METHODOLOGY FOR ONLINE INCIPIENT FAULT-DETECTION IN SINGLE-PHASE SQUIRREL-CAGE INDUCTION-MOTORS USING ARTIFICIAL NEURAL NETWORKS

This paper develops a new approach for on-line detection of incipient faults in single-phase squirrel-cage induction motors through the use of artificial neural networks. The on-line incipient fault detector is composed of two parts : (1) a disturbance and noise filter artificial neural network to filter out the transient measurements while retaining the steady-state measurements, and (2) a high-order incipient fault detection artificial neural network to detect incipient faults in single-phase squirrel-cage induction motors based on data collected from the motor. Simulation results show that neural networks yield satisfactory performance for on-line detection of incipient faults in single-phase squirrel-cage cage induction motors. The neural network fault detection methodology presented in this paper is not only limited to single-phase squirrel-cage motors (used as prototype) but can also be applied to many other types of rotating machines, with the appropriate modifications.