| 一种基于子域搜索的高效遗传算法 |
| |
| 引用本文： | 葛培明,陈虬.一种基于子域搜索的高效遗传算法[J].计算机工程与应用,2006,42(1):47-49,82. |
| |
| 作者姓名： | 葛培明 陈虬 |
| |
| 作者单位： | 西南交通大学应用力学与工程系,成都,610031 |
| |
| 基金项目： | 西南交通大学校科研和教改项目 |
| |
| 摘 要： | 论文根据机器学习的思想利用有限离散的方法设计了一种新的实数编码遗传算法——基于子域搜索的遗传算法(SBGA),该算法能够根据学习规则记忆前面搜索过的样本点信息,并利用这些信息指导后续的搜索。理论分析和数值仿真都表明了算法的稳健性,能够消除过早收敛现象,处理复杂约束,避免重复采样等。
|
| 关 键 词： | 遗传算法 早熟 约束处理 子域 机器学习 |
| 文章编号： | 1002-8331-（2006）01-0047-03 |
A Subdomains-based Genetic Algorithms of High Performance |
| |
| Ge Peiming,Chen Qiu.A Subdomains-based Genetic Algorithms of High Performance[J].Computer Engineering and Applications,2006,42(1):47-49,82. |
| |
| Authors: | Ge Peiming Chen Qiu |
| |
| Affiliation: | Department of Applied Mechanics and Engineering, Southwest Jiaotong University, Chengdu 610031 |
| |
| Abstract: | A new method for real number encoding genetic algorithms is described in this paper.This machine-learning-based algorithm can utilize the sequence of points explored during a search to guide further search.The results from both theory analysis and numerical experiments show the proposed method can significantly improve the performance of genetic algorithms in many aspects,such as premature convergence,constraint handling and resampling. |
| |
| Keywords: | Genetic Algorithms premature convergence constraint handling subdomains machine learning |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
