1st Edition
Intelligent Manufacturing Systems Digitalization of Industrial Production
Chapter 1: Transformer Based Computer Vision Technique for Improving Manufacturing Quality
1.1 Evolution of Computer Vision Applications in Manufacturing
1.1.1 Computer Vision in Manufacturing
1.2 Introduction
1.2.1 Vision Transformer
1.2.2 Role of Vision Transformer in Manufacturing
1.2.3 Challenges and Applications in ViT
1.3 Literature Review
1.4 Proposed Methodology
1.4.1 Data Pre-processing
1.4.2 Model Architecture
1.4.3 Convolutional Neural Networks
1.4.4 Vision Transformers
1.4.5 Loss Function and Position Monitoring
1.5 Use Case Description
1.6 Comparative Analysis of CNN and ViT for Casting Defect Detection
1.7 Results and Discussion
1.7.1 Training and Validation Loss
1.7.2 Training and Validation Accuracy
1.7.3 Class Distribution
1.7.4 Predicted Probabilities Distribution
1.8 Conclusion
References
Chapter 2: Production and Operations Management for Intelligent Manufacturing
2.1 Integration and Production and Operations Management in Intelligent Manufacturing
2.2. IMS techniques in Total Quality Management
2.2.1. Impact of AI/ML on TQM function
2.2.2. IoT and TQM
2.2.3 Robotics and Automation in TQM
2.2.4 Big Data Analytics in TQM
2.2.5 Digital Twins and Simulation in TQM
2.3. Integration of IMS with SCM – Revitalising the objectives and goals of Supply
Chain Management
2.3.1 SCM and AI/ML
2.3.2 IoT and SCM
2.3.3 SCM and Big data Analytics (BDA)
2.3.4 SCM and Advanced Robotics and Automation (ARA)
2.3.5 Digital Twins/Simulation in SCM
2.4. Maintenance management and IMS techniques
2.4.1 MM and AI / ML
2.4.2 Challenges in PM 4.0
2.4.3 MM and IoT
2.4.4 ARA and Maintenance management
2.4.5 BDA in Maintenance management
2.4.6 Digital Twin and Simulation in Maintenance management
2.5 Digital Twin technology in scheduling and inventory management of Intelligent Manufacturing Systems
Conclusion
Chapter 3: Generation and Optimization of Mid-term Production Distribution Plan Using Metaheuristic Techniques
3.1 Introduction
3.2 Discrete Nonlinear Optimization Using Integer Variables
3. 2.1 Notations
3.2.2 Factors affecting decision
3.3 Presumptions
3.4 Solution Methodology
3.4.1 A Conventional Method
3.4.2 Genetic Algorithm
3.4.3 Solution
3.4.4 GA process
3.5 Simulated Annealing Algorithm
3.5.1 Solution methodology
3.6 Memetic Algorithm
3.7 Discrete Particle Swarm Optimization Algorithm
3.7.1 DPSOA Procedure
3.8 Application and Testing of Models
3.9 Computational Results and Discussion
3.9.1 GA Solution
3.9.2 SA Solution
3.9.3 MA Solution
3.9.4 DPSOA solution
3.10 Conclusion
References
Chapter 4: Big Data in Intelligent Manufacturing
4.1 Introduction
4.1.1 Overview of Intelligent Manufacturing
4.1.2 Big Data in Manufacturing
4.1.3. Need for Big Data
4.1.4. Scope of the Chapter
4.2. Literature Survey
4.3. Applications of Big Data in Intelligent Manufacturing
4.3.1 Predictive Maintenance
4.3.2. Supply Chain Optimization
4.3.3 Energy Management
4.3.4. Product Quality Enhancement
4.4 Big Data Tools and Platforms for Manufacturing
4.5. Result and Analysis
4.6. Future Trends and Research Directions
4.7. Conclusion
References
Chapter 5: Deep Learning for Intelligent Manufacturing
5.1.Introduction
5.2.Literature Review
5.3.Architectures of Deep Learning for Intelligent Manufacturing
5.3.1. Architecture of Siamese RPN
5.3.2. Architecture of Multi objective optimization architecture (MOO)
5.3.3. Architecture of LSTM
5.3.4. Architecture of Intelligent Manufacturing system
5.4.Applications in Intelligent Manufacturing
5.4.1. Quality control and inspection
5.4.2. Predictive maintenance
5.4.3. Process optimization
5.4.4. Autonomous Systems and Robotics
5.5.Case studies
5.5.1. LSTM In Automotive Plant
5.5.2. Manufacturing with CNN-based Defect Detection
5.5.3. Optimizing Chemical Manufacturing with Reinforcement Learning
5.6.Challenges and Limitations
5.6.1. Data Quality and availability
5.6.2. Model Interpretability
5.6.3. Computational Resources
5.6.4. Scalability and maintenance of AI models
5.6.5. Handling high dimensional and noisy data
5.6.6. High cost of implementation
5.6.7. Dynamic Manufacturing Environment
5.7.Future Trends in Intelligent Manufacturing
5.7.1. Edge Computing and Real time data processing
5.7.2. Digital Twins and Virtual simulation
5.7.3. AI driven Automation and Decision making
5.7.4. Sustainability and Green Manufacturing
6. Conclusion
References
Chapter 6: AI And ML Techniques for Manufacturing Domain
6.1. Introduction and background
6.1.1. Introduction
6.1.2. Background
6.2. Fundamentals of AI and ML techniques in manufacturing domain
6.3. The impact of AI and ML on the manufacturing domain
6.3.1. Enhanced automation and efficiency
6.3.2. Predictive maintenance and downtime reduction
6.3.3. Enhanced quality control and defect detection
6.3.4. Supply chain optimization and resilience
6.3.5. Human-AI collaboration (industry 5.0)
6.3.6. Energy efficiency and sustainable manufacturing
6.3.7. Customization and agility in production
6.3.8. Digital twins and simulation
6.4. AI and ML applications in manufacturing domain
6.5. How AI and ML solutions contribute to achieving manufacturing excellence?
6.6. AI and ML in manufacturing: opportunities and challenges
6.6.1. Opportunities of AI and ML in manufacturing
6.6.2. Challenges of AI and ML in manufacturing
6.7. Conclusion
References
Chapter 7 : Development of a Cloud-Based Intelligent Manufacturing
7.1. Introduction of Manufacturing
7.2. Historical Background of Manufacturing
7.2.1. Revolts for Industrial
7.2.1.1. Revolt for First Industrial
7.2.1.2. Revolt for Second Industrial
7.2.1.3. Revolt for Third Industrial
7.2.1.4. Revolt for Fourth Industrial
7.3. Cloud Manufacturing Framework
7.4. SMSD based on virtual twins
7.4.1. Function design of SMS based on Virtual twins
7.4.1.1. Planning processes using Virtaul twins
7.4.1.2. Mechanical design of equipment based on virtual twins
7.4.2. SMS structural design based on Virtual twins
7.4.2.1. Layout planning and topology optimization using virtual twins
7.4.2.2. Tooling and buffer design based on virtual twins
7.4.3. Behavior design of SMS based on virtual twins
7.4.3.1. Designing equipment behavior with virtual twins
7.4.3.2. WIP/material handling based on Virtual twins
7.4.4. SMS control design based on Virtual twins
7.4.4.1. Process optimization and equipment control design using Virtual twins
7.4.4.2.Commissioning is managed via a system based on Virtual twins.
7.4.5. SMS intelligence model design based on Virtual twins
7.4.5.1.SMS machine learning model design based on Virtual twins
7.4.5.2.SMS computational optimization model design based on Virtual twins
7.4.6. SMS performance design with Virtual twins
7.4.6.1. Virtual twin-based SMSD that prioritizes quality
7.4.6.2. Virtual twin-based SMSD with flexibility
7.4.6.3. Virtual twin-based SMSD with a focus on reconfigurability
7.4.6.4. Virtual twin-based SMSD with a focus on sustainability
7.4.6.5. Virtual twin-based SMSD that is focused on security and safety
7.5.SMSD models built on Virtual twins
7.5.1.CMCO quad-play model
7.5.2.Shop-floor Virtual twin model
7.6.SMSD cases based on Virtual twins
7.7. Innovative Production Platform Capabilities and Challenges
7.7.1.Smart Manufacturing Security Concerns
7.7.2.Integration of Systems
7.7.3.Interoperability
7.7.4.Safety in Cooperation Between Humans and Robots
7.7.5.Being multilingual
7.7.6.Return on Investment for New Technology
7.8 Conclusion
References
Chapter 8: Digital Twin for Manufacturing
8.1 Introduction
8.1.1 Industrial Evolution
8.1.2 Digital Twin Evolution
8.2 Applications of Digital Twin in Smart Manufacturing
8.2.1 Production Systems
8.2.2 Monitoring and Modifying the Part Production
8.2.3 Method and Product Efficacy Enhancement
8.2.4 Predictive Maintenance
8.3 DTs Case Study in Manufacturing
8.3.1 BMW
8.3.2 GENERAL ELECTRIC (GE)
8.3.3 SIEMENS
8.3.4 BOEING
8.3.5 IBM
8.4 DT Framework for Intelligent Manufacturing System
8.4.1 Background
8.4.2 Objective
8.4.3 Proposed DT Methodology
8.4.3.1 Acquisition Layer
8.4.3.2 Digital Twin Layer
8.4.3.3 Anomaly Detection Engine
8.4.3.4 Decision Making Support
8.4.3.5 Monitoring Interface
8.5 DTs Setbacks, Threats, and Complications
8.5.1 Recurring Setbacks and Restrictions
8.5.2 Deployment Setbacks
8.5.3 Confidentiality, Security Hazards, and Unanticipated Consequences
8.6 Conclusion and Future Investigation Work Guidelines
References
Chapter 9: Internet of Things for Intelligent Manufacturing Systems
9.1 Introduction
9.2 Literature Review
9.3 Methodology
9.3.1 System Architecture Design
9.3.2 Data Acquisition and Processing
9.3.3 Security Enhancement Using Blockchain
9.3.4 Mathematical Model for Blockchain-Based Security in IoT Manufacturing
9.3.5. Overview Of Iot Architecture
9.3.6. Components Of An Intelligent Manufacturing System
9.4. RESULTS AND DISCUSSION
9.4.1 IoT Sensor Deployment in Manufacturing
9.4.2 Blockchain Implementation for Secure Data Management
9.4.3 AI-Driven Predictive Analytics for Anomaly Detection
9.4.4 Comparison Table for Model Performance.
9.4.5 Performance Metrics and Comparative Evaluation:
9.5 CASE STUDY - NETWORK MODELING AND ANALYTICS
9.6 Conclusion
References
Chapter 10. Industrial Internet of Things and Cyber Manufacturing Systems
10.1 Introduction
10.2 Literature Review
10.3 Fundamentals of CMS
10.3.1 Cyber-Physical Systems
10.3.2 Digital Twin Technology
10.3.3 Data Analytics and Integration
10.4 System Model
10.4.1 System Architecture Design
10.4.2 Data Management Processes
10.4.3 Layers of IIoT and CMS
10.5 Applications in Manufacturing
10.5.1 Advanced usage of distributed sensing processes for maintenance
10.5.2 Robotics Integration with Industrial Internet and Computer Management
System
10.5.3 Real-Time Inventory Management and Supply Chain Control
10.5.4 AI-Powered Quality Control
10.5.5 Energy management and sustainability
10.5.6 Complex Additive Manufacturing
10.5.7 Training and Operations in the Light of Augmented Reality
10.5.8 AI-Optimized Scheduling
10.5.9 Environmental Sustainability
10.5.10 Cyber-Physical Systems and Digital Twins
10.6 IIoT-Enabled Adaptive Scheduling Algorithm (IIoT-ASA)
10.6.1 Methodology
10.6.2 Results and Discussion on IIoT-ASA
10.7 Experimental Analysis on a case study
10.7.1 Evaluating Energy Efficiency and Production Quality in IIoT Enabled CMS manufacturing System
10.8 Challenges and Risk Management
10.9 Case Studies and Implementations
10.9.1 Real-life applications of the IIoT and CMS
10.10 Future Trends and Research Directions
10.11 Conclusion
10.11.1 Summary and Key Insights
10.11.2 Future of Manufacturing
References
Chapter 11: Intelligent Robotics in Manufacturing: The Role of AI-Driven Automation
11.1 Introduction
11.2 Industry 5.0
11.3 Robots Capable of Independent Movement
11.4 Problems with Working Together Between People and Robots
11.5 The Evolution of AI-Driven Robots in Manufacturing
11.6 Robotic Innovations Based on Machine Learning
11.7 Using Machine Learning and AI to Build Robots
11.7.1 Systems and Mechanisms for Sensing and Perceiving
11.7.2 Making Independent Choices in Robotics
11.7.3 Learning and Adapting in Smart Robots
11.7.4 Real-Life Uses of Robotics with AI
11.7.5 AI Is Used in Self-Driving Cars and Robots for Healthcare
11.7.6 What AI Does in Modern Robotics
11.8 Industrial Evolution Through Smart Robotics
11.8.1 Different Kinds of Smart Robots That Can Be Used in Manufacturing
11.8.2 Application and Advantages
11.9 Smart Robotics and the Future of Manufacturing
11.9.1 Smart Robots for Smarter Factories
11.9.2 Cognitive Intelligence in Industrial Robots for Smart Manufacturing
11.10 Conclusions
Biography
Dr. Pravin Kumar Singh is an accomplished academician and researcher in the field of Mechanical Engineering, currently serving as an Associate Professor at Galgotias University, Greater Noida, India. With over 8 years of teaching and research experience, he holds a Ph.D. in Manufacturing Engineering from NIT Jamshedpur, specializing in vibratory welding techniques and materials processing.
Dr. Singh's core areas of expertise include advanced welding technology, robotics welding, smart manufacturing, 3D printing, and sensors and transducers. He has contributed extensively to academia through peer-reviewed publications in SCI/Scopus-indexed journals, book chapters with Springer and Elsevier, and as an editor of reputed international conference proceedings. He is also a reviewer for several renowned journals under Elsevier and IOP.
A strong advocate of industry-academia collaboration, Dr. Singh has coordinated numerous internships and skill development programs in partnership with top-tier companies such as BOSCH, TSPDI, and Prinston Engineering Ltd. He has also played key roles in institutional development, including NAAC accreditation processes, curriculum innovation, and student mentorship initiatives.
Prof. (Dr.) P. Suresh is a Professor in the Department of Mechanical Engineering and also serves as Controller of Examinations at J.J college of Engineering and Technology, Tamil Nadu, India. He has also served as the University-level Academic Coordinator at Galgotias University, Greater Noida.
Dr. Suresh received his Ph.D. in Faculty of Mechanical Engineering from Anna University, Tamil Nadu, in 2014. He completed his Master of Engineering in Engineering Design from Bharathiyar University, Coimbatore in 2001 and his Bachelor of Engineering from the University of Madras, Chennai, in 2000.
With over 24 years of experience in academic and research, his areas of expertise include optimizations, machinability of materials, composite materials and metal matric composite materials. He has authored more than 55 research publications in reputed international journals, conferences and book chapters published by Elsevier, Springer, IET and other leading publishers.
Dr. T. Poongodi is presently working as a Professor in the Department of Computer Science and Engineering, School of Engineering at the Dayananda Sagar University, Bangalore, India. She received her Ph.D. degree in Information Technology (Information and Communication Engineering) from Anna University, Tamil Nadu, India. She is the author of over 50+ (Scopus Indexed) book chapters including some reputed publishers such as Springer, Elsevier, IET, Wiley, De-Gruyter, CRC Press, etc. and 30+ (SCI/Scopus) international journals and conferences. She has published 15+ authored/edited books in the areas of Internet of Things, Data Analytics, Blockchain Technology, Artificial Intelligence, Machine Learning, and Healthcare Informatics, published by renowned publishers. With over 19 years of extensive experience in teaching and multi-disciplinary research, she has been recognized with several prestigious awards, including the Research and Innovation award and Excellence in the area of Research & Innovation/ Academic Excellence from Galgotias University, Delhi-NCR. She is a senior member of The Institute of Electrical and Electronics Engineers (IEEE).
Dr. Gopal Rathinam received his master’s degree from Department of Computer Science and Engineering, Anna University, India, in 2010 and Ph.D. degree from Department of Information and communication Engineering, Anna University, India, in 2018. He is currently working as Assistant Professor, in college of Engineering, University of Buraimi, Oman. His research interests span wireless sensor networks, malicious node detection, Cooperative network, and Internet of Things. He got a grant of 40,000 OMR from the ministry of Higher Education and research and Innovation and 10,000 OMR grant in internal funded project. He has served on many technical program committees and as reviewer in reputed journals like wireless Personal Communication Springer. He has a list of publication in reputed journals, editor for 3 Scopus indexed books and published 9 book chapters.
Dr. P. Senthil received his Master’s degree in Mechanical Engineering from Bharathiar University, India, in 2002, and his Ph.D. in Mechanical Engineering from Anna University, India, in 2012. He is currently serving as a Senior Lecturer at the College of Engineering and Technology, University of Technology and Applied Sciences (UTAS), Muscat, Sultanate of Oman.
His research interests include Squeeze Casting, Pressure Die Casting, Non-ferrous Composites, Rapid Prototyping, and Process Optimization. He has published extensively in reputed international journals and conference proceedings. Dr. Senthil has also contributed to the academic community by serving on various technical program committees and acting as a reviewer for several esteemed international journals.
