Detection of broken rotor bar fault in an induction motor using convolution neural network

Induction motors are prime component in the industries. Hence, condition monitoring and fault diagnosis of induction motor important to avoid shutdowns unplanned maintenance. A technique based on time-domain grayscale current signal imaging (TDGCI) convolutional neural network (CNN) is proposed for intelligent detection broken rotor bar an motor. The standard dataset made available by Aline Elly Treml Western Parana State University used analysis. This acquired simulating healthy (BRB) conditions with four increasing severity levels (1BRB, 2BRB, 3BRB, 4BRB) at eight loading varying from no load full load. Conventional machine learning techniques have limitations feature selection, while can automatically extract features given input image. TDGCIs obtained as exploit enormous capability CNN carry out image classification, thereby classifying faults embedded images. efforts presented design parameters achieve classification accuracy 99.58% all cases optimized computational time. significant reduction time compared peer published work contribution.