Optimal control of the fermentation process based on improved differential evolutionary algorithm

Aiming at the complexity of the glutamic acid fermentation process, a neural network dynamic model of the fermentation process was established. The improved differential evolutionary algorithm (DEA) was used to the multi-variables optimal control of the fermentation process and the optimal control trajectories of operating variables were found out. Some improvements of the primitive DEA were made by the means of randomly selecting the mutation factor and the re-initialization of the individuals in the population on a suitable time, so that it could solve the constrained optimization effectively and avoid the problem caused by premature. Simulation results show the proposed method is effective.