东北大学学报(自然科学版) ›› 2005, Vol. 26 ›› Issue (4): 219-221.DOI: -

• 论著 • 上一篇    下一篇

一种基于实数编码的改进遗传算法

董颖;刘欢杰;许宝栋;唐加福   

  1. 东北大学信息科学与工程学院;东北大学信息科学与工程学院;东北大学信息科学与工程学院;东北大学信息科学与工程学院 辽宁沈阳 110004
  • 收稿日期:2013-06-24 修回日期:2013-06-24 出版日期:2005-04-15 发布日期:2013-06-24
  • 通讯作者: Dong, Y.
  • 作者简介:-
  • 基金资助:
    国家自然科学基金资助项目(70002009);;教育部新世纪优秀人才基金资助项目;;国家教育部优秀青年教师基金资助项目;;教育部科技研究重点资助项目(104064);;辽宁省自然科学基金资助项目(20022019)·

Modified genetic algorithm based on real-coding

Dong, Ying (1); Liu, Huan-Jie (1); Xu, Bao-Dong (1); Tang, Jia-Fu (1)   

  1. (1) Sch. of Info. Sci. and Eng., Northeastern Univ., Shenyang 110004, China
  • Received:2013-06-24 Revised:2013-06-24 Online:2005-04-15 Published:2013-06-24
  • Contact: Dong, Y.
  • About author:-
  • Supported by:
    -

摘要: 在介绍基于实数编码遗传算法的优点和分析原有遗传操作机制存在缺陷的基础上,重点研究了实数编码的改进线性交叉算子,提出了一种改进遗传算法(MGA)·该改进线性交叉算子的优点是在交叉之后,一个子代位于两父代之间,另一子代位于靠近较好的父代的一侧,使解向好的方向发展,并且都是可行解·通过对几个典型的实例计算并与其他基于实数编码的遗传算法进行比较,结果表明,本算法在求解优化问题的收敛速度和精确性方面具有优势·

关键词: 遗传算法, 交叉操作, 实数编码, 优化问题, 遗传机制

Abstract: Analyzing the advantages of real-coded genetic algorithm and disadvantages of its genetic mechanism, a modified genetic algorithm (MGA) is developed focusing on its linear crossover operator in real coding. The merits of this genetic operator lies in that after crossover a filial generation is in between the parents and the other one is in the vicinity of a better paternal generation so that they are feasible with an optimal solution available. Calculating some typical instances and comparing the results with other real-coded genetic algorithms, the proposed algorithm shows its superiority in convergence rate and precision for solving optimization problems.

中图分类号: