基于DKPCA的聚合釜故障诊断研究

Fault of Polymerization Reactor Based on DKPCA Algorithm

针对聚合釜聚合生产聚氯乙烯过程的故障种类较多、故障类型复杂等特点,同时生产过程存在严重的非线性、动态性,提出一种基于DKPCA的故障诊断算法.过程中分别采用主元分析、核主元分析和动态核主元分析分别对PVC聚合过程进行故障诊断,其中主元分析和核主元分析的错报率较高,而动态核主元分析对PVC聚合过程能够得到较好的诊断结果,从而可以对实际的PVC聚合生产过程进行监测.

For the characteristics of PVC polymerization process that fault types are varied and complex,while the production process is serious nonlinear and dynamic,a fault diagnosis algorithm is proposed based on DKPCA. In the process component analysis,kernel principal component analysis and dynamic kernel principal component analysis are used to carry out fault diagnosis on the PVC polymerization process. PCA and KPCA misstatements rate is serious,and dynamic kernel principal component analysis for PVC polymerization process fault diagnosis has better diagnostic result. The actual process for the production of PVC polymerization can be monitored.