Distribution Network Fault Diagnosis Technology Based on Multi-Source Data Fusion

doi:10.16183/j.cnki.jsjtu.2022.317

Abstract

Abstract:

How to make full use of existing information to improve the accuracy of fault diagnosis in distribution networks, and provide accurate research and judgement for emergency repair of distribution networks, is an urgent problem to be solved. To address the problem of the single source of fault diagnosis information in existing distribution networks, a fault diagnosis model of distribution network is proposed which integrates the medium and low voltage information of the distribution networks and the outgoing current information of the substation. The model first applies the existing overcurrent diagnosis method to the problem of large-scale distribution network, and adopts hierarchical reduction of the size of the distribution networks to improve the location speed of fault section. Then, in view of the accuracy of overcurrent alarm information, an auxiliary fault judgment method for distribution networks based on switch relay protection sequence of events (SOE) data and substation outgoing load sag data is proposed. Finally, the steps for fault diagnosis in distribution networks of multi-directional information and data fusion in practical engineering are summarized, which provides reference for fault diagnosis of dispatchers. Engineering practice proves that the method proposed in this paper can effectively diagnose faults and is very adaptable to large-scale distribution networks. The auxiliary diagnosis model combining switch operation SOE and telemetering voltage information can compensate for the accuracy requirements of the overcurrent diagnosis model for remote communication information, which is complementary to each other and has a good engineering value.

Key words: large scale distribution network, multi source data, fault diagnosis, telemetry, relay protection

CLC Number:

TM745

ZHANG Chunmei, XU Xingque, LIU Silin. Distribution Network Fault Diagnosis Technology Based on Multi-Source Data Fusion[J]. Journal of Shanghai Jiao Tong University, 2024, 58(5): 739-746.

Figures/Tables 12

Fig.1

Fig.2

Fig.3

Tab.1

Fig.4

Fig.5

Fig.6

Fig.7

Tab.2

Fig.8

Fig.9

Tab.3

References 17

[1]	LI C B, TANG S W, CAO Y J, et al. A new stepwise power tariff model and its application for residential consumers in regulated electricity markets[J]. IEEE Transactions on Power Systems, 2013, 28(1): 300-308.
[2]	LI C B, CAO Y J, ZHANG M, et al. Hidden benefits of electric vehicles for addressing climate change[J]. Scientific Reports, 2015, 5: 9213. doi: 10.1038/srep09213 pmid: 25790439
[3]	林君豪, 张焰, 赵腾, 等. 基于改进卷积神经网络拓扑特征挖掘的配电网结构坚强性评估方法[J]. 中国电机工程学报, 2019, 39(1): 84-96.
	LIN Junhao, ZHANG Yan, ZHAO Teng, et al. Structure strength assessment method of distribution network based on improved convolution neural network and network topology feature mining[J]. Proceedings of the CSEE, 2019, 39(1): 84-96.
[4]	刘健, 张志华, 芮骏, 等. 基于限流级差配合的城市配电网高选择性继电保护方案[J]. 电力系统自动化, 2019, 43(5): 101-106.
	LIU Jian, ZHANG Zhihua, RUI Jun, et al. Highly selective relay protection scheme for urban distribution network based on current limiting difference[J]. Automation of Electric Power Systems, 2019, 43(5): 101-106.
[5]	张建雨, 姜睿智, 李俊刚, 等. 基于5G通信的配电网差动保护技术研究[J]. 电力系统保护与控制, 2021, 49(7): 17-23.
	ZHANG Jianyu, JIANG Ruizhi, LI Jungang, et al. Research on differential protection of a distribution network based on 5G communication[J]. Power System Protection & Control, 2021, 49(7): 17-23.
[6]	屈志坚, 范明明, 周锐霖, 等. 海量配电网调度监测信息的非主行键倒排索引查询技术[J]. 电力系统保护与控制, 2018, 46(23): 162-168.
	QU Zhijian, FAN Mingming, ZHOU Ruilin, et al. Inverted index query technique of non-primary key for mass dispatch and monitoring information of distribution network[J]. Power System Protection & Control, 2018, 46(23): 162-168.
[7]	郑涛, 马龙, 李博文. 基于馈线终端装置信息畸变校正的有源配电网故障区段定位[J]. 电网技术, 2021, 45(10): 3926-3934.
	ZHENG Tao, MA Long, LI Bowen. Fault section location of active distribution network based on feeder terminal unit information distortion correction[J]. Power System Technology, 2021, 45(10): 3926-3934.
[8]	ADEWOLE A C, TZONEVA R, BEHARDIEN S. Distribution network fault section identification and fault location using wavelet entropy and neural networks[J]. Applied Soft Computing, 2016, 46: 296-306.
[9]	XU H H. Fastest adaptive estimation algorithms for topological structure errors in smart grid networks[J]. Computer Communications, 2020, 160: 197-203.
[10]	苏译, 彭敏放, 朱亮, 等. 基于信息还原与膜计算的配电网故障定位[J]. 仪器仪表学报, 2014, 35(12): 2700-2708.
	SU Yi, PENG Minfang, ZHU Liang, et al. Fault section location for distribution networks based on information restoration and membrane computing[J]. Chinese Journal of Scientific Instrument, 2014, 35(12): 2700-2708.
[11]	王秋杰, 金涛, 谭洪, 等. 基于分层模型和智能校验算法的配电网故障定位技术[J]. 电工技术学报, 2018, 33(22): 5327-5337.
	WANG Qiujie, JIN Tao, TAN Hong, et al. The technology on fault location of distribution network based on hierarchical model and intelligent checking algorithm[J]. Transactions of China Electrotechnical Society, 2018, 33(22): 5327-5337.
[12]	吉兴全, 张朔, 张玉敏, 等. 基于IELM算法的配电网故障区段定位[J]. 电力系统自动化, 2021, 45(22): 157-166.
	JI Xingquan, ZHANG Shuo, ZHANG Yumin, et al. Fault section location for distribution network based on improved electromagnetism-like mechanism algorithm[J]. Automation of Electric Power Systems, 2021, 45(22): 157-166.
[13]	程云祥, 李阳, 卢芳, 等. 多源信息辅助分区的主动配电网故障区段定位[J]. 电力系统保护与控制, 2020, 48(17): 147-154.
	CHENG Yunxiang, LI Yang, LU Fang, et al. Fault-section location for active distribution networks assisted by multi-source information[J]. Power System Protection & Control, 2020, 48(17): 147-154.
[14]	孙志达, 杨涛, 吴栋萁, 等. 基于多源信息和遗传算法的配电网故障定位模型[J]. 智慧电力, 2021, 49(12): 104-110.
	SUN Zhida, YANG Tao, WU Dongqi, et al. Fault location model for distribution networks based on multi-source information and genetic algorithm[J]. Smart Power, 2021, 49(12): 104-110.
[15]	汪文达, 张伟. 基于多源非健全信息融合的配电网主动故障研判方法[J]. 电气传动, 2021, 51(12): 47-51.
	WANG Wenda, ZHANG Wei. Active fault diagnosis method for distribution network based on multi-source imperfect information fusion[J]. Electric Drive, 2021, 51(12): 47-51.
[16]	马洲俊, 樊飞龙, 王勇, 等. 基于多源异构数据的配电网故障信息挖掘与诊断[J]. 供用电, 2018, 35(8): 31-39.
	MA Zhoujun, FAN Feilong, WANG Yong, et al. Distribution network fault information mining and diagnosis based on multi-source heterogeneous data[J]. Distribution & Utilization, 2018, 35(8): 31-39.
[17]	崔建双, 车梦然. 基于多分类支持向量机的优化算法智能推荐系统与实证分析[J]. 计算机工程与科学, 2019, 41(1): 153-160.
	CUI Jianshuang, CHE Mengran. An intelligent recommendation system for optimization algorithms based on multi-classification support vector machine and its empirical analysis[J]. Computer Engineering & Science, 2019, 41(1): 153-160.

保护动作情况	故障位置
上级II、III段,本级I、II、III段	本级线路上级II段后备保护范围内
上级III段,本级I、II、III段	本级线路上级II段后备保护范围外,本级I段范围内
上级III段,本级II、III段	本级线路I段保护范围外

算法	单点故障		多点故障
算法	时间/s	准确率/%	时间/s	准确率/%
本文方法	3.67	100	4.07	100
膜算法	27.84	87.32	30.92	77.62
和声算法	78.8	71.2	82.2	68.21

开关编号	实际负荷/kW	占比/%
SB1	85.51	10.19
SB2	28.98	3.56
SB3	25.23	3.02
SB4	1.02	0.12
CB2	486.77	60.42
SB5	120.84	15.08
CB3	221.62	27.40