Multi-branch active distribution network fault location using TGCN-iFlowformer based on time-frequency and topology fusion

ZHANG Yumin; WANG Delong; JI Xingquan; ZHONG Runfeng; WEN Fushuan; LIN Zengsheng

doi:10.19783/j.cnki.pspc.260374

English Version Journal Login

您当前的位置：

首页 >

文章列表页 >

Multi-branch active distribution network fault location using TGCN-iFlowformer based on time-frequency and topology fusion

更新时间：2026-09-28

- Multi-branch active distribution network fault location using TGCN-iFlowformer based on time-frequency and topology fusion
- Power System Protection and Control Vol. 54, Issue 19, (2026)
- 作者机构：
- 作者简介：
- 基金信息：
- DOI：10.19783/j.cnki.pspc.260374
  CLC：
- Published：2026
- 稿件说明：
移动端阅览
ZHANG Yumin, WANG Delong, JI Xingquan, et al. Multi-branch active distribution network fault location using TGCN-iFlowformer based on time-frequency and topology fusion[J]. Power System Protection and Control, 2026, 54(19).
DOI：

ZHANG Yumin, WANG Delong, JI Xingquan, et al. Multi-branch active distribution network fault location using TGCN-iFlowformer based on time-frequency and topology fusion[J]. Power System Protection and Control, 2026, 54(19). DOI： 10.19783/j.cnki.pspc.260374.

摘要

针对多分支有源配电网中故障特征时空耦合复杂和现有深度学习方法时频特征与拓扑图融合不足致使故障定位精度受限的问题，提出一种基于时频-拓扑融合的时序图卷积神经网络(temporal graph convolutional network

TGCN)-iFlowformer多分支有源配电网故障定位方法。首先，采用小波包变换提取故障三相电压与零模分量的能量特征，并融合时域统计特征，结合配电网图结构构建反映节点空间关联关系的多维故障特征空间。其次，构建TGCN-iFlowformer故障定位模型，利用TGCN刻画故障特征的空间关联特性与短序列时序动态，引入iFlowformer的流式注意力机制捕获长序列时序关系，以提高故障定位精度。最后，在PSCAD/EMTDC中对33节点配电网进行仿真验证。结果表明，所提方法仅在电源侧配置测量装置的条件下即可有效实现故障定位，受过渡电阻、初相角及故障类型的影响小，具有良好的经济性和鲁棒性。

Abstract

In multi-branch active distribution networks

existing deep learning methods have limited fault-location accuracy due to the complex spatiotemporal coupling of fault characteristics and the insufficient integration of time-frequency features with topological graph information. To address this issue

a temporal graph convolutional network (TGCN)- iFlowformer-based fault-location method with time-frequency and topology fusion is proposed. First

wavelet packet transform is employed to extract the energy features of the faulty three-phase voltages and zero-mode component. These features are then fused with time-domain statistical features and combined with the distribution network graph structure to construct a multidimensional fault feature space that characterizes the spatial correlations among different nodes. Next

a TGCN-iFlowformer fault-location model is developed. TGCN is used to capture the spatial correlation characteristics and short-sequence temporal dynamics of fault features

while the flow-based attention mechanism in iFlowformer is introduced to model long-sequence temporal dependencies

thereby improving fault-location accuracy. Finally

simulations are carried out on a 33-node distribution network in PSCAD/EMTDC. The results show that the proposed method can effectively achieve fault location with measuring devices installed only at the source side

while exhibiting low sensitivity to fault resistance

initial phase angle

and fault type

as well as good cost-effectiveness and robustness.

关键词

Keywords

references

ALIZADEH A, ZAREI S F, SHATERI M. Islanding detection for active distribution networks using a WaveNet+ UNet classifier[J]. Protection and Control of Modern Power Systems, 2025, 10(5): 152-164.

LUO Jian, LIU Yao, CUI Qiushi, 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.

CUI Haonan, YANG Qing, SUN Jian, et al. Electromagnetic time reversal fault location method based on characteristic frequency of traveling waves[J]. IEEE Transactions on Power Delivery, 2023, 38(5): 3033-3044.

THOMAS J B, CHAUDHARI S G, VERMA N K. CNN- based transformer model for fault detection in power system networks[J]. IEEE Transactions on Instrumentation and Measurement, 2023, 72: 1-10.

WANG Guanbo, ZHUANG Chijie, DENG Jun, et al. A fault location method based on electromagnetic transient convolution considering frequency-dependent parameters and lossy ground[J]. IEEE Transactions on Power Delivery, 2024, 39(2): 1012-1022.

YUAN Wanqi, LI Yongli, CHEN Xiaolong, et al. Research on distance protection scheme for single-phase to ground faults in active distribution networks with gap-grounded transformers[J]. Protection and Control of Modern Power Systems, 2025, 10(5): 123-141.

ZHANG Zhihua, SHI Haojie, LI Guang, et al. A method for identifying the medium-voltage phase-to-phase short- circuit fault section in active distribution networks based on the equivalent impedance ratio of low-voltage monitoring nodes[J]. IEEE Transactions on Smart Grid, 2025, 16(6): 4534-4548.

SHU Hongchun, LIU Haoming, TANG Yutao, et al. Fault identification method for measured travelling wave of transmission line based on CSCRFAM-transformer[J]. Protection and Control of Modern Power Systems, 2025, 10(2): 69-82.

MARQUES L A M. Detection and location of non-technical losses in low voltage distribution networks[D]. Portugal: Universidade do Porto, 2016.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

基于时域差分运算的配电网多分支线路故障定位方法

考虑μPMU节点优化配置的含DG配电网故障分层定位方法

A fault location technique for stator ground faults in generators based on third harmonics and mesh current method

Interphase fault location method for active distribution networks based on time-domain voltage similarity comparison

Fault type identification method for distribution networks with distributed generation

Related Author

JI Xingquan

HUANG Xinyue

ZHANG Yumin

YE Pingfeng

PEI Younan

ZHAI Hefeng

GAO Fengyang

LI Long

Related Institution

ZHAI Hefeng(1. College of Electrical Engineering and Automation, Shandong University of Science and Technology

School of Electrical and Information Engineering

School of Electrical Engineering, University of Jinan

Electric Power Research Institute of China Southern Power Grid

ZHA Pengtang(1. School of Automation and Electrical Engineering, Lanzhou Jiaotong University

AI问答

⁰