融合模拟退火和混沌的混合粒子群算法

Hybrid particle swarm optimization algorithm merging simulated annealing and chaos

为了改善粒子群算法的全局搜索能力,把模拟退火思想融于惯性权重的选取之中,再利用混沌运动的特性来融合混沌算法,对早熟的种群进行自适应混沌变异。数值仿真结果表明,所产生的混合粒子群算法能更好地平衡局部寻优和全局寻优,提高了全局寻优的能力和计算的精度。

To improve the global search ability of Particle Swarm Optimization algorithm （PSO）,simulated annealing idea is applied in selecting PSO＇s inertia weight and chaos algorithm is merged into PSO according to the properties of chaos to make adaptively chaotic mutation for premature population.The numerical experiments demonstrate that the produced hybrid PSO algorithm has the ability to balance local optimizing and global optimizing and improves the ability of global optimization and the precision of computation.