首页 | 本学科首页   官方微博 | 高级检索  
检索        

一种基于椋鸟群行为的改进型蝙蝠算法
引用本文:胡飞,孙自强.一种基于椋鸟群行为的改进型蝙蝠算法[J].医学教育探索,2017,43(4):525-532,562.
作者姓名:胡飞  孙自强
作者单位:华东理工大学化工过程先进控制和优化技术教育部重点实验室, 上海 200237,华东理工大学化工过程先进控制和优化技术教育部重点实验室, 上海 200237
摘    要:蝙蝠算法是一种新兴的元启发式算法,基本蝙蝠算法(BA)存在寻优精度低、易陷入局部最优等缺点。将椋鸟群的集体性行为引入到基本蝙蝠算法中,有效地提高了算法的搜索范围;引入线性递减权重,用于平衡全局搜索和局部搜索。通过一些测试函数对该算法进行仿真研究,结果表明改进的蝙蝠算法有效地避免了种群个体陷入局部最优,提高了算法的寻优精度,优化效果得到改善。

关 键 词:蝙蝠算法(BA)  椋鸟群行为  权重  局部最优
收稿时间:2016/11/1 0:00:00

An Improved Bat Algorithm Based on Starling Flock Behavior
HU Fei and SUN Zi-qiang.An Improved Bat Algorithm Based on Starling Flock Behavior[J].Researches in Medical Education,2017,43(4):525-532,562.
Authors:HU Fei and SUN Zi-qiang
Institution:Key Laboratory of Advanced Chemical Process Control and Optimization Technology, Ministry of Education, East China University of Science and Technology, Shanghai 200237, China and Key Laboratory of Advanced Chemical Process Control and Optimization Technology, Ministry of Education, East China University of Science and Technology, Shanghai 200237, China
Abstract:Bat algorithm (BA) is a new metaheuristic algorithm.However,the standard BA has some shortcomings,e.g.,low convergence precision and easily relapsing into the local optima.In this work,by introducing the collective behavior of the starling group into BA algorithm,the searching range of the standard BA algorithm can be effectively improved.Besides,a linear decreasing weight is introduced to balance the global search and the local search.Simulation results from Benchmark functions show that the improved algorithm can effectively avoid the local optimum and attain higher convergence precision.
Keywords:bat algorithm (BA)  starling group behavior  weight  local optima
点击此处可从《医学教育探索》浏览原始摘要信息
点击此处可从《医学教育探索》下载免费的PDF全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号