基于多分类相关向量机的变压器故障诊断新方法

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...

Full description

Saved in:

Bibliographic Details
Published in:	电力系统保护与控制 Vol. 41; no. 5; pp. 77 - 82
Main Author:	尹金良朱永利俞国勤
Format:	Journal Article
Language:	Chinese
Published:	华北电力大学电气与电子工程学院,河北保定 071003%上海电力公司,上海 200025 2013
Subjects:	变压器故障诊断多分类支持向量机相关向量机贝叶斯网络 multi-classification relevance vector machine 相关向量机支持向量机贝叶斯网络 support vector machine transformer fault diagnosis 多分类变压器故障诊断 Bayesian network
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	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。
Bibliography:	multi-classification; relevance vector machine; Bayesian network; support vector machine; transformer fault diagnosis 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 that the diagnosis speed is sufficient for project needs and M-RVM shows higher diagnosis accuracy compared with BN and SVM. YIN Jin-liang, ZHU Yong-li, YU G
ISSN:	1674-3415