Fault Detection and Isolation in Electrical Machines using Deep Neural Networks

M. Sai; Parth Upadhyay; Babji Srinivasan

doi:10.14429/dsj.69.14413

M. Sai Department of Electrical Engineering, Indian Institute of Technology, Gandhinagar
Parth Upadhyay Department of Electrical Engineering, Indian Institute of Technology, Gandhinagar
Babji Srinivasan Department of Electrical Engineering, Indian Institute of Technology, Gandhinagar

DOI: https://doi.org/10.14429/dsj.69.14413

Keywords: Electric machine, Non stationary, Faults, Convolution neural network

Abstract

Condition and health monitoring of electrical machines during dynamic loading is a common, yet challenging problem in main battle tanks. Existing methods address this issue by extracting various features which are subsequently used in a classifier to isolate faults. However, this approach relies on the feature set being extracted and therefore most of the time does not provide expected accuracy in identification of faults. In this work, we have used convolution neural network that utilises the original time domain measurements for fault detection and isolation (FDI). Results from experimental studies indicate that the proposed approach can perform FDI with more than 95\% accuracy using commonly available current measurements.

Author Biographies

M. Sai, Department of Electrical Engineering, Indian Institute of Technology, Gandhinagar

Mr M. Sai, has completed BTech (Electrical Engineering) from BIT Sindri and MTech (Electrical Engineering) from Indian Institute of Technology Gandhinagar.

Parth Upadhyay, Department of Electrical Engineering, Indian Institute of Technology, Gandhinagar

Mr Parth Upadhyay, received his BTech from L.D. College of Engineering, and MTech from PDPU, Gujarat. He is currently pursuing PhD in Department of Electrical Engineering, Indian Institute of Technology, Gandhinagar.

Babji Srinivasan, Department of Electrical Engineering, Indian Institute of Technology, Gandhinagar

Dr Babji Srinivasan received his BTech (Instrumentation and Control Engineering) from the Madras Institute of Technology, India, in 2005, and PhD (Chemical Engineering) from Texas Tech University, in 2011. Presently working as Assistant Professor position at Indian Institute of Technology Gandhinagar. His research interests include: design, monitoring and control of cyber physical systems.