模糊支持向量机在变压器故障诊断中的应用  

Application of fuzzy support vector machine in transformer fault diagnosis

作　　者：史丽萍[1] 余鹏玺 罗朋[1] 徐天然[1] 刘鹏[1] 李佳佳[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221008

出　　处：《电测与仪表》2015年第8期115-119,共5页Electrical Measurement & Instrumentation

摘　　要：为了解决在变压器故障诊断时复杂难辨的问题,提出了利用模糊支持向量机构建变压器故障诊断模型的方法。该方法是在支持向量机(SVM)的基础上引入模糊度隶属函数,从而有效消除噪声和野点对诊断结果的影响。通过模糊C均值算法(FCM)求取模糊支持向量机的隶属度,对所得样本进行预处理,然后利用交叉验证和网格搜索相结合的方法对支持向量机进行参数寻优。实验表明,该方法比改良IEC比值法和传统支持向量机法具有更高的准确率,更适用于变压器故障诊断。In order to solve the problem of correctly identifying fault classes in transformer fault diagnosis, a novel fault diagnosis method of the transformer model based on fuzzy support vector machine （FSVM） is proposed in this pa- per. This method is developed in introducing the fuzzy membership function based on support vector machine （ SVM）, aiming to overcome the sensitivity to noise and outliers. In this paper, the membership value of the FSVM is obtained by fuzzy C-means clustering algorithm to preselect the achieved samples, and the gird search method based on cross. validation is chosen to determine the optimized parameters of the SVM model. The experiment shows that the proposed method is more effective and accurate than the method of IEC and normal SVM, and this method is proper in fault di- agnosis of transformer.

关 键 词：模糊支持向量机 故障诊断 模糊C均值算法 变压器 

分 类 号：TM411[电气工程—电器]