To handle the fault diagnosis of multilevel inverter, a new approach based on hybrid intelligent algorithms has been proposed in this paper. Firstly, the wavelet packet transform (WPT) is applied for the multi-scale wavelet packet decomposition of the fault signal, and the fault feature vector is extracted from the reconstructed wavelet packet energy. Then, the principal component analysis (PCA) is employed to extract the principal information with lower dimension. Finally, the BP neural network (NN) is used for the fault diagnosis and identification. The simulation results show that the proposed method is more accurate for the fault diagnosis of multilevel inverter than traditional methods and more robust to the noise of fault signals A NEW APPROACH TO FAULT DIAGNOSIS OF MULTILEVEL INVERTER