Application of Artificial Intelligence to Real-Time Fault Detection in Permanent-Magnet Synchronous Machines

Abstract

This paper discusses faults in rotating electrical machines in general and describes a fault detection technique using artificial neural network (ANN) which is an expert system to detect short-circuit fault currents in the stator windings of a permanent-magnet synchronous machine (PMSM). The experimental setup consists of PMSM coupled mechanically to a dc motor configured to run in torque mode. Particle swarm optimization is used to adjust the weights of the ANN. All simulations are carried out in MATLAB/SIMULINK environment. The technique is shown to be effective and can be applied to real-time fault detection.