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.