引用本文:胡 伟,李 勇,曹一家,张志鹏,赵庆周,段义隆.基于LOF和SVM的智能配电网故障辨识方法[J].电力自动化设备,2016,36(6):
HU Wei,LI Yong,CAO Yijia,ZHANG Zhipeng,ZHAO Qingzhou,DUAN Yilong.Fault identification based on LOF and SVM for smart distribution network[J].Electric Power Automation Equipment,2016,36(6):
【打印本页】   【HTML】   【下载PDF全文】   查看/发表评论  【EndNote】   【RefMan】   【BibTex】
←前一篇|后一篇→ 过刊浏览    高级检索
本文已被:浏览 5698次   下载 2732  
基于LOF和SVM的智能配电网故障辨识方法
胡 伟1, 李 勇1, 曹一家1, 张志鹏1, 赵庆周2, 段义隆1
1.湖南大学 电气与信息工程学院,湖南 长沙 410082;2.山东电力工程咨询院有限公司,山东 济南 250013
摘要:
针对现有智能配电网保护方法存在保护装置整定复杂、协调性差以及易误动等问题,提出一种基于局部异常因子(LOF)检测的配电网保护算法,并对配电网在故障定位后不能进行有效的故障类型辨识这一问题,提出LOF和支持向量机(SVM)相结合的智能配电网故障类型判别方法。根据各节点LOF值的大小实现智能配电网的故障检测与定位;然后对故障处的三相电压进行小波变换,以三相电压的小波奇异熵值建立故障特征样本库,利用反映接地故障信息的零序电压低频能量对故障进行预分类,并以此为基础建立SVM故障类型判别预测模型。该算法可对智能配电网的故障进行有效的检测与定位,并能对故障区域的不同故障类型进行合理分类。
关键词:  智能配电网  故障定位  局部异常因子  小波变换  支持向量机
DOI:
分类号:
基金项目:国家电网公司科技项目
Fault identification based on LOF and SVM for smart distribution network
HU Wei1, LI Yong1, CAO Yijia1, ZHANG Zhipeng1, ZHAO Qingzhou2, DUAN Yilong1
1.College of Electrical and Information Engineering,Hunan University,Changsha 410082,China;2.Shandong Electric Power Engineering Consulting Institute Co.,Ltd.,Ji’nan 250013,China
Abstract:
Aiming at the complicated settings,poor coordination and misoperation of protective equipments of existing protection methods,a protection method based on LOF(Local Outlier Factor) detection is proposed for smart distribution network. A hybrid fault identification method combining LOF and SVM(Support Vector Machine) is proposed to effectively identify the fault type after fault is located. The fault of smart distribution network is detected and located according to the LOF value of each node. The three-phase voltages at the fault point are analyzed by wavelet transform to obtain the wavelet singularity entropy for constructing the fault characteristic sample base. The low-frequency energy of zero-sequence voltage,which reflects the information of grounding fault,is used to pre-classify the fault,based on which,an SVM prediction model is constructed for identifying the fault type. The proposed method can effectively detect and locate the fault of smart distribution network,as well as reasonably classify its type.
Key words:  smart distribution network  electric fault location  local outlier factor  wavelet transforms  support vector machine

用微信扫一扫

用微信扫一扫