基于空间距离的多目标进化算法  

A Multi-Objective Evolutionary Algorithm Based on Spatial Distance

作　　者：李密青[1] 郑金华[1] 肖桂霞[1] 谢炯亮[1] 

机构地区：[1]湘潭大学信息工程学院,湘潭411105

出　　处：《模式识别与人工智能》2009年第4期589-596,共8页Pattern Recognition and Artificial Intelligence

基　　金：国家自然科学基金项目(No.60773047);湖南省教育厅重点科研项目(No.06A074)资助

摘　　要：为提高多目标进化算法的收敛性,提出一种基于空间距离的多目标进化算法.定义一种密度估计指标——树聚集距离,在考虑非支配前沿的同时,利用个体的空间距离及树聚集距离进行个体选择操作.另外,在外部种群的非支配解个数超过规定的种群规模时,用基于个体邻近距离的维护方法对其进行维护.通过6个测试问题和5个方面的测试标准,与NSGA-II和SPEA2进行比较,该算法在拥有更好收敛度的同时,保持良好的均匀性和分布广度.To improve the convergence of multi-objective evolutionary algorithm, a measure based on distance is proposed. A density estimation metric -tree crowding distance is defined. The individual distance and the tree crowing distance are used as the selection criteria when the non-dominated front is considered. When the size of non-dominated solution set exceeds that of the population, a method based on neighboring distance is employed to truncate population. By examining of five performance metrics on six test problems, the proposed algorithm is demonstrated to be more competitive in uniformity and spread and performs better in converging to the pareto front, compared to NSGA-Ⅱ and SPEA2.

关 键 词：空间距离 个体选择 种群维护 多目标进化算法 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]