首页 | 本学科首页   官方微博 | 高级检索  
     

改进的多目标粒子群算法
引用本文:熊盛武,刘麟,王琼,史旻. 改进的多目标粒子群算法[J]. 武汉大学学报(理学版), 2005, 51(3): 308-312
作者姓名:熊盛武  刘麟  王琼  史旻
作者单位:武汉理工大学,计算机科学与技术学院,湖北,武汉,430070
基金项目:国家863计划(2002AA1Z1490),湖北省自然科学基金项目(2002AB040)资助
摘    要:提出了一个改进的粒子群算法并将其用于解决多目标优化问题.该算法利用粒子群算法的信息传递机制,引入多目标演化算法常用的归档技术,采用SPEA2算法的环境选择和配对选择策略,使得整个群体在保持适当的选择压力的情况下收敛于Pareto最优解集.标准测试函数的数值实验结果表明,所提出的算法能够使找到的解集快速收敛到Pareto非劣最优目标域,并且解集沿着Pareto非劣最优目标域有很好的扩展性.

关 键 词:多目标优化  粒子群算法  Pareto最优解
文章编号:1671-8836(2005)03-0308-05
修稿时间:2004-06-09

Improved Multi-Objective Particle Swarm Algorithm
XIONG Sheng-wu,LIU Lin,WANG Qiong,SHI Min. Improved Multi-Objective Particle Swarm Algorithm[J]. JOurnal of Wuhan University:Natural Science Edition, 2005, 51(3): 308-312
Authors:XIONG Sheng-wu  LIU Lin  WANG Qiong  SHI Min
Abstract:An improved particle swarm algorithm to solve multi-objective problems is proposed. The algorithm uses both the information transfer strategy of particle swarm algorithm and the archiving technique which is commonly used in multi-objective evolutionary algorithms. Environmental selection and matching selection strategy of SPEA2 algorithm are also adopted to assure the population converge to the true Pareto front while keeping proper selection pressure. The benchmark problems numerical experiment results demonstrate that the proposed method can rapidly converge to the Pareto optimal front and spread widely along the front.
Keywords:multi-objective optimization  particle swarm algorithm  Pareto solutions
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