首页 | 本学科首页   官方微博 | 高级检索  
     检索      

一种改进的非支配排序遗传算法
引用本文:吴中元,关志华,李光泉.一种改进的非支配排序遗传算法[J].北京科技大学学报,2002,24(6):679-682.
作者姓名:吴中元  关志华  李光泉
作者单位:1. 天津大学系统工程研究所,天津,300072;天津工业大学管理学院,天津300065;2. 天津大学系统工程研究所,天津,300072
基金项目:国家自然科学基金;69974026;
摘    要:为克服非支配排序遗传算法计算复杂度高, 未采用精英策略, 需要特别指定共享半径的缺点,提出了一种改进的非支配排序遗传算法.通过实验验证,该算法在几个给定的函数优化时都能取得比较好的结果.

关 键 词:NSGA  INSGA  计算复杂性  精英策略  共享
修稿时间:2001年6月21日

An Improved Evolutionary Algorithm for Multi-objective Optimization
WU Zhongyuan,GUAN Zhihua,LI GuangquanInstitute of Systems Engineering,Tianjin University,Tianjin ,China,Management school,Tianjin Polytechnic University,Tianjin ,China.An Improved Evolutionary Algorithm for Multi-objective Optimization[J].Journal of University of Science and Technology Beijing,2002,24(6):679-682.
Authors:WU Zhongyuan  GUAN Zhihua  LI GuangquanInstitute of Systems Engineering  Tianjin University  Tianjin  China  Management school  Tianjin Polytechnic University  Tianjin  China
Institution:WU Zhongyuan,GUAN Zhihua,LI GuangquanInstitute of Systems Engineering,Tianjin University,Tianjin 300072,China,Management school,Tianjin Polytechnic University,Tianjin 300065,China
Abstract:Multi-objective evolutionary algorithms which use non-dominated sorting and sharing have been mainly criticized for the problems, (1) O(mN3)computational complexity (where m is the number of objectives and n is the population size), (2) non-elitism approach, and (3) the need for specifying a sharing parameter. This paper suggests a non-dominated sorting based the multi-objective evolutionary algorithm INSGA which alleviates all the above three difficulties. Simulation results on five difficult test problems show that the proposed INSGA is able to find much better spread of solutions in all problems compared to NSGA.
Keywords:NSGA  INSGA  computational complexity  elitism approach  sharing  
本文献已被 CNKI 维普 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号