基于混沌搜索解决早熟收敛的混合粒子群算法  

A Hybrid Particle Swarm Optimization Based on Chaos Strategy to Handle Local Convergence

作　　者：刘华蓥[1] 林玉娥[1] 张君施[2] 

机构地区：[1]大庆石油学院计算机与信息技术学院,大庆163318 [2]北京工商大学基础部,北京100037

出　　处：《计算机工程与应用》2006年第13期77-79,共3页Computer Engineering and Applications

摘　　要：针对标准粒子群优化算法(PSO)在处理高维复杂函数时存在的收敛速度慢、易陷入局部极小等问题,提出了新的混合粒子群算法——基于混沌优化搜索解决早熟收敛的粒子群算法。采用了基于群体适应值方差的早熟判断机制,同时提出了一种缩小混沌搜索的变量空间范围的新方法,提高了搜索效率。基于典型高维复杂函数的数值实验表明,混合粒子群算法效率高、优化性能好、对初值具有很强的鲁棒性。尤其是,混合粒子群算法具有很强的避免局部极小能力,其性能远远优于单一优化方法。Using Particle Swarm Optimization to handle complex functions with high-dimension has the problems of low convergence speed and sensitivity to local convergence.This paper proposes an effective hybrid optimization strategy handling local convergence based on Chaos Optimization.The method of judging the local convergence by the variance of the population＇s fitness and reducing the searching space of variable optimized is proposed,which enhances the searching efficiency.Numerical simulation results on benchmark complex functions with high dimension show that the hybrid Particle Swarm Optimization is effective,efficient,fairly robust to initial conditions.Especially the hybrid Particle Swarm Optimization is of strong ability to avoid being trapped in local minima,and performances are fairly superior to single method.

关 键 词：粒子群优化算法 混沌优化 早熟 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]