分层多目标最优化进化算法  

A Lexicographically Stratified Multiobjective Optimization with Evolu tionary Algorithm

作　　者：刘海林[1] 陆志峰[2] 王宇平[3] 刘永清[4] 

机构地区：[1]广东工业大学应用数学系,广州510090 [2]广东工业大学计算中心,广州510090 [3]西安电子科技大学数学科学系,西安710071 [4]华南理工大学自动控制工程系,广州510640

出　　处：《计算机工程与应用》2002年第15期36-38,90,共4页Computer Engineering and Applications

基　　金：国家自然科学重点基金资助(编号:69934030);教育部留学回国人员科研启动基金;陕西省自然科学基金(编号:200106)

摘　　要：文章用进化算法给出了求解二层字典分层多目标最优化的方法,该算法把求解问题转化为多目标最优化,并研究了这两个问题的解集之间的联系。对多目标最优化定义了一个新的选择算子和适应值函数,这样定义的选择算子和适应值函数结合均匀设计能有效地引导搜索,直接求出问题的解而不用逐层求解。数值模拟表明该方法十分有效。The paper supposes to solve two -levels lexicographically stratified multiobjective optimization with evolutionary algorithm.This algorithm transforms the two-levels lexicographically stratified multiobjective optimization into a general multiobjective optimization problem,and the relationship is given between the original problem and new problem.The paper supposes a novel selection operator and fitness function.The selection operator and fitness function defined in this way can guide the search more effectively by combined with uniform design method.As result,the novel evolutionary algorithm can solve the problem directly and need not stratify to make solution.The computer simulation shows that the proposed algorithm is effective.

关 键 词：分层规划 多目标最优化 进化算法 计算机 

分 类 号：O224[理学—运筹学与控制论] TP301.6[理学—数学]