计算机工程与应用 ›› 2018, Vol. 54 ›› Issue (3): 136-141.DOI: 10.3778/j.issn.1002-8331.1608-0364

• 模式识别与人工智能 • 上一篇    下一篇

飞蛾纵横交叉混沌捕焰优化算法

吴伟民,李泽熊,林志毅,吴汪洋,方典禹   

  1. 广东工业大学 计算机学院,广州 510006
  • 出版日期:2018-02-01 发布日期:2018-02-07

Moth-flame optimization algorithm based on chaotic crisscross operator

WU Weimin, LI Zexiong, LIN Zhiyi, WU Wangyang, FANG Dianyu   

  1. School of Computer, Guangdong University of Technology, Guangzhou 510006, China
  • Online:2018-02-01 Published:2018-02-07

摘要: 针对基本飞蛾捕焰优化(MFO)算法收敛速度慢和易陷入局部最优的缺陷,提出一种飞蛾纵横交叉混沌捕焰(CCMFO)算法。为飞蛾捕焰引入纵横交叉机制和混沌算子,通过横向全方位交叉寻优减少搜索盲点,纵向维交叉开发和混沌映射增强跳出局部最优的能力,火焰信息在种群中纵横交叉呈链式反应传播,加快收敛速度和避免算法早熟。通过仿真对比实验,证明了该算法具有较好的收敛速度、求解精度和稳定性。

关键词: 飞蛾捕焰优化算法, 纵横交叉机制, 混沌算子, 元启发式算法

Abstract: For the Moth-Flame?Optimization(MFO) algorithm’s slow convergence speed and easy falling into the partial optimization, a method of MFO algorithm based on Chaotic Crisscross operator(CCMFO) is proposed. The?crisscross mechanism and chaotic operator?are introduced for flame?scratching. Search blind spots are reduced by vertical cricross. Dimension-crisscross and chaotic mapping enhance the ability of skipping?the?partial?optimization. Flame information spreads rapidly like chain reaction by double-crisscross, accelerates the convergence speed and avoids algorithm premature. Through simulation experiments, it is proved that the new algorithm?has?high?convergence rate, solution accuracy and stability.

Key words: Moth-Flame Optimization(MFO) algorithm, crisscross mechanism, chaotic operator, metaheuristic