基于D-FNN的聚合过程转化速率软测量建模及重构

Soft-sensor modeling and reconfiguration of conversion velocity in PVC polymerization process based on D-FNN

引言以氯乙烯单体（VCM）为原料,采用悬浮法聚合工艺生产聚氯乙烯（PVC）树脂是一种典型的间歇式化工生产过程。VCM的转化率对PVC树脂产品质量有很大影响,

For forecasting the key technology indicator conversion velocity of vinyl chloride monomer（VCM）in the polyvinylchloride（PVC）polymerization process,a soft-sensor modeling method based on dynamic fuzzy neural network（D-FNN）was proposed.Firstly,kernel principal component analysis（KPCA）method was adopted to select the auxiliary variables of soft-sensing model in order to reduce the model dimensionality.Then the learning algorithm of D-FNN included the rule extraction principles,the classification learning strategy,the precedent parameters arrangements,the rule trimming technology based on error descendent ratio and the consequent parameters decision based on extended Kalman filter（EKF）.The proposed soft-sensor model could automatically decide the fuzzy rules so as to realize the nonlinear mapping between input and output variables of the discussed soft-sensor model.Model migration method was adopted to realize the on-line adaptive revision and reconfiguration of soft-sensor model.In the end,simulation results showed that the proposed model could significantly enhance the prediction accuracy and robustness of the technico-economic indices and satisfy the real-time control requirements of PVC polymerization process.