Advanced Signal Processing for Industry 4.0, Volume 1: Evolution, communication protocols, and applications in manufacturing systems

This document was uploaded by one of our users. The uploader already confirmed that they had the permission to publish it. If you are author/publisher or own the copyright of this documents, please report to us by using this DMCA report form.

Simply click on the Download Book button.

Yes, Book downloads on Ebookily are 100% Free.

Sometimes the book is free on Amazon As well, so go ahead and hit "Search on Amazon"

This book describes the use of advance signal processing techniques for different Industry 4.0 applications, including: Non-destructive testing, Decisions under Parametric Uncertainty, Deep learning for industrial sector, Energy-efficient Industry 4.0 etc. The book will help readers to understand future needs of industries.

Author(s): Irshad Ahmad Ansari, Varun Bajaj
Publisher: IOP Publishing
Year: 2023

Language: English
Pages: 356

Cover
Title
Copyright
Contents
Preface
Acknowledgments
Editor biographies
List of contributors
Contributors’ biographies
1 Robotics vision for industrial automation
1.1 Introduction
1.1.1 Code scanning
1.1.2 Robotic guidance
1.1.3 Machine control
1.1.4 Sorting
1.2 Computer vision system
1.2.1 Image representation
1.2.2 RGB colour model
1.2.3 HSV colour model
1.2.4 Greyscale image
1.2.5 Image segmentation
1.2.6 Thresholding
1.2.7 Blurring
1.2.8 Edge detection
1.2.9 Object detection
1.2.10 Region of interest (ROI)
1.3 Applications of vision system
1.3.1 Vision controlled robotic arm
1.3.2 In manufacturing and mining
1.3.3 In industry application
1.4 Proposed work
1.4.1 Proposed model
1.4.2 Model design
1.4.3 Working (model-I)
1.4.4 Evolution (model-I)
1.4.5 Working (model-II)
1.4.6 Evaluation (model-II)
1.5 Industrial demo (apple sorting)
1.5.1 Yellow apple sorting
1.5.2 Red apple sorting
1.6 Conclusion
References
2 Capnography signal processing in trend with Industry 4.0 advancement
2.1 Capnography 4.0
2.2 Capnography measurement and physiology
2.3 Capnography signal interpretation
2.4 Capnography—annotation and classification
2.5 Capnography in medical interpretation
2.5.1 Airway integrity
2.5.2 Asthma
2.5.3 Procedural sedation
2.5.4 Apnea monitoring
2.5.5 Cardiac arrest and resuscitation
2.5.6 Pulmonary embolism
2.5.7 Laparoscopy
2.6 Capnography at intensive care units
2.7 Capnogram modeling for respiratory monitoring
2.8 Capnography signal outside healthcare environment
2.8.1 Ice core analysis
2.8.2 Mines
2.8.3 Space station
2.8.4 Submarines
2.9 Conclusion
Acknowledgments
References
3 The future of Industry 4.0: private 5G networks
3.1 Introduction
3.1.1 Advantage of 5G: high speed and capacity
3.1.2 Industry 4.0 and mobile connectivity
3.1.3 Industry 4.0 opportunities and challenges
3.2 Private 5G networks’ flexibility in Industry 4.0
3.3 Use cases of 5G networks in manufacturing
3.4 Specific technological elements for private networks
3.5 Other benefits of 5G features for private networks
3.5.1 Edge computing
3.5.2 5G network slicing
3.5.3 Open networking
3.6 Advantages and applications of private 5G networks
3.6.1 Advantages of private 5G networks
3.6.2 Automated and robotic deployments in retail
3.6.3 Smart cities, smart offices, smart factories, and the gaming industry
3.6.4 Applications in healthcare
3.6.5 Fixed wireless access
3.7 Citizens broadband radio service (CBRS) for private 5G network
3.7.1 CBRS overview
3.7.2 Requirements for CBRS
3.7.3 Components of the CBRS network architecture
3.7.4 Network structure for CBRS
3.8 Modeling of 5G private networks’ economic impact
3.8.1 Overview
3.8.2 Business perspective
3.8.3 Perspective of a service provider
3.8.4 View from an infrastructure vendor
3.8.5 New player perspective
3.8.6 Various models of funding for private networks
3.8.7 Finding synergies in common
3.9 Conclusion
References
4 Applications of infrared imaging for non-destructive testing and evaluation of industrial components
4.1 Introduction
4.2 Theory
4.2.1 Linear frequency modulated thermal wave imaging
4.2.2 Pre-processing using polynomial fit
4.2.3 Signal processing using pulse compression
4.2.4 Image processing: segmentation, edge detection
4.3 Modeling and simulation
4.4 Experimentation
4.5 Results and discussions
4.6 Conclusion
Acknowledgments
References
5 Customer-driven healthcare through mission-focused approach in 4IR
5.1 Introduction
5.2 Fourth Industrial Revolution in healthcare
5.2.1 Possibilities and challenges
5.2.2 Digital twins in healthcare
5.2.3 Wearable sensors in continuous health monitoring
5.3 Customer-centric design in the context of Industry 4.0
5.3.1 Targeting and evaluating customer-centered service design
5.3.2 Customer-centric healthcare with a mission-strategic emphasis
5.3.3 Mission-strategic perspective, ethics, and overall quality in healthcare
5.3.4 Customer-centric design through metadesign
5.4 Enhancing customer orientation in organizations
5.4.1 Customer-centric service policy through comprehensive training
5.4.2 Shared mission in multidisciplinary design and action
5.5 Process reengineering with renewed mission
5.5.1 Case: customer-centric dental care
5.5.2 Process reengineering with mission-strategic vision
5.6 Conclusions
Acknowledgments
References
6 The application of Industry 4.0 technologies for automated health monitoring and surveillance during pandemics and post-pandemic life
6.1 Introduction
6.2 Industry 4.0
6.2.1 IoT
6.2.2 AI, ML, big data, and cloud computing
6.3 Comprehensive literature review
6.4 Automated monitoring and surveillance techniques
6.5 Conclusion and future scope
Acknowledgments
References
7 A novel computational intelligence approach to making efficient decisions under parametric uncertainty of practical models and its applications to Industry 4.0
7.1 Introduction
7.2 Exponential distribution
7.2.1 Two-parameter exponential distribution
7.3 Analytical inferences for constructing new-sample prediction limits
7.3.1 Example of constructing new-sample (1−α)-prediction limits
7.4 Analytical inferences for constructing within-sample prediction limits
7.4.1 Example of constructing within-sample (1−α)-prediction limits
7.5 Optimization of anticipated inspection process
7.6 Optimization of single-period decision-making models
7.7 Advanced techniques of signal processing in terms of hypotheses testing and misclassification probability
7.7.1 Optimizing the product acceptance process in terms of misclassification probability
7.7.2 Model of signal detection process in terms of hypotheses testing
7.7.3 Statistical hypotheses testing whether two samples come from the same distribution under parametric uncertainty
7.7.4 Parametric estimation via shortest-length confidence intervals
7.8 Conclusion
References
8 Role of artificial intelligence in industries for advanced applications
8.1 Introduction
8.2 Seven top technologies of AI that are responsible for profoundly influencing the fourth industrial revolution
8.2.1 Artificial intelligence of things (AIOT)
8.2.2 Additive manufacturing
8.2.3 Data science
8.2.4 Cloud computing
8.2.5 Computer vision
8.2.6 Natural language processing (NLP)
8.2.7 Robotics
8.3 Conclusion
References
9 Artificial intelligence based flexible manufacturing system (FMS)
9.1 Introduction
9.2 Background of AI in automation and FMS
9.3 Application areas of AI
9.3.1 Supply chain management
9.3.2 AI in design and manufacturing
9.3.3 AI in warehouse management
9.3.4 AI process automation
9.3.5 AI for predictive maintenance
9.3.6 AI-based product development
9.3.7 AI-based visual inspections and quality control
9.3.8 AI order management
9.4 Some of the real industrial set up and AI application
9.4.1 Maintenance applications
9.4.2 Warehouse logistics, MES, and ERP applications
9.4.3 Operational simulation and optimization
9.5 Process planning
9.5.1 Problem description
9.5.2 Selection
9.5.3 Elaboration
9.5.4 Sequencing
9.6 Design strategies
9.7 Rule-based model
9.8 Structure of FMS
9.8.1 Process planning in FMS
9.8.2 Process control and scheduling
9.8.3 Scheduling
9.8.4 Intelligent scheduling
9.8.5 Knowledge base
9.8.6 Declarative knowledge
9.8.7 Knowledge-based scheduling system
9.9 Conclusion
References
10 Applications of deep learning in revolutionizing industrial sectors
10.1 Introduction
10.2 Relevance in Industry 4.0
10.3 How does a network learn?
10.4 Application in stock market
10.4.1 A brief about the stock market
10.4.2 A generalized approach
10.4.3 The RNN and LSTM models
10.4.4 Deep learning researches in stock market analysis
10.5 Application in marketing industry
10.5.1 A brief overview
10.5.2 Resolving issues through deep learning
10.5.3 Recommender systems
10.6 Application in bioinformatics
10.6.1 Diverse areas and scope
10.6.2 Deep learning implementation in genomics
10.6.3 Challenges and strategies
10.6.4 Concept of federated learning
10.7 Application in cybersecurity
10.7.1 The need
10.7.2 Landscape and desired solutions
10.7.3 Deep learning researches
10.7.4 Challenges of using deep learning models in industry
10.8 Case study: stock market prediction
10.8.1 About the dataset
10.8.2 Statistical analysis and preprocessing
10.8.3 Computational models and their comparative analysis
10.9 Conclusion
References
11 Digitalization in family businesses—a case study in a food industry in Turkey
11.1 Introduction
11.2 Conceptual framework
11.2.1 Industry 4.0
11.2.2 Digitalization and digital transformation
11.2.3 Family businesses and digital transformation process
11.3 Research method
11.4 Research results
11.4.1 Information about the business and interviewees
11.4.2 Where does the business see itself in digital transformation?
11.4.3 What kind of digitalization actions have been taken within the scope of which business functions in the enterprise?
11.4.4 The impact of being a family business on digitalization
11.5 Conclusion
11.6 Future research directions
References
Key terms and definitions
12 Automatic identification of finger movements for industrial robotic applications using electromyogram signals
12.1 Introduction
12.2 Methodology
12.2.1 Dataset
12.2.2 TQWT
12.2.3 Feature extraction
12.2.4 Classification methods
12.2.5 Performance metrics
12.3 Results
12.4 Conclusion
References
13 Data-driven approach to design energy-efficient precoder for QoS-aware MIMO-MRCN system in context of Industry 4.0
13.1 Introduction
13.2 Related works
13.3 System model
13.3.1 Relay selection and precoder design schemes
13.3.2 A DL-based low complexity approach for precoder designing
13.3.3 DNN architecture
13.3.4 Dataset generation, training, and deployment phase
13.4 Numerical results
13.5 Conclusion
References