计算机工程

• 人工智能及识别技术 • 上一篇    下一篇

基于当前最优解的人工蜂群算法

周长喜1,毛 力1,吴 滨1,杨 弘2,肖 炜2   

  1. (1. 江南大学物联网工程学院轻工过程先进控制教育部重点实验室,江苏无锡214122;2. 中国水产科学研究院淡水渔业研究中心,江苏无锡214081)
  • 收稿日期:2014-06-23 出版日期:2015-06-15 发布日期:2015-06-15
  • 作者简介:周长喜(1989 - ),男,硕士研究生,主研方向:人工智能;毛 力,副教授;吴 滨,讲师;杨 弘,研究员;肖 炜,助理研究员。
  • 基金项目:

    国家青年科学基金资助项目(F030204);国家现代农业产业技术体系专项基金资助项目(CARS-49);轻工过程先进控制教育部重点实验室开放课题(江南大学)基金资助项目(APCLI1004)。

Artificial Bee Colony Algorithm Based on Current Optimal Solution

ZHOU Changxi 1,MAO Li 1,WU Bin 1,YANG Hong 2,XIAO Wei 2   

  1. (1. Key Laboratory of Advanced Process Control for Light Industry, Ministry of Education,School of IoT Engineering,Jiangnan University,Wuxi 214122,China; 2. Freshwater Fisheries Research Center of Chinese Academy of Fishery Sciences,Wuxi 214081,China)
  • Received:2014-06-23 Online:2015-06-15 Published:2015-06-15

摘要:

为克服人工蜂群算法在求解函数优化问题时存在收敛精度低、收敛速度慢的缺点,提出一种改进的人工蜂群算法。为提高人工蜂群算法的局部搜索能力和避免早熟收敛,跟随蜂在当前最优解的周围进行局部搜索,并随着迭代次数的增加,逐渐缩小侦查蜂在当前最优解周围的局部搜索范围。通过6 个标准测试函数完成仿真实验, 结果表明,与基本人工蜂群算法相比,改进算法在寻优精度和收敛速度上均得到提高。

关键词: 人工蜂群算法, 当前最优解, 局部搜索, 早熟收敛, 侦查蜂

Abstract:

An efficient modified Artificial Bee Colony(ABC) algorithm is proposed for function optimization problems to overcome the drawbacks of low computational accuracy and slow convergence of conventional ABC algorithm. In this algorithm,in order to enhance the local search capability of the ABC algorithm,and avoid the premature convergence effectively,onlooker bees do the local search around the current optimal solution,and the radius of the search around the current optimal solution for scout bees is gradually decreased with the increase of iterations. Simulation results of six standard functions show that compared with the basic ABC algorithm,the modified ABC algorithm can attain significant improvement on solution accuracy and convergence rate.

Key words: Artificial Bee Colony (ABC) algorithm, current optimal solution, local search, premature convergence, scout bee

中图分类号: