Computer Engineering and Applications ›› 2007, Vol. 43 ›› Issue (17): 85-88.

• 学术探讨 • Previous Articles     Next Articles

Hybrid particle swarm optimization based on crossover and mutation

KOU Bao-hua,YANG Tao,ZHANG Xiao-jin,ZHANG Qing-bin,LIU Wei,GE Jian-quan   

  1. College of Aerospace and Material Engineering,NUDT,Changsha 410073,China
  • Received:1900-01-01 Revised:1900-01-01 Online:2007-06-11 Published:2007-06-11
  • Contact: KOU Bao-hua

基于交叉变异的混合粒子群优化算法

寇保华,杨 涛,张晓今,张青斌,刘 巍,葛健全   

  1. 国防科技大学 航天与材料工程学院,长沙 410073
  • 通讯作者: 寇保华

Abstract: Particle swarm optimization(PSO) is a global optimization algorithm based on swarm intelligence theory,and search the problem space effectively through cooperation and competition among the individuals of the population.Aiming at the shortcoming of basic PSO algorithm,that is slow convergence rate at ending and easily plunging into the local optimum,a new hybrid PSO is proposed.By changing the method of initialization and adding the crossover and mutation to the algorithm,the hybrid PSO’s performance is significant improved.Experimental results indicate that the modified PSO has good behavior both on improving the global convergence ability and enhancing convergence rate.

Key words: particle swarm optimization, crossover, mutation, hybrid

摘要: 粒子群优化算法是一种基于群体智能理论的全局优化算法,通过群体中粒子间的合作与竞争实现对问题空间的高效搜索。针对算法后期收敛速度较慢、易陷入局部最优的缺点,提出了一种混合粒子群算法。该算法通过改变种群初始化方法,引入交叉和变异机制等措施改善基本粒子群算法的性能。数值试验结果表明,改进型粒子群算法在提高全局寻优能力和加快收敛速度等方面均有良好的表现。

关键词: 粒子群优化算法, 交叉, 变异, 混合