State estimation model of ferment process based on PSO

In order to get real-time and on-line biology parameters in fermentation process, a soft sensor model based on support vector regression (SVR) is provided for estimating the biology parameters. It is well known that the complexity and generalization performance of SVR model depend on a good setting of the three parameters (ε, c, γ). So an algorithm called Particle Swarm Optimization (PSO) is applied to optimize the parameters (ε, c, γ). Basing on the proposed method, a PSO-SVR model is developed to estimate the products concentration of γ-mannanase for feedstuff. The results show that the model has good learning accuracy and generalization performance so as to acquire the real-time and on-line estimation values of products concentration of γ-mannanase.