摘要
文章采用年龄代、相似度和价值函数等新技术对用于堆芯换料优化的遗传算法加以改进,其中年龄技术赋予了算法及时总结前一阶段方案搜索"经验"、引导算法更好地在局部最优邻域内进行搜索的能力;在对方案进行杂交之前首先评估方案的相似度,避免了对两个过于相似的方案进行杂交,从而防止算法早熟;价值函数的运用赋予算法依据较优方案共性特征的统计来产生新方案的能力。针对一个两环路堆芯换料优化基准题的数值检验说明,经改进的遗传算法可显著提高算法的搜索效率,同时也使优化解的质量得以提高。
In this study, the age technique, the concepts of relativeness degree and worth function are exploited to improve the performance of genetic algorithm （GA） for PWR loading pattern search. Among them, the age technique endows the algorithm be capable of learning from previous search ＂experience＂ and guides it to do a better search in the vicinity of a local optimal; the introduction of the relativeness degree checks the relativeness of two loading patterns before performing crossover between them, which can significantly reduce the possibility of prematurity of the algorithm; while the application of the worth function makes the algorithm be capable of generating new loading patterns based on the statistics of common features of evaluated good loading patterns. Numerical verification against a loading pattern search benchmark problem of a two-loop reactor demonstrates that the adoption of these techniques is able to significantly enhance the efficiency of the genetic algorithm while improves the quality of the final solution as well.
出处
《核科学与工程》
CSCD
北大核心
2009年第4期294-298,共5页
Nuclear Science and Engineering
关键词
遗传算法
年龄技术
价值函数
相似度
布料优化基准题
genetic algorithm
age technique
worth function
relativeness degree
benchmark problem for loading pattern search
