融合时空图信息的配电网故障区段定位及可解释性分析方法

doi:10.19595/j.cnki.1000-6753.tces.250260

Abstract
Figure/Table
References
Related Citation (15)

Download: PDF (2883 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract With the continuous advancement of the Carbon Peaking and Carbon Neutrality Goal and the construction of new power systems, the high penetration of distributed generation, power electronic devices/loads makes the transition from traditional distribution networks to new distribution systems an inevitable trend. Under complex operational scenarios such as renewable energy output fluctuations and frequent topology reconfigurations, improving the accuracy and interpretability of existing AI-based fault diagnosis and location schemes for distribution networks has become an urgent challenge. To address this issue, this paper proposes a spatiotemporal graph-based fault section location and interpretability analysis method for distribution networks.
Firstly, generators (or buses), loads, and other components in the distribution network are abstracted as nodes, and each line is abstracted as an edge. Based on the spatial relationships of measurement points, a spatiotemporal graph structure dataset for the distribution network is constructed, integrating temporal continuity and spatial integrity.
Secondly, a fault location model based on spatio-temporal graph convolution (STGCN) is developed. This model extracts implicit spatiotemporal features through a temporal information capture basic block (TIC-Block) and a spatial feature perception basic block (SFP-Block). The mapping relationship between high-dimensional features and fault sections is then depicted via a segment classification module.
Then, an interpretability analysis module is designed, generating a spatial weight map of measurement points. This enables post-hoc interpretability analysis of the model's decision basis and internal mechanisms, thereby verifying the fault location results.
Finally, a typical distribution system simulation model is constructed in Matlab/Simulink to validate the proposed method, the following conclusions were drawn: (1) The proposed STGCN-based fault location scheme achieves an accuracy of 94.74%, outperforming single-function schemes such as CNN, LSTM, and GCN. This highlights the model's ability to effectively extract fault features from the spatiotemporal graph structure data of distribution networks. (2)Under complex operating scenarios such as renewable energy output fluctuations, noise interference, and topology reconfigurations, the proposed fault location scheme demonstrates strong generalization capability, providing an effective solution for fault location in dynamically operating distribution networks. (3) The interpretability analysis module designed in this paper quantifies the contribution of each measurement point to the output results by reconstructing the spatial weight map, thereby verifying the rationality of fault section location.
The results show that compared to existing similar methods, the proposed scheme maintains excellent generalization capability under complex operational scenarios such as distributed generation variations, noise interference and data loss, and topology reconfigurations. It demonstrates high location accuracy, strong robustness, and good interpretability, offering a new research perspective for enhancing the interpretability of fault location schemes in distribution networks.

Key words： Distribution network fault location topology change spatio-temporal graph convolutional network (STGCN) interpretability

Received: 20 February 2025

PACS:

TM726

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	Liu Changyu
	Wang Xiaojun
	Zhang Dahai
	Liu Zhao
	Shang Boyang
	Dou Jiaming

Cite this article:

Liu Changyu,Wang Xiaojun,Zhang Dahai等. Research on Fault Section Location Method in Distribution Networks Integrating Spatio-Temporal Graph Information and Interpretability[J]. Transactions of China Electrotechnical Society, 2026, 41(5): 1623-1636.

URL:

https://dgjsxb.ces-transaction.com/EN/10.19595/j.cnki.1000-6753.tces.250260 OR https://dgjsxb.ces-transaction.com/EN/Y2026/V41/I5/1623

[1] 盛万兴, 刘科研, 李昭, 等. 新型配电系统形态演化与安全高效运行方法综述[J]. 高电压技术, 2024, 50(1): 1-18.
Sheng Wanxing, Liu Keyan, Li Zhao, et al.Review of basic theory and methods of morphological evolution and safe & efficient operation of new distribution system[J]. High Voltage Engineering, 2024, 50(1): 1-18.
[2] 罗国敏, 谭颖婕, 吴梦宇, 等. 考虑电压跌落差异的有源配电网功率差动保护[J]. 电工技术学报, 2025, 40(4): 1287-1306.
Luo Guomin, Tan Yingjie, Wu Mengyu, et al.Power differential protection for active distribution networks considering voltage drop differences[J]. Transactions of China Electrotechnical Society, 2025, 40(4): 1287-1306.
[3] 詹惠瑜, 刘科研, 盛万兴, 等. 有源配电网故障诊断与定位方法综述及展望[J]. 高电压技术, 2023, 49(2): 660-671.
Zhan Huiyu, Liu Keyan, Sheng Wanxing, et al.Review and prospects of fault diagnosis and location method in active distribution network[J]. High Voltage Engineering, 2023, 49(2): 660-671.
[4] 齐郑, 黄朝晖, 陈艳波. 基于零序分量的阻抗法配电网故障定位技术[J]. 电力系统保护与控制, 2023, 51(6): 54-62.
Qi Zheng, Huang Zhaohui, Chen Yanbo.Impedance fault location technology for a distribution network based on a zero-sequence component[J]. Power System Protection and Control, 2023, 51(6): 54-62.
[5] 王小君, 任欣玉, 和敬涵, 等. 基于μPMU相量信息的配电网络故障测距方法[J]. 电网技术, 2019, 43(3): 810-818.
Wang Xiaojun, Ren Xinyu, He Jinghan, et al.Distribution network fault location based on μPMU information[J]. Power System Technology, 2019, 43(3): 810-818.
[6] Deng Feng, Zhong Yihan, Zeng Zhe, et al.A single-ended fault location method for transmission line based on full waveform features extractions of traveling waves[J]. IEEE Transactions on Power Delivery, 2023, 38(4): 2585-2595.
[7] 郑雨霖, 郭谋发, 陈方旭, 等. 不依赖同步对时的配电网接地故障双端行波测距方法及其误差分析[J]. 电工技术学报, 2025, 40(15): 4860-4873.
Zheng Yulin, Guo Moufa, Chen Fangxu, et al.A double-terminal traveling wave grounding fault location scheme in distribution networks independent of time synchronization and its error analysis[J]. Transactions of China Electrotechnical Society, 2025, 40(15): 4860-4873.
[8] 邢晓东, 石访, 张恒旭, 等. 基于同步相量的有源配电网自适应故障区段定位方法[J]. 电工技术学报, 2020, 35(23): 4920-4930.
Xing Xiaodong, Shi Fang, Zhang Hengxu, et al.Adaptive section location method for active distribution network based on synchronized phasor measurement[J]. Transactions of China Electrotechnical Society, 2020, 35(23): 4920-4930.
[9] 和敬涵, 罗国敏, 程梦晓, 等. 新一代人工智能在电力系统故障分析及定位中的研究综述[J]. 中国电机工程学报, 2020, 40(17): 5506-5516.
He Jinghan, Luo Guomin, Cheng Mengxiao, et al.A research review on application of artificial intelligence in power system fault analysis and location[J]. Proceedings of the CSEE, 2020, 40(17): 5506-5516.
[10] Jamali S, Bahmanyar A, Ranjbar S.Hybrid classifier for fault location in active distribution networks[J]. Protection and Control of Modern Power Systems, 2020, 5(1): 17.
[11] 褚旭, 鲍泽宏, 许立强, 等. 基于时序卷积残差网络的主动配电系统线路短路故障诊断方案[J]. 电工技术学报, 2023, 38(8): 2178-2190.
Chu Xu, Bao Zehong, Xu Liqiang, et al.Fault line diagnosis scheme of active distribution system based on time-sequence convolution residual network[J]. Transactions of China Electrotechnical Society, 2023, 38(8): 2178-2190.
[12] Zhao Meng, Barati M.A real-time fault localization in power distribution grid for wildfire detection through deep convolutional neural networks[J]. IEEE Transactions on Industry Applications, 2021, 57(4): 4316-4326.
[13] Luo Guomin, Shang Boyang, Wang Xiaojun, et al.Intelligent location method with limited measurement information for multibranch distribution networks[J]. IEEE Transactions on Instrumentation and Measurement, 2024, 73: 2508815.
[14] Li Zijing, Lin Shuyue, Guo Moufa, et al.A decentralized fault section location method using autoencoder and feature fusion in resonant grounding distribution systems[J]. IEEE Systems Journal, 2022, 16(4): 5698-5707.
[15] 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.
[16] 李佳玮, 王小君, 和敬涵, 等. 基于图注意力网络的配电网故障定位方法[J]. 电网技术, 2021, 45(6): 2113-2121.
Li Jiawei, Wang Xiaojun, He Jinghan, et al.Distribution network fault location based on graph attention network[J]. Power System Technology, 2021, 45(6): 2113-2121.
[17] 王小君, 窦嘉铭, 刘曌, 等. 可解释人工智能在电力系统中的应用综述与展望[J]. 电力系统自动化, 2024, 48(4): 169-191.
Wang Xiaojun, Dou Jiaming, Liu Zhao, et al.Review and prospect of explainable artificial intelligence and its application in power systems[J]. Automation of Electric Power Systems, 2024, 48(4): 169-191.
[18] 陈晓龙, 孙丽蓉, 李永丽, 等. 基于图注意力网络和一致性风险控制的配电网故障区段定位方法[J]. 电网技术, 2023, 47(12): 4866-4877.
Chen Xiaolong, Sun Lirong, Li Yongli, et al.A fault section location method based on graph attention network and conformal risk control in distribution network[J]. Power System Technology, 2023, 47(12): 4866-4877.
[19] 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.
[20] 李泽文, 夏翊翔, 吴国瑞, 等. 基于时空数据立方体的配电网故障辨识方法[J/OL]. 中国电机工程学报, 2024: 1-10. (2024-12-03). https://link.cnki.net/doi/10.13334/j.0258-8013.pcsee.241276.
Li Zewen, Xia Yixiang, Wu Guorui, et al. Fault identification method for distribution networks based on spatio-temporal data cube[J/OL]. Proceedings of the CSEE, 2024: 1-10. (2024-12-03). https://link.cnki.net/doi/10.13334/j.0258-8013.pcsee.241276.
[21] Yan Sijie, Xiong Yuanjun, Lin Dahua.Spatial temporal graph convolutional networks for skeleton-based action recognition[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2018, 32(1): 7444-7452.
[22] Yu Bing, Yin Haoteng, Zhu Zhanxing.Spatio-temporal graph convolutional networks: a deep learning framework for traffic forecasting[C]//Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, Stockholm, Sweden, 2018: 3634-3640.
[23] 庄颖睿, 肖谭南, 程林, 等. 基于时空图卷积网络的电力系统暂态稳定评估[J]. 电力系统自动化, 2022, 46(11): 11-18.
Zhuang Yingrui, Xiao Tannan, Cheng Lin, et al.Transient stability assessment of power system based on spatio-temporal graph convolutional network[J]. Automation of Electric Power Systems, 2022, 46(11): 11-18.
[24] 杜东来, 韩松, 荣娜. 基于时空图卷积网络和自注意机制的频率稳定性预测[J]. 电工技术学报, 2024, 39(16): 4985-4995.
Du Donglai, Han Song, Rong Na.Frequency stability prediction method based on modified spatial temporal graph convolutional networks and self-attention[J]. Transactions of China Electrotechnical Society, 2024, 39(16): 4985-4995.
[25] 张鹏飞, 胡博, 何金松, 等. 基于时空图卷积网络的短期空间负荷预测方法[J]. 电力系统自动化, 2023, 47(13): 78-85.
Zhang Pengfei, Hu Bo, He Jinsong, et al.Short-term spatial load forecasting method based on spatio-temporal graph convolutional network[J]. Automation of Electric Power Systems, 2023, 47(13): 78-85.
[26] 温楷儒, 陈祝云, 黄如意, 等. 基于可解释时空图卷积网络的多传感数据融合诊断方法[J]. 机械工程学报, 2024, 60(12): 158-167.
Wen Kairu, Chen Zhuyun, Huang Ruyi, et al.Multi-sensor data fusion diagnosis method based on interpretable spatial-temporal graph convolutional network[J]. Journal of Mechanical Engineering, 2024, 60(12): 158-167.