基于强化交叉算子的快速非支配排序遗传算法Ⅱ  

Fast non-dominated sorting genetic algorithmⅡbased on enhanced crossover operator

作　　者：汪镭[1] 张茂清 郭为安 吴启迪[1] WANG Lei;ZHANG Maoqing;GUO Weian;WU Qidi(School of Electronics and Information;Sino-Germany College of Applied Sciences,Tongji University,Shanghai 201804,China)

机构地区：[1]同济大学电子与信息工程学院,上海201804 [2]同济大学中德学院,上海201804

出　　处：《南昌工程学院学报》2020年第1期10-14,共5页Journal of Nanchang Institute of Technology

基　　金：科技部科技冬奥项目(2018YFF0300505);国家自然科学基金资助项目(71771176,61503287,61703279)。

摘　　要：锦标赛选择策略是NSGA-Ⅱ中用于选择交叉父代的方法,其虽然可以保留较优个体的基因给后代个体,然而锦标赛策略也容易导致重复选择父代个体的问题,从而导致后代多样性降低。为解决此问题,提出基了于强化交叉算法的快速非支配排序遗传算法Ⅱ。此算法通过将多个交叉父代引入交叉操作降低重复选择父代的概率;为结合两种交叉算子优势,进一步提出将两种交叉算子融合进NSGA-Ⅱ。实验结果对比说明,所提策略有效改善了NSGA-Ⅱ的性能。Tournament selection strategy is an efficient strategy of NSGA-Ⅱfor selecting parent individuals to do crossover.However,although tournament selection strategy can pass on the good genes to the next generation,it may result in the repeated parent individuals.To tackle this problem,this paper proposes fast non-dominated sorting genetic algorithmⅡbased on enhanced crossover operator(ECNSGA-Ⅱ).ECNSGA-Ⅱis able to decrease the probability of repeatedly selected parent individuals by incorporating multiple crossover parents to crossover operator.To combine the advantages of the two crossover operators,this paper further proposes to incorporate the two crossover operators into NSGA-Ⅱ.The experimental results demonstrate that the proposed strategy can efficiently improve the performance of NSGA-Ⅱ.

关 键 词：NSGA-Ⅱ 交叉算子 多目标优化 种群多样性 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]