一种约束工程设计问题的入侵性杂草优化算法(英文)  

An invasive weed optimization algorithm for constrained engineering design problems

作　　者：苏守宝[1,2] 汪继文[2] 张铃[2] 方杰[1,2] 李付鹏[2] 

机构地区：[1]皖西学院计算机科学与技术系,安徽六安237012 [2]安徽大学计算智能与信号处理教育部重点实验室,安徽合肥230039

出　　处：《中国科学技术大学学报》2009年第8期885-893,共9页JUSTC

基　　金：Supported partly by the Key Project of Provincial Natural Scientific Research Fund from the Educational Bureau of Anhui Province of China(KJ2007A087);National Natural Science Foundation of China(60475017);National Basic Research (973) Program of China (2004CB318108);Natural Science Foundation of Anhui Province of China (090412045,090412261X)

摘　　要：提出了一种新颖的求解约束问题的群智能优化算法.该算法模拟杂草克隆、占地生长与繁殖的自然行为,具有入侵性杂草的鲁棒性、适应性和随机性等特点,算法简单而有效,具有准确的全局搜索能力.结合罚函数方法将提出的算法应用于求解工程设计优化问题,实验结果及比较表明提出的算法获得了更优的结果,同时也显示了它在求解复杂工程设计优化问题时的全局寻优能力.进一步实验与统计分析了关于参数选择对算法性能的影响,得到了有利参数选择的结论.A novel swarm intelligence optimization technique for constrained problems was presented. The algorithm was inspired from colonizing weeds, which is used to mimic the natural behavior of weeds in colonizing and occupying suitable places for growth and reproduction. It has the robustness, adaptation and randomness and is simple but effective with an accurate global search ability. Some applications of the new algorithm on constrained engineering design optimization via employing a penalty approach suggest that the experimental results from the proposed algorithm are promising. Also, experimental applications and comparisons show that the presented algorithm is a potential global search technique for solving complex engineering design optimization problems. Extensive simulations are conducted along with statistical tests to yield helpful conclusions regarding the effects of parameter settings on the algorithm＇s performance.

关 键 词：全局优化 入侵性杂草优化 约束设计优化 罚函数方法 智能优化 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程] TB237[自动化与计算机技术—控制科学与工程]