计算机工程与应用 ›› 2009, Vol. 45 ›› Issue (28): 69-71.DOI: 10.3778/j.issn.1002-8331.2009.28.020

• 研究、探讨 • 上一篇    下一篇

强社会认知能力的粒子群优化算法

曾传华1,2,申元霞1,李订芳2   

  1. 1.重庆文理学院 数学与统计学院,重庆 402160
    2.武汉大学 数学与统计学院,武汉 430072
  • 收稿日期:2008-11-11 修回日期:2009-02-02 出版日期:2009-10-01 发布日期:2009-10-01
  • 通讯作者: 曾传华

Particle Swarm Optimization algorithm with abundant social cognition

ZENG Chuan-hua1,2,SHEN Yuan-xia1,LI Ding-fang2   

  1. 1.School of Mathematics and Statistics,Chongqing University of Arts and Science,Chongqing 402160,China
    2.School of Mathematics and Statistics,Wuhan University,Wuhan 430072,China
  • Received:2008-11-11 Revised:2009-02-02 Online:2009-10-01 Published:2009-10-01
  • Contact: ZENG Chuan-hua

摘要: 针对粒子群优化算法的“早熟”问题,提出了强社会认知能力粒子群优化算法,该算法通过学习概率和选择概率确定粒子跟踪的局部极值。算法中学习概率的自适应调整有效权衡了粒子的个体认知能力和社会认知能力。通过经典函数的测试结果表明,新算法的全局搜索能力有了显著提高,并且能够有效避免早熟问题。

关键词: 粒子群优化算法, 学习概率, 选择概率

Abstract: A particle swarm optimization with abundant social cognition is developed for solving premature convergence of particle swarm optimization.In this algorithm,the optimum from the particles experiments is determined by learning probability and selective probability.The learning probability is adjusted to balance between personal cognitive and social cognitive.Experimental results for complex function optimization show this algorithm improves the global convergence ability and efficiently prevents the algorithm from the local optimization and early maturation.

Key words: Particle Swarm Optimization(PSO), learning probability, selective probability

中图分类号: