基于2D-LPEWT的特征提取方法在电缆局部放电分析中的应用

doi:10.19595/j.cnki.1000-6753.tces.180057

摘要
图/表
参考文献
相关文章 (15)

全文: PDF (2354 KB)
输出: BibTeX | EndNote (RIS)

摘要

局部放电检测对识别电力电缆绝缘缺陷具有重要意义,其中提取有效的特征参量为其研究重点。该文提出一种基于二维Littlewood-Paley经验小波变换（2D-LPEWT）的特征提取方法,可实现电缆局部放电不同缺陷类型的准确识别。通过搭建电缆绝缘局部放电检测平台,利用2D-LPEWT对四种典型缺陷模型下局部放电产生的φ-Q-n图谱进行分解,对得到的经验小波系数子图提取了Tamura特征、矩特征和熵特征,并讨论了不同的特征提取方法对KNN、决策树、支持向量机（SVM）三种分类算法性能的影响。结果表明所提出的特征提取方法在不同的分类器下均可达到很高的识别精度,具有很好的实用性。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	秦雪
	钱勇
	许永鹏
	盛戈皞
	江秀臣

关键词 ：二维Littlewood-Paley经验小波变换, 电力电缆, 局部放电, 特征提取, 分类器

Abstract：

Partial discharge detection is important for identifying insulation defects of power cables. And the extraction of effective characteristic parameters is the emphasis of the study. In this paper, a feature extraction method based on 2 dimensions Littlewood-Pale empirical wavelet transform (2D-LPEWT) is proposed to realize the accurate identification of different types of defects in cable discharge. By constructing a cable-insulated partial discharge detection platform, three-dimensional spectrum of four typical defect models was decomposed by 2D-LPEWT. And then Tamura, moments and entropy characteristics were extracted from the obtained wavelet coefficients sub-graphs. The effects of different feature extraction methods on performance of K-nearest neighbour (KNN), decision tree and support vector machine (SVM) were discussed. Results show that the proposed feature extraction method can achieve high recognition accuracy under different classifiers, and has good practicability.

Key words： 2 dimensions Littlewood-Pale empirical wavelet transform power cable partial discharge feature extraction classification algorithm

收稿日期: 2018-01-09 出版日期: 2019-01-10

PACS:

TM85

基金资助:

国家重点研发计划资助项目（2017YFB0902705）

通讯作者: :钱勇男,1977年生,助理研究员,博士,研究方向为输变电设备状态监测与智能化。E-mail：qianyong@sjtu.edu.cn

作者简介: 秦雪女,1996年生,硕士研究生,研究方向为电气设备在线监测及故障绝缘诊断。E-mail：quency123@sjtu.edu.cn

引用本文:

秦雪, 钱勇, 许永鹏, 盛戈皞, 江秀臣. 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): 170-177. Qin Xue, Qian Yong, Xu Yongpeng, Sheng Gehao, Jiang Xiuchen. Application of Feature Extraction Method Based on 2D-LPEWT in Cable Partial Discharge Analysis. Transactions of China Electrotechnical Society, 2019, 34(1): 170-177.

链接本文:

https://dgjsxb.ces-transaction.com/CN/10.19595/j.cnki.1000-6753.tces.180057 https://dgjsxb.ces-transaction.com/CN/Y2019/V34/I1/170

[1] 杨帆, 杨旗, 程鹏, 等. 电缆接头内部气隙放电缺陷下的绝缘劣化程度表征方法[J]. 电工技术学报, 2017, 32(2): 24-32. Yang Fan, Yang Qi, Cheng Peng, et al. Study of cracking extent for gap discharge in insulating material of power cable joint[J]. Transactions of China Electrotechnical Society, 2017, 32(2): 24-32.
[2] 魏钢, 唐炬, 文习山, 等. 局部放电信号在交联聚乙烯高压电力电缆中的衰变及其检测[J]. 高电压技术, 2011, 37(6): 1377-1383. Wei Gang, Tang Ju, Wen Xishan, et al. Decay and detection of partial discharge signals in high-voltage cross-linked polyethylene power cable[J]. High Voltage Engineering, 2011, 37(6): 1377-1383.
[3] Gulski E, Cichecki P, Wester F, et al.On-site testing and PD diagnosis of high voltage power cables[J]. IEEE Transactions on Dielectrics and Electrical Insulation, 2008, 15(6): 1691-1700.
[4] 李臻, 罗林根, 盛戈皞, 等. 基于压缩感知的特高频局部放电定位法[J]. 电工技术学报, 2018, 33(1) : 202-208. Li Zhen, Luo Lingen, Sheng Gehao, et al. Ultrahigh frequency partial discharge localization methodology based on compressed sensing[J]. Transactions of China Electrotechnical Society, 2018, 33(1): 202-208.
[5] 魏振, 齐波, 左健, 等. 基于局部放电图像特征的换流变压器油纸绝缘缺陷诊断方法[J]. 电网技术, 2015, 39(4): 1160-1166. Wei Zhen, Qi Bo, Zuo Jian, et al. A method to diagnose defects in oil-paper insulation of converter transformer based on image feature of partial discharge[J]. Power System Technology, 2015, 39(4): 1160-1166.
[6] 杨丰源, 许永鹏, 郑新龙, 等. 基于压缩感知的高压直流电缆局部放电模式识别[J]. 高电压技术, 2017, 41(2): 446-452. Yang Fengyuan, Xu Yongpeng, Zheng Xinlong, et al. Partial discharge pattern recognition of HVDC cable based on compressive sensing[J]. High Voltage Engineering, 2017, 41(2): 446-452.
[7] Li Jian, Sun Caixin, Grzybowski S.Partial discharge image recognition influenced by fractal image compression[J]. IEEE Transactions on Dielectrics and Electrical Insulation, 2008, 15(2): 496-504.
[8] Hoof M, Freisleben B, Patsch R.PD source identification with novel discharge parameters using counter propagation neural networks[J]. IEEE Transactions on Dielectrics and Electrical Insulation, 1997, 4(1): 17-32.
[9] 张晓星, 唐炬, 孙才新, 等. 基于核统计不相关最优鉴别矢量集的GIS局部放电模式识别[J]. 电工技术学报, 2008, 23(9): 111-117. Zhang Xiaoxing, Tang Ju, Sun Caixin, et al. PD pattern recognition based on kernel statistical uncorrelated optimum discriminant vectors in GIS[J]. Transactions of China Electrotechnical Society, 2008, 23(9): 111-117.
[10] Gilles J.Empirical wavelet transform[J]. IEEE Transactions on Signal Processing, 2013, 61(16): 3999-4010.
[11] Arber W, Henle W, Hofschneider P H.Current topics in microbiology and immunology[J]. The Quarterly Review of Biology, 1975, 50(3): 77-78.
[12] Gilles J, Tran G, Osher S.2D empirical transforms, wavelets, ridgelets, and curvelets revisited[J]. SIAM Journal on Imaging Sciences, 2014, 7(1): 157-186.
[13] Averbuch A, Coifman R R, Donoho D L, et al.Fast and accurate polar Fourier transform[J]. Applied & Computational Harmonic Analysis, 2006, 21(2): 145-167.
[14] Averbuch A, Coifman R R.A framework for discrete integral transformations I-the Pseudopolar Fourier transform[J]. Siam Journal on Scientific Computing, 2014, 30(2): 764-784.
[15] 黄南天, 张书鑫, 蔡国伟, 等. 采用EWT和OCSVM的高压断路器机械故障诊断[J]. 仪器仪表学报, 2015, 36(12): 2773-2781. Huang Nantian, Zhang Shuxin, Cai Guowei, et al. Mechanical fault diagnosis of high voltage circuit breakers utilizing empirical wavelet transform and one-class support vector machine[J]. Chinese Journal of Scientific Instrument, 2015, 36(12): 2773-2781.
[16] Rao A R.A taxonomy for texture description and identification[M]. New York: Springer Science & Business Media, 2012.
[17] 赵爱罡, 王宏力, 杨小冈, 等. 纹理粗糙度在红外图像显著性检测中的应用[J]. 光学精密工程, 2016, 24(1): 220-228. Zhao Aigang, Wang Hongli, Yang Xiaogang, et al. Application of texture coarseness in saliency detection of infrared image[J]. Optics and Precision Engineering, 2016, 24(1): 220-228.
[18] 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): 259-267. 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): 259-267.
[19] Tamura H, Mori S, Yamawaki T.Textural features corresponding to visual perception[J]. IEEE Transactions on Systems Man & Cybernetics, 1978, 8(6): 460-473.
[20] Shannon C.A mathematical theory of communication[J]. Bell System Technical Journal, 1948, 27(1-2): 623-656.
[21] Pincus S M.Approximate entropy as a measure of system complexity[J]. Proceeding of the National Academy Sciences USA, 1991, 88(6): 2297-2301.
[22] 胡红英, 马孝江. 局域波近似熵及其在机械故障诊断中的应用[J]. 振动与冲击, 2006, 25(4): 38-40. Hu Hongying, Ma Xiaojiang. Application of local wave approximate entropy in mechanical fault diagnosis[J]. Journal of Vibration and Shock, 2006, 25(4): 38-40.
[23] Richman J S, Moorman J R.Physiological time-series analysis using approximate entropy and sample entropy[J]. American Journal of Physiology, Heart And Circulatory Physiology, 2000, 278(6): H2039.
[24] 姚林朋, 徐颖敏, 钱勇, 等. 基于关联规则的XLPE电缆局部放电模糊识别研究[J]. 电工技术学报, 2012, 27(5): 92-98. Yao Linpeng, Xu Yingmin, Qian Yong, et al. Fuzzy pattern recognition of partial discharge in XLPE cable based on association rule[J]. Transactions of China Electrotechnical Society, 2012, 27(5): 92-98.
[25] 叶海峰, 钱勇, 刘宗杰, 等. 一种新型的放电源空间定位用特高频传感器[J]. 电工技术学报, 2015, 30(8): 333-340. Ye Haifeng, Qian Yong, Liu Zongjie, et al. A new UHF sensor for spatial location of partial discharge sources[J]. Transactions of China Electrotechnical Society, 2015, 30(8): 333-340.
[26] 杨丽君, 孙才新, 廖瑞金, 等. 油纸绝缘老化状态判别的局部放电特征量[J]. 电力系统自动化, 2007, 31(10): 55-60. Yang Lijun, Sun Caixin, Liao Ruijin, et al. Partial discharge features applied in aging condition discrimination of oil paper insulation[J]. Automation of Electric Power Systems, 2007, 31(10): 55-60.
[27] Zhang Xiaoxing, Xiao Song, Shu Na, et al.GIS partial discharge pattern recognition based on the chaos theory[J]. IEEE Transactions on Dielectrics & Electrical Insulation, 2014, 21(2): 783-790.