Machine Learning based Fault Classification using Stray Flux and Stator Current in Induction Motor

Induction motors have wide range of applications in many industrial processes. Fault detection and classification is an important subject for the sake of safe and reliable operation of induction motors. In this work, ANSYS Maxwell-based simulations are performed for four different loading conditions (25%, 50%, 75%, and 100%) of the induction motor to obtain the stator current and stray flux data under normal and faulty conditions (BRB1, BRB2, BRB3, FPP, and SE). A deep neural network (DNN) machine learning (ML) algorithm is then proposed and compared with support vector machine (SVM) and random forest classifiers (RFC) for the detection and classification of various faults in induction motors using stray flux and stator current. The proposed deep neural network algorithm has shown better accuracy for stray flux compared with SVM and RFC on 100% loading conditions, however, it could not perform well on stator current. The results indicate that the overall performance of all machine learning algorithms is less efficient for stator current than that of stray flux.