Predictive Analytics for Mechanical Engineering: A Beginners Guide (eBook)

This book focus on key component required for building predictive maintenance model. The current trend of Maintenance 4.0 leans towards the preventive mechanism enabled by predictive approach and condition-based smart maintenance. The intelligent decision support, earlier detection of spare part failure, fatigue detection is the main slices of intelligent and predictive maintenance system (PMS) leading towards Maintenance 4.0 This book presents prominent use cases of mechanical engineering using PMS along with the benefits. Basic understanding of data preparation is required for development of any AI application; in view of this, the types of the data and data preparation processes, and tools are also presented in this book.

Dr. Parikshit is a senior member IEEE and is a Dean Research and Development, professor and the head of Department of Artificial Intelligence and Data Science at Vishwakarma Institute of Information Technology, Pune, India and has 23 years of teaching and research experience. He completed his Ph.D. from Aalborg University, Denmark, and continued as a postdoc researcher at CMI, Copenhagen, Denmark. His research interests are machine learning, data science, algorithms, Internet of things, identity management and security. He is guiding eight Ph.D. students in the area of IoT and machine learning, and recently, six students have successfully defended their Ph.D. under his supervision. He is also the recipient of 'Best Faculty Award' by Sinhgad Institutes and Cognizant Technologies Solutions. He has delivered 200 plus lectures at national and international level and authored 54 books.

 

Dr. Pravin P. Hujare is working as an associate professor in Department of Mechanical Engineering, Vishwakarma Institute of Information Technology, Pune, India. He has done Ph.D. in Noise & Vibration Control from COEP, Savitribai Phule Pune University, Pune. He has 24 + years of teaching and research experience. He obtained M.E. (Mechanical Engineering) degree from University of Mumbai. He has 15 patents and 35+ research publications in national and international conferences and journals. He has received research funding for the project 'Investigations on Damping Performance of Segmented Passive Constrained Layer Damping Treatment' by SPPU, Pune. He has presented a research article in SAE Noise and Vibration International Conference, Grand Rapids. USA. His research interests are machine design, mechanical vibration and noise control, machine learning and data analytics.

 

Dr. Gitanjali R. Shinde has overall 14 years of experience and presently working as an associate professor in the Department of Computer Engineering, Vishwakarma Institute of Information Technology, Pune, India. She has done Ph.D. in Wireless Communication from CMI, Aalborg University, Copenhagen, Denmark, on Research Problem Statement 'Cluster Framework for Internet of People, Things and Services' - Ph. D. awarded on 8 May 2018. She obtained M.E. (Computer Engineering) degree from the University of Pune, Pune, in 2012 and B.E. (Computer Engineering) degree from the University of Pune, Pune, in 2006. She has received research funding for the project 'Lightweight group authentication for IoT' by SPPU, Pune. She has presented a research article in World Wireless Research Forum (WWRF) meeting, Beijing, China. She has published 50+ papers in national and international conferences and journals.

---

This book focus on key component required for building predictive maintenance model. The current trend of Maintenance 4.0 leans towards the preventive mechanism enabled by predictive approach and condition-based smart maintenance. The intelligent decision support, earlier detection of spare part failure, fatigue detection is the main slices of intelligent and predictive maintenance system (PMS) leading towards Maintenance 4.0 This book presents prominent use cases of mechanical engineering using PMS along with the benefits. Basic understanding of data preparation is required for development of any AI application; in view of this, the types of the data and data preparation processes, and tools are also presented in this book.