计算机工程与应用 ›› 2008, Vol. 44 ›› Issue (35): 50-52.DOI: 10.3778/j.issn.1002-8331.2008.35.015

• 理论研究 • 上一篇    下一篇

混合变异算子的人工鱼群算法

曲良东,何登旭   

  1. 广西民族大学 数学与计算机科学学院,南宁 530006
  • 收稿日期:2007-12-20 修回日期:2008-02-27 出版日期:2008-12-11 发布日期:2008-12-11
  • 通讯作者: 曲良东

Artificial fish-school algorithm based on hybrid mutation operators

QU Liang-dong,HE Deng-xu   

  1. College of Mathematics and Computer Science,Guangxi University for Nationlities,Nanning 530006,China
  • Received:2007-12-20 Revised:2008-02-27 Online:2008-12-11 Published:2008-12-11
  • Contact: QU Liang-dong

摘要: 在分析基本人工鱼群算法存在不足的基础上,提出了基于高斯变异算子与差分进化变异算子相结合的人工鱼群算法,该算法克服了人工鱼漫无目的随机游动或在非全局极值点的大量聚集,显著提高了求解质量和运行效率.通过仿真实验测试验证,表明该算法是可行的和有效的。

关键词: 人工鱼群算法, 高斯变异算子, 差分进化变异算子

Abstract: After analyzing the disadvantages of Artificial Fish-School Algorithm(AFSA),this paper presents a hybrid artificial fish-school algorithm based on Gauss mutation and differential evolution mutation.By adding mutation operators to AFSA in evolution process,the ability of AFSA to break away from artificial fish stochastic moving without a definite purpose or heavy getting together round the local optimum solution is greatly improve.The proposed algorithm can greatly improve the ability of seeking the global excellent result and convergence property and accuracy.Several computer simulation results show that the proposed algorithm is significantly superior to original AFSA.

Key words: Artificial Fish-School Algorithm(AFSA), Gauss mutation operator, differential evolution mutation operator