A New Rotor Broken Bar Fault Diagnosis by Using CNN Based Current Signal of An Induction Motor

Abstract

Abstract— In industrial contexts, the efficient operation of induction motors is paramount, necessitating robust condition monitoring and fault diagnosis techniques to mitigate costly disruptions. In this study, we introduce an innovative approach for intelligent fault detection of broken rotor bars in induction motors, harnessing the "Signal2Image" method and convolutional neural networks (CNN). Leveraging a comprehensive current signal dataset from Aline Elly Treml Western Parana State University, encompassing various levels of broken rotor bar (BRB) faults and diverse loading conditions, our method automatically extracts essential features from input data. The "Signal2Image" process transforms time-domain current signals into 2D grayscale pixel images, facilitating CNN-based image classification to identify fault-related patterns. Through meticulous CNN parameter tuning, we achieve an impressive fault classification accuracy of 88% across all fault cases while optimizing computational efficiency. A significant contribution of this work is the substantial reduction in computational time for fault classification, surpassing existing approaches. This research enhances fault detection accuracy and streamlines the process, contributing to the field of predictive maintenance for induction motors.