基于IMF能量矩和SVM的电力线路故障区段定位.doc

基于IMF能量矩和SVM的电力线路故障定位 徐舜1，杨毅1，王奕2，张健2，曾祥君1 （1 长沙理工大学 电气与信息工程学院 智能电网运行与控制湖南省重点实验室，长沙 410004 2 广东电网有限公司电力科学研究院， 广州 510000） 摘要：针对配电网拓扑结构日益复杂化以及线路单相接地时故障信息难以提取等问题，论文提出了一种基于本征模函数IMF（Intrinsic Mode Function） 关键词：经验模式分解；本征模函数；能量矩；支持向量机 中图分类号：TM713 文献标识码：A 文章编号：1001－1390（2015）00－0000－00 ault line selection for power transmission line based on intrinsic mode function energy moment and SVM Xu Shun1, Yang Yi1, Wang Yi2, Zhang Jian2 , Zeng Xiangjun1 (1. Hunan Province Key Laboratory of Smart Grids Operation and Control, College of Electrical and Information Engineering, Changsha University of Science and Technology, Changsha 410004, China.2. Guangdong Power Grid Corporation Electric Power Research Institute, Guangzhou 510000, China) Abstarct: For the problem about complicated topological structures and hard-to-extract information when single-phase grounding fault occurs in power distribution network, and a new method of fault selection based on the intrinsic-mode-function (IMF) energy moment and SVM (Support Vector Machines) is proposed in this paper. The localization characteristics of EMD are used to quantify the fault, and then the SVM is combined to classify the fault. Firstly, the fault current signals are decomposed into certain IMF (Intrinsic Mode Function). Secondly, an integral of selected IMF components along time axis is calculated to obtain the IMF energy moment eigenvectors. Finally, the IMF energy moments of high correlation coefficient are taken as the eigenvectors to input into SVM classifier for fault selection. As a result, the fault selection model is obtained. The simulation results of 66kV line model show that the proposed method can recognize fault line accurately and effectively with only measurement of fault current signals. Keywords：EMD, IMF, energy moment, SVM 0 引 言 随着我国经济的高速发展，配电网的运行方式也日益复杂化。电网发生故障后，准确可靠地找到故障线路，对减少故障恢复时间，提高电力系统的可靠性起着十分重要的作用[1]。然而配电网小电流接地系统单相接地信号检测困难，所以配电保护的关键的是如何从微弱的非平稳故障信号中抽取得到平稳的特征向量。 针对故障信号的提取，目前提出的方法有傅里叶变换、短时傅里叶变换、小