Transactions of China Electrotechnical Society  2020, Vol. 35 Issue (3): 659-668    DOI: 10.19595/j.cnki.1000-6753.tces.181954
Current Issue| Next Issue| Archive| Adv Search |
Pattern Recognition of Partial Discharges in DC XLPE Cables Based on Convolutional Neural Network
Zhu Yufeng1, Xu Yongpeng1, Chen Xiaoxin2, Sheng Gehao1, Jiang Xiuchen1
1. Department of Electrical Engineering Shanghai Jiao Tong University Shanghai 200240 China;
2. Electric Power Research Institute of State Grid Zhejiang Electric Power Co. Ltd Hangzhou 310014 China

Download: PDF (2790 KB)   HTML (1 KB) 
Export: BibTeX | EndNote (RIS)      
Abstract  Present partial discharge (PD) pattern recognition of DC cross-linked polyethylene (XLPE) cables has some limitations on the feature extraction of strong random signals. In order to solve this problem, this paper proposes a self-adaptive pattern recognition based on convolutional neural network (CNN). Convolutional architecture for fast feature embedding (CAFFE) was used to train the CNN. First, PD signals of four typical insulation defects were collected as the input samples of CAFFE. Then, the training cycles were iterated by taking self-adaptive convolution kernels to extract features, pooling layers to map features, nonlinear multi-classifiers to classify different types, until the CAFFE network was completely trained. After comparison of different parameters of solver, network structures and numbers of training samples, it is found that pattern recognition framework using the modified Alexnet network and attenuation learning rate method has the highest accuracy of 91.32%. Moreover, it has at least 8.97% improvement compared with traditional methods. The powerful self-adaptive learning capabilities of the new method provide a new idea for pattern recognition of DC cable fault diagnosis.
Key wordsConvolutional neural network      convolutional architecture for fast feature embedding      self-adaptive feature extraction      DC XLPE cable      partial discharge     
Received: 22 December 2018      Published: 12 February 2020
PACS: TM85  
Service
E-mail this article
Add to my bookshelf
Add to citation manager
E-mail Alert
RSS
Articles by authors
Zhu Yufeng
Xu Yongpeng
Chen Xiaoxin
Sheng Gehao
Jiang Xiuchen
Cite this article:   
Zhu Yufeng,Xu Yongpeng,Chen Xiaoxin等. Pattern Recognition of Partial Discharges in DC XLPE Cables Based on Convolutional Neural Network[J]. Transactions of China Electrotechnical Society, 2020, 35(3): 659-668.
URL:  
https://dgjsxb.ces-transaction.com/EN/10.19595/j.cnki.1000-6753.tces.181954     OR     https://dgjsxb.ces-transaction.com/EN/Y2020/V35/I3/659
Copyright © Transactions of China Electrotechnical Society
Supported by: Beijing Magtech