Clustering Separation Method Based on Multi-Source Partial Discharge Signal Data Stream

doi:10.16183/j.cnki.jsjtu.2021.195

Abstract

Abstract:

In partial discharge(PD) detection, due to the simultaneous and constantly changing phenomenon of multiple discharge sources and on-site interference sources, it is difficult to effectively separate and identify multiple PD sources. An efficient adaptive efficient adaptive online data stream clustering algorithm (EAOStream) is proposed. The algorithm uses natural neighborhoods to create K-dimensional (KD) trees to improve the efficiency of querying neighbors. That is, the adaptive neighborhood radius and the area density are obtained through the characteristics of the flow data, which can search locally and form clusters, and realize the real-time online separation of multiple local discharge sources. The superiority of EAOStream is verified in the artificial data set and the real data set. After comparing EAOStream with the traditional DenStream and SE-Stream algorithms, it is applied to the pattern recognition of gas-insulated substation faults. Experimental test results show that the clustering accuracy of EAOStream in the real network intrusion detection, the forest cover type, and the multi-source PD signal data sets reaches 95.28%, 98.47%, and 97.23%, verifying the practicability and effectiveness of the algorithm in fault diagnosis of gas-insulated substations.

Key words: data stream, cluster separation, local adaptation, natural neighborhood, partial discharge (PD)

CLC Number:

TM835

CHEN Changchuan, LIU Kai, LIU Renguang, FENG Xiaozong, QIN Yanjia, DAI Shaosheng, ZHANG Tianqi. Clustering Separation Method Based on Multi-Source Partial Discharge Signal Data Stream[J]. Journal of Shanghai Jiao Tong University, 2022, 56(8): 1014-1023.

Figures/Tables 10

Fig.1

Fig.2

Fig.3

Fig.4

Tab.1

Fig.5

Fig.6

Fig.7

Fig.8

Tab.2

References 22

[20]	LIAO R J, YANG L J, LI J, et al. Aging condition assessment of transformer oil-paper insulation model based on partial discharge analysis[J]. IEEE Transactions on Dielectrics and Electrical Insulation, 2011, 18(1): 303-311. doi: 10.1109/TDEI.2011.5704522 URL
[21]	SAKO H, MIO K, OKADA S. Analysis of Phase Resolved Partial Discharge patterns with microstrip antenna[C]// 2015 IEEE Electrical Insulation Conference. Seattle, WA, USA: IEEE, 2015: 346-357.
[1]	LI G Y, WANG X H, LI X, et al. Partial discharge recognition with a multi-resolution convolutional neural network[J]. Sensors, 2018, 18(10): 1-27. doi: 10.3390/s18010001 URL
[2]	段韶峰, 李志兵, 詹花茂, 等.252 kV GIS中特快速瞬态过电压和特快速瞬态电流特性试验研究[J]. 电网技术, 2015, 39(7): 2046-2051.
	DUAN Shaofeng, LI Zhibing, ZHAN Huamao, et al. Experimental study on the characteristics of VFTO and VFTC in 252 kV GIS[J]. Power System Technology, 2015, 39(7): 2046-2051.
[3]	周承科, 李明贞, 王航, 等. 电力电缆资产的状态评估与运维决策综述[J]. 高电压技术, 2016, 42(8): 2353-2362.
	ZHOU Chengke, LI Mingzhen, WANG Hang, et al. Review of condition assessment and maintenance strategy of power cable assets[J]. High Voltage Engineering, 2016, 42(8): 2353-2362.
[4]	ZHU M X, XUE J Y, ZHANG J N, et al. Classification and separation of partial discharge ultra-high-frequency signals in a 252 kV gas insulated substation by using cumulative energy technique[J]. IET Science, Measurement & Technology, 2016, 10(4): 316-326. doi: 10.1049/iet-smt.2015.0171 URL
[5]	卢启付, 李端姣, 唐志国, 等. 局部放电特高频检测技术[M]. 北京: 中国电力出版社, 2017.
	LU Qifu, LI Duanjiao, TANG Zhiguo, et al. Partial discharge ultra-high frequency detection technology[M]. Beijing: China Electric Power Press, 2017.
[6]	郭俊, 吴广宁, 张血琴, 等. 局部放电检测技术的现状和发展[J]. 电工技术学报, 2005, 20(2): 29-35.
	GUO Jun, WU Guangning, ZHANG Xueqin, et al. The actuality and perspective of partial discharge detection techniques[J]. Transactions of China Electrotechnical Society, 2005, 20(2): 29-35.
[7]	BELTLE M, MULLER A, TENBOHLEN S. Statistical analysis of online ultrahigh-frequency partial-discharge measurement of power transformers[J]. IEEE Electrical Insulation Magazine, 2012, 28(6): 17-22. doi: 10.1109/MEI.2012.6340520 URL
[8]	张广东, 秦睿, 张忠元, 等. 基于超高频特高频法的GIS局部放电特征图谱提取与研究[J]. 高压电器, 2016, 52(9): 71-77.
	ZHANG Guangdong, QIN Rui, ZHANG Zhongyuan, et al. Extraction and analysis of characteristic spectrum of partial discharge in GIS based on UHF method[J]. High Voltage Apparatus, 2016, 52(9): 71-77.
[9]	代少升, 杨雨, 聂合文, 等. UHF局部放电信号包络检波电路设计与实现[J]. 重庆邮电大学学报(自然科学版), 2021, 33(5): 736-742.
	DAI Shaosheng, YANG Yu, NIE Hewen, et al. UHF partial discharge signal envelope detection circuit design and implementation[J]. Journal of Chongqing University of Posts and Telecommunications (Natural Science Edition): 2021, 33(5): 736-742.
[10]	TAREQ M, SUNDARARAJAN E A, MOHD M, et al. Online clustering of evolving data streams using a density grid-based method[J]. IEEE Access, 2020, 8: 166472-166490. doi: 10.1109/ACCESS.2020.3021684 URL
[11]	PUTRI G H, READ M N, KOPRINSKA I, et al. ChronoClust: Density-based clustering and cluster tracking in high-dimensional time-series data[J]. Knowledge-Based Systems, 2019, 174: 9-26. doi: 10.1016/j.knosys.2019.02.018 URL
[12]	ISLAM M K, AHMED M M, ZAMLI K Z. A buffer-based online clustering for evolving data stream[J]. Information Sciences, 2019, 489: 113-135. doi: 10.1016/j.ins.2019.03.022 URL
[13]	郑祺, 黄德才. 基于引力相似度和相对密度的不确定数据流聚类[J]. 上海交通大学学报, 2016, 50(6): 873-878.
	ZHENG Qi, HUANG Decai. Uncertain data stream clustering algorithm based on gravity similarity and relative density techniques[J]. Journal of Shanghai Jiao Tong University, 2016, 50(6): 873-878.
[14]	XU J, WANG G Y, LI T R, et al. Fat node leading tree for data stream clustering with density peaks[J]. Knowledge-Based Systems, 2017, 120: 99-117. doi: 10.1016/j.knosys.2016.12.025 URL
[15]	龙真真, 张策, 王维平, 等. 一种基于数据流聚类的动态目标分群框架[J]. 上海交通大学学报, 2010, 44(7): 921-925.
	LONG Zhenzhen, ZHANG Ce, WANG Weiping, et al. A dynamic framework for target-grouping based on clustering data streams[J]. Journal of Shanghai Jiao Tong University, 2010, 44(7): 921-925.
[16]	HAHSLER M, BOLAÑOS M. Clustering data streams based on shared density between micro-clusters[J]. IEEE Transactions on Knowledge and Data Engineering, 2016, 28(6): 1449-1461. doi: 10.1109/TKDE.2016.2522412 URL
[17]	于晓飞, 葛洪伟. 噪声环境下复杂流形数据的势能层次聚类算法[J]. 重庆邮电大学学报(自然科学版), 2018, 30(6): 848-854.
	YU Xiaofei, GE Hongwei. A hierarchical clustering algorithm of potential energy for complex manifold data in noisy environment[J]. Journal of Chongqing University of Posts and Telecommunications (Natural Science Edition), 2018, 30(6): 848-854.
[18]	CAO F, ESTERT M, QIAN W N, et al. Density-based clustering over an evolving data stream with noise[C]// Proceedings of the 2006 SIAM International Conference on Data Mining. Philadelphia, PA, USA: Society for Industrial and Applied Mathematics, 2006: 328-339.
[19]	CHAIRUKWATTANA R, KANGKACHIT T, RAKTHANMANON T, et al. Efficient evolution-based clustering of high dimensional data streams with dimension projection[C]// 2013 International Computer Science and Engineering Conference. Nakhonpathom, Thailand: IEEE, 2013: 185-190.
[22]	BENTLEY J L. Multidimensional binary search trees used for associative searching[J]. Communications of the ACM, 1975, 18(9): 509-517. doi: 10.1145/361002.361007 URL

算法	数据集	F	P	F_m
EAOStream	KDD CUP'99	95.95	95.28	97.49
	Forest Covertype	92.58	98.47	98.07
	MS-PD	98.75	97.23	98.14
DenStream	KDD CUP'99	90.35	89.25	89.92
	Forest Covertype	88.95	75.03	76.82
	MS-PD	82.21	83.48	82.32
SE-Stream	KDD CUP'99	97.62	90.27	91.33
	Forest Covertype	91.13	90.84	91.62
	MS-PD	93.45	90.83	92.19

N	颜色	N	颜色
1~20		181~700
21~60		701~2600
61~180		>2600