摘要
进化算法在各类电磁结构优化设计中有着广泛的应用,但由于需要在参数空间中进行随机搜索并仿真试探,优化效率普遍较低.针对这一问题,提出受限差分进化(Differential Evolution,DE)算法与Kriging代理模型相结合的电磁结构快速优化算法.算法根据参考设计结果建立圆柱管道空间,通过参数变换将进化区域限制在管道内部.Kriging模型学习管道内样本及其仿真数据,代替电磁仿真快速预测进化产生下一代种群的响应.相比整个参数空间,该算法DE寻优和Kriging学习的区域被显著减小,优化效率得到提升.通过一个波导双孔定向耦合器的优化设计,表明该方法的求解质量和收敛速度优于现有算法.
Evolution algorithm(EA) is widely used for the optimization of various electromagnetic (EM) structures, however, its efficiency is generally low because of the random search in parameter space and numerous simulation trials. To address this problem, an efficient EM structure which combines constrained differential evolution (DE) with Kriging model is prop cording to reference designs, a tube space is first established by the algorithm, the optimization algorithm osed in this paper. area of evolution is Ac re-
出处
《电波科学学报》
CSCD
北大核心
2017年第3期273-278,共6页
Chinese Journal of Radio Science
基金
安徽省高等教育提升计划项目(TSKJ2014B05
TSKJ2015B19)
关键词
电磁结构
优化算法
KRIGING
受限差分进化
波导定向耦合器
electromagnetic structure
optimization
kriging
constrained differential evolution
waveguide directional coupler