基于动态门控数据融合的 GCN-Transformer 配电网故障区段定位方法

杨楠; 候少波; 邢超; 王灿; 关钦月; 叶学程; 李斯吾; 黄悦华

doi:10.19783/j.cnki.pspc.251301

欢迎来到能源电力期刊网！

English Version 期刊登录

您当前的位置：

首页 >

文章列表页 >

基于动态门控数据融合的 GCN-Transformer 配电网故障区段定位方法

应用研究 | 更新时间：2026-05-14

- 基于动态门控数据融合的 GCN-Transformer 配电网故障区段定位方法
- Fault section location method for distribution networks based on dynamic gated data fusion and GCN-Transformer
- 电力系统保护与控制 2026年54卷第10期
- 作者机构：
- 作者简介：
- 基金信息：
- DOI：10.19783/j.cnki.pspc.251301
  中图分类号：
- 纸质出版：2026
- 稿件说明：
移动端阅览
杨楠, 候少波, 邢超, 等. 基于动态门控数据融合的 GCN-Transformer 配电网故障区段定位方法[J]. 电力系统保护与控制, 2026,54(10).

YANG Nan, HOU Shaobo, XING Chao, et al. Fault section location method for distribution networks based on dynamic gated data fusion and GCN-Transformer[J]. Power System Protection and Control, 2026, 54(10).
杨楠, 候少波, 邢超, 等. 基于动态门控数据融合的 GCN-Transformer 配电网故障区段定位方法[J]. 电力系统保护与控制, 2026,54(10). DOI： 10.19783/j.cnki.pspc.251301.

YANG Nan, HOU Shaobo, XING Chao, et al. Fault section location method for distribution networks based on dynamic gated data fusion and GCN-Transformer[J]. Power System Protection and Control, 2026, 54(10). DOI： 10.19783/j.cnki.pspc.251301.

摘要

在智能电网快速发展背景下，如何有效利用不同测量设备获取的多源数据，以满足不同故障场景下的配电网故障定位需求，对提升含分布式电源配电网的供电可靠性和运行安全性具有重要意义。鉴于此，提出一种基于动态门控数据融合的图卷积神经网络 (graph convolution network

GCN) 与 Transformer 相结合的配电网故障区段定位方法。首先，通过基于掩码感知的动态门控数据融合方法实现同步相量数据与同步波形数据的融合。然后，构建 GCN-Transformer 模型完成故障特征提取与融合，并引入焦点监督对比混合损失函数优化模型。最后，通过全连接分类层实现故障区段定位。仿真结果表明，所提方法在不同故障场景及样本不平衡条件下均表现出良好的故障定位性能。

Abstract

With the rapid development of smart grids

effectively utilizing multi-source data obtained from different measurement devices to meet the fault location requirements under different fault scenarios is of great significance for improving the power supply reliability and operational safety of distribution networks with distributed generation. To this end

a fault section location method for distribution networks based on dynamic gated data fusion and a combination of graph convolution network (GCN) and Transformer is proposed. First

the synchrophasor data and synchronized waveform data are fused through a dynamic gated data fusion method based on mask perception. Then

a GCN-Transformer model is constructed to extract and fuse fault features

and a focal supervised contrastive hybrid loss function is introduced to optimize the model. Finally

the fault section location is achieved through a fully connected classification layer. Simulation results show that the proposed method exhibits strong fault location performance under different fault scenarios and sample imbalance conditions.

关键词

Keywords

references

YANG Nan, XIONG Zhendong, DING Li, et al. A game-based power system planning approach considering real options and coordination of all types of participants[J]. Energy, 2024, 312.

JIANG Qiao, YIN Xianggen, WANG Yikai, et al. A multi-terminal traveling wave fault location method for active distribution network based on residual clustering[J]. International Journal of Electrical Power Energy Systems, 2021, 131.

YANG Nan, HAO Juncong, LI Zhengmao, et al. Data-driven decision-making for SCUC: an improved deep learning approach based on sample coding and Seq2Seq technique[J]. Protection and Control of Modern Power Systems, 2025, 10(2): 13-24.

MO Haojie, PENG Yonggang, WEI Wei, et al. SR-GNN based fault classification and location in power distribution network[J]. Energies, 2022, 16(1).

FAZA A, AL-MOUSA A, ALQUDAH R. Optimal PMU placement for fault classification and localization using enhanced feature selection in machine learning algorithms[J]. International Journal of Energy Research, 2024(1).

AHMADI-GORJAYI F, MOHSENIAN-RAD H. Data-driven models for sub-cycle dynamic response of inverter-based resources using WMU measurements[J]. IEEE Transactions on Smart Grid, 2023, 14(5): 4125-4128.

MANSOUR L M, HOSSEINPOUR H, LIVANI H, et al. Waveform measurement unit-based fault location in distribution feeders via short-time matrix pencil method and graph neural network[J]. IEEE Transactions on Industry Applications, 2022, 59(2): 2661-2670.

ZOU K, TUNCALI K, SILVERMAN S G. Correlation and simple linear regression[J]. Radiology, 2003, 227(3): 617-628.

MAMUYA Y D, LEE Y D, SHEN J, et al. Application of machine learning for fault classification and location in a radial distribution grid[J]. Applied Sciences, 2020, 10(14).

JORKESH S, POSHTAN J. Fault diagnosis of an induction motor using data fusion based on neural networks[J]. IET Science, Measurement Technology, 2021, 15(8): 681-689.

KHOSLA P, TETERWAK P, WANG C, et al. Supervised contrastive learning[J]. Advances in Neural Information Processing Systems, 2020, 33: 18661-18673.

JAMIL M, ANEES A S. Optimal sizing and location of SPV (solar photovoltaic) based MLDG (multiple location distributed generator) in distribution system for loss reduction, voltage profile improvement with economical benefits[J]. Energy, 2016, 103: 231-239.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于偏离度引导全局搜索规则的煤矿电网线路故障区段定位

基于一维卷积和图神经网络的配电网故障区段定位方法

基于台区变压器二次侧电压变化的配电网故障区段定位

基于多源异构数据融合的综合管廊电力舱系统保护

基于整数线性规划的配电网故障定位容错算法