融合注意力机制的波达方向估计算法
DOI:
CSTR:
作者:
作者单位:

中国人民公安大学信息网络安全学院北京100038

作者简介:

通讯作者:

中图分类号:

TN911.7

基金项目:


DOA estimation algorithm integrating attention mechanism
Author:
Affiliation:

School of Information and Network Security,People’s Public Security University of China, Beijing 100038,China

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    针对现有波达方向(direction of arrival,DOA)估计算法在阵列误差和低信噪比(signal-to-noise ratio,SNR)条件下估计精度较低、鲁棒性较弱的问题,提出了一种基于高效通道注意力残差网络(efficient channel attention residual network,ECAR-Net)的DOA估计算法。首先,利用全连接层将信号映射到高维空间,解耦信号中的非线性成分;其次,重塑特征向量以便于后续卷积操作;然后,通过高效通道注意力(efficient channel attention,ECA)残差块对特征进一步提取和深化,展平特征向量并通过全连接层输出特征增强后的信号;最后,对输出的信号进行矩阵运算生成空间谱,通过峰值搜索得到DOA估计值。实验模拟存在多种阵列误差的仿真环境,在这些仿真环境下对ECAR-Net、多信号分类(multiple signal classification,MUSIC)方法、正交匹配追踪(orthogonal matching pursuit,OMP)方法和超分辨率波达方向(super-resolution direction of arrival network,SDOA-Net)估计方法进行性能对比。仿真结果表明,在所设置的SNR范围内,ECAR-Net的平均DOA估计精度要优于SDOA-Net、MUSIC和OMP的平均DOA估计精度,在SNR为-10 dB时,ECAR-Net的平均DOA估计精度相较于SDOA-Net、MUSIC和OMP分别提升了9.06%、20.49%和12.76%。同时经过累积分布函数(cumulative distribution function,CDF)评估,ECAR-Net也拥有比这3种方法更强的鲁棒性和更好的估计误差分布特性。

    Abstract:

    To address the issues of low estimation accuracy and weak robustness in array imperfections and low signal-to-noise ratio (SNR) conditions in existing direction of arrival (DOA) estimation algorithms, this paper proposes a DOA estimation algorithm based on efficient channel attention residual network (ECAR-Net). Firstly, a fully connected layer is utilized to map the signal into a high-dimensional space and decouple the nonlinear components within the signal. Secondly, the feature vectors are reshaped to facilitate subsequent convolutional operations. Then, the features are further extracted and refined through efficient channel attention (ECA) residual block. The feature vectors are flattened and fully connected layer outputs the signal with enhanced features. Finally, perform matrix operations on the output signal to generate spatial spectrum, and obtain the DOA estimation value through peak search. The experiments simulated array environments with multiple array imperfections and compared the performance of ECAR-Net, multiple signal classification (MUSIC) method, orthogonal matching pursuit (OMP) method and super-resolution direction of arrival network (SDOA-Net). Simulation results demonstrate that across the tested SNR range, ECAR-Net achieves higher mean DOA estimation accuracy than SDOA-Net, MUSIC and OMP. At -10 dB SNR, the mean DOA estimation accuracy of ECAR-Net has improved by 9.06%, 20.49% and 12.76% compared to SDOA-Net, MUSIC and OMP, respectively. Cumulative distribution function (CDF) evaluation further demonstrates ECAR-Net’s stronger robustness and better estimation error distribution characteristics than SDOA-Net, MUSIC and OMP.

    参考文献
    相似文献
    引证文献
引用本文

林钏咏,曹之俊,卜凡亮.融合注意力机制的波达方向估计算法[J].电子测量与仪器学报,2026,40(9):309-320

复制
分享
相关视频

文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:
  • 最后修改日期:
  • 录用日期:
  • 在线发布日期: 2026-11-13
  • 出版日期:
文章二维码
×
《电子测量与仪器学报》
关于防范虚假编辑部邮件的郑重公告