考虑广域行波信号强噪声干扰的输电线路故障定位  

Fault Location of Transmission Line Considering Strong Noise Interference of Wide-area Traveling Wave Signal

作　　者：黄南天 刘洋[1] 蔡国伟 Huang Nantian;Liu Yang;Cai Guowei(Key Laboratory of Modern Power System Simulation Control and Green Power New Technology,Ministry of Education,Ministry of Education(Northeast China Electric Power University),Jilin Jilin 132000,China)

机构地区：[1]现代电力系统仿真控制与绿色电能新技术教育部重点实验室(东北电力大学),吉林吉林132000

出　　处：《电气自动化》2023年第5期81-83,87,共4页Electrical Automation

基　　金：国家重点研发计划资助“可再生能源与火力发电耦合集成与灵活运行控制技术”(2019YFB1505405)。

摘　　要：为解决噪声数据影响故障定位精度及现有定位模型对相邻测点信息利用不足的问题,提出了时-空多级去噪与时-空图卷积网络相结合的输电网故障定位方法。首先,利用时-空多级去噪方法实现各测点行波信号的噪声抑制;其次,将行波测点及测点间的架空线作为节点和边构建广域行波图数据;然后,时-空图卷网络根据各测点的拓扑关联挖掘广域行波特征,选定故障线路并利用自适应权重融合多源测距结果;最后进行算例分析。结果表明,所提方法在强噪声干扰环境下故障选线精度高且故障测距误差小,可有效提高输电网运行的经济性。In order to solve the problem that noise data affected the accuracy of fault location and that the existing location models did not make full use of the information of adjacent measuring points,a fault location method for transmission network was proposed,which combined time-space multi-level noise removal and time-space map convolution network.Firstly,the noise suppression of the traveling-wave signal at each measuring point was realized by using the time-space multi-level denoising method;secondly,the traveling wave survey points and the overhead lines between the survey points were used as nodes and edges to construct wide-area traveling wave map data;then,the time-space map network dug the wide-area traveling wave characteristics according to the topological association of each measuring point,and selected the fault line and fused the multi-source ranging results with adaptive weights;finally,the example was analysied.The results of a progressive example show that the proposed method has high accuracy of fault line selection and small error of fault location under strong noise interference environment,and can effectively improve the economy of transmission network operation.

关 键 词：故障定位 输电网 时-空多级去噪 时-空图卷积网络 广域行波信号 

分 类 号：TM72[电气工程—电力系统及自动化]