计算机工程与应用 ›› 2010, Vol. 46 ›› Issue (33): 46-48.DOI: 10.3778/j.issn.1002-8331.2010.33.013

• 研究、探讨 • 上一篇    下一篇

自适应模糊的粒子群优化算法

周松华1,欧阳春娟1,2,刘昌鑫1,朱 平1   

  1. 1.井冈山大学 电子信息工程学院,江西 吉安 343009
    2.深圳大学 信息工程学院,广东 深圳 518060
  • 收稿日期:2010-07-20 修回日期:2010-10-11 出版日期:2010-11-21 发布日期:2010-11-21
  • 通讯作者: 周松华

Adaptive fuzzy particle swarm optimization algorithm

  1. 1.College of Electronics and Information Engineering,Jinggangshan University,Ji’an,Jiangxi 343009,China
    2.College of Information Engineering,Shenzhen University,Shenzhen,Guangdong 518060,China
  • Received:2010-07-20 Revised:2010-10-11 Online:2010-11-21 Published:2010-11-21

摘要: 标准粒子群算法易陷入局部最优值。根据粒子群算法中的不确定性因素,提出自适应模糊的粒子群优化算法(AFPSO)。在该算法中,对惯性权值和位置更新采用模糊控制,用所有粒子的个体最优的加权平均替代全局最优值,增强了粒子之间相互学习的能力。仿真实验表明,AFPSO算法简单,可灵活地调节全局搜索和局部搜索能力,与已有相关算法比较,较好地解决了粒子群早熟问题,并提高了搜索精度。

关键词: 粒子群, 模糊控制, 全局最优, 收敛

Abstract: Standard particle swarm algorithm is easy to fall into local optimum.An Adaptive Fuzzy Particle Swarm Optimization(AFPSO) based on the uncertainty of the PSO is proposed.In the improved algorithm,the inertia weight and the particle position update are controlled by fuzzy membership function,and the global optimal value is replaced by the weighted average of all particles optimal value to enhance the learning ability among particles.The experimental results show that,compared with the correlation algorithm,the proposed method is simple and more flexible to adjust global and local search,which also avoids the premature convergence problem,and improves the search accuracy.

Key words: particle swarm, fuzzy control, global optimal, convergence

中图分类号: