基于小波的自适应主元分析在过程监测中的应用  

The Application of the Adaptive PCA Based on Wavelets in Process Monitoring

作　　者：范少荟[1] 文成林[1] 

机构地区：[1]河南大学计算机与信息工程学院,河南开封475004

出　　处：《弹箭与制导学报》2008年第1期283-285,292,共4页Journal of Projectiles,Rockets,Missiles and Guidance

基　　金：国家自然科学基金(60572051);浙江省科学重点科研国际合作项目(2006C24G2040012);浙江省教育厅科技计划重点项目(20050530)资助

摘　　要：用传统主元分析(PCA)建立的过程统计模型是时不变的,而实际的工业过程却具有慢时变的特性。文中针对慢时变引起的过程运行中的误报警问题,给出了一种小波分析与自适应主元分析相结合的混合方法,用小波去噪后再用自适应主元分析递归更新主元模型。利用此方法进行的在线过程监测的计算机仿真结果表明,该方法不仅能大大减少虚警点,还提高了故障检测的准确性。The process statistical model built by conventional PCA is time-invariant, while real industrial processes are slowly time-varying. To overcome the false-alarm caused by the time-varying process condition, an approach is presented which first utilizes wavelets to eliminate noise and then uses adaptive PCA to update the PCA model recursively by combining the ability of wavelets and adaptive PCA. The simulation result of the on-line process monitoring shows this method can not only reduce the false-alarm points, but also improve the effect of the fault detection.

关 键 词：自适应主元分析 小波分析 过程监测 故障检测 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]