摘要
针对约束多目标优化问题,结合Pareto支配思想、锦标赛选择和排挤距离技术,采用双种群搜索策略,引进免疫机制,对传统的粒子更新策略进行改进,提出一种用于求解约束多目标优化问题的混合粒子群算法。通过4个标准约束多目标函数进行测试,测试结果表明,该方法有效可行,相比传统多目标优化算法更优。
A hybrid particle swarm algorithm for solving constrained multi-objective optimization problem is proposed, in which two populations are adopted, and Pareto non-dominated ranking, tournament selection, crowding distance method are integrated into a new based wash out rule by improving the update strategy of particles.Finally, four classical fimctions are used to test the performance of the algorithm.Experimental results show that the proposed approach is an efficient and out- perform conventional algorithm.
出处
《计算机工程与应用》
CSCD
北大核心
2011年第15期49-52,111,共5页
Computer Engineering and Applications
基金
国家自然科学基金No.60461001
广西自然科学基金(No.0832082
No.0991086)
国家民委科研基金(No.08GX01)
广西民族大学科研项目启动基金资助项目~~
关键词
粒子群
约束优化
多目标优化
PARETO支配
免疫机制
particle swarm optimization
constrained optimization
multi-objective optimization
Pareto non-dominated
immune algorithm