自调整非线性遗传算法  

Self-adjusting Nonlinear Genetic Algorithm

作　　者：崔志华[1] 曾建潮[1] 徐玉斌[1] 

机构地区：[1]太原重型机械学院系统仿真与计算机应用研究所,太原030024

出　　处：《系统仿真学报》2003年第5期742-744,共3页Journal of System Simulation

基　　金：山西省自然科学基金资助

摘　　要：通过对简单遗传算法的理论分析,得出了复制、杂交、变异等算子的每次作用均相当于对所作用的个体进行一次线性变换。因此,通过对传统遗传算子进行修改,作者提出了非线性遗传算法。本文发现规范化操作对算法的计算效率有很大的影响,并且给出各遗传算子的一种等价线性表示。因此,如果针对不同的优化问题动态的进行规范化操作及遗传算子的选择,将会大大提高算法的效率。本文提出一种新的自调整非线性遗传算法(Self-Ajusting Nonlinear Genetic Algorithm,SANGA),该算法通过规范化操作的动态选择,结合简单的遗传算子,对算法的效率有很大的提高。仿真结果表明该算法的有效性。Through mechanism analysis of Simple Genetic Algorithm(SGA), every genetic operator of SGA can be considered as a linear transformation to the corresponding individuals. So, by modifying the traditional genetic operators, the nonlinear genetic algorithm(NGA) is introduced. In this paper, a linear equivalent representation of crossover, mutation and selection operators is introduced, in which, the normalized mapping f plays an important role and the calculation efficiency can be greatly affected. According to the above method, the self-adjusting nonlinear genetic algorithm (SANGA) is introduced. Normalized mapping f is modified to nonlinear transform and the selection principles of mapping f are discussed. The optimization computing of some examples is made to show that the new genetic algorithm is useful and simple.

关 键 词：自调整 非线性遗传算法 规范化操作 遗传算法 

分 类 号：O195[理学—数学]