Probabilistic diagnosis of insulation failure of motor winding based on feature distributions

This paper proposes a novel and simple method for diagnosing insulation failure (short-circuit) in stator windings of motors under load conditions. The method involves probabilistic process for gauging the probability of failure occurrence by considering distributions of features, i.e. magnitude and phase of current flowing into stator windings, depending on the condition of the insulation failure of windings. A series of laboratory experiments and analyses of the results for motors with artificially introduced insulation failure prove that the proposed method is promising.