基于D-S证据理论的配电网接地故障原因综合辨识模型

doi:10.11930/j.issn.1004-9649.202405007

中国电力 ›› 2024, Vol. 57 ›› Issue (10): 133-142.DOI: 10.11930/j.issn.1004-9649.202405007

• 新型配电系统保护与控制关键技术 • 上一篇下一篇

基于D-S证据理论的配电网接地故障原因综合辨识模型

胡云鹏¹(), 都成刚¹(), 齐军²(), 郑日红², 阿敏夫³, 张浩⁴, 梁永亮⁴()

1. 南京南瑞继保电气有限公司，江苏南京　211102
2. 内蒙古电力（集团）有限责任公司阿拉善供电分公司，内蒙古阿拉善盟　750306
3. 内蒙古电力（集团）有限责任公司，内蒙古呼和浩特　010010
4. 山东大学电气工程学院，山东济南　250061

收稿日期:2024-05-06 出版日期:2024-10-28 发布日期:2024-10-25
作者简介:胡云鹏（1974—），男，高级工程师，从事电网二次继电保护研究，E-mail：huyp@nrec.com
都成刚（1976—），男，硕士，高级工程师，从事电力系统自动化研究，E-mail：13912950066@163.com
齐军（1979—），男，硕士，高级工程师（教授级），长期从事电力系统安全稳定运行与控制工作，E-mail：qmvu@163.com
梁永亮（1987—），男，通信作者，博士，副研究员，从事配电网接地故障辨识研究，E-mail：liangyl@sdu.edu.cn
基金资助:
内蒙古电力（集团）有限责任公司科技项目（2022JBGS0044）。

D-S Evidence Theory Based Comprehensive Identification Model for Cause of Grounding Fault in Distribution Network

Yunpeng HU¹(), Chenggang DU¹(), Jun QI²(), Rihong ZHENG², Minfu A³, Hao ZHANG⁴, Yongliang LIANG⁴()

1. NR Electric Co., Ltd. Nanjing, Nanjing 211102, China
2. Alxa Power Supply Branch, Inner Mongolia Electric Power (Group) Co., Ltd. Alxa League, Inner Mongolia 750306, China
3. Inner Mongolia Electric Power (Group) Co., Ltd. Hohhot, Inner Mongolia 010010, China
4. School of Electrical Engineering, Shandong University. Jinan 250061, China

Received:2024-05-06 Online:2024-10-28 Published:2024-10-25
Supported by:
This work is supported by Science and technology project of Inner Mongolia Electric Power (Group) Co., Ltd. (No.2022JBGS0044)

摘要/Abstract

摘要：

单相接地故障（single-phase-to-ground fault，SPGF）是配电网中最常见的故障，严重影响配电系统的可靠性和安全性，准确辨识SPGF可以提高配电网接地故障处理的精细化水平。首先，从故障波形中提取能有效反映不同接地故障原因的多域特征组成候选波形特征集，通过多元方差法分析波形特征与接地故障原因的相关性，筛选识别接地故障原因的有效特征；然后，分别设计基于极限学习机和支持向量机的故障原因辨识模型，利用Dempster-Shafer（D-S）证据融合理论对模型的识别结果进行融合，建立了接地故障原因综合辨识模型；最后，基于现场数据对所建立的综合辨识模型的有效性进行了验证，结果表明综合辨识模型优于任何单一辨识模型，验证了该模型的优势和可行性。

关键词: 接地故障原因, 单相接地故障, 极限学习机, 支持向量机, D-S证据理论

Abstract:

Single-phase-to-ground fault (SPGF), being the most prevalent issue in distribution networks, significantly impacts the reliability and safety of the distribution system. Accurate identification of SPGF can enhance the level of refinement in handling grounding faults in distribution networks. Firstly, a set of candidate waveform features that effectively reflect various grounding fault causes is extracted from the fault waveforms. These features are then subjected to multivariate analysis of variance (MANOVA) to assess their correlation with grounding fault causes, thereby selecting effective features for identifying the root causes. Subsequently, fault cause identification models based on Extreme Learning Machine (ELM) and Support Vector Machine (SVM) are designed respectively. These models' recognition results are fused using Dempster-Shafer (D-S) theory of evidence fusion, establishing a comprehensive identification model for grounding fault causes. Finally, the validity of the established comprehensive identification model is verified based on field data, demonstrating its superiority over any single identification model and confirming its feasibility.

Key words: ground fault cause, single-phase-to-ground fault, extreme learning machine, support vector machine, D-S evidence theory.

胡云鹏, 都成刚, 齐军, 郑日红, 阿敏夫, 张浩, 梁永亮. 基于D-S证据理论的配电网接地故障原因综合辨识模型[J]. 中国电力, 2024, 57(10): 133-142.

Yunpeng HU, Chenggang DU, Jun QI, Rihong ZHENG, Minfu A, Hao ZHANG, Yongliang LIANG. D-S Evidence Theory Based Comprehensive Identification Model for Cause of Grounding Fault in Distribution Network[J]. Electric Power, 2024, 57(10): 133-142.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: https://www.electricpower.com.cn/CN/10.11930/j.issn.1004-9649.202405007

https://www.electricpower.com.cn/CN/Y2024/V57/I10/133

图/表 8

图 1 时间-频率域中的特征选择说明

Fig.1 Explanation of feature selection in the time-frequency domain

表 1 故障原因及其对应符号

Table 1 Fault types and their corresponding symbols

符号		接地故障原因
F1		避雷器击穿
F2		线路到横杆放电
F3		电缆绝缘损坏
F4		绝缘子击穿
F5		树形触点
F6		其他原因

表 2 基于MANOVA的波形特征统计结果

Table 2 Statistical results for waveform features based on MANOVA

波形特点	F-数据	排序
C3	289.64	1
C2	235.40	2
C1	120.25	3
C4	115.25	4
C10	108.65	5
C11	83.13	6
C5	79.84	7
C9	39.94	8
C6	18.96	9
C8	10.78	10
C7	10.61	11

表 3 每种故障原因的数据大小

Table 3 Data size for each fault type

故障原因		数量
F1		61
F2		61
F3		61
F4		55
F5		59
F6		145

图 2 PSO中适应度相对于迭代次数的变化

Fig.2 The variation of fitness relative to the number of iterations in PSO

表 4 不同实例的诊断准确性

Table 4 Diagnostic accuracy for different cases

激活功能	隐藏层神经元数量
激活功能	11	15	20	25	30
sig	88.1	89.1	91.6	90.1	90.6
sin	85.6	86.6	87.6	87.6	87.1
hardlim	75.7	80.2	80.7	80.7	83.7

表 5 不同故障原因的测试集数据大小和识别准确率

Table 5 Test set data size and recognition accuracy rate for different fault types

故障原因	测试数据	识别准确率/%
F1	21	100
F2	21	100
F3	21	90.5
F4	15	93.3
F5	19	89.5
F6	105	93.3
总计	202	94.1

表 6 部分数据识别结果

Table 6 Recognition results of partial data

实际故障	识别方法
实际故障	ELM	SVM	融合模型
F3	F3	F3	F3
F3	F2	F3	F3
F3	F3	F3	F3
F3	F3	F3	F3
F4	F3	F4	F4
F4	F4	F4	F4
F4	F4	F4	F4
F5	F5	F4	F5
F5	F5	F4	F5

参考文献 26

1	刘洪波, 刘珅诚, 盖雪扬, 等. 高比例新能源接入的主动配电网规划综述[J]. 发电技术, 2024, 45 (1): 151- 161. DOI
	LIU Hongbo, LIU Shencheng, GAI Xueyang, et al. Overview of active distribution network planning with high proportion of new energy access[J]. Power Generation Technology, 2024, 45 (1): 151- 161. DOI
2	吴江雄, 郑茂然, 王欣, 等. 基于暂态零序导纳值的谐振接地系统单相接地故障选线方法[J/OL]. 南方电网技术, 2024: 1–9. (2024-04-26). https://kns.cnki.net/kcms/detail/44.1643.TK.20240424.1107.002.html.
	WU Jiangxiong, ZHENG Maoran, WANG Xin, et al. Single-phase grounding fault line selection method for resonant grounding system based on transient zero-sequence admittance value[J/OL]. Southern Power System Technology, 2024: 1–9. (2024-04-26). https://kns.cnki.net/kcms/detail/44.1643.TK.20240424.1107.002.html.
3	王晓卫, 岳阳, 郭亮, 等. 注入电流分布特性辨识的配电网故障选线方法[J/OL]. 中国电力, 2024: 1–12. (2024-02-26). https://kns.cnki.net/kcms/detail/11.3265.TM.20240226.1229.004.html.
	WANG Xiaowei, YUE Yang, GUO Liang, et al. Fault line selection method for distribution network based on injection current distribution characteristics identification[J/OL]. Electric Power, 2024: 1–12. (2024-02-26). https://kns.cnki.net/kcms/detail/11.3265.TM.20240226.1229.004.html.
4	徐丙垠, 李天友, 薛永端. 配电网继电保护与自动化[M]. 北京: 中国电力出版社, 2017.
5	AN J G, SONG J U, OH Y S. A fuzzy-based fault section identification method using dynamic partial tree in distribution systems[J]. International Journal of Electrical Power & Energy Systems, 2023, 153, 109344.
6	LI B H, CHENG T F, JIANG Q, et al. Faulty feeders identification for single-phase-to-ground fault based on multi-features and machine learning[J]. IEEE Transactions on Industry Applications, 2023, 59 (6): 7259- 7270. DOI
7	YOU J L, ZHANG D, GONG Q W, et al. Fault phase selection method of distribution network based on wavelet singular entropy and DBN[C]//2022 China International Conference on Electricity Distribution (CICED). Changsha, China. IEEE, 2022: 1742–1747.
8	黄亚峰, 王浩天, 朱登宝, 等. 基于零序电流特性的中性点灵活接地系统的故障选线方法[J]. 东北电力大学学报, 2023, 43 (3): 16- 22, 71.
	HUANG Yafeng, WANG Haotian, ZHU Dengbao, et al. Fault line selection method for neutral flexible grounding system based on zero sequence current characteristics[J]. Journal of Northeast Electric Power University, 2023, 43 (3): 16- 22, 71.
9	李泽文, 黎文娇, 彭维馨, 等. 基于IHHT-RF的配电网单相接地故障选线方法[J]. 电力科学与技术学报, 2024, 39 (1): 171- 182.
	LI Zewen, LI Wenjiao, PENG Weixin, et al. Single-phase-to-ground fault line selection method of distribution network based on IHHT-RF[J]. Journal of Electric Power Science and Technology, 2024, 39 (1): 171- 182.
10	喻锟, 倪聪, 曾祥君, 等. 中性点柔性接地配电网故障相恢复电压暂态时域特征分析[J]. 中国电机工程学报, 2024, 44 (3): 992- 1007.
	YU Kun, NI Cong, ZENG Xiangjun, et al. Analysis of transient time domain characteristics of fault phase recovery voltage in neutral flexible grounding distribution networks[J]. Proceedings of the CSEE, 2024, 44 (3): 992- 1007.
11	张玉玺, 王增平, 李振钊, 等. 基于特征频带暂态无功功率的配电网故障选线新方法[J]. 电力系统保护与控制, 2023, 51 (1): 1- 11.
	ZHANG Yuxi, WANG Zengping, LI Zhenzhao, et al. A new method of fault line selection in a distribution network based on characteristic frequency band transient reactive power[J]. Power System Protection and Control, 2023, 51 (1): 1- 11.
12	刘丰, 曾祥君, 谢李为, 等. 基于相电压差值极性的配电网单相接地故障检测方法[J]. 电力系统保护与控制, 2023, 51 (15): 155- 165.
	LIU Feng, ZENG Xiangjun, XIE Liwei, et al. Single-phase grounding fault detection method for a distribution network based on phase voltage difference polarity value[J]. Power System Protection and Control, 2023, 51 (15): 155- 165.
13	白浩, 潘姝慧, 邵向潮, 等. 基于小波去噪与随机森林的配电网高阻接地故障半监督识别方法[J]. 电力系统保护与控制, 2022, 50 (20): 79- 87.
	BAI Hao, PAN Shuhui, SHAO Xiangchao, et al. A high impedance grounding fault semi-supervised identification method based on wavelet denoising and random forest[J]. Power System Protection and Control, 2022, 50 (20): 79- 87.
14	吴岩, 关石磊, 孟晓丽, 等. 综合多域特征及融合算法的配电网单相接地故障类型识别[J]. 高电压技术, 2023, 49 (5): 2059- 2067.
	WU Yan, GUAN Shilei, MENG Xiaoli, et al. Classification of single-phase ground faults in distribution network based on multi-domain features and fusion algorithm[J]. High Voltage Engineering, 2023, 49 (5): 2059- 2067.
15	XI Y H, LI M T, ZHOU F, et al. SE-inception-ResNet model with focal loss for transmission line fault classification under class imbalance[J]. IEEE Transactions on Instrumentation and Measurement, 2024, 73, 3500917.
16	梁钟颖, 周凯, 孟鹏飞, 等. 基于频域反射系数谱的电缆故障定位与故障类型识别方法研究[J]. 电工电能新技术, 2022, 41 (8): 79- 88. DOI
	LIANG Zhongying, ZHOU Kai, MENG Pengfei, et al. Research on cable fault location and fault type identification based on frequency domain reflection coefficient spectrum[J]. Advanced Technology of Electrical Engineering and Energy, 2022, 41 (8): 79- 88. DOI
17	赵书静, 龚梁涛, 詹博博, 等. 基于FMCW的10kV配电电缆故障定位及类型识别方法[J]. 中国电机工程学报, 2023, 43 (11): 4452- 4463.
	ZHAO Shujing, GONG Liangtao, ZHAN Bobo, et al. 10kV cable fault location and type identification method based on FMCW[J]. Proceedings of the CSEE, 2023, 43 (11): 4452- 4463.
18	XIANG N W, PAN Y F, WANG C Q. Study on the discharge and defect characteristics of the binding wire to the insulated conductor in the distribution network[C]//2023 IEEE 6th International Electrical and Energy Conference (CIEEC). Hefei, China. IEEE, 2023: 3499-3502.
19	ZHOU L J, TIAN Y, CHEN W J, et al. Characteristics of partial discharge on 10 kV covered conductor around tower head[J]. IEEE Access, 2022, 10, 98140- 98152. DOI
20	LIU J, HAN B G, LIANG Y L, et al. Fusion model for recognition of single-phase-to-ground fault caused by insulation deterioration in medium-voltage distribution networks[C]//2022 China International Conference on Electricity Distribution (CICED). Changsha, China. IEEE, 2022: 1456–1461.
21	LIANG H Q, LIU Y D, SHENG G H, et al. Fault-cause identification method based on adaptive deep belief network and time–frequency characteristics of travelling wave[J]. IET Generation, Transmission & Distribution, 2019, 13(5): 724–732.
22	GEIGER B C, KOCH T. On the information dimension of stochastic processes[J]. IEEE Transactions on Information Theory, 2019, 65 (10): 6496- 6518. DOI
23	常雪. 中压配电电缆潜伏性故障辨识方法研究[D]. 济南: 山东大学, 2023.
	CHANG Xue. Research on identification method of latent fault of medium voltage distribution cables[D]. Jinan: Shandong University, 2023.
24	刘科研, 詹惠瑜, 谭云耀, 等. 基于改进极限学习机的配电网高阻接地故障检测方案[J]. 电网技术, 2023, 47 (5): 1886- 1899.
	LIU Keyan, ZHAN Huiyu, TAN Yunyao, et al. High impedance grounding fault detection in distribution network based on improved extreme learning machine[J]. Power System Technology, 2023, 47 (5): 1886- 1899.
25	ZHANG J W, JIA H Y, ZHANG N. Alternate support vector machine decision trees for power systems rule extractions[J]. IEEE Transactions on Power Systems, 2023, 38 (1): 980- 983. DOI
26	钟鸣, 陶军, 刘洵宇, 等. 智能变电站光纤虚实回路映射及故障诊断技术[J]. 中国电力, 2023, 56 (10): 171- 178.
	ZHONG Ming, TAO Jun, LIU Xunyu, et al. Smart substation optical fiber virtual and real loop mapping and fault diagnosis technology[J]. Electric Power, 2023, 56 (10): 171- 178.

[1]	席磊, 王艺晓, 何苗, 程琛, 田习龙. 基于反向鲸鱼-多隐层极限学习机的电网FDIA检测[J]. 中国电力, 2024, 57(9): 20-31.
[2]	郭亮, 屈新宇, 王晓卫, 王毅钊, 田影, 张帆. 基于改进Hough变换的消弧线圈接地配电网故障选线新方法[J]. 中国电力, 2024, 57(7): 132-142.
[3]	郑鹏, 韩鹏程, 王国栋, 娄颖. 中压配电线路断线高阻接地故障精细化诊断方法[J]. 中国电力, 2024, 57(4): 220-228.
[4]	王晓卫, 岳阳, 郭亮, 王雪, 王毅钊, 张志华, 杨峰峰. 注入电流分布特性辨识的配电网故障选线方法[J]. 中国电力, 2024, 57(10): 78-89.
[5]	王尧平, 李特, 姜凯华, 李文辉, 吴强, 王羽. 基于气象特征挖掘与AdaBoost-MEA-ELM模型的绝缘子盐密预测[J]. 中国电力, 2023, 56(9): 157-167.
[6]	叶远波, 章昊, 王同文, 王志华, 陈勇. 基于边缘物联的电力系统二次继保设备测试管控技术[J]. 中国电力, 2023, 56(7): 156-162,174.
[7]	安佳坤, 杨书强, 王涛, 贺春光, 张菁, 袁超, 窦春霞. 电动汽车聚合下的微能源互联网优化调度策略[J]. 中国电力, 2023, 56(5): 80-88.
[8]	徐一伦, 张彬桥, 黄婧, 谢枭, 王若昕, 沈丹青, 何丽娜, 杨凯帆. 考虑天气类型和相似日的IWPA-LSSVM光伏发电功率预测[J]. 中国电力, 2023, 56(2): 143-149.
[9]	韩伟, 段文岩, 杜兴伟, 姚峰, 马伟东, 刘磊. 基于数字孪生的在运安控系统故障诊断方法[J]. 中国电力, 2023, 56(11): 121-127.
[10]	钟鸣, 陶军, 刘洵宇, 杨逸, 杨炳元. 智能变电站光纤虚实回路映射及故障诊断技术[J]. 中国电力, 2023, 56(10): 171-178.
[11]	严亚兵, 褚旭, 肖豪龙, 梁文武, 李辉, 夏振兴. 基于改进支持向量机的数字化变电站安全措施生成技术[J]. 中国电力, 2023, 56(10): 194-201.
[12]	刘昳娟, 陈云龙, 刘继彦, 张雪梅, 吴潇雨, 孔维政. 基于集成学习的分布式光伏发电功率日前预测[J]. 中国电力, 2022, 55(9): 38-45.
[13]	陈铁, 冷昊伟, 李咸善, 陈一夫. 基于油中气体分析与类重叠特征的变压器分层故障诊断模型[J]. 中国电力, 2022, 55(7): 22-32,41.
[14]	彭生江, 孙传帅, 妥建军, 袁铁江. 面向统一能源系统的中长期氢负荷预测[J]. 中国电力, 2022, 55(1): 84-90.
[15]	李登峰, 杨旼才, 刘育明, 徐瑞林, 余霞, 李昭炯. 基于SVR数据驱动的发电机进相极限最优化求解方法[J]. 中国电力, 2021, 54(8): 136-143,153.

基于D-S证据理论的配电网接地故障原因综合辨识模型

D-S Evidence Theory Based Comprehensive Identification Model for Cause of Grounding Fault in Distribution Network

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 8

参考文献 26

相关文章 15

编辑推荐

Metrics

模态框（Modal）标题

基于D-S证据理论的配电网接地故障原因综合辨识模型

D-S Evidence Theory Based Comprehensive Identification Model for Cause of Grounding Fault in Distribution Network

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 8

参考文献 26

相关文章 15

编辑推荐

Metrics