基于正弦载波的粒子群算法  

Particle Swarm Optimization Based on the Sine Carrier-Wave

作　　者：庄敏慧[1] 王振雷[1] 钱锋[1] 

机构地区：[1]华东理工大学化工过程先进控制和优化技术教育部重点实验室,上海200237

出　　处：《华东理工大学学报（自然科学版）》2009年第3期428-434,共7页Journal of East China University of Science and Technology

基　　金：国家杰出青年科学基金(60625302);国家自然科学基金面上项目(60704029;20876044);长江学者和创新团队发展计划资助(IRT0721);高等学校学科创新引智计划资助(B08021);上海市重点学科建设项目资助(B504);国家科技支撑计划(2007BAF22B05);国家973项目(2009CB320603);国家863计划(2008AA042902;2007AA041402);上海市国际科技合作基金项目(08160710500)

摘　　要：针对传统粒子群算法（Traditional Particle Swarm Optimization,TPSO）存在的易陷入局部最优、收敛速度慢等缺点,提出了一种基于载波的粒子群算法（carrier-wave Particle Swarm Optimization,CWPSO）。根据正弦函数具有的自变量连续变化而值域不变的特点,该算法设计了以载波自变量变化确定粒子搜索位置的新方法,从而极大地提高了全局搜索能力。同时对于搜索到的可能极值点,通过载波扩展的方法进行局部寻优,以进行精确搜索。对一系列测试函数的寻优结果表明：CWPSO算法不仅都能找到最优值,且寻优时间仅为TPSO算法和惯性权值线性下降的改进PSO算法（Line-WPSO,LWPSO）的1/3-1/5;同时,CWPSO具有对寻优问题维数不敏感的优点,大大扩展了该算法的适用范围。The traditional PSO algorithm（TPSO） is easily trapped in the local optimum and converges slowly. Coping with the above shortcomings, a novel PSO algorithm based on the carrier-wave, Carrier- Wave PSO （CWPSO） is presented in this paper. By means of the sine wave＇s character that the value domain is steady while the independent variable is continuously changing, the CWPSO algorithm uses the changing independent variables of every carrier-waves to fix the positions of every particle so as to obviously improve the global searching ability. At the same time, for the possible extreme points, a precise search process based on the carrier-wave extending is taken. By the simulation on a series of benchmark functions, it is shown that the CWPSO algorithm can not only find all the optimum values, but also spends only about 1/3 to 1/5 times as the TPSO and LWPSO algorithms. Furthermore, the CWPSO algorithm is not sensitive to the dimensions of the optimum-searching problems such that the applied field is greatly enlarged.

关 键 词：粒子群算法(PSO) 正弦载波 载波扩展 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]