基于卷积神经网络的直流XLPE电缆局部放电模式识别技术

doi:10.19595/j.cnki.1000-6753.tces.181954

Abstract
Figure/Table
References
Related Citation (15)

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 words： Convolutional 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

[1] 何金良, 党斌, 周垚, 等. 挤压型高压直流电缆研究进展及关键技术述评[J]. 高电压技术, 2015, 41(5): 1417-1429.
He Jinliang, Dang Bin, Zhou Yao, et al.Reviews on research progress and key technology in extruded cables for HVDC transmission[J]. High Voltage Engineering, 2015, 41(5): 1417-1429.
[2] 杜伯学, 李忠磊, 杨卓然, 等. 高压直流交联聚乙烯电缆应用与研究进展[J]. 高电压技术, 2017, 43(2): 344-354.
Du Boxue, Li Zhonglei, Yang Zhuoran, et al.Application and research progress of HVDC XLPE cables[J]. High Voltage Engineering, 2017, 43(2): 344-354.
[3] 钟力生, 任海洋, 曹亮, 等. 挤包绝缘高压直流电缆的发展[J]. 高电压技术, 2017, 43(11): 3473-3489.
Zhong Lisheng, Ren Haiyang, Cao Liang, et al.Development of high voltage direct current extruded cables[J]. High Voltage Engineering, 2017, 43(11): 3473-3489.
[4] 周远翔, 赵健康, 刘睿, 等. 高压/超高压电力电缆关键技术分析及展望[J]. 高电压技术, 2014, 40(9): 2593-2612.
Zhou Yuanxiang, Zhao Jiankang, Liu Rui, et al.Key technical analysis and prospect of high voltage and extra-high voltage power cable[J]. High Voltage Engineering, 2014, 40(9): 2593-2612.
[5] Kreuger F H.Industrial high DC voltage[D]. Delft: Delft University of Technology, 1995.
[6] Jeroense M J P. Charges and discharges in HVDC cables[D]. Delft: Delft University of Technology, 1997.
[7] Fromm U.Interpretation of partial discharges at DC voltages[J]. IEEE Transactions on Dielectrics and Electrical Insulation, 1995, 2(5): 761-770.
[8] Pirker A, Schichler U.Partial discharge measurement at DC voltage-Evaluation and characterization by NoDi? pattern[J]. IEEE Transactions on Dielectrics and Electrical Insulation, 2018, 25(3): 883-891.
[9] 吴广宁, 李晓华, 冉汉政, 等. 高压脉冲造成储能电容器老化的直流局部放电测试技术[J]. 电工技术学报, 2010, 25(7): 172-178.
Wu Guangning, Li Xiaohua, Ran Hanzheng, et al.Partial discharge under DC condition with pulse discharge degradation of high voltage storage capacitors[J]. Transactions of China Electrotechnical Society, 2010, 25(7): 172-178.
[10] 齐波, 魏振, 李成榕, 等. 交直流复合电场中油纸绝缘沿面放电现象及特征[J]. 电工技术学报, 2016, 31(10): 59-67.
Qi Bo, Wei Zhen, Li Chengrong, et al.The phenomena and characteristics of oil-paper insulation surface discharge under AC and DC voltage[J]. Transactions of China Electrotechnical Society, 2016, 31(10): 59-67.
[11] Li Yuan, Zhang Qiaogen, Ding Yuqin, et al.Effect of cellulose impurities on partial discharges in oil-pressboard insulation under DC voltage[J]. IEEE Transactions on Dielectrics and Electrical Insulation, 2017, 24(4): 2271-2273.
[12] 秦雪, 钱勇, 许永鹏, 等. 基于2D-LPEWT的特征提取方法在电缆局部放电分析中的应用[J]. 电工技术学报, 2019, 34(1): 170-178.
Qin Xue, Qian Yong, Xu Yongpeng, et al.Application of feature extraction method based on 2D-LPEWT in cable partial discharge analysis[J]. Transactions of China Electrotechnical Society, 2019, 34(1): 170-178.
[13] Gu Xiao, He Shuang, Xu Yang, et al.Partial discharge detection on 320 kV VSC-HVDC XLPE cable with artificial defects under DC voltage[J]. IEEE Transactions on Dielectrics and Electrical Insulation, 2018, 25(3): 939-946.
[14] Liu Mechen, Liu Yunpeng, Li Yanda, et al.Growth and partial discharge characteristics of electrical tree in XLPE under AC-DC composite voltage[J]. IEEE Transactions on Dielectrics and Electrical Insulation, 2017, 24(4): 2282-2290.
[15] Xu Yongpeng, Qian Yong, Yang Fengyuan, et al.DC cable feature extraction based on the PD image in the non-subsampled contourlet transform domain[J]. IEEE Transactions on Dielectrics and Electrical Insulation, 2018, 25(2): 533-540.
[16] Yang Fengyuan, Sheng Gehao, Xu Yongpeng, et al.Partial discharge pattern recognition of XLPE cables at DC voltage based on the compressed sensing theory[J]. IEEE Transactions on Dielectrics and Electrical Insulation, 2017, 24(5): 2977-2985.
[17] 陈焕栩, 解浩, 张建文, 等. 基于灰度共生矩阵纹理特征的局部放电模式识别[J]. 电力系统保护与控制, 2018, 46(5): 25-30.
Chen Huanxu, Xie Hao, Zhang Jianwen, et al.Partial discharge pattern recognition based on texture feature of gray level co-occurrence matrix[J]. Power System Protection and Control, 2018, 46(5): 25-30.
[18] 于生宝, 何建龙, 王睿家, 等. 基于小波包分析和概率神经网络的电磁法三电平变换器故障诊断方法[J]. 电工技术学报, 2016, 31(17): 102-112.
Yu Shengbao, He Jianlong, Wang Ruijia, et al.Fault diagnosis of electromagnetic three-level inverter based on wavelet packet analysis and probabilistic neural networks[J]. Transactions of China Electrotechnical Society, 2016, 31(17): 102-112.
[19] 杨帆, 王干军, 彭小圣, 等. 基于卷积神经网络的高压电缆局部放电模式识别[J]. 电力自动化设备, 2018, 38(5): 123-128.
Yang Fan, Wang Ganjun, Peng Xiaosheng, et al.Partial discharge pattern recognition of high-voltage cables based on convolutional neural network[J]. Electric Power Automation Equipment, 2018, 38(5): 123-128.
[20] 聂洪岩, 张潮海, 顾哲屹, 等. 局部放电条件下干式空心电抗器匝间绝缘的电老化特性研究[J]. 电工技术学报, 2018, 33(13): 3071-3079.
Nie Hongyan, Zhang Chaohai, Gu Zheyi, et al.The research on electrical aging characteristics of turn-to-turn insulation of dry-type air core reactor under partial discharge[J]. Transactions of China Electrotechnical Society, 2018, 33(13): 3071-3079.
[21] Jia Yanqing, Shelhamer E, Donahue J, et al.Caffe: convolutional architecture for fast feature embedding[C]// ACM International Conference on Multimedia, Orlando, FL, USA, 2014: 675-678.
[22] Yan Kewen, Huang Shaohui, Song Yaoxian, et al.Face recognition based on convolution neural network[C]// Chinese Control Conference, Dalian, China, 2017: 4077-4081.
[23] Turchenko V, Luczak A.Creation of a deep convolutional auto-encoder in Caffe[C]// 2017 9th IEEE International Conference on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications (IDAACS), Bucharest, 2017: 651-659.
[24] 常亮, 邓小明, 周明全, 等. 图像理解中的卷积神经网络[J]. 自动化学报, 2016, 42(9): 1300-1312.
Chang Liang, Deng Xiaoming, Zhou Mingquan, et al.Convolutional neural networks in image understanding[J]. Acta Automatica Sinica, 2016, 42(9): 1300-1312.