Anomaly detection of a 5-phase AC electric motor using Machine Learning classification methods

With the goal of performing condition monitoring and anomaly detection applied to electric machines, tagged datasets are synthetically generated, consisting of time series of electrical and mechanical variables from a 5-phase AC synchronous motor, in different conditions of health or abnormal states. Different off-the-shelf Machine Learning classification methods are then applied to those datasets, to generate models that can identify the different abnormal states from the measured variables. Models’ performance is compared, and the best candidate selected for doing real-time anomaly detection and predictive maintenance of similar AC electric motors.