基于亲和度的改进引力搜索算法  

Improved Gravitational Search Algorithm Based on Affinity

作　　者：周少武[1] 陈微[1] 唐东成[1] 张红强[2] 王汐[1] 周游[1] 

机构地区：[1]湖南科技大学信息与电气工程学院,湖南湘潭411201 [2]湖南大学电气与信息工程学院,长沙410082

出　　处：《计算机工程》2014年第8期201-204,216,共5页Computer Engineering

基　　金：国家自然科学基金资助项目(51374107);湖南省自然科学基金资助项目(13JJ8014)

摘　　要：为提高引力搜索算法的收敛性和搜索精度,提出一种基于亲和度的改进引力搜索算法PGSA。分析已有引力搜索算法的原理,通过改变粒子的引力合力计算公式对其进行改进,构造亲和度,即通过粒子间的质量差来表示粒子间的亲和度,将其作适当变换构造一个系数改造基本引力搜索算法。采用Matlab对该算法进行验证,数值仿真结果表明,改进后的引力搜索算法具有较快的收敛速度和较高的搜索精度。This paper puts forward the improvement of gravitational search algorithm called PGSA based on affinity to improve the algorithm convergence and search precision,and this improved Gravitational Search Algorithm （GSA） changes the particle＇ s gravitational force calculation formula.It includes the principles of gravitational search algorithm and the structure of the affinity,namely,it is the affinity between particles which is represented by the quality value of the difference between the particles,and the affinity for the appropriate transformation is added to the formula resultant force.Then the formula resultant force is modified.Ultimately,this paper verifies the algorithm by means of Matlab,and experiments show that the improved algorithm has better convergence and better solution

关 键 词：引力搜索算法 合力 亲和度 质量差 可调参数 系数 

分 类 号：TP311.12[自动化与计算机技术—计算机软件与理论]