Fault diagnosis of power electronic device based on wavelet and neural network

A novel method for fault diagnosis based on wavelet and neural network of three-phase bridge inverter circuit is proposed in this paper. In the proposed method, the wavelet packet is used to decompose the fault signal and extract fault characteristics effectively. BP neural network and PSO-optimized neural network are perform to the circuit fault diagnoses separately and the results of both method are compared. Finally, the proposed method is modeled and simulated on the MATLAB/Simulink platform. The result shows that the PSO-BP neural network has faster convergence speed and higher diagnostic accuracy and is more effective in fault diagnosis of power electronic circuits.