Metaheuristic Algorithms in Industry 4.0 (Advances in Metaheuristics)

✍ Scribed by Pritesh Shah (editor), Ravi Sekhar (editor), Anand J. Kulkarni (editor), Patrick Siarry (editor)

• Publisher: CRC Press
• Year: 2021
• Tongue: English
• Leaves: 301
• Edition: 1
• Category: Library

✦ Synopsis

Due to increasing industry 4.0 practices, massive industrial process data is now available for researchers for modelling and optimization. Artificial Intelligence methods can be applied to the ever-increasing process data to achieve robust control against foreseen and unforeseen system fluctuations. Smart computing techniques, machine learning, deep learning, computer vision, for example, will be inseparable from the highly automated factories of tomorrow. Effective cybersecurity will be a must for all Internet of Things (IoT) enabled work and office spaces.  

This book addresses metaheuristics in all aspects of Industry 4.0. It covers metaheuristic applications in IoT, cyber physical systems, control systems, smart computing, artificial intelligence, sensor networks, robotics, cybersecurity, smart factory, predictive analytics and more.

Key features:

• Includes industrial case studies. 
• Includes chapters on cyber physical systems, machine learning, deep learning, cybersecurity, robotics, smart manufacturing and predictive analytics.
• surveys current trends and challenges in metaheuristics and industry 4.0.

Metaheuristic Algorithms in Industry 4.0 provides a guiding light to engineers, researchers, students, faculty and other professionals engaged in exploring and implementing industry 4.0 solutions in various systems and processes.

✦ Table of Contents

Cover
Half Title
Series Page
Title Page
Copyright Page
Table of Contents
Preface
Editors
Contributors
1. A Review on Cyber Physical Systems and Smart Computing: Bibliometric Analysis
1.1 Introduction
1.2 Data Selection and Extraction
1.3 Distribution of Publications along Different Verticals
1.3.1 Publications Analysed: Year-on-Year Basis
1.3.2 Research Directions of Publications
1.3.3 Popular Places
1.3.4 Productive Organizations and Researchers
1.4 Analysis along the Collaboration Vertical
1.4.1 Collaboration Strength amongst the Researchers
1.4.2 Collaboration Strength of Organizations
1.4.3 Collaborative Strength of Places
1.5 Analysis along the Citation Landscape
1.5.1 The Citation Landscape for Research Papers
1.5.2 The Citation Landscape for Researchers
1.5.3 The Citation Landscape for Organizations
1.5.4 The Citation Landscape for Places
1.6 Timeline Analysis and Burst Detection
1.6.1 Timeline Review Analysis
1.6.2 Keyword Burst Detection
1.6.3 References Burst Detection
1.7 Conclusion
References
2. Design Optimization of Close-Fitting Free-Standing Acoustic Enclosure Using Jaya Algorithm
2.1 Introduction
2.2 Insertion Loss
2.2.1 Mathematical Model for Prediction of Insertion Loss
2.2.2 Need for Optimization
2.2.2.1 Effect of Variation in Panel Thickness (h) on IL
2.2.2.2 Effect of Variation in Source to Panel Distance (d) on IL
2.2.2.3 Effect of Variation in Internal Damping Coefficient (η) on IL
2.2.3 Optimization
2.2.3.1 Formulation of Optimization Problem
2.2.3.2 Optimization by Jaya Algorithm
2.2.3.3 Final Dimensions of the Enclosure
2.3 Experimentation
2.3.1 Experimental Set-up
2.3.2 Experimental Procedure
2.4 Results and Discussion
2.4.1 Theoretically Predicted Vs Experimentally Obtained Results
2.5 Conclusions and Future Scope
References
3. A Metaheuristic Scheme for Secure Control of Cyber-Physical Systems
3.1 Introduction
3.2 Setup and Preliminaries
3.2.1 System Description
3.2.2 A Moving Target Defense Scheme Using Switching Controllers
3.2.3 Problem Formulation
3.3 System Analysis in the Absence of Cyber Attack
3.4 System Analysis in the Presence of Cyber Attack
3.4.1 A Detection Scheme for the Presence of Actuator Intrusion
3.4.2 An MTD Control Scheme to Mitigate Cyber Attack
3.5 Optimization of the Proposed MTD Control Scheme
3.5.1 Basic Algorithm of PSO
3.5.2 PSO-Based LQR Tuning
3.6 Simulation Example
3.7 Conclusions and Future Scope
Acknowledgments
References
4. Application of Salp Swarm Algorithm to Solve Constrained Optimization Problems with Dynamic Penalty Approach in Real-Life Problems
4.1 Introduction
4.2 Framework of Salp Swarm Algorithm
4.3 Dynamic Penalty Approach
4.4 Proposed Methodology
4.5 Design of Experiments
4.5.1 Selection of Orthogonal Array
4.5.2 Experimental Data
4.5.3 Problem Formulation
4.6 Results and Discussion
4.7 Conclusion
References
5. Optimization of Robot Path Planning Using Advanced Optimization Techniques
Notation
5.1 Introduction
5.1.1 Navigational Methodology Used for Mobile Robot Path Planning
5.1.1.1 Classical Approaches for Mobile Robot Navigation
5.1.1.2 Reactive Approaches for Mobile Robot Navigation
5.1.2 Classification of Navigation Strategy
5.2 Literature Review
5.3 Optimization Algorithms
5.3.1 Jaya Algorithm
5.3.2 Rao Algorithms
5.4 Applications of the Jaya and Rao Algorithms to Robot Path Planning Optimization
5.4.1 Case Study 1
5.4.1.1 Objective Function Formulation for Case Study 1
5.4.1.2 Obstacle Avoidance Behavior for Case Study 1
5.4.1.3 Goal Searching Behavior for Case Study 1
5.4.1.4 Case Study 1: Example 1
5.4.1.5 Case Study 1: Example 2
5.4.2 Case Study 2
5.4.2.1 Objective Function Formulation for Case Study 2
5.4.2.2 Obstacle Avoidance Behavior for Case Study 2
5.4.2.3 Goal Searching Behavior for Case Study 2
5.4.2.4 Case Study 2: Example 1
5.4.2.5 Case Study 2: Example 2
5.4.2.6 Case Study 2: Example 3
5.4.2.7 Case Study 2: Example 4
5.4.2.8 Case Study 2: Example 5
5.4.3 Case Study 3
5.4.3.1 Objective Function Formulation for Case Study 3
5.4.3.2 Obstacle Avoidance Behavior for Case Study 3
5.4.3.3 Target-Seeking Behavior for Case Study 3
5.4.3.4 Case Study 3: Example 1
5.4.3.5 Case Study 3: Example 2
5.4.3.6 Case Study 3: Example 3
5.4.4 Case Study 4
5.4.4.1 Objective Function Formulation for Case Study 4
5.4.4.2 Case Study 4: Example 1
5.4.4.3 Case Study 4: Example 2
5.5 Conclusions
References
6. Semi-Empirical Modeling and Jaya Optimization of White Layer Thickness during Electrical Discharge Machining of NiTi Alloy
Abbreviations
6.1 Introduction
6.1.1 Research Novelty
6.2 Method and Material
6.2.1 Experimental Details
6.2.2 Empirical Modeling
6.2.3 Jaya Optimization
6.2.4 Convergence Analysis for WLT
6.3 Results and Discussions
6.3.1 Comparative Analysis of WLT
6.3.2 WLT Evaluation Using ImageJ Software
6.3.3 Optimum Parameter Setting Using Jaya Technique
6.4 Conclusions
References
7. Analysis of Convolution Neural Network Architectures and Their Applications in Industry 4.0
7.1 Introduction
7.2 Evolution of Convolution Neural Network Architectures
7.2.1 LeNet
7.2.1.1 Architecture Description
7.2.1.2 Limitations
7.2.2 AlexNet
7.2.2.1 Architecture Description
7.2.2.2 Limitations
7.2.3 GoogLeNet
7.2.3.1 Architecture Description
7.2.3.2 Limitations
7.2.4 VGG
7.2.4.1 Architecture Description
7.2.4.2 Limitations
7.2.5 ResNet
7.2.5.1 Architecture Description
7.2.5.2 Limitations
7.2.6 R-CNN
7.2.6.1 Architecture Description
7.2.6.2 Limitations
7.2.7 You Only Look Once (YOLO)
7.2.7.1 Architecture Description
7.2.7.2 Limitations
7.2.8 Generative Adversarial Networks (GANs)
7.2.8.1 Limitations
7.3 Applications of Convolution Neural Networks in Industry 4.0
7.3.1 Healthcare Sector
7.3.2 Automotive Sector
7.3.3 Fault Detection
7.4 Conclusion
References
8. EMD-Based Triaging of Pulmonary Diseases Using Chest Radiographs (X-Rays)
Abbreviations
Symbols
Chapter Organization
8.1 Introduction
8.1.1 Motivation for Building This Tool
8.1.2 Earth Mover’s Distance
8.1.3 Dataset
8.1.4 Parameter Settings
8.2 Results and Discussion
8.2.1 Conclusion and Anticipated Outcomes
8.2.2 Anticipated Outcomes
References
9. Adaptive Neuro Fuzzy Inference System to Predict Material Removal Rate during Cryo-Treated Electric Discharge Machining
Abbreviations
9.1 Introduction
9.2 Materials and Experimental Set-up
9.3 Results and Discussion
9.4 Conclusions
References
10. A Metaheuristic Optimization Algorithm-Based Speed Controller for Brushless DC Motor: Industrial Case Study
10.1 Introduction
10.2 Speed Control of Sensorless BLDC Motor Drives
10.2.1 Mathematical Model of BLDC Motors
10.2.2 Sensorless Speed Control Scheme of BLDC Motors
10.2.2.1 Principle of Sensorless Position Detection
10.2.2.2 Sensorless Speed Control of BLDC Motors
10.2.2.3 Sensorless Control Strategy
10.3 Analysis of Metaheuristics Optimization Algorithm-Based Controller
10.3.1 Methods of Optimal Tuning of Controller
10.3.1.1 Analysis of Optimization Techniques Based on PID Controller
10.3.1.2 Analysis of Optimization Techniques Based on FOPID Controller
10.4 Metaheuristic Optimization Algorithm-Based Controller Tuning
10.4.1 Controller Design
10.4.2 Basic Structure of Optimal Tuning of Controller
10.4.3 Optimization Techniques Based on Controller Tuning for Brushless DC Motor
10.4.4 Effect of Controller Parameters
10.4.5 Problem Formulation
10.5 Results and Discussions
10.5.1 Simulink Model
10.5.2 Speed Response under Constant Load Condition
10.5.3 Speed Response under Varying Load Conditions
10.5.4 Speed Response under Varying Set Speed Conditions
10.5.5 Speed Response under Combined Operating Conditions
10.5.6 Mean, Standard Deviation and Convergence
10.6 Conclusion and Future Research Direction
References
11. Predictive Analysis of Cellular Networks: A Survey
List of Abbreviations
11.1 Introduction
11.2 Traffic Characteristics and Aspects of Analysis
11.2.1 Traffic Characteristics
11.2.1.1 Self-Similarity
11.2.1.2 Seasonality
11.2.1.3 Non-Stationarity
11.2.1.4 Multifractal
11.2.1.5 Long-Range Dependency (LRD)
11.2.1.6 Short-Range Dependency (SRD)
11.2.2 Aspects of Analysis
11.3 Overview of Predictive Analysis
11.3.1 Time-Series Analysis
11.3.2 CDR Analysis
11.3.3 Mobility and Location Analysis
11.4 Time-Series Analysis of Network Traffic
11.4.1 Stochastic Models
11.4.2 Research Contribution
11.5 CDR Analysis
11.5.1 Predicted Outputs
11.5.1.1 Mobility Analysis
11.5.1.2 Anomaly Detection
11.5.1.3 Social Influence Analysis
11.5.1.4 Voice Traffic Analysis
11.5.2 Big Data Analysis of CDR
11.6 Mobility and Location Analysis
11.6.1 Predicted Outputs
11.6.1.1 Moving Direction
11.6.1.2 Future Locations
11.6.1.3 User Trajectory
11.6.1.4 The Next Cell Id
11.6.2 Mobility Analysis
11.6.3 Location Analysis
11.7 Network Analysis for Special Parameters
11.7.1 Hotspot Detection
11.7.2 Holiday Traffic Prediction
11.7.3 Customer Churn Prediction
11.7.4 Fault Prediction
11.7.5 Anomaly Detection
11.8 Predictive Analysis-Enabled Applications
11.8.1 Resource Allocation
11.8.2 Handover Management
11.8.3 Location-Based Services
11.8.4 Interference Management
11.8.5 Energy Efficiency
11.9 Deep Learning in Predictive Analysis of Cellular Networks
11.9.1 Deep Learning State-of-the-Art
11.9.1.1 Convolutional Neural Networks
11.9.1.2 Recurrent Neural Networks
11.9.1.3 Deep Belief Networks
11.9.1.4 Autoencoders
11.9.1.5 Long Short-Term Memory
11.9.2 Deep Learning-Based Time-Series Analysis
11.9.3 Deep Learning-Based CDR Analysis
11.9.4 Deep Learning-Based Mobility & Location Analysis
11.10 Emerging Intelligent Networks
11.10.1 Characteristics of SON
11.10.1.1 Scalability
11.10.1.2 Stability
11.10.1.3 Agility
11.10.2 Classes of SON
11.10.2.1 Self-Configuration
11.10.2.2 Self-Optimization
11.10.2.3 Self-Healing
11.10.3 Applications of SON
11.10.3.1 Coverage and Capacity Optimization
11.10.3.2 Mobility Robustness Optimization
11.10.3.3 Mobility Load Balancing
11.10.3.4 RACH Optimization
11.11 Conclusion
References
12. Optimization Techniques and Algorithms for Dental Implants – A Comprehensive Review
12.1 Introduction
12.1.1 Structural Optimization
12.1.2 Surface Morphology Optimization
12.1.3 Material Properties Optimization
12.2 FEA Aspect of Optimization Techniques
12.3 Optimization Techniques and Algorithms
12.3.1 Genetic Algorithm
12.3.2 Topology Optimization Algorithm
12.3.2.1 SKO (Soft Kill Option)
12.3.2.2 Solid Isotropic Material with Penalization (SIMP)
12.3.3 Particle-Swarm Optimization
12.3.4 Multiobjective Optimization Algorithm
12.3.5 Approximate Optimization
12.3.6 Uncertainty Optimization Algorithm
12.3.7 Memetic Search Optimization
12.4 Parameters for Optimization
12.4.1 Structural Parameters
12.4.2 Material Properties and Surface Morphology
12.4.3 Osseointegration, Implant Design, Surgical Technique and Excessive Loading
12.5 Complementary Techniques Used with Optimization Algorithms
12.5.1 Surrogate Models for Optimization Algorithms
12.5.1.1 Artificial Neural Networks (ANN)
12.5.1.2 Kriging Interpolation
12.5.1.3 Use of Support Vector Regression (SVR)
12.6 Conclusion
Acknowledgement
References
Index