基于Pareto支配的两阶段多目标优化算法  

Two Stage Multi-Objective Optimization Algorithm Based on Pareto Dominance

作　　者：王学武[1] 高进[1] 陈三燕 顾幸生[1] WANG Xuewu;GAO Jin;CHEN Sanyan;GU Xingsheng(Key Laboratory of Smart Manufacturing in Energy Chemical Process,Ministry of Education,East China University of Science and Technology,Shanghai 200237,China)

机构地区：[1]华东理工大学能源化工过程智能制造教育部重点实验室,上海200237

出　　处：《华东理工大学学报（自然科学版）》2022年第6期806-815,共10页Journal of East China University of Science and Technology

基　　金：国家自然科学基金(62076095,61973120)。

摘　　要：针对二维和三维的多目标优化问题,提出了一种基于Pareto支配的两阶段多目标优化算法(MOEA-PT)。全局搜索阶段根据Pareto支配关系将种群进行排序,依据临界层子集的排序等级执行相应的选择策略;局部调整阶段对种群中的个体进行微调,将新产生的个体与距离其最近的个体进行支配关系、分布性、收敛性的对比,替换较差的个体。分析了两个阶段对算法性能的影响,同时对引入局部调整策略后的种群进行了对比,结果表明局部调整策略能有效增强算法性能。通过对标准测试函数的求解,并与其他经典的多目标算法进行对比,验证了本文算法在收敛性和分布性等方面具有一定的优越性。Based on Pareto dominance, this paper proposes a two-stage multi-objective optimization algorithm for two-dimensional and three-dimensional multi-objective problems. In the global search stage, the population is sorted according to the Pareto dominance relation, and the corresponding selection strategy is carried out according to the ranking level of the critical layer subset. In the local adjustment stage, the individuals in the population are fine-tuned.The new obtained individuals are compared with the nearest individuals in terms of dominance, distribution and convergence, and then, the poor individuals are replaced. The effects of the two stages on the performance of the algorithm are analyzed, and the locally adjusted population is compared, whose results show that the local adjustment strategy can effectively enhance the algorithm performance. By solving the standard test function and comparing with other classical multi-objective algorithms, it is verified that the proposed algorithm can attain better convergence and distribution.

关 键 词：多目标优化 PARETO支配 全局搜索 局部调整 选择策略 

分 类 号：TP301[自动化与计算机技术—计算机系统结构]