求解全局优化问题的改进人工鱼群算法  

A New Improved Artificial Fish Swarm Algorithm for Global Optimization

作　　者：范永利 胡春燕[1] 张悦 潘添 FAN Yong-li;HU Chun-yan;ZHANG Yue;PAN Tian(School of Photoelectric Information and Computer Engineering,University of Shanghai for Science and Technology,Shanghai 200093,China)

机构地区：[1]上海理工大学光电信息与计算机工程学院

出　　处：《软件导刊》2019年第6期80-84,88,共6页Software Guide

摘　　要：针对人工鱼群算法的不足,提出一种改进的人工鱼群算法NAFAS。该算法对原有觅食行为进行改进,引进双高斯函数与其融合,使在寻优后期人工鱼群能快速逃离局部极值区域,从而提高全局寻优能力。与其它多种智能算法进行仿真测试并比较分析,结果表明,改进的人工鱼群算法搜索速度快、寻优精度高。Artificial fish swarm algorithm optimizes through the simulation of the fish behaviors,such as preying,swarming,following and moving in the search area,which is an application of the swarm intelligence. It has the advantages of the better global search abili-ties and the excellent robustness. What’s more,the algorithm is easily and simply operated. But it is easy to fall into local optima in the flat area and becomes lower in the later period of algorithm. To overcome the shortages of the artificial fish swarm algorithm,this paper presents an improved artificial fish swarm algorithm which is named NAFAS. In order to enhance the global searching ability ,the bi-modal Gaussian is integrated into the function of the prey behavior. so the artificial fish can escape from local extreme areas quickly. Compared with some typical evolutionary algorithms,the numerical experiment results show that NAFAS not only has efficient search performance on the optimal precision excellently,but is also an excellent algorithm for solving global optimization problems.

关 键 词：人工鱼群算法 双高斯函数 全局优化 智能算法 

分 类 号：TP312[自动化与计算机技术—计算机软件与理论]