For two core issues of fault feature extraction and fault identification,a novel method based on principal component analysis and improved multi-population genetic algorithm optimized BP neural network were presented for diagnosis of three-phase rectifiers.Firstly, principal component analysis is used to extract the features corresponding to various fault,then fault types are identified through multi-population genetic algorithm of immigration operator and migration operator optimized neural network.Simulation results show that this method for three-phase full-bridge controlled rectifier fault diagnosis can identify and locate each fault type accurately,and has better robustness and better diagnostic accuracy rate characteristics.
