CNN-BiGRU-ATT multi-branched distribution network fault location based on multi-dimensional fault feature extraction

张玉敏; 王德龙; 张晓; 吉兴全; 张祥星; 黄心月; 王学林

doi:10.11930/j.issn.1004-9649.202507050

English Version Reader LoginJournal Login

您当前的位置：

首页 >

文章列表页 >

CNN-BiGRU-ATT multi-branched distribution network fault location based on multi-dimensional fault feature extraction

更新时间：2026-02-03

- CNN-BiGRU-ATT multi-branched distribution network fault location based on multi-dimensional fault feature extraction
- Vol. 59, Issue 1, Pages: 163-174(2026)
- 作者机构：
  
  1. 山东科技大学电气与自动化工程学院,山东,青岛,266590
  2. 国网山东省电力公司德州市陵城区供电公司,山东,德州,253500
  3. 青岛科技大学自动化与电子工程学院,山东,青岛,266061
- 作者简介：
- 基金信息：
- DOI：10.11930/j.issn.1004-9649.202507050
  CLC：
- Published Online：13 January 2026，
  
  Published：13 January 2026
- 稿件说明：
移动端阅览
张玉敏, 王德龙, 张晓, 吉兴全, 张祥星, 黄心月, 王学林. 基于多维故障特征提取的CNN-BiGRU-ATT多分支配电网故障定位[J]. 中国电力, 2026, 59(1): 163-174.

张玉敏, 王德龙, 张晓, et al. CNN-BiGRU-ATT multi-branched distribution network fault location based on multi-dimensional fault feature extraction[J]. 2026, 59(1): 163-174.
张玉敏, 王德龙, 张晓, 吉兴全, 张祥星, 黄心月, 王学林. 基于多维故障特征提取的CNN-BiGRU-ATT多分支配电网故障定位[J]. 中国电力, 2026, 59(1): 163-174. DOI： 10.11930/j.issn.1004-9649.202507050.

张玉敏, 王德龙, 张晓, et al. CNN-BiGRU-ATT multi-branched distribution network fault location based on multi-dimensional fault feature extraction[J]. 2026, 59(1): 163-174. DOI： 10.11930/j.issn.1004-9649.202507050.

摘要

针对多分支配电网故障定位在微弱故障条件下故障特征提取困难的问题，提出了基于多维故障特征提取的卷积神经网络（convolution neural network，CNN）-双向门控循环单元（bidirectional gated recurrent unit，BiGRU）-注意力机制（attention mechanism，ATT）多分支配电网故障定位方法。首先，分析不同故障位置和故障分支的行波特性，采用基于直线检测（line segment detector，LSD）的波头标定方法提取故障波头的坐标、幅值和斜率等信息，利用主成分分析法（principal component analysis，PCA）构造与故障位置成映射关系的多维故障特征空间；其次，构建CNN-BiGRU-ATT故障定位模型，深入挖掘时序特征和幅值特征与故障位置之间的关联；最后，结合分类与回归任务，分别实现故障区段定位与精准定位。在有限样本的情况下，区段定位准确率达99.6429%，精准定位误差55.77 m，跨工况误差最低2.95 m。结果表明，该模型能有效关联多维故障特征与故障信息，较对比模型具有更优的故障定位精度稳定性与场景泛化能力。

Abstract

To address the difficulty in fault feature extraction for multi-branched distribution network fault location under weak fault conditions

this paper proposes a fault location method based on multi-dimensional feature extraction

which integrates the convolutional neural network (CNN)

bidirectional gated recurrent unit (BiGRU)

and attention mechanism (ATT). Firstly

the traveling wave characteristics of different fault locations and fault branches are analyzed. A wavefront calibration method based on the line segment detector (LSD) is employed to extract information features such as the coordinates

amplitudes

and slope of fault wavefronts

and principal component analysis (PCA) is used to construct a multi-dimensional fault-feature space that maps to fault locations. Then

a CNN-BiGRU-ATT fault location model is established to deeply explore the correlations between temporal features

amplitude features

and fault locations. Finally

classification and regression tasks are integrated to achieve both fault section identification and precise fault location. Under the condition of limited samples

the fault section location accuracy reaches 99.6429%

the accurate location error is 55.77 m

and the cross-condition error is as low as 2.95 m. The results show that the proposed model can effectively correlate multi-dimensional fault features with fault information

and exhibits superior stability of fault location accuracy and scenario generalization ability compared with the comparative models.

关键词

Keywords

references

1王宇杉, 王晨, 王淑侠, 等. 基于IWOA的配电网故障定位方法[J]. 智慧电力, 2024, 52 (11): 98- 105.

WANG Yushan, WANG Chen, WANG Shuxia, et al. Fault location method for distribution network based on improved IWOA[J]. Smart Power, 2024, 52 (11): 98- 105.

2吉兴全, 张祥星, 张玉敏, 等. 基于LSD算法的多分支配电网故障定位[J]. 中国电力, 2025, 58 (9): 54- 67.

JI Xingquan, ZHANG Xiangxing, ZHANG Yumin, et al. Multi-branch distribution network fault location based on LSD algorithm[J]. Electric Power, 2025, 58 (9): 54- 67.

3吴振杰, 胡晨, 陈海燕, 等. 基于双比例补偿系数的有源配电网电流差动保护[J]. 浙江电力, 2024, 43 (12): 104- 113.

WU Zhenjie, HU Chen, CHEN Haiyan, et al. Differential current protection for active distribution networks with dual proportional compensation coefficients[J]. Zhejiang Electric Power, 2024, 43 (12): 104- 113.

4何宇宁, 王自主, 乔依林, 等. 某330MW亚临界机组供热改造后一次调频控制策略优化[J]. 电力科技与环保, 2023, 39 (2): 120- 128.

HE Yuning, WANG Zizhu, QIAO Yilin, et al. Optimization of primary frequency control strategy for a 330MW sub-critical unit after heating transformation[J]. Electric Power Technology and Environmental Protection, 2023, 39 (2): 120- 128.

5YANG Z, WANG H Y, LIAO W L, et al. Protection challenges and solutions for AC systems with renewable energy sources: a review[J]. Protection and Control of Modern Power Systems, 2025, 10 (1): 18- 39.

6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.

7胡满琳, 李楠, 李一鸣, 等. 基于负序分量的含光伏电源配电网故障区段定位方法[J]. 中国电力, 2024, 57 (5): 188- 199.

HU Manlin, LI Nan, LI Yiming, et al. Fault location method for distribution network with photovoltaic power based on negative sequence component[J]. Electric Power, 2024, 57 (5): 188- 199.

8钱达, 陈浩, 马刚. 基于改进正余弦算法的配电网无功优化[J]. 综合智慧能源, 2024, 46 (10): 40- 47.

QIAN Da, CHEN Hao, MA Gang. Reactive power optimal scheduling of distribution network based on improved sine-cosine algorithm[J]. Integrated Intelligent Energy, 2024, 46 (10): 40- 47.

9李铁成, 张卫明, 臧谦, 等. 基于混合整数线性规划的配电网在线自愈方案[J]. 中国电力, 2023, 56 (5): 129- 136.

LI Tiecheng, ZHANG Weiming, ZANG Qian, et al. Online self-healing scheme of distribution network based on mixed integer linear programming[J]. Electric Power, 2023, 56 (5): 129- 136.

10梁栋, 赵月梓, 贺国润, 等. 基于图半监督与多任务学习的配电网故障区段与类型统一辨识[J]. 电力系统保护与控制, 2024, 52 (12): 25- 32.

LIANG Dong, ZHAO Yuezi, HE Guorun, et al. Unified identification of fault section and type for distribution networks based on graph semi-supervised and multi-task learning[J]. Power System Protection and Control, 2024, 52 (12): 25- 32.

11SUN Y, FAN Y F, HOU J J, et al. A unit protection scheme based on the transient current coordinate mapping interval[J]. Protection and Control of Modern Power Systems, 2025, 10 (1): 103- 120.

12麦章渠, 曾颖, 张禄亮, 等. 基于改进哈里斯鹰优化算法的有源配电网故障定位[J]. 智慧电力, 2022, 50 (11): 104- 111.

MAI Zhangqu, ZENG Ying, ZHANG Luliang, et al. Fault location of active distribution network based on improved Harris Hawks optimization algorithm[J]. Smart Power, 2022, 50 (11): 104- 111.

13ALI BUKHARI S B, KIM C H, MEHMOOD K K, et al. Convolutional neural network-based intelligent protection strategy for microgrids[J]. IET Generation, Transmission & Distribution, 2020, 14 (7): 1177- 1185.

14白通, 王慧芳, 杨林刚, 等. 基于图神经网络的海上风电场集电线路故障区段定位方法[J]. 电力系统及其自动化学报, 2024, 36 (10): 108- 116.

BAI Tong, WANG Huifang, YANG Lingang, et al. Fault segment location method for collector lines in offshore wind farms based on graph neural network[J]. Proceedings of the CSU-EPSA, 2024, 36 (10): 108- 116.

15ZHANG M, WANG D, GAO H L, et al. Novel traveling wave fault location method for HVDC transmission line based on wavefront frequency[J]. Electric Power Systems Research, 2024, 234, 110598.

16WU H, WANG J, NAN D L, et al. Fault location and fault cause identification method for transmission lines based on pose normalized multioutput convolutional nets[J]. IEEE Transactions on Instrumentation and Measurement, 2025, 74, 3500412.

17吉兴全, 陈金硕, 张玉敏, 等. 基于CNN-SVM的配电网故障分类研究[J]. 智慧电力, 2022, 50 (1): 94- 100.

JI Xingquan, CHEN Jinshuo, ZHANG Yumin, et al. Fault classification in distribution network based on CNN-SVM[J]. Smart Power, 2022, 50 (1): 94- 100.

18WANG D, YU D C, GAO H L, et al. Frequency modification algorithm-based traveling wave fault location approach for overhead transmission lines with structural changes[J]. Protection and Control of Modern Power Systems, 2025, 10 (2): 1- 12.

19CHEN K J, HU J, ZHANG Y, et al. Fault location in power distribution systems via deep graph convolutional networks[J]. IEEE Journal on Selected Areas in Communications, 2020, 38 (1): 119- 131.

20何小龙, 高红均, 黄媛, 等. 基于一维卷积和图神经网络的配电网故障区段定位方法[J]. 电力系统保护与控制, 2024, 52 (17): 27- 39.

HE Xiaolong, GAO Hongjun, HUANG Yuan, et al. Fault section location for a distribution network based on one-dimensional convolution and graph neural networks[J]. Power System Protection and Control, 2024, 52 (17): 27- 39.

21黄南天, 程铎, 蔡国伟. 基于改进时空图神经网络的高渗透率有源配电网故障定位[J]. 电力系统自动化, 2025, 49 (10): 112- 122.

HUANG Nantian, CHENG Duo, CAI Guowei. Fault location for active distribution network with high penetration rate based on improved spatio-temporal graph neural network[J]. Automation of Electric Power Systems, 2025, 49 (10): 112- 122.

22LUO J, LIU Y, CUI Q S, et al. Single-ended time domain fault location based on transient signal measurements of transmission lines[J]. Protection and Control of Modern Power Systems, 2024, 9 (2): 61- 74.

23尚博阳, 罗国敏, 茹嘉昕, 等. 基于有限量测信息的多分支配电线路故障定位方法[J]. 高电压技术, 2023, 49 (6): 2308- 2319.

SHANG Boyang, LUO Guomin, RU Jiaxin, et al. Fault location method of multi-branch distribution lines based on limited measurement information[J]. High Voltage Engineering, 2023, 49 (6): 2308- 2319.

24鲁晓天, 唐金锐, 尹昕, 等. 基于多维时频特征的新型配电系统单相接地故障定位方法[J]. 高电压技术, 2025, 51 (2): 903- 914.

LU Xiaotian, TANG Jinrui, YIN Xin, et al. Single-phase-to-ground fault section location in new-type distribution system based on multidimensional time-frequency distribution characteristics[J]. High Voltage Engineering, 2025, 51 (2): 903- 914.

25邓丰, 史鸿飞, 冯思旭, 等. CNN-LSTM全景故障特征挖掘的配电网单端定位方法[J]. 中国电机工程学报, 2023, 43 (S1): 114- 126.

DENG Feng, SHI Hongfei, FENG Sixu, et al. Single-ended traveling wave location method for distribution network based on CNN-LSTM panoramic fault feature mining[J]. Proceedings of the CSEE, 2023, 43 (S1): 114- 126.

27张亚丽, 王聪, 张宏立, 等. 基于非平稳Transformer的超短期风电功率多步预测[J]. 智慧电力, 2024, 52 (1): 108- 115.

ZHANG Yali, WANG Cong, ZHANG Hongli, et al. Multi-step prediction of ultra-short-term wind power based on non-stationary transformer[J]. Smart Power, 2024, 52 (1): 108- 115.

28吉兴全, 薛科壮, 叶平峰, 等. 基于自调参深度双Q网络算法的配电网智能组网规划[J]. 智慧电力, 2025, 53 (11): 48- 55.

JI Xingquan, XUE Kezhuang, YE Pingfeng, et al. Smart networking planning for distribution networks based on an automatically adjusting parameters-based deep double Q network algorithm[J]. Smart Power, 2025, 53 (11): 48- 55.

29赵唯嘉, 白云霄, 张云勇, 等. 基于关键特征对比分析的异常电价成因溯源方法[J]. 中国电力, 2025, 58 (5): 110- 120.

ZHAO Weijia, BAI Yunxiao, ZHANG Yunyong, et al. Traceability method for the causes of abnormal electricity prices based on comparative analysis of key features[J]. Electric Power, 2025, 58 (5): 110- 120.

30王传琦, 伍历文, 邓志斌, 等. 时间累积架空输电线路覆冰预测模型与算法综述[J]. 中国电力, 2024, 57 (6): 153- 164, 234.

WANG Chuanqi, WU Liwen, DENG Zhibin, et al. Review of icing prediction model and algorithm for overhead transmission lines considering time cumulative effects[J]. Electric Power, 2024, 57 (6): 153- 164, 234.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Smart Substation Optical Fiber Virtual and Real Loop Mapping and Fault Diagnosis Technology

Fault Location Method for Communication Link in Smart Substation Based on Deep Learning

Online Self-Healing Scheme of Distribution Network Based on Mixed Integer Linear Programming

An Active Ground Fault Location Method for Low-Voltage DC Lines Based on DFFT

Fault Location Method for Distribution Lines Based on Loss Power Matching

Related Author

Jun TAO

Xunyu LIU

Yi YANG

Bingyuan YANG

Ming ZHONG

Zhiyong PI

Yi ZHU

Xuan LIAO

Related Institution

Inner Mongolia Ultra High Voltage Power Supply Company

Inner Mongolia University of Technology

Inner Mongolia Enterprise Key Laboratory of Smart Grid Simulation of Electrical Power System

Inner Mongolia Power Research Institute

State Grid Hubei Jingmen Electric Power Supply Company

AI问答

⁰