斥力势场下的多粒子群协同动态优化算法及其应用  

Multi-swarm Cooperation for Dynamic Optimization Problems in Repulsive Potential Field

作　　者：胡成玉[1,2] 吴湘宁[1] 王永骥[2] 

机构地区：[1]中国地质大学计算机学院,武汉430074 [2]华中科技大学控制科学与工程系,武汉430074

出　　处：《小型微型计算机系统》2011年第7期1325-1330,共6页Journal of Chinese Computer Systems

基　　金：国家自然科学基金项目(60873107)资助;中央高校基本科研业务费专项资金项目(CUGL090236)资助

摘　　要：动态环境下的优化问题是当前智能计算领域一个研究热点.针对当前多种群动态优化存在的问题,提出一种基于斥力势场的多粒子群协同优化算法,利用多个种群并行搜索,当发现局部极值点后,在局部极值点处建立人工斥力势场,防止多种群对该区域重复搜索,当环境变化时,采用柯西变异对种群进行初始化,通过对DF仿真,验证了改进算法具有较好的跟踪性能.另外,本文从数学上证明了多种群搜索的优越性,分析了柯西变异优于其它变异的原因,为算法的改进策略提供了理论依据.最后将该方法应用于动态系统PID控制器的参数整定上,获得了满意的控制效果.Dynamic optimization problems are currently a hot research topic in evolutionary computation area. In this paper, an advanced PSO has been proposed. Multiple swarms are used to optimize concurrent and artificial repulsive potential field on local points are set up to prevent multiple swarm converging to the same place. As the environment changes, Cauchy mutation is adapted to initialize the populations＇ positions and velocities. The advanced PSO is tested on dynamic functions （ DF1 ） and the results show a superior tracking performance, In addition, this paper provides a theoretical basis for the strategies used in the advanced algorithm. Finally, the method is applied to the tuning of the parameters of PID controller for dynamic system and a satisfactory control effect is obtained.

关 键 词：粒子群算法 动态优化问题 多种群协同 柯西变异 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]