CRACK DETECTION AND LOCALIZATION IN A COMPOSITE SHAFT USING ML APPROACH – A REVIEW

Authors

Mr. Vinod M. Bansode, Research Scholar, Dr. Manish Billore, Professor
Department of Mechanical Engineering (Ph.D.), Oriental University, Indore (M.P), India.

Abstract

Identification of crack depth and crack location is an area of concern for researchers across the world. This article presents a critical review of recent research done on crack identification and localization in rotary shaft using numerical and experimental modal analysis. Crack detection and localization in transmission shaft are very essential in various engineering applications. Excessive Vibrations in rotary shaft cause catastrophic failure of machine parts. To avoid catastrophic failure of rotary shaft it is required to recognize the damage in time. Experimental analysis is used to study the vibration characteristics of structures like natural frequency, damping and mode shapes. Natural frequency of rotary shaft can be obtained using the modal analysis method. Also artificial neural network can be used to identify crack depth and crack location. From the review of different research papers, it is observed that a lot of the research done on machine shaft with open transverse crack. Critical speed and natural frequency for known crack location and crack depth can be used to train an artificial neural network. With the help of artificial neural network crack location, and crack depth will be identified accurately.