用遗传算法求解三维埋入体的电磁逆散射问题  

Reconstruction of Objects Buried in Planarly Layered Media By Using Genetic Algorithm

作　　者：彭文兵[1] 肖柏勋 朱国强[1] 陈飞[1] 王雷[1] 

机构地区：[1]武汉大学电子信息学院,湖北武汉430072 [2]长江工程地球物理勘测研究院,湖北武汉430010

出　　处：《武汉大学学报（理学版）》2005年第3期384-388,共5页Journal of Wuhan University:Natural Science Edition

基　　金：国家自然科学基金资助项目(50099620)

摘　　要：采用遗传算法(GA)结合稳定的双共轭梯度-快速傅立叶变换(BCGS-FFT)方法求解了平面分层媒质中埋入目标的电磁逆散射问题.首先定义目标函数为测量电场与在假定目标区域电磁参数分布下的计算电场的差值的平方和,然后使用遗传算法最小化这个目标函数可得到目标区域的电磁参数分布,从而完成逆散射问题的求解.数值计算的结果表明:该算法可以求解多层媒质中任意三维非均匀埋入目标的电磁逆散射问题.This paper proposes an effective method to reconstruct three-dimensional objects buried in layered media. The reconstruction is obtained from the iterative inversion method that minimizes the cost function by using Genetic Algorithm, where the cost function is defined as the squared magnitude of the difference between the measured fields and the calculated fields from the assumed profile of the object. The scattered fields are calculated by the biconjugate-gradient fast Fourier transform (BCGS-FFT) algorithm. Numerical result shows these methods are capable of reconstructing an arbitrary 3-D inhomogeneous object buried in a multilayered medium.

关 键 词：分层媒质 埋入体 探地雷达 共轭梯度 遗传算法 玻恩迭代方法 

分 类 号：O441.3[理学—电磁学]