Neural Network Algorithms and Their Engineering Applications
- 1st Edition - January 9, 2025
- Authors: Chao Huang, Hailong Huang, Yiying Zhang
- Language: English
- Paperback ISBN:9 7 8 - 0 - 4 4 3 - 2 9 2 0 2 - 6
- eBook ISBN:9 7 8 - 0 - 4 4 3 - 2 9 2 0 3 - 3
Neural Network Algorithms and Their Engineering Applications presents the relevant techniques used to improve the global search ability of neural network algorithms in solvin… Read more
Purchase options
Institutional subscription on ScienceDirect
Request a sales quoteNeural Network Algorithms and Their Engineering Applications presents the relevant techniques used to improve the global search ability of neural network algorithms in solving complex engineering problems with multimodal properties. The book provides readers with a complete study of how to use artificial neural networks to design a population-based metaheuristic algorithm, which in turn promotes the application of artificial neural networks in the field of engineering optimization.
The authors provide a deep discussion for the potential application of machine learning methods in improving the optimization performance of the neural network algorithm, helping readers understand how to use machine learning methods to design improved versions of the algorithm. Users will find a wealth of source code that covers all applied algorithms. Code applications enhance readers' understanding of methods covered and facilitate readers' ability to apply the algorithms to their own research and development projects.
The authors provide a deep discussion for the potential application of machine learning methods in improving the optimization performance of the neural network algorithm, helping readers understand how to use machine learning methods to design improved versions of the algorithm. Users will find a wealth of source code that covers all applied algorithms. Code applications enhance readers' understanding of methods covered and facilitate readers' ability to apply the algorithms to their own research and development projects.
- Provides a comprehensive understanding of the development of metaheuristics, helping readers grasp the principle of employing artificial neural networks to design a population-based metaheuristic algorithm
- Shows readers how to overcome the challenges faced in applying neural network algorithms to complex engineering optimization problems with multimodal properties
- Demonstrates how to design new variants of neural network algorithms and how to apply machine learning methods to neural network algorithms
- Covers source code to help readers solve engineering optimization problems
- Shows readers how to develop the offered source code to create innovative solutions to their problems
Computer Science researchers, artificial intelligence researchers, and researchers and practitioners working in the fields of data science, machine learning, and optimization. The primary audience also includes data analysts, software engineers, as well as researchers and professionals across the field of engineering
- Title of Book
- Cover image
- Title page
- Table of Contents
- Copyright
- Preface
- 1: Introduction
- 1.1. The development and classification of metaheuristic algorithms
- 1.2. Overview and organization of the book
- 2: Neural network algorithms
- 2.1. Motivation
- 2.2. Structure and implementation
- 2.3. Challenges in engineering problems with multimodal properties
- Appendix 2.A. Source code of NNA
- Appendix 2.B. Source code of GSA
- Appendix 2.C. Source code of TLBO
- 3: Constrained engineering design optimization problems
- 3.1. Problem statement
- 3.1.1. Rolling element bearing design problem
- 3.1.2. Speed-reducer design problem
- 3.1.3. Pressure-vessel design problem
- 3.2. Chaotic neural network algorithm with competitive learning
- 3.2.1. Motivation of CCLNNA
- 3.2.2. The framework and implementation of CCLNNA
- 3.3. CCLNNA for real-world engineering design problems
- 3.3.1. CCLNNA for the rolling element bearing design problem
- 3.3.2. CCLNNA for the speed-reducer design problem
- 3.3.3. CCLNNA for the pressure-vessel design problem
- 3.4. Discussion on the validity of chaos theory and competitive learning
- Appendix 3.A. Source code of CCLNNA
- Appendix 3.B. Source code of GWO
- Appendix 3.C. Source code of WOA
- Appendix 3.D. Source code of SCA
- Appendix 3.E. Source code of MVO
- Appendix 3.F. Source code of HHO
- Appendix 3.G. Source code of MFO
- Appendix 3.H. Source code of HGSO
- Appendix 3.I. Source code of SHO
- 4: Parameter estimation of proton exchange membrane fuel cell models
- 4.1. Problem statement
- 4.1.1. Basic knowledge
- 4.1.2. Mathematical formulation
- 4.1.3. Objective function
- 4.2. Multiple learning neural network algorithm
- 4.2.1. Motivation
- 4.2.2. The framework of MLNNA
- 4.2.3. Implementation of MLNNA
- 4.3. Application in the parameter estimation of PEMFC models
- 4.3.1. Experimental results on the BCW 500 W PEMFC model
- 4.3.2. Experimental results on the NedStack PS6 PEMFC model
- 4.4. Discussion on the effectiveness of the improved strategies
- Appendix 4.A. Source code of MLNNA
- Appendix 4.B. Source code of SOA
- Appendix 4.C. Source code of TSO
- Appendix 4.D. Source code of BSA
- Appendix 4.E. Source code of JAYA
- Appendix 4.F. Source code of STOA
- 5: Parameter extraction of photovoltaic models
- 5.1. Problem statement
- 5.1.1. Solar photovoltaic modeling
- 5.1.2. Problem formulation
- 5.2. TLNNA
- 5.2.1. Teaching–learning-based optimization
- 5.2.2. The frame of TLNNA
- 5.2.3. The implementation of TLNNA
- 5.3. TLNNA for unconstrained benchmark functions
- 5.3.1. Benchmark test functions
- 5.3.2. Parameter settings
- 5.3.3. Results and analysis
- 5.4. Application in the parameter extraction of PV models
- 5.4.1. Experimental results for SDM
- 5.4.2. Experimental results for DDM
- 5.4.3. Experimental results for PVM
- 5.5. Discussion on the effectiveness of the hybrid strategy
- Appendix 5.A. Source code of TLBO
- Appendix 5.B. Source code of PGJAYA
- Appendix 5.C. Source code of MLBSA
- Appendix 5.D. Source code of SSA
- Appendix 5.E. Source code of PSO
- 6: Energy consumption optimization of a UAV-assisted IoT data collection system
- 6.1. Problem statement
- 6.2. The proposed method
- 6.2.1. Basic knowledge
- 6.2.2. Adaptive neural network algorithm
- 6.3. Results and discussion
- Appendix 6.A. Source code of DEVIPS
- Appendix 6.B. Source code of DEEM
- Appendix 6.C. Source code of DE
- 7: Conclusion
- 7.1. Content review
- 7.2. Future direction
- Appendix 7.A. Source code of SRLBSA
- Acronyms
- Index
- No. of pages: 242
- Language: English
- Edition: 1
- Published: January 9, 2025
- Imprint: Morgan Kaufmann
- Paperback ISBN: 9780443292026
- eBook ISBN: 9780443292033
CH
Chao Huang
Dr. Chao Huang received the B.Sc. degree in automation, from China University of Petroleum, Beijing, China, in June 2012, and received Ph.D degree from the University of Wollongong, Australia, in Dec. 2018. From Sep. 2018 to Sep. 2019, she worked as a project leader at National Institute of Informatics, Tokyo, Japan. From Oct. 2019 to July 2021, she worked as a postdoctoral research fellow at the School of Mechanical and Aerospace Engineering, Nanyang Technological University, Singapore. She is now a research assistant professor at the Department of Industrial and Systems Engineering, the Hong Kong Polytechnic University, Hong Kong. Her interests include motion planning, human machine collaboration, fault tolerant, and automotive control and application.
Affiliations and expertise
Research Assistant Professor, Department of Industrial and Systems Engineering, the Hong Kong Polytechnic University, Hong KongHH
Hailong Huang
Dr. Hailong Huang received a B.Sc. degree in automation, from China University of Petroleum, Beijing, China, in June 2012, and received Ph.D degree in Systems and Control from the University of New South Wales, Sydney, Australia, in March 2018. From Feb. 2018 to July 2021, he worked as a postdoctoral research fellow at the School of Electrical Engineering and Telecommunications, University of New South Wales, Sydney, Australia. He is now an assistant professor at the Department of Aeronautical and Aviation Engineering, the Hong Kong Polytechnic University. His current research interests include the coordination, navigation and control of ground robots and unmanned aerial vehicles.
Affiliations and expertise
Assistant Professor, Department of Aeronautical and Aviation Engineering, the Hong Kong Polytechnic University, Hong KongYZ
Yiying Zhang
Dr Yiying ZHANG received the B.S. degree from Yanshan University, Qinhuangdao, China, in 2014, the M.S. degree from Harbin Institute of Technology, Harbin, China, in 2016, and the Ph.D. degree from Tianjin University, Tianjin, China, in 2021, all in information and communication engineering. He is currently a postdoctoral fellow of the Hong Kong Polytechnic University. His research interests include machine learning, evolutionary computation, and path planning of unmanned aerial vehicles.
Affiliations and expertise
Hong Kong Polytechnic University, Hong KongRead Neural Network Algorithms and Their Engineering Applications on ScienceDirect