基于小波能量比的同杆双回输电线路故障识别  

FAULT IDENTIFICATION OF DOUBLE-CIRCUIT TRANSMISSION LINES ON THE SAME TOWER BASED ON WAVELET ENERGY RATIO

作　　者：杨亮 吴浩 陈佳豪 顾小平 杨杰 刘益岑 Yang Liang;Wu Hao;Chen Jiahao;Gu Xiaoping;Yang Jie;Liu Yicen(School of Automation and Information Engineering,Sichuan University of Science&Engineering,Zigong 643000,Sichuan,China;Electric Power Research Institute of State Grid Sichuan Electric Power Company,Chengdu 610000,Sichuan,China)

机构地区：[1]四川轻化工大学自动化与信息工程学院,四川自贡643000 [2]国网四川电力公司电力科学研究院,四川成都610000

出　　处：《计算机应用与软件》2023年第6期48-56,共9页Computer Applications and Software

基　　金：人工智能四川省重点实验室项目(2019RYY01);四川省科技厅项目(2018GZDZX0043,2019YJ0477);国家电网有限公司科技项目(521997180016)。

摘　　要：为提高行波保护的灵敏性和可靠性,在分析同杆双回线路发生区内/外故障后一段时窗内反行波电流幅值关系的基础上,提出一种基于小波能量比的故障识别方法。利用小波分解将故障后一段时窗内的反行波电流分解到6个尺度上,提取两端各尺度下的小波能量比组成特征向量,针对样本的不平衡性,使用SMOTE算法对少数类样本进行扩充后,训练支持向量机分类器,对区内外故障进行识别。实验表明,该方法不受故障位置、故障类型、过渡电阻和故障初始角的影响,在CT饱和、噪声干扰的情况下也能较好地识别区内外故障。In order to improve the sensitivity and reliability of traveling wave protection,on the basis of analyzing the relationship of the anti-traveling wave current amplitude in the window after the internal/external failure of the double circuit line on the same tower,a fault identification method based on wavelet energy ratio is proposed.Wavelet decomposition was used to decompose the anti-traveling wave current in a time window after the fault into 6 scales,and the wavelet energy ratio at each scale at both ends was extracted to form a feature vector.Aimed at the imbalance of the sample,the SMOTE algorithm was used to expand the minority class samples,and the support vector machine classifier was trained to identify the internal and external faults.Experiments show that this method is not affected by fault location,fault type,transition resistance and fault initial angle,and can better identify internal and external faults even under CT saturation and noise interference.

关 键 词：同杆双回线路 反行波电流 小波能量比 SMOTE算法 支持向量机 故障识别 

分 类 号：TP3[自动化与计算机技术—计算机科学与技术] TM75[电气工程—电力系统及自动化]