基于多分类相关向量机的变压器故障诊断新方法 new transformer fault diagnosis method based on multi-class relevance vector machine.pdfVIP

第 41 卷 第 5 期 电力系统保护与控制 Vol.41 No.5 2013 年 3 月 1 日 Power System Protection and Control Mar.1, 2013 基于多分类相关向量机的变压器故障诊断新方法 1 1 2 尹金良 ，朱永利 ，俞国勤 （1.华北电力大学电气与电子工程学院，河北 保定 071003；2.上海电力公司，上海 200025） 摘要：变压器故障诊断本质为多分类问题，具有故障样本数据少，故障不确定因素多的特点。现有变压器故障诊断方法中， 贝叶斯网络(BN)需要大量样本数据且计算量大，支持向量机(SVM)存在规则化系数确定困难的局限。针对此现状，提出基于 多分类相关向量机(M-RVM)的变压器故障诊断新方法。该方法以变压器溶解气体含量比值作为 M-RVM 模型的输入，采用快 速 type-II 最大似然(Fast Type-II ML)和最大期望估计(EM)的方法进行模型推断，诊断输出为各故障类别的概率，以概率最大 的故障类别作为诊断结果。实例分析表明该方法诊断速度较快，能满足工程需要，同基于 BN 和 SVM 的变压器故障诊断方 法相比，具有较高的诊断正确率。 关键词：多分类；相关向量机；贝叶斯网络；支持向量机；变压器故障诊断 New transformer fault diagnosis method based on multi-class relevance vector machine 1 1 2 YIN Jin-liang , ZHU Yong-li , YU Guo-qin (1. School of Electrical and Electronic Engineering, North China Electric Power University, Baoding 071003, China； 2. Shanghai Electric Power Company, Shanghai 200025, China) Abstract: The transformer fault diagnosis is naturally a multi-classification problem with few sample data and a lot of uncertainties. Among the existing transformer fault diagnosis methods, a large number of sample data and amount of computation are needed for Bayesian Network (BN), and the adjustment of the coefficient is difficult for support vector machine (SVM). So a new method of transformer fault diagnosis based on multi-class relevance vector machine (M-RVM) is proposed. The method takes ratios of feature gases as inputs and Fast Type-II ML and expectation maximization (EM) are adopted. Diagnostic outputs are probability for each fault category and fault type with the highest probability is taken as diagnosis result. Experimental results show