摘要
粒子群优化算法是一种性能优越的寻优算法,但由于早熟问题,影响了算法性能的发挥,同时PID控制器是一类广泛使用的控制器,其参数的选取可等效为优化问题,在标准微粒子群算法的基础上,分析了惯性权重对不同粒子的影响,提出了一种基于适应度值的多惯性权重动态调整机制,同时针对标准微粒子群算法易陷入局部最优的特点,引入混沌扰动机制,利用混沌的遍历性、随机性来改善种群的多样性,并将该方法用于PID控制器参数整定,仿真结果表明了方法的有效性和优越性。
Particle Swarm Optimizer is a probability algorithm with excellent performance. But the premature phenomenon limits the effect of PSO. PID controller is a widely used controller,its performance depends on the optimization of PID controller paramerters. Based on the standard PSO algorithm,the influence of inertial weight on different particles is analyzed, and a Multi -weight dynamic adjusting mechanism based on fitness value is proposed. In view the disadvantage that the standard PSO algorithms would easily be trapped in local optimum,the paper introduces the chaos perturbation mechanism to improve the swarm variety by using randomicity and ergodicity,and this improved PSO is utilized to optimize PID controller paramerters. Simulation results show that this method is effective and execllent.
出处
《计算机仿真》
CSCD
北大核心
2009年第9期156-159,共4页
Computer Simulation
关键词
微粒子算法
多惯性权重动态调整
混沌扰动
比例积分微分控制器
Particle swarm optimization algorithm
Multi - weight dynamic adjusting
Chaos perturbation
PID controller
