基于群体适应度方差的自适应混沌粒子群算法

Adaptive chaos particle swarm optimization based on colony fitness variance

已有的混沌粒子群算法多使用Logistic混沌映射,但Logistic混沌映射产生的混沌序列不够均匀,影响了混沌粒子群算法的性能。提出在混沌粒子群算法中引入均匀性更好的An混沌映射,利用An混沌映射初始化粒子群的位置和速度,并通过适应度方差的变化来自适应控制部分粒子进行混沌更新,以改善混沌粒子群算法的性能。数值仿真的结果表明,改进算法的收敛性和全局搜索能力都有所提高,能有效避免早熟收敛。

All existing chaos particle swarm optimization algorithm（PSO） uses Logistic chaos,but the uniformity and rando-mization of the sequence come from the Logistic chaos are not enough,it influences the algorithm＇s performance.This paper suggested introducing An chaos into PSO,An chaos had better uniformity,using An chaos to initialize the particle swarm＇s position and velocity,and using the colony fitness variance＇s variation to start the substitution of part partial particle,to improve the performance.The results of the numerical simulation indicate that the convergence and global searching capacity of the presented algorithm are enhanced,and the algorithm can effectively avoid being trapped in local minima.