一种启发式粒子群优化算法(HPSO)及其在结构优化设计中的应用  

A Heuristic Particle Swarm Optimizer and Its Application to Structural Optimization

作　　者：刘锋[1] 黄志斌[1] 李丽娟[1] 吴青华 

机构地区：[1]广东工业大学建设学院,广东广州510006 [2]Department of Electrical Engineering and Electronics,The University of Liverpool,Liverpool,L69 3GJ,UK

出　　处：《应用基础与工程科学学报》2008年第1期57-64,共8页Journal of Basic Science and Engineering

基　　金：国家自然科学基金(10772052);广东省自然科学基金(06104655)

摘　　要：在介绍了标准的粒子群优化算法(PSO)及被动群集的粒子群优化算法(PSOPC)的基础上,指出了两者使用"回飞技术"(fly-back mechanism)方法处理约束条件的不足之处,在基于"和谐搜索"算法(harmony search)产生新解的思想基础上,提出了一种新的启发式粒子群优化算法(HPSO),该算法可以明显提高离子群算法的收敛速度和稳定性.应用PSO、PSOPC及所提出的HPSO三种算法分别对两个桁架结构进行了截面优化设计,并对算法的收敛性和稳定性进行了分析.结果表明,本文提出的启发式粒子群优化算法(HPSO)可以有效地搜索到最优解,并且比PSO和PSOPC两种算法拥有更高的收敛速度和稳定性,尤其在迭代计算的初期,收敛效果非常明显.The standard particle swarm optimization （PSO） algorithm and the particle swarm optimizer with passive congregation （PSOPC） algorithm are introduced in this paper, and their deficiency of dealing with restricted boundary conditions, by fly-back mechanism,is indicated. A heuristic particle swarm optimizer （HPSO）, based on the harmony search algorithm, is presented. It makes the global solution with great efficiency. The HPSO algorithm presented in this paper is tested by two truss structure optimal problems and is compared with the standard PSO and the PSOPC algorithms. The calculation results show that the HPSO algorithm has the fastest convergence rate and the best stability among these three algorithms. The HPSO algorithm has faster convergence rate especially during the early iteration steps.

关 键 词：粒子群优化算法 收敛速度 桁架结构优化 

分 类 号：TU311.4[建筑科学—结构工程]