Artificial Intelligence for Smart Manufacturing: Methods, Applications, and Challenges

Contents
Introduction to Smart Manufacturing   with Artificial Intelligence
	1 Introduction
	2 Main Features of This Book
	3 Structure of the Book
	4 Conclusion
	References
Artificial Intelligence for Smart Manufacturing in Industry 5.0: Methods, Applications, and Challenges
	1 Introduction
	2 Overview of Artificial Intelligence and Augmented Intelligence Techniques
		2.1 The AI Algorithms
		2.2 The AuI Techniques
	3 Transition from Industry 4.0 to Industry 5.0
	4 Artificial Intelligence and Augmented Intelligence Techniques for Smart Manufacturing in Industry 5.0
	5 Dificulties, Challenges, and Perspectives for Application of Artificial Intelligence Techniques for Smart Manufacturing in Industry 5.0
		5.1 5G, 6G, and Smart Manufacturing
		5.2 Product Design
		5.3 Predictive Maintenance
		5.4 Quality Control
		5.5 Digital Twin
		5.6 Cybersecurity in Smart Manufacturing
		5.7 Wearable Technology for Smart Manufacturing  in the Industry 5.0
		5.8 Human-Centric and Sustainable Manufacturing
		5.9 Quantum Machine Learning
		5.10 Human-Centered Design of AI and Explainable AI  for Industry 5.0
		5.11 Manufacturing in the Metaverse
	6 Concluding Remarks
	References
Quality Control for Smart Manufacturing in Industry 5.0
	1 Introduction
	2 Quality Control in Industrial Manufacturing
		2.1 The History of Quality Control
		2.2 Quality Control Definition
		2.3 Quality Control Methods Classification
	3 Machine Learning and Computer Vision for the Quality Control
	4 Dificulties, Challenges, and Perspectives for AI-Based Quality Control for Smart Manufacturing in the Industry 5.0
		4.1 The Use of Anomaly Detection Techniques for Quality Control
		4.2 AI and IIoT-Based Solutions for Quality Control
		4.3 Human-Centric Quality Control
	5 A Case Study
		5.1 Dataset
		5.2 Machine Learning Model
		5.3 Results
	6 Concluding Remarks
	References
Dynamic Process Monitoring Using Machine Learning Control Charts
	1 Introduction
	2 Some Representative Machine Learning Control Charts
		2.1 Control Chart Based on Artificial Contrasts
		2.2 Control Chart Based on Real Time Contrasts
		2.3 Control Chart Based on Support Vector Machine
		2.4 Control Chart Based on the KNN Classification
	3 Suggested Modified Machine Learning Control Charts for Dynamic Process Monitoring
		3.1 Estimation of the Regular Multivariate Longitudinal Pattern
		3.2 Dynamic Process Monitoring
	4 Simulation Studies
		4.1 Evaluation of the IC Performance
		4.2 Evaluation of the OC Performance
	5 An Application
	6 Concluding Remarks
	References
Fault Prediction of Papermaking Process Based on Gaussian Mixture Model  and Mahalanobis Distance
	1 Introduction
	2 Process Modeling
		2.1 Data Pre-processing
		2.2 Feature Engineering
		2.3 Health Benchmark Model
	3 Case Studies
	4 Conclusion
	References
Multi-objective Optimization of Flexible Flow-Shop Intelligent Scheduling Based on a Hybrid Intelligent Algorithm
	1 Introduction
	2 Literature Review
	3 Production Scheduling Model of Flexible Flow Workshop
		3.1 Problem Description and Modeling
		3.2 Method Introduction
	4 Case Study
		4.1 Production Process of Papermaking Production Workshop
		4.2 Optimization Objectives
		4.3 Experimental Data
		4.4 Parameter Settings
		4.5 Results and Analysis
	5 Conclusions
	References
Personalized Pattern Recommendation System of Men's Shirts
	1 Introduction
	2 Morphological Analysis of The Human Body
		2.1 Anthropometric Measuring Methods
		2.2 Human Body Shape Classification
		2.3 Classification of Knowledge
		2.4 Human Upper Body Segmentation
		2.5 Anthropometric Subject Selection
		2.6 Comparing Classification Methods
		2.7 Classification Model for Segmented Upper Body Shapes
		2.8 Feature Measurements Selection
	3 Parametric Garment Pattern-Making
		3.1 Basic Pattern Parametric Pattern-Making Method
		3.2 Pattern Generation Based on Parametric
		3.3 3D Basic Pattern Design and 2D Basic Pattern Flattening
		3.4 Personalized Basic Pattern (Men) Database Construction
		3.5 A Regression Model Enabling to Infer from Basic Pattern to Personalized Basic Pattern
		3.6 Personalized Shirt Pattern Plotting Method
		3.7 Garment Fitting Evaluation
		3.8 Design of the System Framework
		3.9 PBP's Parametric Pattern-Making Effect
		3.10 PBPshirt Parametric Pattern-Making Effect
		3.11 The Efficiency of Parametric Pattern-Making
	4 Conclusion
	References
Efficient and Trustworthy Federated Learning-Based Explainable Anomaly Detection: Challenges, Methods, and Future Directions
	1 Introduction
	2 Anomaly Detection
	3 Federated Learning-Based Anomaly Detection
	4 Dificulties and Challenges for Federated Learning
		4.1 Expensive Communication
		4.2 Systems and Data Heterogeneity
		4.3 Resource Constraints
		4.4 Security and Privacy Concerns
		4.5 Hyperparameter Optimization
	5 A Perspective about Efficient and Trustworthy Federated Learning-Based Explainable Anomaly Detection System
		5.1 Rationale and Consideration
		5.2 An End-to-End Efficient and Trustworthy Federated Learning-Based Explainable Anomaly Detection System
	6 Future Aspects
		6.1 Hybrid Digital-Analog Network Transmission for Federated Learning
		6.2 Quantum Computing and Quantum Machine Learning Perspective
	7 Concluding Remarks
	References
Multimodal Machine Learning  in Prognostics and Health Management  of Manufacturing Systems
	1 Introduction
	2 Terminologies of Multimodal Machine Learning
		2.1 Modality
		2.2 Multimodality
		2.3 Multimodal Versus Multimedia
		2.4 Multimodal Versus Heterogeneous Data
		2.5 Multimodal Learning
	3 Overview of Multimodal Machine Learning Studies
		3.1 Brief Literature Review of the Evolution of Multimodal Machine Learning
		3.2 Challenges of Multimodal Machine Learning
		3.3 Tools and Techniques in Multimodal Deep Learning
	4 Review of Multimodal Machine Learning in PHM
		4.1 Multimodal Machine Learning in Fault Detection  and Diagnostics
		4.2 Multimodal Machine Learning in Prognostics
		4.3 Multimodal Machine Learning for Prescriptive Maintenance
	5 Detailed Example of Multimodal Machine Learning in PHM of Manufacturing Systems
		5.1 Case Study Description
		5.2 Proposed Methodology
		5.3 Result Discussion
	6 Conclusion and Perspectives
	References
Explainable Articial Intelligence  for Cybersecurity in Smart Manufacturing
	1 Introduction
	2 Cybersecurity and Manufacturing Cybersecurity
	3 Explainable Artificial Intelligence
	4 Explainable Artificial Intelligence Enable Cybersecurity for Smart Manufacturing in the Industry 5.0
		4.1 The State-of-the-Art
		4.2 Toward Smart Manufacturing in the Industry 5.0
	5 Perspectives for Explainable Cybersecurity for Smart Manufacturing in the Industry 5.0
		5.1 Designing of XAI-Based Anomaly Detection System Over Edge Computing
		5.2 Explainable Augmented Intelligence for Cybersecurity
		5.3 Cybersecurity for the Applications of 5G, 6G in Smart Manufacturing
	6 Case Study—Explainable Anomaly Detection  for Industrial Control Systems
		6.1 Anomaly Detection Using the Hybrid Autoencoder LSTM Model
		6.2 Integration of Explainable Artificial Intelligence
		6.3 Illustrative Performance Evaluation
	7 Concluding Remarks
	References
Wearable Technology for Smart Manufacturing in Industry 5.0
	1 Introduction
	2 Wearable Technology
	3 Wearable Industrial Internet of Things
		3.1 Application of Wearable Industrial Internet of Things
		3.2 Artificial Intelligence in Wearable Technology
		3.3 Internet of Things Wearable Sensors
	4 Wearable IoT Technology for Smart Manufacturing
	5 Human Cyber-Physical Systems and Smart Garment's Adoptions in Smart Manufacturing
	6 Difficulties, Challenges, and Perspectives for Application of Wearable Technology Techniques for Smart Manufacturing in Industry 5.0
		6.1 Data Security and Privacy
		6.2 Data Processing
		6.3 Battery Life Expectancy
		6.4 Smart Garment for Human Cyber-Physical Systems  in Smart Manufacturing
		6.5 Factors Influence User Acceptance of Wearable IoT Devices
	7 Case Studies
		7.1 Case study 1: HAR with Federated Learning
		7.2 Case study 2: Fall Detection and Classification with Federated Learning
	8 Concluding Remarks
	References
Benefits of Using Digital Twin for Online Fault Diagnosis of a Manufacturing System
	1 Introduction
	2 State of the Art
	3 Proposed Approach
		3.1 Automated Production Systems Modeled as DES
		3.2 Proposal
		3.3 Data Acquisition
		3.4 Data Preprocessing
		3.5 Model Training
	4 Application on the Sorting by Height System
		4.1 Use Case Descreption
		4.2 Experimental Results
		4.3 Diagnoser Results
	5 Conclusion
	References