自适应差分进化算法的研究及其在聚丙烯牌号切换优化中的应用

Research on adaptive differential evolution algorithm and its application in optimal grade transition in polypropylene production process

针对常规差分进化算法易"早熟"的问题,提出了自适应的差分进化算法,该算法在计算过程中自适应地调整变异率,使得种群在初期保持个体多样性,避免早熟,到后期保留优良信息,加快全局搜索速度;同时该算法还引入了扰动交叉算子,有助于在搜索过程中保持群体的多样性.测试表明,新算法的寻优性能有明显改善,并成功地应用于聚丙烯牌号切换优化问题.

Focusing on the ＂premature＂ problem in conventional differential evolution algorithm,the adaptive differential evolution algorithm is proposed in this paper.The mutation rate can be adjusted adaptively in the calculation process in this method.It can improve the diversity of populations and avoid premature.It also can keep the good information in the late stage and accelerate the pace of global search.In the meantime,a disturbance crossover factor is introduced in order to keep the population diversity of populations. The experiments show that the optimization performance of the new algorithm has significantly improved. Finally, the new algorithm has been successfully applied in optimal grade transition in polypropylene production process.