Fault diagnosis of power electronic circuits based on neural network and waveform analysis

Abstract

Based on neural network theory, a new fault diagnosis method for power electronic circuits is presented. By keeping the relations between faults and waveforms in a neural network, the neural network can be trained to detect faults. So automation of fault diagnosis can be realized. In this paper, the fault diagnosis of a three-phase SCR rectifier circuit will be taken as an example to illustrate the new method. Both simulation and experimental results are given.