132 Predictive Functional Control Algorithm Design Based on SVM Model of Batch Reactor

A predictive functional control (PFC) algorithm based on support vector machine (SVM) model is proposed to deal with the temperature control of batch reactor. The support vector machine model is used to describe the dynamic behavior of the batch reaction process, which is an important foundation to the model-based control algorithm. Using the reference trajectory design of the predictive functional control algorithm, PFC based on SVM model can deal with the big step change and little step change of the temperature set point simultaneously. To evaluate its robustness, PFC based on SVM model has been applied to the temperature control of an exothermic batch reaction process. Simulation results show PFC based on SVM model enable a precise tracking of the set-point temperature.