Resolving anomalies of current signatures owing to stator winding faults and voltage unbalances in induction motor through machine learning

Purpose The early detection of frequently occurring motor faults owing to various operational stresses in the industrial environment is of utmost importance to safeguard the motors against disastrous failures. The purpose of this study is to put emphasis on the detection of varying severity of incipient stator winding inter-turn-short-circuit faults in a three-phase induction motor and to differentiate such faults from the anomalies introduced in the line currents due to unbalanced supply voltage. Design/methodology/approach First, feature extraction was performed by estimating 11 conventional statistical parameters from the normalized three-phase stator currents. Then, all the statistical features were fed to a linear discriminant analysis classifier to classify the different fault types, namely, inter-turn-short-circuit fault, voltage unbalance and voltage unbalance equivalent to turn-turn fault. Findings A minimum of 0.28% of shorted turn could be detected with 98.7% classification accuracy. Successful detection of faults on different rating of motors at different loads establishes the proposed fault diagnosis method independent of machine rating and load level. Originality/value Several fault diagnosis techniques have been presented in the referenced articles. Mostly, all the proposed techniques were carried out on balanced supply voltages. But, this study reports a novel condition monitoring method for detection of stator winding inter-turn-short-circuit faults in a three-phase induction motor, considering the unbalanced supply voltage scenarios.