|
|
Slide—m odel M PCA approach with applications in fault detecting of m ultiVariable nonlinear process |
CHEN Yong, LIANG Jun |
National Lab of Industrial Control Technology,Zhejiang University,Hangzhou 310027,China |
|
|
Abstract M ultiway principal component analysis (M PCA )is widely used in performance monitoring and fault diagnosis of batch processes.However,it could not be efficiently applied to a process with high nonlinear dynamics.A method combining M PCA and slide-model is developed to deal with this class of batch process.The experiment results for industrial batch process indicate that the method iS effective and available.
|
Published: 28 June 2003
|
滑动模型MPCA在非线性系统故障监测与诊断中的应用
多向主元分析(MPCA)是一种应用于间歇生产过程故障监测与诊断的较为有效的方法,但由于其线性化建模特征以及本身的一些局限性,它在高度复杂的非线性系统的应用中往往难以保证故障诊断的准确性和实时性.结合MPCA方法的优缺点,提出一种滑动模型的MPCA方法,讨论了该方法的建模及其在故障监测与诊断中的应用,并采用对称式DTW算法解决了多元轨迹同步化的问题.在实际生产设备上的试验表明,该方法具有良好的精确性和实时性.
关键词:
多向主元分析,
间歇生产,
滑动模型,
故障诊断,
动态时间错位
|
Viewed |
|
|
|
Full text
|
|
|
|
|
Abstract
|
|
|
|
|
Cited |
|
|
|
|
|
Shared |
|
|
|
|
|
Discussed |
|
|
|
|