基于自适应变异的混沌粒子群优化算法

Chaotic particle swarm optimization algorithm with adaptive mutation

粒子群优化算法参数少,寻优速度快,但其寻优效率低且在寻优后期易早熟收敛。为改善其寻优性能,在标准粒子群优化算法中,通过引入混沌映射和自适应变异策略,提出具有自适应变异的混沌粒子群优化(ACPSO)算法,以增强种群的全局寻优性能和局部寻优效率。六个基准测试函数的仿真结果表明,ACPSO算法比已有的五个算法具有更好的寻优能力。

Basic particle swarm optimization algorithm has fewer parameters and fast optimization speed, but it suffers some drawbacks such as low optimization efficiency and falling easily into local optimal point in the optimization process. To improve the global optimization performance and local optimization efficiency of particle swarm optimization algorithm, this paper proposes a chaotic particle swarm optimization algorithm with adaptive mutation（ACPSO）by introducing a chaotic mapping and an adaptive strategy. Compared to five existing algorithms, numerical results on six benchmark test functions indicate that ACPSO algorithm has better performance.