| 摘要: |
| 针对常规深度学习模型在阵列信号波达方向（Direction of Arrival，DOA）估计中易受跨界误差和过拟合影响的挑战，提出一种融合混合注意力和动态学习率调度的残差网络模型。该模型以阵列信号的空间协方差矩阵为输入，输出对应信号源的DOA估计值。模型整体构建于残差神经网络框架之上，集成了角度限制策略以有效解决周期边界误差问题，引入混合注意力机制以增强关键特征提取能力，结合标签平滑技术缓解模型过拟合风险，并采用余弦退火调度策略动态调整学习率以进一步提升训练性能。实验结果表明，在单源输入下的均匀线阵与非均匀线阵条件下，所提模型性能均优于传统方法，在多个典型仿真场景中均保持最低误差。 |
| 关键词: DOA估计 残差网络 混合注意力 标签平滑 动态学习率调度 深度学习 |
| DOI：10.20079/j.issn.1001-893x.250319001 |
|
| 基金项目:国家自然科学基金资助项目（52101383） |
|
| DOA Estimation with a Residual Network Integrating Hybrid Attention and Dynamic Scheduling |
| YANG Hankun,YANG Wentie,WANG Zuoshuai,XU Yidong |
| (1.Yantai Research Institute，Harbin Engineering University，Yantai 265500，China;2.Hubei Key Laboratory of Marine Electromagnetic Detection and Control，Wuhan Second Ship Design and Research Institute，Wuhan 430064，China) |
| Abstract: |
| To address the challenges of boundary-crossing errors and overfitting commonly encountered in conventional deep learning models for direction-of-arrival（DOA） estimation in array signal processing，the authors propose a residual network model that integrates hybrid attention and dynamic learning rate scheduling.The model takes the spatial covariance matrix of array signals as input and outputs the estimated direction of the signal sources.Built upon a residual neural network framework，the model incorporates an angular constraint strategy to effectively mitigate periodic boundary errors，employs a hybrid attention mechanism to enhance the extraction of key features，applies label smoothing to alleviate overfitting，and adopts a cosine annealing schedule to dynamically adjust the learning rate for improved training performance.Experimental results demonstrate that the proposed model consistently outperforms traditional methods under both uniform and non-uniform linear array conditions with single-source input，achieving the lowest estimation errors across various typical simulation scenarios. |
| Key words: DOA estimation residual network hybrid attention label smoothing dynamic learning rate scheduling deep learning |
《电讯技术》编辑部 