Modelling a penicillin fed-batch fermentation using least squares support vector machines.
- Author:
Yi LIU
1
;
Hai-Qing WANG
Author Information
1. National Laboratory of Industrial Control Technology, Institute of Industrial Process Control, Zhejiang University, Hangzhou 310027, China.
- Publication Type:Journal Article
- MeSH:
Biomass;
Computer Simulation;
Fermentation;
Least-Squares Analysis;
Models, Biological;
Models, Statistical;
Nonlinear Dynamics;
Penicillins;
analysis;
biosynthesis
- From:
Chinese Journal of Biotechnology
2006;22(1):144-149
- CountryChina
- Language:Chinese
-
Abstract:
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.
