一种基于多峰值多规则并行搜索的遗传算法  

A Parallel Genetic Algorithm Based on Multiple Peak Values and Multiple Rules

作　　者：郭立新[1,2] 武丽梅[1,2] 李庆忠 李波[1,2] 张国忠[1,2] 

机构地区：[1]东北大学 [2]沈阳航空工业学院

出　　处：《机械科学与技术》1999年第3期406-408,411,共4页Mechanical Science and Technology for Aerospace Engineering

摘　　要：利用Ｈａｍｍｉｎｇ距离控制种群中个体间的差异，建立了峰值库，利用多峰值点外抛点法、一点和多点的交叉与变异方式，以及多峰值点邻域搜索策略，从而使改进后的遗传算法在解决有约束非线性问题时表现出良好的速度和有效性。The Hamming distance is used to control the differences among individuals of a population, in this paper, and a base of peak values is established. Some methods are used, such as point casting method around peak values, crossovers and mutations of one point and multi point, and searching strategies close to peak values. What have been used make the improved genetic algorithm speedy and effective to solve non linear functions with restrictive equations.

关 键 词：遗传算法 峰值库 个体差异控制 多规则 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]