基于模糊理论与支持向量机的变压器故障诊断方法  

Transformers fault diagnosis based on fuzzy theory and support vector machine

作　　者：张金江[1,2] 梁耀升 尹玉娟[2] 郭创新[2] 

机构地区：[1]浙江科技学院自动化与电气工程学院,浙江杭州310023 [2]浙江大学电气工程学院,浙江杭州310027 [3]南宁超高压输电公司,广西南宁530028

出　　处：《电力科学与技术学报》2011年第2期61-66,共6页Journal of Electric Power Science And Technology

基　　金：浙江省自然科学基金(Y1100243)

摘　　要：针对变压器结构的复杂性和故障机理的多样性,提出一种基于模糊理论和支持向量机的变压器故障诊断方法.该方法首先采用模糊理论对故障样本数据进行预处理,提取故障特征,再用支持向量机方法进行故障分类,通过采用一对多(1-a-r)的方法实现多目标分类,得出诊断结果.针对支持向量机参数不易确定的问题,采用多层动态自适应算法与k-折交叉验证方法结合对参数进行优化分析.故障诊断实例测试结果显示,该方法不仅克服了传统比值法中编码缺失、编码边界过于绝对的问题,诊断结果具有更高的准确率,而且也具有较好的适用性.To deal with the complexity of power transformers and the variety of fault mechanisms,a fault diagnosis method based on the fuzzy theory and the support vector machine（SVM） is proposed in this paper.In this method,the fault data are firstly preprocessed using fuzzy theory and then identified using SVM in which multi-objective classification and diagnosis results are achieved by employing the one-against-all method.To counter the difficulty of parameters decision in SVM,the multi-layer adaptive algorithm and the k-fold cross validation method are combined to optimize the parameters.Fault diagnosis cases analysis results show that the proposed method can overcoming the conventional diagnosis methods shortcomings of missing codes and absolute coding borders,and it is with more accurate and suitable in practice applications.

关 键 词：变压器 故障诊断 模糊理论 支持向量机 

分 类 号：TM711[电气工程—电力系统及自动化] TM744