2 Energy Efficiency Management 264

10.5.3 Smart Manufacturing 265

10.5.4 Conditional Monitoring via Edge Computing Locally 266

10.5.5 Lesson Learned 266

10.6 Conclusion 267

References 267

11 Optimization Methodologies in Intelligent Manufacturing Systems: Application and Challenges 271
Hiranmoy Samanta, Pradip Kumar Talapatra, Kamal Golui and Atiur Alam

11.1 Introduction 272

11.2 Literature Review 273

11.3 Intelligent Manufacturing System Framework 275

11.3.1 Principles of Developing Industry 4.0 Solutions 277

11.3.2 Quantitative Analysis 279

11.3.2.1 Optimization Characteristics and Requirements of Industry 4.0 279

11.3.3 Optimization Methodologies and Algorithms 281

11.4 Bayesian Networks (BNs) 287

11.4.1 Instance-Based Learning (IBL) 288

11.4.2 The IB1 Algorithm 288

11.4.3 Artificial Neural Networks 289

11.4.4 A Comparison Between Recurrent Neural Networks (RNN) and Convolutional Neural Networks (CNN) 291

11.5 Problems of Implementing Machine Learning in Manufacturing 293

11.6 Conclusions 293

References 294

12 Challenges of Warehouse Management Towards Smart Manufacturing: A Case of an Indian Consumer Electrical Company 297
Natarajan Ramanathan, Neeraj Vairagi, Sakti Parida, Sushanta Tripathy, Ashok Kumar Sar, Kumar Mohanty and Alisha Lakra

12.1 Introduction 298

12.2 Literature Review 300

12.2.1 Shortage of Space 301

12.2.2 Non-Moving Materials 301

12.2.3 Lack of Action on Liquidation 302

12.2.4 Defective Material from Both Ends 302

12.2.5 Gap Between the Demand and the Supply 302

12.2.6 Multiple Price Revision 303

12.2.7 More Manual Timing for Loading and Unloading 303

12.2.8 Operational Challenges for Seasonal Products 303

12.2.9 Lack of Automation 303

12.2.10 Manpower Balancing Between Peak and Off 304

12.3 The Proposed ISM Methodology 304

12.3.1 Establishment of the Structural Self-Interaction Matrix (SSIM) 306

12.3.2 Creation of the Reachability Matrix 307

12.3.3 Implementation of the Level Partitions 308

12.3.4 Classification of the Selected Challenges 309

12.3.5 Development of the Final ISM Model 310

12.4 Results and Discussion 311

12.5 Practical Implications 312

12.6 Conclusions 313

References 314

13 The Impact of Organizational Ergonomics on Teaching Rapid Prototyping 319
Yaone Rapitsenyane, Patience Erick, Oanthata Jester Sealetsa and Richie Moalosi

Abbreviations 320

13.1 Introduction 320

13.2 Organizational Ergonomics 322

13.2.1 Aim of Organizational Ergonomics 323

13.3 Rapid Prototyping and Teaching Rapid Prototyping 323

13.4 Industry 4.0 Factors Associated with Organizational Ergonomics in a Rapid Prototyping/Manufacturing Facility 325

13.4.1 Technology 326

13.4.2 Communication 327

13.4.3 Teamwork 328

13.4.4 Human Resource 328

13.4.5 Quality Management 329

13.5 Implications of Industry 4.0 on Prototyping and Prototyping Facilities in Design Schools 329

13.6 The Influence of Cooperative Working Ergonomics of Distributed Manufacturing in Teaching and Learning Rapid Prototyping 332

13.7 Health and Safety in Rapid Prototyping Laboratories 333

13.7.1 Common Health Hazards in 3D Printing 333

13.7.2 Chemical Hazards 335

13.7.3 Flammable/Explosion Hazards 336

13.7.4 UV and Laser Radiation Hazard 336

13.7.5 Other Hazards 336

13.7.6 Hazard Controls 337

13.7.7 Engineering Controls 337

13.7.8 Administrative Controls 338

13.7.9 Personal Protective Equipment 338

13.8 Impact of Digital/Rapid Prototyping on Organizational Ergonomics 339

13.9 Implications of the Study for Academicians and Practitioners 340

13.10 Conclusions and Future Work 341

References 343

14 Sustainable Manufacturing Practices through Additive Manufacturing: A Case Study on a Can-Making Manufacturer 349
Kiren Piso, Aezeden Mohamed, Bikash Ranjan Moharana, Kamalakanta Muduli and Noorhafiza Muhammad

14.1 Introduction 350

14.2 Literature Review 352

14.3 Research Set Up 354

14.4 Additive Manufacturing Techniques 356

14.4.1 Types of Additive Manufacturing 356

14.4.1.1 Fused Deposition Modelling (FDM) 356

14.4.1.2 Stereolithography (SLA) 356

14.4.1.3 Selective Laser Sintering (SLS) 357

14.4.1.4 Direct Energy Deposition (DED) 357

14.4.1.5 Digital Light Processing (DLP) 358

14.5 Strategies Used by Production Company 358

14.5.1 Maintenance Strategies 358

14.5.1.1 Breakdown Maintenance (BM) 358

14.5.1.2 Preventive Maintenance (PM) 358

14.5.1.3 Periodic Maintenance (Time Based Maintenance – TBM) 359

14.5.1.4 Predictive Maintenance (PM) 359

14.5.1.5 Corrective Maintenance (CM) 359

14.5.1.6 Maintenance Prevention (PM) 359

14.5.2 Inventory Control in Manufacturing 359

14.5.2.1 Inventory Control and Maintenance in Manufacturing 360

14.5.2.2 Warehouse Storages 360

14.5.3 Time Factor in Manufacturing 361

14.5.3.1 Breakdown Time 361

14.5.3.2 Set-Up Time 361

14.5.3.3 Manned Time (Available Time) 361

14.5.3.4 Operating Working Time 361

14.5.3.5 Operating Time 362

14.5.3.6 Production Time 362

14.6 Sustainable Manufacturing 362

14.6.1 Social Aspect of Sustainable Manufacturing 363

14.6.2 Environmental Aspects of Sustainable Manufacturing 364

14.6.3 Economical Aspect of Sustainable Manufacturing 364

14.7 Sustainable Additive Manufacturing 365

14.7.1 Energy 365

14.7.2 Cost 366

14.7.2.1 Downtime Cost 366

14.7.3 Supply Chain 368

14.7.4 Maintenance with Additive Manufacturing 368

14.8 Additive Manufacturing with IFC CMD: A Case Study 369

14.9 Contribution of Additive Manufacturing Towards Sustainability 370

14.10 Limitations of Additive Manufacturing 372

14.11 Conclusions and Recommendations 373

References 373

Index 377