中国电力2026，Vol.59Issue(1)：163-174,12.DOI:10.11930/j.issn.1004-9649.202507050
基于多维故障特征提取的CNN-BiGRU-ATT多分支配电网故障定位
CNN-BiGRU-ATT multi-branched distribution network fault location based on multi-dimensional fault feature extraction
摘要
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),bidirec-tional 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 99.642 9%,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
故障定位/多分支配电网/LSD/多维故障特征/CNN-BiGRU-ATTKey words
fault location/multi-branched distribution network/LSD/multi-dimensional fault features/CNN-BiGRU-ATT引用本文复制引用
ZHANG Yumin,WANG Delong,ZHANG Xiao,JI Xingquan,ZHANG Xiangxing,HUANG Xinyue,WANG Xuelin..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):163-174,12.基金项目
国家自然科学基金青年资助项目(52107111) （52107111）
中国博士后面上资助项目(2023M734092) （2023M734092）
山东省自然科学基金资助项目(ZR2022ME219,ZR2023QE181,ZR2024ME029). This work is supported by National Natural Science Foundation of China(No.52107111),China Postdoctoral Science Found-ation(No.2023M734092),Shandong Province Natural Science Foundation(No.ZR2022ME219,No.ZR2023QE181 and No.ZR2024ME029). （ZR2022ME219,ZR2023QE181,ZR2024ME029）
