quotation:[Copy]
[Copy]
【Print page】 【Download 【PDF Full text】 【View/Add Comment】【Download reader】【 Close 】

←Previous page|Page Next →

Back Issue    Advanced search

This Paper:Browse 291   Download 103 本文二维码信息
码上扫一扫!
双骨干轻量抗噪的无人机射频信号识别模型
尹童,伍春,江虹,乔仟,张秋云,曾闵
0
(西南科技大学 信息与控制工程学院,四川 绵阳 621000)
摘要:
针对复杂噪声环境下无人机射频信号识别准确率低、模型复杂度高的问题,提出了一种轻量级异构双骨干卷积神经网络(Heterogeneous Dual-backbone Convolutional Neural Network,HDB-CNN)。该模型以短时傅里叶变换生成的时频图为输入;高效卷积骨干采用通道扩展和残差连接,增强对短时突变特征的捕捉能力;密集连接骨干通过逐层特征复用和多尺度池化,挖掘长时频带关联性;两骨干特征经拼接融合,实现时频特征互补;结合大尺寸全局平均池化压缩参数,降低过拟合风险。模型参数量较MobileNet v3减少57%,适合边缘设备部署。在基于DroneRFa数据集的实验中,HDB-CNN在高斯白噪声下平均准确率较ResNet50提高7.8%,在-9 dB混合高斯白噪声与脉冲噪声下提升8.9%。
关键词:  无人机射频信号识别;异构双骨干网络(HDB-CNN);轻量级卷积神经网络  抗噪识别
DOI:10.20079/j.issn.1001-893x.250418003
基金项目:〖JP2〗国家自然科学基金资助项目(62441111);四川省国际港澳台合作项目(2025YFHZ0199);四川省自然科学基金面上项目(2024NSFSC0476)〖JP〗
A Dual-backbone Lightweight and Noise-robust Model for UAV RF Signal Recognition
YIN Tong,WU Chun,JIANG Hong,QIAO Qian,ZHANG Qiuyun,ZENG Min
(School of Information and Control Engineering,Southwest University of Science and Technology,Mianyang 621000,China)
Abstract:
To address the problems of low recognition accuracy and high model complexity of unmanned aerial vehicle(UAV) radio frequency(RF) signals recognition in complex noise environments,a lightweight heterogeneous dual-backbone convolutional neural network(HDB-CNN) is proposed.This model takes the time-frequency graph generated by short-time Fourier transform(STFT) as input.The efficient convolution backbone adopts channel expansion and residual connections to enhance the capture ability of short-term abrupt features.The densely-connected backbone explores long-term frequency band correlations through layer-by-layer feature reuse and multi-scale pooling.The features of the two backbones are concatenated and fused to achieve complementary time-frequency features,and large-size global average pooling(GAP) is combined to compress parameters and reduce overfitting risk.Compared with MobileNet v3,the model reduces the number of parameters by 57%,enabling its suitability for edge device deployment.In experiments based on the DroneRFa dataset,HDB-CNN improves the average accuracy by 7.8% compared with ResNet50 under Gaussian white noise,and by 8.9% under -9 dB mixed Gaussian white noise and impulse noise.
Key words:  UAV RF signal recognition  heterogeneous dual-backbone convolutional neural network(HDB-CNN)  lightweight CNN  anti-noise identification