Modeling of Glumatic Acid Fermentation Process Based on PSO-SVM

In a fermentation process several variables, such as biomass concentration are conventionally determined by off-line laboratory analysis, i.e., the process control is unavailable to industrial production in time just because of time delay that often makes the analysis results inefficient. Utilizing the ability simple in application and quick in convergence of Particle Swarm Optimization (PSO) algorithm - and the high generalization ability of Support Vector Machine(SVM), selecting the appropriate state variables, a dynamic time-varying model has been built. Using the model and algorithm to per-estimate some biochemical state variables which can not be measured on-line, and to optimize some operational variables It is proved that the method is efficiency through the practical application of Glumatic Acid fermentation process.