基于自适应粒子群算法的约束布局优化研究  

A Study of Constrained Layout Optimization Using Adaptive Particle Swarm Optimizer

作　　者：雷开友[1] 邱玉辉[1] 

机构地区：[1]西南大学计算机与信息科学学院,重庆400715

出　　处：《计算机研究与发展》2006年第10期1724-1731,共8页Journal of Computer Research and Development

基　　金：教育部科学技术重点基金项目(104262);重庆市科委自然科学基金项目(2003-7881)~~

摘　　要：二维带平衡及不干涉约束的圆集在圆容器内的布局优化问题(如卫星舱布局)在理论上属于带性能约束的布局优化问题,它是NP-hard问题的难点,由于它的复杂性,传统的粒子群优化算法难于求解.通过对传统的粒子群优化算法的多重改进,提出了一种自适应粒子群优化算法,该算法在整个搜索过程中,既能保持粒子群原有基本结构,同时又能扩大搜索范围,在提高多样性的同时保证搜索精度,从而加快了收敛速度,有效避免早熟收敛问题,得到最优解.将改进后的算法应用于约束布局问题,建立了此类问题的粒子群算法,通过3个算例的数值计算,验证了该算法的可行性和有效性.The optimal layout problem of circle group in a circular container with performance constraints of equilibrium belong to an NP-hard problem. Due to its complexity, the general particle swarm optimization algorithm converges slowly and easily converges to local optima. Taking the layout problem of satellite cabins as background, a novel adaptive particle swarm optimizer is presented based on multi-modified strategies, which can not only escape from the attraction of local optima of the later phase to heighten particle diversity, and avoid the premature problem, but also maintain the characteristic of fast speed search in the early convergence phase to get global optimum. Thus, the algorithm has a better search performance to deal with the constrained layout optimization problem. Experimental results on three examples show that this algorithm is feasible and efficient.

关 键 词：粒子群算法 早熟收敛问题 圆集 约束布局优化 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程] TP391[自动化与计算机技术—控制科学与工程]