Robust Open-Circuit Fault Diagnosis for PMSM Drives Using Wavelet Convolutional Neural Network With Small Samples of Normalized Current Vector Trajectory Graph

Abstract

Open-circuit fault is one of the most common faults in permanent magnet synchronous machine (PMSM) drives. The open-circuit fault can cause the obvious change of stator currents of PMSM. Hence, the previous artificial intelligence based-fault diagnosis method mainly relies on the samples extracted from stator currents. However, the large sets of the samples are required due to the variation of the PMSM operating point, increasing the complexity of fault diagnosis. What's more, stator currents are easily affected by the noise, decreasing the accuracy of fault diagnosis. To solve the issues, this paper proposes a robust open-circuit fault diagnosis method using wavelet convolutional neural network with small samples of normalized current vector trajectory graph. The proposed method uses current normalization to establish small sample sets and combines convolutional neural network with discrete wavelet transform to enhance robustness to noise. The proposed fault diagnosis method is validated by simulation and experiment. Both the results show that the proposed method can effectively diagnose 22 kinds of open-circuit fault types (including healthy mode), being with great antinoise ability and robustness to different working conditions.