基于微粒群本质特征的混沌微粒群优化算法

在总结对微粒群优化(PSO)算法本质的主要研究成果的基础上,提出了基于微粒群本质特征的混沌微粒群优化(CPSO)算法.该算法用混沌搜索方法代替随机数产生器在较好的区域搜索最优解.为了提高粒子群的多样性,用由粒子邻域内若干个个体最优位置依其适应值加权平均得到的中心位置代替标准PSO算法的全局历史最优位置.然后,根据粒子个体最优位置与上述中心位置间的距离自适应地调整混沌搜索区域半径.用几个经典测试函数的仿真结果及与其它几种PSO算法的比较结果验证了新算法的有效性.

Chaotic Particle Swarm Optimization Algorithm Based on the Essence of Particle Swarm

A chaotic particle swarm optimization(CPSO) algorithm based on the essence of PSO was proposed,following an introduction to the studies on the essence of PSO algorithm.The new algorithm uses chaotic search rather than a random number generator to search a promising region.To increase the diversity,the globally best position in standard PSO algorithm is replaced by the center or weighted mean of the personal best positions of several particles in the same neighborhood.The radius of the chaotic searching region is then adaptively adjusted according to the distance between the personal best position of each particle and the center.Several benchmark functions were simulated with CPSO,and the results were compared with those obtained with some existing PSO algorithms.The comparison verifies the efficiency of CPSO.