双中心粒子群优化算法  

Double Center Particle Swarm Optimization Algorithm

作　　者：汤可宗[1,2,3] 柳炳祥[2] 杨静宇[1] 孙廷凯[1] 

机构地区：[1]南京理工大学模式识别与机器智能研究所,南京210094 [2]景德镇陶瓷学院信息工程学院,江西景德镇333000 [3]南昌工程学院信息工程学院,南昌330099

出　　处：《计算机研究与发展》2012年第5期1086-1094,共9页Journal of Computer Research and Development

基　　金：国家自然科学基金项目(60632050;60803049);国家科技支撑计划基金项目(2012BAH25F02);江西省青年基金项目(GJJ12642)

摘　　要：粒子群优化(PSO)算法是一种新兴的群体智能优化技术,由于其原理简单、参数少、效果好等优点已经广泛应用于求解各类复杂优化问题.而影响该算法收敛速度和精度的2个主要因素是粒子个体极值与全局极值的更新方式.通过分析粒子的飞行轨迹和引入广义中心粒子和狭义中心粒子,提出双中心粒子群优化(double center particle swarm optimization,DCPSO)算法,在不增加算法复杂度条件下对粒子的个体极值和全局极值更新方式进行更新,从而改善了算法的收敛速度和精度.采用Rosenbrock和Rastrigrin等6个经典测试函数,按照固定迭达次数和固定时间长度运行2种方式进行测试,验证了新算法的可行性和有效性.Particle swarm optimization （PSO） algorithm is a new promising swarm intelligence optimization technology, and it has been extensively applied to solve all kinds of complex optimization problems because of its advantages of simpler theory, less parameter and better performance. However, each particle＇s individual minimum and population＇s minimum are two major factors to affect the algorithm＇s convergence speed and precision. This paper proposes a double center particle swarm optimization algorithm （DCPSO）. We analyze particle＇s flying trajectory and introduce general center particle and special center particle in the DCPSO, which consequently improves PSO algorithm＇s converging speed and precision without increasing computing complexity. Six classical test functions, including Rosenbrock, Rastrigrin and so on, are used to verify the proposed algorithm in two ways： fixed iteration number test and fixed time length test. Experimental results show that the proposed algorithm is feasible and efficient.

关 键 词：粒子群优化 群体智能 中心粒子 优化问题 极值 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]