| 低维函数的快速优化算法 |
| |
| 引用本文： | 蒲保兴,杨路明.低维函数的快速优化算法[J].邵阳学院学报(自然科学版),2008,5(1):55-58. |
| |
| 作者姓名： | 蒲保兴 杨路明 |
| |
| 作者单位： | 1. 邵阳学院信息与电气工程系,湖南,邵阳,422001;中南大学信息科学与工程学院,湖南,长沙,410083
2. 中南大学信息科学与工程学院,湖南,长沙,410083 |
| |
| 基金项目： | 湖南省教育厅自然科学基金 |
| |
| 摘 要： | 基于群体的进化算法是求解函数优化问题的常用方法，但存在收敛速度慢和易陷入早熟的缺点．提出了一个基于（1＋1）-ES分块进化的低维函数优化算法，采用分块进化，引入丢弃不重要分块和二次优化求精的策略，实现了全局搜索过程和局部搜索过程的分离．通过算法分析，表明了算法比较适合于低维函数．仿真结果表明了提出的算法的抗早熟能力和求解效率均优于FEP．
|
| 关 键 词： | 分块进化 丢弃不重要块 二次优化 |
| 文章编号： | 1672-7010(2008)01-0055-04 |
| 修稿时间： | 2007年12月12 |
A Fast Optimization Algorithm for Low Dimensional Function |
| |
| PU Bao-xing,YANG Lu-ming.A Fast Optimization Algorithm for Low Dimensional Function[J].Journal of Shaoyang University:Science and Technology,2008,5(1):55-58. |
| |
| Authors: | PU Bao-xing YANG Lu-ming |
| |
| Institution: | PU Bao-xing,YANG Lu-ming (1.Department of Information and Electrical Engineering, Shaoyang College, Shaoyang 422001,Hunan, China; 2. School of Information Science and Engineering, Central South University, Changsha 410083, China) |
| |
| Abstract: | The evolutionary algorithms based on population are frequently used to solve the function optimization problem, which have some shortcomings that the convergence rate is slow and the premature is apt to arise. A novel optimization algorithm bases on partitioned （1＋1）-ES for low dimensional function is proposed, which adopts a series of strategies including partitioned evolution, discarding unimportance block and re-optimizing so as to separate local search process from global search process. By Analyzing algorithm,it is indicated that the proposed algorithm is suitable for low dimensional function. Simulation results show that the proposed algorithm outperforms the FEP in terms of performance. |
| |
| Keywords: | partitioned evolution discarding unimportance block re-optimizing |
| 本文献已被 维普 万方数据 等数据库收录！ |
|
