回归型支持向量机在电机故障诊断中的研究  

Research on Motor Fault Diagnosis in Support Vector Regression

作　　者：王罗[1] 张桂新[1] 陈特放[1] 

机构地区：[1]中南大学信息科学与工程学院,湖南长沙410075

出　　处：《计算机测量与控制》2007年第12期1691-1694,共4页Computer Measurement &Control

基　　金：国家自然科学基金项目(60674003)

摘　　要：通过分析电机故障模式识别的原理,提出应用回归型支持向量机进行电机故障特征学习和分类的方法;从回归型支持向量机的基本原理出发,探讨线性回归与非线性回归两种情形,对其预测能力进行分析得到误差计算公式;在其基础上建立同步电机故障诊断模型并进行仿真,通过电压波形处理前后的对比,能够及时检测到故障的发生并进行识别,从而验证了回归型支持向量机是电机故障诊断在线检测的一种有效方法;但如何把已有的先验知识应用到SVM训练中仍然是一个悬而未决的问题。Bring forward and apply the support vector regression to learn and classify the feature of motor fault by analyzing pattern recognition of the motor fault. Starting from basic principle of the support vector regression and discussing both the linearity regression and nonlinearity regression situation, then analyses its forecast ability and gains the error calculus formula, final gives the imitating model of the synchronous machine and checks the fault in time by contrasting the voltage wave of disposal before and after. By this it can be known that the support vector regression is a good way to diagnose the motor fault. But how can the prior knowledge apply in SVMS training which all the same is a pendent question.

关 键 词：回归型支持向量机 电机故障诊断 预测能力 仿真 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置]