一种基于矩阵遗传算子的优化组合遗传算法  

Optimization Combination Genetic Algorithm Based on Matrix Genetic Operator

作　　者：帅训波[1] 马书南[2] 周相广[1] 欧阳永林[1] 

机构地区：[1]中国石油勘探开发研究院廊坊分院地球物理与信息研究所,河北廊坊065007 [2]北京工业大学计算机学院,北京100022

出　　处：《小型微型计算机系统》2009年第5期951-954,共4页Journal of Chinese Computer Systems

摘　　要：针对遗传算法中全局搜索与局部搜索之间的矛盾,应用二进制编码具有对搜索空间表示精细、容易位值计算的特点,提出矩阵遗传算子,实现群体性对样本空间探索,从而增强遗传算法的全局搜索性能,与具有良好局部搜索性能的遗传算子组合应用,构造了基于矩阵遗传算子的优化组合遗传算法,保证了算法的全局收敛性.实验结果表明,该算法具有更好的整体寻优能力,对利用基于二进制编码遗传算法求解复杂非线性优化问题具有重要借鉴意义.In order to resolve the contradiction between global searching and local searching of genetic algorithm, matrix genetic operator is proposed based on binary code describing search space free and calculating fitness easier. Global searching of genetic algorithm is improved by the matrix genetic operator making good use of colony information to fred new space. An optimization combination genetic algorithm is constructed through combining the matrix genetic operator with better local searching operator, and this constructed genetic algorithm is proved to be convergent. The test results show the efficiency of the genetic algorithm in searching is better than classical genetic algorithm＇s. It is a significant reference for other optimum problem resolved through genetic algorithm based on binary coding.

关 键 词：全局搜索 局部搜索 矩阵遗传算子 逆序算子 对偶算子 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]