Quality prediction based on sub-stage LS-SVM for PVC polymer particle

For multistage, nonlinear characteristic of PVC process, a sub-stage least square support vector machines (LS-SVM) method is proposed for quality prediction. Firstly, using an clustering arithmetic, PCAP-loading matrices of time-slice matrices are clustered according to relevance and batch process is divided into several operation stages, the most relevant stage to the quality variable is defined, and then applying correlation analysis in un-fold stage data in order to get irrelevant input variables, and sub stage LS-SVM models are developed in every stage for quality prediction. The proposed method easily handles static single model and may be efficient in compressing and extracting nonlinear process data. The results have demonstrated the effectiveness of the proposed method.