Optimization of nosiheptide fermentation process based on the improved differential evolution algorithm for multi-objective optimization
基于改进多目标差分进化算法的诺西肽发酵过程优化

Multi-objective optimization is an effective way to solve the problem of low yield and low efficiency in the nosiheptide fermentation process. Based on the differential evolution algorithm, we propose an improved differential evolution algorithm for multi-objective optimization(IDEMO), in which the selection operation is based on the Pareto rank and the crowding distance of each individual in the population. The adaptive mutation operator and the chaotic migration operator are developed to improve the performance of the algorithm. Based on the kinetic models of the nosiheptide batch fer-mentation process, we develop a multi-objective optimization model(IDEMO) for its optimization. Application results show its effectiveness.