基于PCA-SVM集成阀门故障诊断方法研究  

A Fault Detection and Diagnosis Method Base on Principal Component Analysis and Support Vector Classifier Apply to Valve

作　　者：杨海荣[1] 薄翠梅[1] 龚伟俊[1] 张广明[1] 

机构地区：[1]南京工业大学,江苏南京210009

出　　处：《流体机械》2009年第7期28-32,12,共6页Fluid Machinery

基　　金：国家自然科学基金项目(60804027);江苏省自然科学基金项目(BK2006176);江苏省工业装备数学制造及控制技术重点实验项目(BM2007201);江苏省高校自然科学基金项目(07KJB510042)

摘　　要：提出了一种基于主元分析和支持向量多分类器的故障诊断方法。该方法首先对工业故障数据进行主元分析提取数据集特征并降低数据维数,再把故障特征数据通过支持向量多分类器进行模式分类,最后通过特征分类诊断故障。在DAMADICS阀门模型上进行了仿真,并利用Lublin Sugar Factory工业故障数据进行了验证。仿真结果表明该方法可以快速准确地检测与诊断故障。The principal component analysis and support vector multi-classifier of the fault diagnosis method is introduced, first of all, the failure data has been extracted PCA data sets and reduce the characteristics of the data dimension , Second, the failure characteristics data has been classified by support vector classifier, final diagnosis failure by features. Some simulations were carried out on DAMADICS valve model and Lublin Sugar Factory failure data is used to further verify. The simulation results show that the method can detection and diagnosis failure fast and accurately.

关 键 词：主元分析 支持向量机 故障诊断 阀门故障 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]