采用最小二乘支持向量机的青霉素发酵过程建模研究

生化过程通常是严重非线性和时变的复杂动态系统,而且重要过程参数缺少在线测量仪表,对其建立机理模型往往非常耗时和困难。采用最小二乘支持向量机(LS_SVM)并以Pensim仿真平台为例对青霉素发酵这一典型生化过程进行建模研究。给出了LS_SVM参数的调整策略和分析结果,建立了青霉素产物浓度、菌体浓度和底物浓度等重要过程变量的在线预报模型。仿真结果表明用LS_SVM建立的在线预报模型拟合误差小,推广性能好,可以作为发酵过程的进一步控制和优化的参考依据。

Modelling a Penicillin Fed-batch Fermentation Using Least Squares Support Vector Machines

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.