摘要： 针对标准粒子群优化算法易陷入局部最优解、收敛速度慢等缺点，从提高全局和局部搜索能力2个方面出发，提出一种自适应动态控制参数的粒子群优化算法。根据粒子的适用度动态改变粒子学习公式中学习因子和惯性权重的取值，提高算法的搜索能力。在典型测试函数上与标准粒子群优化算法进行对比实验，结果表明，该算法具有更高的收敛效率和更快的收敛速度。

关键词: 粒子群优化算法, 粒子适用度, 习因子, 性权重, 部搜索能力, 局搜索能力

Abstract: In the standard Particle Swarm Optimization(PSO), the premature convergence and slow searching of particles decrease the optimization ability of the algorithm. By analyzing global and local search ability, a new adaptive PSO algorithm of dynamic control parameters is proposed. It changes the parameter’s value of learning factor and Inertia weight by particle’s fitness to enhance particle’s search ability. Compared with the standard PSO, experimental result of some typical testing functions proves that the new algorithm has a higher convergence efficiency and faster search speed.

Key words: Particle Swarm Optimization(PSO) algorithm, particle fitness, learning factor, inertia weight, local searching ability, global searching ability

中图分类号: 

• TP391.41