基于多分类支持向量机的逆变器卡件故障诊断模型研究

Research on transformer fault diagnosis model based on CRO-BP neural network

为提高逆变器故障诊断准确率,提出一种基于偏二叉树双子支持向量机（partial binary tree algorithm and twin support vector machines,TWSVM）故障诊断模型.将双子支持向量机引入诊断模型,利用偏二叉树多分类方法构造多个2分类器,实现逆变器诊断的多类分类.通过实例验证,提出的故障诊断模型提高了故障诊断精度和泛化能力,时间消耗短,对于逆变器的故障预测和实时诊断具有实际参考意义.

In order to improve the accuracy of inverter fault diagnosis,a fault diagnosis model based on partial binary tree algorithm and twin support vector machines（TWSVM）is proposed.A two-class classifier is constructed based on the two-cube tree multi-classification method based on double support vector machine to realize multi-class classification of inverter diagnosis.The results show that the fault diagnosis model proposed in this paper not only has high fault diagnosis accuracy and good generalization ability,but also has short time consumption and high fault diagnosis efficiency.It has certain fault detection and realtime diagnosis reference meaning.