Partial Discharge Pattern Recognition of High Voltage Cables Based on the Stacked Denoising Autoencoder Method

Abstract

Partial Discharge (PD) pattern recognition is one of the most important steps of PD based condition monitoring of high voltage cables, which is challenging as some types of the PD induced by cable defects are with high similarity. In recently years, deep learning based pattern recognition methods have achieved impressive pattern recognition accuracy on speech recognition and image recognition, which is one of the most potential techniques applicable for PD pattern recognition. The Stacked Denoising Autoencoder (SDAE) based deep learning method for PD pattern recognition of different insulation defects of high voltage cables is presented in the paper. Firstly, five types of artificial insulation defects of ethylene-propylene-rubber cables are manufactured in the laboratory, based on which PD testing in the high voltage lab is carried out to produce 5 types of PD signals, 500 samples for each defect types. PD feature extraction is carried out to generate 34 kinds of PD features, which are the input parameters of the PD pattern recognition methods. Secondly, the principle and network architecture of SDAE method and the flowchart of SDAE based PD pattern recognition are presented in details. Thirdly, the SDAE method is evaluated with the experimental data, 5 different types of PD signals, which achieves a recognition accuracy of 92.19%. Finally, the proposed method is compared with the traditional pattern recognition methods, Support Vector Machine (SVM) and Back Propagation Neural Network (BPNN). The results show that the pattern recognition accuracy of the proposed method is improved by 5.33% and 6.09% compared with the SVM method and the BPNN method respectively, which is applicable for pattern recognition of PD signals with high similarity.