Modelling a Penicillin Fed-batch Fermentation Using Least Squares Support Vector Machines
采用最小二乘支持向量机的青霉素发酵过程建模研究

The biochemical processes are usually characterized as seriously time varying and nonlinear dynamic systems. Building their first_principle models are very costly and difficult due to the absence of inherent mechanism and efficient on_line sensors. Furthermore, these detailed and complicated models do not necessary guarantee a good performance in practice. An approach via least squares support vector machines (LS_SVM) based on Pensim simulator is proposed for modelling the penicillin fed_batch fermentation process, and the adjustment strategy for parameters of LS_SVM is presented. Based on the proposed modelling method, the predictive models of penicillin concentration, biomass concentration and substrate concentration are obtained by using very limited on_line measurements. The results show that the models established are more accurate and efficient, and suffice for the requirements of control and optimization for biochemical processes.