一种新的群集智能算法——自由搜索  

A Novel Swarm Intelligent Algorithm—Free Search

作　　者：周晖[1] 李丹美[1] 邵世煌[1] 袁从明[2] 

机构地区：[1]东华大学信息科学与技术学院,上海201620 [2]南通大学电子信息学院,江苏南通226019

出　　处：《东华大学学报（自然科学版）》2007年第5期579-583,共5页Journal of Donghua University(Natural Science)

基　　金：教育部高校博士点基金(20060266006);江苏省高校自然科学基金项目(07KJB510095;06KJD510156)

摘　　要：介绍一种新的群集智能优化方法——自由搜索(FS)算法,该算法借鉴自然界动物种群中的个体存在各异的嗅觉和活动半径,提出了灵敏度和邻域搜索半径的概念,并且利用释放信息素的机理,通过信息素和灵敏度的比较确定寻优目标.研究并实现了FS算法,对典型函数的优化问题进行计算实验.结果证明,该算法与同类算法相比,全局搜索能力好、收敛速度快,验证了算法的有效性.最后,对FS算法进行总结并指出进一步研究的方向.A novel algorithm of swarm intelligence, Free Search （FS） is introduced, which is used to solve function optimization problems. Considering an animal＇s behavior in natural, it is assumed that the sense and the mobility support the search within the natural environment. In the algorithm each animal has original peculiarities called sensibility and mobility. During the exploration each animal achieves some favor （an objective function solution） and distributes a pheromone in amount proportional to the amount of the found favor （the quality of the solution）. The effect of several parameters at the performances of the algorithm is analyzed. The experimental results have shown that, compared with similar algorithms, the good performance of the algorithm such as avoiding local optima and quick convergence. Finally, an overview of the algorithm is offered and the directions for further study are also provided.

关 键 词：自由搜索(FS) 进化计算 群集智能 函数优化 

分 类 号：TP13[自动化与计算机技术—控制理论与控制工程]