欢迎您！东篱公司
退出
-
申报数据库
-
立项数据库
-
成果数据库
-
项目获奖数据库
中文摘要：
搜索鲁棒Pareto最优解是多目标进化算法（MOEA）研究的一个重要方面.目前,优化＂原目标函数＂的传统MOEA与基于＂有效目标函数＂的MOEA（Eff-MOEA）在搜索鲁棒Pareto最优解时都易丢失某些性质的解.为解决这一缺陷,本文定义了一种新的鲁棒Pareto最优解,提出了一种新的搜索鲁棒Pareto最优解的MOEA（MOEA/R）,MOEA/R将多目标鲁棒优化问题（MROP）转化成两目标问题来优化,一个目标为解的质量,另一个目标为解的鲁棒性,每一目标均对应一子优化问题.通过与NSGA-Ⅱ及Eff-MOEA的对比分析,结果表明MOEA/R的结果较好,更重要的是本文探索了一种新的搜索鲁棒Pareto最优解的思想.
英文摘要：
Searching for robust Pareto optimal solutions is one of the most important fields in the research of multi-objective evolutionary algorithm（MOEA）.Recently,both traditional MOEA and EFF-MOEA which optimize ＂original objective function＂ and ＂effective objective function＂ respectively easily lose some kinds of solutions.In order to solve this deficiency,we defined a new robust Pareto optimal solution and proposed a novel MOEA named as MOEA/R,which converts a multi-objective robust optimization problem （MROP） into a bi-objective optimization problem. Each of the two objectives represents a sub-MOP, one opti- mizes solution＇ s quality and the other optimizes solution＇ s robustness. Through the comparison and analysis between MOEA/R, NSGA-Ⅱ and Eff-MOEA,the experimental results demonstrate that MOEA/R can acquire good purposes. The most important contribution of this paper is that MOEA/R explores a novel methodology for searching robust Pareto optimal solutions.
同期刊论文项目
同项目期刊论文
位置：