|
|
|
| Partial discharge characteristic optimization of cables based on support vector machine-recursive feature elimination |
| Li Cheng1, Li Qiang1, Zhang Qichao2, Liu Zirui3, Li Wei4 |
1. State Grid Hanzhong Electric Power Supply Company, Hanzhong, Shaanxi 723000;
2. Shanghai University of Electric Power, Shanghai 200090;
3. State Grid Shaanxi Electric Power Company, Xi’an 710048;
4. State Grid Shaanxi Electric Power Company Electric Power Research Institute, Xi’an 710054 |
|
|
|
|
Abstract Partial discharge (PD) in cables is usually caused by cable defects. The type of defect can be quickly judged by effectively recognizing PD signals. In this paper, a new method of partial discharge feature selection based on support vector machine recursive feature elimination (SVM-RFE) and K-means clustering algorithm is proposed. After extracting features from raw data, K-SVM-RFE feature optimization is carried out, and the ranking results of local features of different types of defects are obtained according to the weights, and the results of the optimal ranking are verified. The results show that the effective characteristic parameters of different types of partial discharge signals are the test voltage the product of phase angle and polarity. The validation results under different algorithms show that the feature optimization method of K-SVM-RFE proposed in this paper is an effective method to select the characteristics of PD, which can greatly improve the fault diagnosis rate of cable defects.
|
|
Received: 05 September 2019
Published: 18 January 2020
|
|
|
|
| Cite this article: |
|
Li Cheng,Li Qiang,Zhang Qichao等. Partial discharge characteristic optimization of cables based on support vector machine-recursive feature elimination[J]. Electrical Engineering, 2020, 21(1): 67-71.
|
|
|
|
| URL: |
|
http://dqjs.cesmedia.cn/EN/Y2020/V21/I1/67
|
[1] Contin A, Pastore S.Classification and separation of partial discharge signals by means of their auto- correlation function evaluation[J]. IEEE Transactions on Dielectrics and Electrical Insulation, 2009, 16(6): 1609-1622.
[2] Renforth L, Mackinlay R, Seltzer-Grant M, et al.On-line partial discharge (PD) spot testing and monitoring of high voltage cable sealing ends.in: proceedings[C]//42nd CIGRE Session. Paris, France, 2008: B1-205.
[3] Peng Xiaosheng, Zhou Chengke, Hepburn DM, et al.Application of K-means method to pattern recognition in on-line cable partial discharge monitoring[J]. IEEE Transactions on Dielectrics and Electrical Insulation, 2013, 20(3): 754-761.
[4] Reid Alistair, Peng Xiaosheng, Hu Xiao, et al.Comparison of partial discharge characteristics from insulation defects in 11kV EPR cable. in: 17th International Symposium on High Voltage Engineering. Hannover, Germany, 2011
[5] Montanari G C, Cavallini A, Pulettli F.A new approach to partial discharge testing of HV cable systems[J]. IEEE Electrical Insulation Magazine, 2006, 22(1): 14-23.
[6] Peng Xiaosheng, Yang Guangyao, Zheng Shijie, et al.Optimal feature selection for partial discharge reco- gnition of cable systems based on the random forest method[C]//International Conference on Electricity Distribution. Xi'an, China, 2016: 1-5.
[7] Williams C I.Learning with kernels: support vector machines, regularization, optimization, and beyond[J]. Publications of the American Statistical Association, 2003, 98(462): 1.
[8] Guyon I.An introduction to variable and feature selection[J]. JM-LR. org, 003, 3
[9] Duan K B, Rajapakse J C, Wang H, et al.Multiple SVM-RFE for gene selection in cancer classification with expression data[J]. IEEE Transactions on Nano- bioscience, 2005, 4(3): 228-234.
[10] 张君琦, 杨帆, 郭谋发. 配电网高阻接地故障时频特征SVM分类识别方法[J]. 电气技术, 2018, 19(3): 37-43.
[11] 陈华丰, 乔磊, 柳双林. 基于小波变换和支持向量机的电能质量扰动识别[J]. 电气技术, 2013, 14(2): 14-18.
[12] 刘起铭, 加玛力汗·库马什, 华东, 等. 基于支持向量机的负荷预测分析[J]. 电气技术, 2013, 14(5): 34-36.
[13] 邱志斌, 阮江军, 唐烈峥, 等. 空气间隙的储能特征与放电电压预测[J]. 电工技术学报, 2018, 33(1): 185-194.
[14] 王智勇, 郭凤仪, 冯晓丽, 等. 基于电流信号特征的弓网电弧识别方法[J]. 电工技术学报, 2018, 33(1): 82-91.
[15] Guyon I, Weston J, Barnhill S, et al.Gene selection for cancer classification using support vector machines[J]. Machine Learning, 2002, 46(1/3): 389-422.
[16] Peng Xiaosheng, Wen Jinyu, Li Zhaohui, et al.SDMF based interference rejection and PD interpretation for simulated defects in HV cable diagnostics[J]. IEEE Transactions on Dielectrics and Electrical Insulation, 2017, 24(1): 83-91.
[17] Peng X, Wen J, Li Z, et al.Rough set theory applied to pattern recognition of partial discharge in noise affected cable data[J]. IEEE Transactions on Dielectrics & Electrical Insulation, 2017, 24(1): 147-156.
[18] 张冠军, 朱明晓, 王彦博, 等. 基于可移动特高频天线阵列的变电站站域放电源检测与定位研究[J]. 中国电机工程学报, 2017, 37(10): 2761-2773. |
|
|
|
2020, Vol. 21 
