Data-driven Fault Diagnosis of Induction Motors Using a Stacked Autoencoder Network

Current signatures from an induction motor are normally used to detect anomalies in the condition of the motor based on signal processing techniques. However, false alarms might occur if using signal processing analysis alone since missing frequencies associated with faults in spectral analyses does not guarantee that a motor is fully healthy. To enhance fault diagnosis performance, this paper proposes a machinelearning based method using in-built motor currents to detect common faults in induction motors, namely inter-turn stator winding-, bearing- and broken rotor bar faults. This approach utilizes single-phase current data, being pre-processed using Welch's method for spectral density estimation. Further, several deep learning features are extracted using stacked autoencoder networks. The proposed scheme can predict the faults at high accuracy while reducing expertise demand. The proposed method is validated on an in-house laboratory setup under variable speed and load conditions, showing a classification accuracy over 95%. Furthermore, multiple support vector machine and k-nearest neighbor classifiers are tested with the same data for a comparative study. Finally, the performance of di erent fault classifiers are evaluated based on accuracy, computational burden and classification consistency.