Abstract: A hybrid multi-objective evolutionary algorithm based on Pareto ranking called PHMOEA is proposed to improve the convergence and diversity of the solution sets in the multi-objective evolutionary algorithm. The algorithm defines interference sets in order to stimulate the composition of the non-dominating sets, meanwhile, improves the crossover operator and mutation operator based on the Pareto sort and the strategy of elite retention. It evaluates PHMOEA with thirteen standard benchmark problems, and is compared with two state-of-the-art multi-objective optimizers, NSGA-II and SPEA2. The results obtained indicate that PHMOEA has good diversity and convergence, what’s more, remains a better uniformity distribution and broader coverage.

Key words: multi-objective evolutionary, convergence, diversity, interference sets, Pareto sort

摘要： 为了改进多目标进化算法的收敛性和解集的多样性，提出一种基于Pareto排序的混合多目标进化算法PHMOEA。在PHMOEA中使用干扰集刺激优化非支配集的构成，改善算法的收敛性和解集的分布性，并根据Pareto等级和精英保留策略改进了交叉算子和变异算子。该算法与著名的NSGA-II和SPEA2多目标进化算法在13个基准测试函数上的对比结果表明，PHMOEA算法不仅多样性较好，而且提高了算法的收敛性，并使获得的最优解集的分布性更均匀，覆盖范围更广。

关键词: 多目标进化算法, 收敛性, 多样性, 干扰集, Pareto等级