配电网高阻接地故障时频特征SVM分类识别方法

Abstract
Figure/Table
References
Related Citation (15)

Download: PDF (16553 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract When the high impedance ground fault (HIF) occurs, the grounding resistance of the fault point is high, and it is often accompanied by arc extinction and restriking. The fault current is very small and strongly random. Detection of HIF is generally difficult by the conventional over-current protection devices, because they cannot draw enough current to operate the devices. In this paper, a new HIF detection method that uses LCD band-pass filter and support vector machine (SVM) is presented. Using this method, HIF can be discriminated from transients such as capacitor switching, load switching, inrush current. LCD band-pass filter is used for obtaining the time-frequency matrices of current waveforms of the bus line. The feature vectors are the standard deviation of each frequency band, and SVM is used for classification.

Key words： MV distribution networks HIF LCD band-pass filter SVM

Received: 18 September 2017 Published: 19 March 2018

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	Zhang Junqi
	Yang Fan
	Guo Moufa

Cite this article:

Zhang Junqi,Yang Fan,Guo Moufa. High impedance ground fault detection based on time-frequency characteristics and SVM[J]. Electrical Engineering, 2018, 19(3): 37-43.

URL:

http://dqjs.cesmedia.cn/EN/Y2018/V19/I3/37

[1] 朱晓娟, 林圣, 张姝, 等. 基于小波能量矩的高阻接地故障检测方法[J]. 电力自动化设备, 2016, 36(12): 161-168.
[2] Sharaf A M, Wang G.High impedance fault detection using feature-pattern based relaying[C]//Transmission and Distribution Conference and Exposition, 2003: 222-226.
[3] Mishra M, Routray P, Rout P.A universal high impedance fault detection technique for distribution system using S-Transform and pattern recognition[J]. Technology and Economics of Smart Grids and Sustainable Energy, 2016, 1(1): 9.
[4] Sedighi A R, Haghifam M R, Malik O P, et al.High impedance fault detection based on wavelet transform and statistical pattern recognition[J]. IEEE Transa- ctions on Power Delivery, 2005, 20(4): 2414-2421.
[5] Michalik M, Lukowicz M, Rebizant W, et al.Verification of the wavelet-based HIF detecting algorithm performance in solidly grounded MV networks[J]. IEEE Transactions on Power Delivery, 2007, 22(4): 2057-2064.
[6] Costa F B, Souza B A, Brito N, et al.Real-Time detection of transients induced by High-Impedance faults based on the boundary wavelet transform[J]. IEEE Transactions on Industry Applications, 2015, 51(6, 2): 5312-5323.
[7] Sedighi A R, Haghifam M R, Malik O P.Soft computing applications in high impedance fault detection in distribution systems[J]. Electric Power Systems Research, 2005, 76(1/3): 136-144.
[8] 陈民铀, 黄永, 瞿进乾. 配电网线路高阻故障识别方法[J]. 重庆大学学报, 2013, 36(9): 83-88.
[9] Samantaray S R.Ensemble decision trees for high impedance fault detection in power distribution network[J]. International Journal of Electrical Power & Energy Systems, 2012, 43(1): 1048-1055.
[10] 郑星炯. 基于支持向量机的配电线路高阻接地故障检测方法[J]. 电子设计工程, 2015, 23(14): 122-125.
[11] 耿建昭, 王宾, 董新洲, 等. 中性点有效接地配电网高阻接地故障特征分析及检测[J]. 电力系统自动化, 2013, 37(16): 85-91.
[12] 郭谋发, 游林旭, 洪翠, 等. 基于LCD-Hilbert谱奇异值和多级支持向量机的配电网故障识别方法[J]. 高电压技术, 2017(4): 1239-1247.
[13] 孙一航, 武建文, 廉世军, 等. 结合经验模态分解能量总量法的断路器振动信号特征向量提取[J]. 电工技术学报, 2014, 29(3): 228-236.
[14] 蔡晋, 林榛, 高伟, 等. 基于HHT及信号注入的配电网谐振与单相接地故障识别[J]. 电气技术, 2015, 16(12): 31-35, 51.
[15] 郭谋发, 刘世丹, 杨耿杰. 采用Hilbert谱带通滤波和暂态波形识别的谐振接地系统故障选线新方法[J].电工电能新技术, 2013, 32(3): 67-74.
[16] 程序, 关永刚, 张文鹏, 等. 基于因子分析和支持向量机算法的高压断路器机械故障诊断方法[J]. 电工技术学报, 2014, 29(7): 209-215.
[17] 魏晓莹, 宋仕江, 郭谋发, 等. 基于振动信号二维特征向量的配变铁心故障诊断[J]. 电气技术, 2016, 17(1): 16-21.
[18] Gautam S, Brahma S M.Detection of high impedance fault in power distribution systems using mathematical morphology[J]. IEEE Transactions on Power Systems, 2013, 28(2): 1226-1234.
[19] 刘超, 刘健, 张志华, 等. 配电网励磁涌流及其概率分布的分析与探讨[J]. 电力系统自动化, 2017, 41(4): 170-175.
[20] 张元胜, 李欣然, 肖园园, 等. 含小水电配网负荷模型实用化方法[J]. 电工电能新技术, 2012, 31(4): 83-87.