摘要
随着雷达组网技术的发展成熟,未来电磁隐身对抗中双站雷达散射截面(radar cross section,RCS)减缩将比单站更为重要.人工电磁超表面为双站RCS减缩提供了全新的技术途径.然而,受制于大规模阵列优化耗时及双站RCS减缩全空间最值特性,目前的双站RCS减缩超表面设计还存在效率不高、性能较差的问题.鉴于此,本文提出了一种小样本条件下的卷积神经网络(convolutional neural network,CNN)方法,通过定向优化超表面相位分布,实现雷达回波全空间均匀散射,从而达到双站RCS减缩效果.本方法结合了卷积特征提取、残差增强与全连接优化模块,配合自定义损失函数,可高效捕捉漫反射相位与RCS全空间最值的多维度复杂关系.理论计算、全波仿真和样品测试结果表明,在7.26—10.74 GHz频段内,利用本方法设计的超表面可实现10 dB以上的双站RCS减缩,相比传统优化算法减缩效果提升17.2%,且优化效率显著提高,有望为武器装备的全空间电磁隐身提供新的技术思路.
Radar cross section(RCS),a crucial physical quantity that characterizes the backscattering intensity of targets under radar illumination,is the primary metric for assessing stealth capabilities.With the development of radar detection technologies,RCS reduction has become a forefront research topic in radar stealth,aiming to minimize target detectability.With the maturity of radar networking technology,the bistatic radar RCS reduction is becoming increasingly important in future electromagnetic stealth countermeasures compared with the monostatic radar RCS reduction.Artificial electromagnetic metasurfaces have introduced innovative technical approaches for realizing the bistatic radar RCS reduction.However,current metasurface designs still face challenges related to inefficiency and suboptimal performance,mainly due to the time-consuming nature of large-scale array optimization and the global extremum characteristics of bistatic radar RCS reduction.To overcome these limitations,this study proposes a few-shot convolutional neural network(CNN)-based approach,which achieves uniform full-space radar echo scattering by directionally optimizing metasurface phase distributions,thereby enabling effective bistatic radar RCS reduction.This approach integrates convolutional feature extraction,residual enhancement,and fully connected optimization modules with a customized loss function to efficiently capture the complex multidimensional relationships between diffuse reflection phases and the full-space RCS extrema.Theoretical calculations,full-wave simulations,and experimental tests show that the metasurface designed with this approach can achieve over 10 dB of Bistatic Radar RCS reduction in a frequency range from 7.26 GHz to 10.74 GHz.The method also ensures uniform diffuse reflection across the full space for various incidence angles(30°,45°,60°).Compared with traditional optimization algorithms,this method enhances RCS reduction by 17.2% while significantly improving computational efficiency.This approach provides a promising new technical paradigm for achieving full-space electromagnetic stealth in advanced weapon systems.
作者
朱顺凯
袁方
胡凯
皮涛涛
朱熙铖
李程
ZHU Shunkai;YUAN Fang;HU Kai;PI Taotao;ZHU Xicheng;LI Cheng(School of Electronics and Information Engineering,Nanjing University of Information Science and Technology,Nanjing 210044,China;The Sixty-third Research Institute,National University of Defense Technology,Nanjing 210007,China;College of Electronic Science and Technology,National University of Defense Technology,Changsha 410073,China)
出处
《物理学报》
北大核心
2025年第10期306-320,共15页
Acta Physica Sinica
基金
国家资助博士后研究人员计划(批准号:GZB20240991)
国家自然科学基金青年科学基金(批准号:62401596)资助的课题。
关键词
超表面
双站雷达散射截面减缩
卷积神经网络
metasurface
bistatic radar cross section reduction
convolutional neural network
