Fault diagnosis of brushless DC motor for an aircraft actuator using a neural wavelet network

Abstract

Intelligent techniques (AI) have been successfully used in machines for fault diagnosis. In this paper a diagnostics approach based on discrete wavelet transform (DWT) and Neural network (NN) for stator winding inter-turn and open phase faults is presented. Simulink/Matlab is used to simulate a phase variable model of the BLDC motor with trapezoidal back - electric motive force (B-emf) under both normal and abnormal operating conditions. The NN classifies the healthy and faulty conditions by analysing the stator current and rotational speed of the motor.