用BP神经网络技术重构介质圆柱体电磁参数

将BP神经网络技术应用于介质圆柱体电磁逆散射问题研究,通过BP神经网络将原逆散射问题转化为一个回归估计问题.设置多个目标散射场观测点,分别以目标不同的电磁参数及其响应下的散射电场的幅值作为BP网络的输出与输入,采用L-M训练算法,经过适当的训练,建立起逆散射模型,再以新的散射电场作为输入,实时重构了自由空间及半空间介质圆柱体的相对介电常数和电导率.数值结果显示了该方法的有效性及准确性,为目标的实时逆散射研究提供了一种高效的方法.

Reconstruction Electromagnetic Parameters of Dielectric Circular Cylinder Based on BP Neural Networks

In this paper,BP neural network technology is applied to the inverse scattering problem of dielectric circular cylinder,The inverse scattering problem is recast into a regression estimation one by means of the BP neural network.The target scattered electric fields are measured at some points,the amplitude of electric fields scattered by the target are fed into the BP network,whose output are the electromagnetic parameter,after proper training by the L-M training algorithm,the inverse scattering model of dielectric circular cylinder has been setup and the relative dielectric permittivity and the electric conductivity of target being in free-space or half-space are reconstructed in real-time.The results show that this method is effective and efficient and provides a highly efficient solution for the real-time inverse scattering of target