遗传支持向量机在电力变压器故障诊断中的应用  

The Application of Genetic Support Vector Machine in Power Transformer Fault Diagnosis

作　　者：肖燕彩[1] 陈秀海[2] 朱衡君[1] 

机构地区：[1]北京交通大学机械与电子控制工程学院,北京100044 [2]北京电力公司,北京100031

出　　处：《上海交通大学学报》2007年第11期1878-1881,1886,共5页Journal of Shanghai Jiaotong University

摘　　要：针对支持向量机中的参数通常靠交叉试验来确定的状况,提出了遗传支持向量机,即使用遗传算法来优化支持向量机中的参数,并将之进一步应用在基于溶解气体分析的变压器故障诊断中.以变压器油中5种主要特征气体作为支持向量机的输入,以7种变压器状态作为相应的输出,选用径向基核,使用遗传算法得到优化参数,充分发挥了支持向量机具有较高泛化能力的优势.实验表明,本文方法能够在较大范围内准确地找到相应的优化参数,并能有效地进行变压器的故障诊断.Considering the fact that parameters in support vector machine are usually decided by crossvalidation, a genetic support vector machine was presented in which the parameters in SVM method are optimized by genetic algorithm. It was then applied to the insulation fault diagnosis of power transformer based on dissolved gas analysis. The concentration of the five characteristic gases dissolved in transformer oil are the inputs of support vector machine, the seven states of the transformer are the outputs. In the built model the radial based kernel is selected, the optimized parameters are used; and the superiority of SVM in processing finite samples is fully brought into play. The test shows the proposed method can find out the optimum accurately in a wide range and the value can be used to diagnose the transformer effectively.

关 键 词：电力变压器 遗传算法 支持向量机 故障诊断 溶解气体分析 

分 类 号：TM855[电气工程—高电压与绝缘技术]