系统工程与电子技术 ›› 2025, Vol. 47 ›› Issue (7): 2406-2413.doi: 10.12305/j.issn.1001-506X.2025.07.33

• 通信与网络 • 上一篇    

基于双路径特征融合网络的背景信号抑制算法

张琬滢1,2, 高由兵1,2, 李泽一1,2, 李鹏飞1,2, 张伟2,3,*   

  1. 1. 中国电子科技集团公司第二十九研究所, 四川 成都 610036
    2. 电磁空间安全全国重点 实验室, 四川 成都 610036
    3. 电子科技大学信息与通信工程学院, 四川 成都 611731
  • 收稿日期:2024-06-26 出版日期:2025-07-16 发布日期:2025-07-22
  • 通讯作者: 张伟
  • 作者简介:张琬滢 (2000—), 女, 硕士研究生, 主要研究方向为电子对抗、信号与信息处理
    高由兵 (1982—), 男, 高级工程师, 硕士, 主要研究方向为电子对抗
    李泽一 (1994—), 男, 工程师, 博士, 主要研究方向为通信对抗
    李鹏飞 (1993—), 男, 高级工程师, 博士, 主要研究方向为电子对抗
    张伟 (1985—), 男, 研究员级高级工程师, 博士, 主要研究方向为电子对抗
  • 基金资助:
    国家自然科学基金(U20B2070);国家自然科学基金(U23B2013)

Background signal suppression algorithm based on dual-path feature fusion net

Wanying ZHANG1,2, Youbing GAO1,2, Zeyi LI1,2, Pengfei LI1,2, Wei ZHANG2,3,*   

  1. 1. The 29th Research Institute of China Electronics Technology Group Corporation, Chengdu 610036, China
    2. National Key Laboratory of Electromagnetic Space Security, Chengdu 610036, China
    3. School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China
  • Received:2024-06-26 Online:2025-07-16 Published:2025-07-22
  • Contact: Wei ZHANG

摘要:

有效抑制接收机中混叠的背景信号, 对关键重要信号的检测至关重要。现有方法缺乏对信号上下文信息的有效利用, 难以解决噪声环境下单通道时频交叠的背景信号抑制问题。对此,从中频时域信号出发, 提出一种基于双路径特征融合的掩码抑制(dual-path feature fusion mask-based suppression, DPFF-MS)算法。该算法利用神经网络拟合掩码抑制模型, 实现背景信号抑制。通过一组卷积编解码器实现信号的高维变换和逆变换, 降低噪声影响; 设计一种双路径特征融合(dual-path feature fusion, DPFF)模块, 利用不同路径的长短时记忆(long short-term memory, LSTM)网络交替提取局部特征和全局上下文信息, 并采用迭代注意特征融合(iterative attention feature fusion, iAFF)优化不同尺度特征融合过程, 以充分利用信号脉内和脉间信息, 解决时频交叠情况下的抑制问题。实验结果表明, 相较其他信号处理方法和神经网络模型, 所提模型对尺度不变信号源噪比(scale-invariant source-to-noise ratio, SI-SNR)和背景脉冲抑制率两个指标都有显著提升; 且极大地减少了模型参数, 使其易于部署, 具备较高应用价值。

关键词: 电子侦察, 背景信号抑制, 深度学习, 多尺度特征融合

Abstract:

It is vital for the detection of critical and important signals to suppress background signals at the end of receiver effectively. Current methods inadequately utilize signal context information, rendering it challenging to address the issue of background signal suppression of single channel in noisy environments and time-frequency overlaps. To regard this, a dual-path feature fusion mask-based suppression (DPFF-MS) algorithm is proposed, utilizing mid-frequency time-domain signals. The algorithm utilizes a neural network to fit the mask suppression model, effectively suppressing background signals. The high-dimensional transformation and inverse transformation of signals can be enabled by the employment of a suite of convolutional encoder-decoder networks, diminishing the adverse effects of noise. A dual-path feature fusion (DPFF) module is developed, which leverages long short-term memory (LSTM) networks of varying paths to alternately extract both local features and global contextual information. An iterative attention feature fusion (iAFF) is used to optimize the process of fusing features of different scales, fully exploiting the intra-pulse and inter-pulse information to address the suppression issue in time-frequency overlapping environments. The experimental results indicate that, in comparison to other signal processing approaches and neural network models, the proposed model shows significant enhancements in terms of scale-invariant source-to-noise ratio (SI-SNR) and background pulse suppression rate. Furthermore, it significantly reduces the number of model parameters, making it straightforward to deploy and possess high application value.

Key words: electronic reconnaissance, suppression of background signal, deep learning, multi-scale feature fusion

中图分类号: