Smart Electrical and Mechanical Systems

Smart Electrical and Mechanical Systems

An Application of Artificial Intelligence and Machine Learning

1st Edition - June 21, 2022

Write a review

  • Editors: Rakesh Sehgal, Neeraj Gupta, Anuradha Tomar, Mukund Sharma, Vigna Kumaran
  • Paperback ISBN: 9780323907897
  • eBook ISBN: 9780323914413

Purchase options

Purchase options
DRM-free (PDF, EPub)
Sales tax will be calculated at check-out

Institutional Subscription

Free Global Shipping
No minimum order


Smart Electrical and Mechanical Systems: An Application of Artificial Intelligence and Machine Learning is an international contributed work with the most up-to-date fundamentals and conventional methods used in smart electrical and mechanical systems. Detailing methods and procedures for the application of ML and AI, it is supported with illustrations of the systems, process diagrams visuals of the systems and/or their components, and supportive data and results leading to the benefits and challenges of the relevant applications. The multidisciplinary theme of the book will help researchers build a synergy between electrical and mechanical engineering systems. The book guides readers on not only how to effectively solve problems but also provide high accuracy needed for successful implementation. Interdisciplinary in nature, the book caters to the needs of the electrical and mechanical engineering industry by offering details on the application of AI and ML in robotics, design and manufacturing, image processing, power system operation and forecasting with suitable examples.

Key Features

  • Includes significant case studies related to application of Artificial Intelligence and Machine Learning in Energy and Power, Mechanical Design and Manufacturing
  • Contains supporting illustrations and tables, along with a valuable set of references at the end of each chapter
  • Provides original, state-of-the-art research material written by international and national respected contributors


Researchers, professionals working in the field of Energy, Electrical and Mechanical Engineering, Engineers, energy experts, R&D organizations and industry professionals engaged in research in the field of smart systems

Table of Contents

  • Cover image
  • Title page
  • Table of Contents
  • Copyright
  • List of contributors
  • Chapter One. Machine learning and its applications
  • 1. Artificial intelligence
  • 2. Machine learning and deep learning
  • 3. Real life examples of deep learning and machine learning
  • 4. Components of machine learning
  • 5. Application areas of machine learning and deep learning
  • 6. Benchmark dataset(s)
  • 7. Conclusion
  • Chapter Two. A Multiple Object Recognition Approach via DenseNet-161 Model
  • 1. Introduction
  • 2. Related work
  • 3. DenseNet architecture
  • 4. Methodology
  • 5. Result analysis and discussion
  • 6. Conclusion
  • Chapter Three. Deep learning-based image processing for analyzing combustion behavior of gel fuel droplets
  • 1. Introduction
  • 2. Experimental methodology
  • 3. Edge detection methods
  • 4. Holistically nested edge detection
  • 5. Results
  • 6. Concluding remarks
  • Chapter Four. Deep learning-based methods for detecting surface defects in steel plates
  • 1. Introduction
  • 2. Dataset
  • 3. Metrics
  • 4. Methodology
  • 5. Results and inference
  • 6. Conclusions
  • Chapter Five. Extremum center interpolation-based EMD approach for fault detection of reciprocating compressor
  • 1. Introduction
  • 2. Theoretical background
  • 3. Proposed methodology
  • 4. Experimental setup, results, and discussion
  • 5. Conclusion
  • Chapter Six. Renewable energy sources forecasting and integration using machine learning
  • 1. Introduction
  • 2. Prediction of renewable energy sources
  • 3. Determination of plant size, location, and configuration
  • 4. Grid management
  • 5. Maximum power point tracking
  • 6. Conclusion
  • Chapter Seven. Role of big data analytic and machine learning in power system contingency analysis
  • 1. Introduction
  • 2. Contingency analysis
  • 3. Voltage stability analysis
  • 4. Applications of big data to power system
  • 5. Machine learning in power system application
  • 6. Proposed algorithm
  • 7. Case study and results
  • 8. Conclusion
  • Chapter Eight. Ensemble classifier-based protection scheme for hybrid microgrid
  • 1. Introduction
  • 2. Modeling and simulation of hybrid microgrid system
  • 3. Selection of critical buses for sensor placement using optimization algorithm
  • 4. Development of ESD-based protection scheme for hybrid microgrid
  • 5. Performance analysis
  • 6. Conclusion
  • Chapter Nine. A linear discriminant analysis based protection scheme for DC microgrid under stressed scenarios
  • Acronyms
  • 1. Introduction
  • 2. DC-microgrid architecture and fault analysis
  • 3. DC test microgrid system under study
  • 4. Linear discriminant analysis-based protection scheme
  • 5. Flowchart of the proposed LDA-based scheme
  • 6. Performance validation
  • 7. Conclusions
  • Chapter Ten. Machine learning application to power system forecasting
  • 1. Introduction
  • 2. Forecasting for probabilistic power system planning
  • 3. Data preprocessing steps
  • 4. Probabilistic forecasting using machine learning algorithms
  • 5. Performance comparison of well-established probabilistic PV generation forecasting models
  • 6. Conclusion
  • Chapter Eleven. Machine learning application to industrial control systems
  • 1. Introduction
  • 2. Modeling strategies of continuous stirred tank reactor
  • 3. Controlling strategies of continuous stirred tank reactor
  • 4. Neural network–based modeling and control of CSTR
  • 5. Results and discussions
  • 6. Conclusion
  • Chapter Twelve. Data-driven based optimal power system operation and control in a weak grid
  • 1. Introduction
  • 2. Overview of data-driven-based MG
  • 3. Potential applications of data-driven analysis in smart power grids (Table 12.1)
  • 4. Microgrid structure and its working
  • 5. Networked microgrids
  • 6. Intelligent energy storage devices
  • 7. Operational aspects for distribution system
  • 8. Recent available technologies and their outstanding results
  • 9. Conclusion and future scope
  • Chapter Thirteen. Short-term load forecasting in the presence of grid uncertainties using new methods based on deep learning
  • 1. Introduction
  • 2. Different aspects of LF
  • 3. LF classification and evaluation criteria
  • 4. DL methods
  • 5. Forecasting results analysis and compare
  • 6. Conclusion
  • Index

Product details

  • No. of pages: 314
  • Language: English
  • Copyright: © Academic Press 2022
  • Published: June 21, 2022
  • Imprint: Academic Press
  • Paperback ISBN: 9780323907897
  • eBook ISBN: 9780323914413

About the Editors

Rakesh Sehgal

Rakesh Sehgal is a Professor (Higher Academic Grade) at the National Institute of Technology Srinagar (J&K), India. He is an outstanding leader with sustained international acclaim for his work on synthesis and characterization (mechanical, metallurgical/metallographic, and tribological) of materials for aerospace, automobile, and bio-medical applications. Dr. Sehgal has investigated various materials such as adamite, piston alloys, stir cast aluminum-silicon alloys (hyper and hypo-eutectoid), copolymers, titanium alloys, tool & die steels, polymers, and nano-composites for machining parameters optimization and tribological behaviour. Prof. Sehgal served as Vice-President of Indian Society of Theoretical & Applied Mechanics (ISTAM) during 2001-2003, Executive member of Tribology Society of India (TSI) for 02 terms, and member of academic bodies of many other institutions. He has chaired technical sessions in many prestigious International and National Conferences. Prof. Sehgal received the Best Teacher Award for the year 2006-07. He is instrumental in introducing the concept of Project-Based Learning in NIT Hamirpur which has benefitted a large number of UG students in securing admissions in prestigious International Universities for MS/Ph.D. Prof. Sehgal has a distinguished career of 35 years in the field, teaching, research and administration. Prof. Sehgal has supervised 11 Ph.D. scholars in the area of tribo-materials for various industrial applications in automobile, aerospace, metal rolling and biomedical sectors. He is presently guiding 04 Ph.D. scholars in the area of metal composites for biomedical applications. He has also supervised 09 M.Tech. and 48 B.Tech. dissertations. Prof. Sehgal has published 168 research papers in International/National Journals and International/National conference proceedings. He has attended more than 35 International/National conferences in India and abroad. He has published one reference book on Performance Evaluation of Bearings, thirteen high-quality book chapters, and edited four books for Springer and Elsevier. Prof. Sehgal has completed many externally sponsored research projects worth in the area of Bearings Tribology and Mechatronics. He has established state-of-the-art facilities for research in the area of Bearings and Materials Tribology at NIT Hamirpur (H.P.). Prof. Sehgal has delivered 40 invited expert talks in various organizations in India and Abroad. He is currently working in the field of biomedical science and technology including the synthesis of smart materials, nanomaterials and tribological materials.

Affiliations and Expertise

Director and Professor, Department of Mechanical Engineering, National Institute of Technology Srinagar, Jammu and Kashmir, India

Neeraj Gupta

Dr. Neeraj Gupta is Ph.D. in power systems from Indian Institute of Technology Roorkee, Roorkee, India. He is a senior member of IEEE. He was a faculty with the Thapar University, from 2008 to 2009, Adani Institute of Infrastructure Engineering, Ahmedabad, India, in 2015 and NIT Hamirpur from 2015 to 2018 and presently, he has been working as an Assistant professor with the Electrical Engineering Department, National Institute of Technology, Srinagar, J&K, India. His work has been published in Q-1 international journals of repute like IEEE, Elsevier etc. He is also in the scientific advisory/organizing secretary of many reputed conferences of the country. He is referee of reputed journals of IEEE, Elsevier, Taylor and Francis, IET etc. His research interests include uncertainty quantification of power system, probabilistic power system, solar, wind, and electric vehicle technologies, Artificial intelligence, Machine learning, prediction etc.

Affiliations and Expertise

Assistant professor, Electrical Engineering Department, National Institute of Technology, Srinagar, J&K, India

Anuradha Tomar

Dr. Anuradha Tomar has 12 years of experience and currently is working as Postdoctoral researcher at Eindhoven University of Technology, the Netherlands. She has received her B.E Degree in Electronics Instrumentation & Control with Honours (2007) from University of Rajasthan and M.Tech Degree with Honours in Power System (2009) from National Institute of Technology Hamirpur. She has received her Ph. D in Electrical Engineering, from Indian Institute of Technology Delhi. Dr. Tomar has committed her research work for the development of sustainable, energy efficient solutions for the empowerment of society. Her research interest are Photovoltaic systems, Microgrid, Energy conservation and Automation. She has authored or co-authored 69 research/review papers in various reputed International, National Journals, and Conferences. Her research interests include photovoltaic systems, microgrids, energy conservation. She has also filled seven Indian patents on her name. Dr. Tomar is Senior member of IEEE, LM of ISTE, IETE, IEI, and IAENG.

Affiliations and Expertise

Postdoctoral Researcher, Eindhoven University of Technology, The Netherlands

Mukund Sharma

Dr. Mukund Dutt Sharma is currently working as Assistant Professor, National Institute of Technology, Srinagar. He received his B.E. Degree in Mechanical Engineering with distinction from UIET, Barkatullah University, Bhopal, M.Tech in CAD-CAM and Ph.D. in Mechanical Engineering from National Institute of Technology, Hamirpur. He has a distinguished career of 8 years in teaching, research, and administration. He is presently guiding 03 Ph.D. scholars in tribology. He has published 22 research papers in International/National Journals and International/National conference proceedings, reviewed book chapters of Manufacturing Technology (Volume 1 and 2) by P N Rao (TMH).

Affiliations and Expertise

Assistant Professor, EED, NIT Srinagar, J&K, India

Vigna Kumaran

Prof Vigna Kumaran completed his Bachelors Degree in Electrical and Electronics Engineering at the University of Manchester Institute of Science and Technology (UMIST), United Kingdom in 1998 under the Malaysian Government scholarship. He then pursued his PhD in Electrical Engineering at UMIST, UK and completed his PhD in 2001. He then joined the Malaysian electric al utility, Tenaga Nasional Berhad in 2002 as an electrical engineer. In 2005, he moved to Universiti Tenaga Nasional (UNITEN) and is presently a Professor in the Institute of Power Engineering.

Affiliations and Expertise

Head of Power Systems, Institute of Power Engineering, University Tenaga Nasional, Jalan, Malaysia

Ratings and Reviews

Write a review

There are currently no reviews for "Smart Electrical and Mechanical Systems"