统计特征参数及多分类SVM的局部放电类型识别  

Partial discharge pattern recognition based on statistical parameters and multi-classifications SVM

作　　者：褚鑫[1] 张建文[1] 韩刚[1] 

机构地区：[1]中国矿业大学信息与电气工程学院,江苏徐州221116

出　　处：《电测与仪表》2015年第7期35-39,96,共6页Electrical Measurement & Instrumentation

摘　　要：局部放电模式识别是诊断变压器绝缘状况的一种有效方法,为提高局部放电类型识别的正确率,提出了基于统计特征参数及多分类SVM的局部放电类型的识别方法。在实验室设计了4种典型的变压器故障缺陷,采用统计特征参数法提取各局部放电图谱的27种特征量,引入M-ary分类思想,将支持向量机的两类分类问题扩展为多类分类,使训练计算量和测试计算量大大减少。实验结果表明,该方法用于局部放电类型识别具有较好地识别效果,并且计算速度快。Partial discharge pattern recognition is an effective method to diagnose the insulation condition of the trans- former. In order to improve the recognition accuracy of partial discharge, this paper presents a partial discharge recog- nition method based on the statistical parameters and multi-classification SVM. In this paper, four typical kinds of transformer faults models are made in the laboratory, 27 statistical characteristic parameters of each partial discharge patterns are extracted. The M-ary classification is apphed to the support vector machine, and by which the binary classification of support vector machine is extended to multi classification, thus, the computation of training and tes- ting has greatly reduced. The test results show that the method is an effective and reliable method for partial discharge pattern recognition, with higher recognition rate and computing speed.

关 键 词：局部放电 模式识别 支持向量机 统计特征参数 

分 类 号：TM60[电气工程—电力系统及自动化]