基于特征博弈预处理的多径抑制与高精度测角方法  

Multipath Suppression and High-precision Angle Measurement Method Based on Feature Game Preprocessing

作　　者：项厚宏 王永良[2] 李雨曦 陈毓锋 王凤玉 曾小路 XIANG Houhong;WANG Yongliang;LI Yuxi;CHEN Yufeng;WANG Fengyu;ZENG Xiaolu(School of Computer and Information,Hefei University of Technology,Hefei 230009,China;Air Force Early Warning Academy,Wuhan 430019,China;Hangzhou Institute of Technology,Xidian University,Hangzhou 311200,China;School of Artificial Intelligence,Beijing University of Posts and Telecommunications,Beijing 100876,China;School of Information and Electronics,Beijing Institute of Technology,Beijing 100081,China)

机构地区：[1]合肥工业大学计算机与信息学院,合肥230009 [2]空军预警学院,武汉430019 [3]西安电子科技大学杭州研究院,杭州311200 [4]北京邮电大学人工智能学院,北京100876 [5]北京理工大学信息与电子学院,北京100081

出　　处：《雷达学报(中英文)》2025年第2期269-279,共11页Journal of Radars

基　　金：国家自然科学基金(62201189);安徽省重大基础研究项目(2023z04020018);西安电子科技大学杭州研究院院士工作站基金(XHKY-202306-0285);中央高校基本科研业务费专项资金(JZ2024HGTB0228)。

摘　　要：米波雷达波束较宽,探测低仰角目标时多径信号严重影响直达信号的显著性,低仰角测角性能较差。针对此问题,该文提出了一种信号级特征博弈的多径抑制与高精度测角方法,构建一组直达信号提取器和直达信号特征检验器,直达信号提取器挖掘出多径信号湮没的直达信号,直达信号特征检验器用于鉴别、分析提取的直达信号的有效性,直达信号提取器和直达信号特征检验器相互博弈、优化,有效实现直达信号增强和多径信号抑制的效果,并利用已有的超分辨算法进行波达方向估计(DOA)。计算机仿真结果表明,所提算法不依赖于严格的目标角度信息,能够有效抑制多径信号,经典的超分辨算法在多种场景下的估计性能显著提升,且较已有的有监督学习模型而言,所提算法对未知的信号参数及多径分布模型具有更好的泛化性。The meter-wave radar,known for its wide beamwidth,often faces challenges in detecting lowelevation targets due to interference from multipath signals.These reflected signals diminish the strength of the direct signal,leading to poor accuracy in low-elevation angle measurements.To solve this problem,this paper proposes a multipath suppression and high-precision angle measurement method.This method,based on a signal-level feature game approach,incorporates two interconnected components working together.The direct signal extractor mines the direct signal submerged within the multipath signal.The direct signal feature discriminator ensures the integrity and validity of the extracted direct signal.By continuously interacting and optimizing one another,these components suppress the multipath interference effectively and enhance the quality of the direct signal.The refined signal is then processed using advanced super-resolution algorithms to estimate the Direction of Arrival(DoA).Computer simulations have shown that the proposed algorithm achieves high performance without relying on strict target angle information,effectively suppressing multipath signals.This approach noticeably enhances the estimation accuracy of classic super-resolution algorithms.Compared to existing supervised learning models,the proposed algorithm offers better generalization to unknown signal parameters and multipath distribution models.

关 键 词：米波雷达 多径信号 直达信号提取 直达信号特征鉴别 角度测量 

分 类 号：TN958[电子电信—信号与信息处理]