统计特征参数及多分类 SVM 的局部放电类型识别

摘要

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 applied 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 .%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。