新的混沌粒子群优化算法  

New chaos-particle swarm optimization algorithm

作　　者：胥小波[1,2] 郑康锋[1,2] 李丹[1,2] 武斌[1,2] 杨义先[1,2] 

机构地区：[1]北京邮电大学信息安全中心,北京100876 [2]北京邮电大学灾备技术国家工程实验室,北京100876

出　　处：《通信学报》2012年第1期24-30,37,共8页Journal on Communications

基　　金：国家自然科学基金资助项目(61070208);国防基础科学研究计划基金资助项目(9140A15060109DZ082);中央高校基本科研业务费专项基金资助项目(BUPT2009RC0218;BUPT2010PTB0501)~~

摘　　要：针对传统粒子群算法初期收敛较快,而在后期容易陷入早熟、局部最优的特点,提出了一种新的混沌粒子群优化算法,不同于己有的混沌粒子群算法的简单粒子序列替换,该算法将混沌融入到粒子运动过程中,使粒子群在混沌与稳定之间交替运动,逐步向最优点靠近。并提出了一种新的混沌粒子群数学模型,进行了非线性动力学分析。数值测试结果表明该方法能跳出局部最优,极大提高了计算精度,进一步提高了全局寻优能力。The original particle swarm optimization （PSO） algorithm has the advantages of fast convergence, but with the shortcoming of premature and local convergence. To overcome this problem, a new chaos-particle swarm optimization algorithm was presented, which was different from the conventional method of replacing pre-particle. Instead, the algo- rithm in this paper made the motion of particles with characteristics of chaos, so as to make particles move between the state of chaos and stable, and gradually close to the optimal value. The nonlinear dynamics of the proposed Mathematical model are analyzed, and the results of the experiment show that the proposed algorithm can result in encouraging results.

关 键 词：粒子群 混沌 混沌粒子群 优化算法 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]