遗传算法求解约束优化问题时产生初始种群的改进方法  

Improved method on generation of initial population by using GA for solving constrained optimization problems

作　　者：徐梅[1] 文士发 王福林[1] 官林[1] 

机构地区：[1]东北农业大学工程学院,哈尔滨150030

出　　处：《东北农业大学学报》2014年第7期104-107,111,共5页Journal of Northeast Agricultural University

基　　金：国家自然科学基金项目(31071331;1151z004)

摘　　要：研究提出初始内点产生新方法,该方法根据约束优化问题的特点,构造由约束条件构成目标函数,将求初始内点问题转化为求解一系列无约束优化问题,通过求解这些无约束优化问题,实现初始内点求解;研究初始种群其余个体产生的一种方法。结果表明,初始种群产生关键在于求得一个初始内点,求得初始内点后,其他个体的产生将占据较少时间。试验验证文章给出的初始种群产生方法快速可靠,可以克服有些约束优化问题初始种群难以产生问题。Through the research we present a new method about initial interior point＆#39;s generation, firstly constructed a constraint posed by the objective function, which is based on the characteristics of constrained optimization problems, and translate the problem of evaluating the initial interior point into solving the problem of solving a series of unconstrained optimization, by solving the unconstrained optimization problem, we achieve the solution of the initial interior point;Based on this, the research has given a method on the generation of the rest initial population individuals. The results showed that the key to generate the initial population was to obtain an initial point, the production of other individuals would take less time after the initial internal point was obtained. We verified by examples that the initial population generation method given by the paper was a fast and reliable method, and thus overcame the problem, which initial population was difficult to be produced in some constrained optimization problems.

关 键 词：遗传算法 初始内点 初始种群 约束优化问题 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]