Open-circuit Fault Diagnosis for Modular Multilevel Converter Using Wavelet Neural Network

Modular multilevel converter (MMC) is the popular AC/DC system commutation equipment, and its reliable operation is related to the stability of the entire AC-DC system. After analyzing the fault characteristics of the sub-module failure of the MMC, a fault diagnosis method based on Wavelet Analysis-BP Neural Network is proposed. Wavelet Analysis is used to extract the fault feature information of, Neural Network is used for fault classification and fault degree determination. The MMC model is built on the PSCAD/EMTDC platform, and the three-phase voltage signals in the normal state and the fault state are collected. Then the wavelet transform is used to decompose the acquired signals to obtain the feature vector and normalize the feature vector. Finally, the feature vector is input into the neural network to diagnose the location and extent of the MMC fault. The simulation results show that the proposed method can accurately identify the open fault and fault extent of the MMC submodule.