Generator Stator Partial Discharge Pattern Recognition Based on PRPD-Grabcut and DSC-GoogLeNet Deep Learning

Abstract

Partial discharge (PD) pattern recognition of typical defects from generator stator bars is the basis of generator condition monitoring and fault diagnosis. A PD pattern recognition method for generator stator bars based on a phase-resolved partial discharge graph cut (PRPD-Grabcut) and Depthwise Separable Convolution GoogLeNet (DSC-GoogLeNet) deep learning neural network is proposed in this paper. First, five typical defects are designed on stator bars in the laboratory. A long-term high voltage test is carried out, and 37500 PRPD original graphs are obtained. Second, a PRPD-Grabcut method based on image segmentation is proposed, which is designed to extract key components of the PRPD map. Finally, a DSC-GoogLeNet based PD pattern recognition method is proposed, which combines the GoogLeNet inception module and depth-wise separable convolution. Experimental results show that the PRPD-Grabcut contributes to certain improvements in the recognition accuracy and training efficiency of the neural network. The DSC-GoogLeNet shows superiority in recognition accuracy, cross-entropy loss, and training time compared to a variety of existing lightweight neural networks. In addition, compared with other networks, the DSC-GoogLeNet greatly improves the recognition accuracy of PD types with similar but different risk levels for stator insulation.