[Modelling a penicillin fed-batch fermentation using least squares support vector machines]

Sheng Wu Gong Cheng Xue Bao. 2006 Jan;22(1):144-9.
[Article in 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.

Publication types

  • English Abstract
  • Research Support, Non-U.S. Gov't

MeSH terms

  • Biomass
  • Computer Simulation
  • Fermentation*
  • Least-Squares Analysis*
  • Models, Biological*
  • Models, Statistical
  • Nonlinear Dynamics
  • Penicillins / analysis
  • Penicillins / biosynthesis*

Substances

  • Penicillins