上海交通大学学报

上海交通大学学报 >

2022 , Vol. 56 >Issue 7: 877 - 885

DOI: https://doi.org/10.16183/j.cnki.jsjtu.2021.209

电子信息与电气工程

基于双通道卷积神经网络的雷达信号识别

展开
  • 中国计量大学 信息工程学院,杭州 310018
全大英(1979-),男,浙江省丽水市人,高级工程师,从事无线测试系统设计、电子侦察信号处理和智能频谱测量计量研究. E-mail: stu_cjlu_sp@outlook.com.

收稿日期: 2021-06-15

  网络出版日期: 2022-08-16

基金资助

浙江省自然科学基金项目(LQ20F020021);浙江省电磁波信息技术与计量检测重点实验室开放式项目(2019KF0003)

收起

Radar Signal Recognition Based on Dual Channel Convolutional Neural Network

Expand
  • College of Information Engineering, China Jiliang University, Hangzhou 310018, China

Received date: 2021-06-15

  Online published: 2022-08-16

Fold

摘要

为解决在低信噪比下特征提取困难、雷达信号识别率低的问题,提出了一种基于Choi-Williams分布(CWD)和多重同步压缩变换(MSST)的双通道卷积神经网络模型.模型通过对雷达信号进行CWD和MSST时频分析,分别获取二维时频图像并进行预处理,然后送入双通道卷积神经网络进行深度特征提取,最后将两路通道获取的特征进行融合,通过卷积神经网络分类器实现对雷达信号的分类识别.仿真结果表明:在信噪比为 -10 dB时,所提模型整体识别准确率能达到96%以上,其在低信噪比下表现优异.

关键词： 低信噪比; Choi-Williams分布; 多重同步压缩变换; 双通道卷积神经网络

本文引用格式

全大英, 陈赟, 唐泽雨, 李世通, 汪晓锋, 金小萍 . 基于双通道卷积神经网络的雷达信号识别[J]. 上海交通大学学报, 2022 , 56(7) : 877 -885 . DOI: 10.16183/j.cnki.jsjtu.2021.209

Abstract

In order to solve the problems of difficult feature extraction and low recognition rate of radar signal at low signal-to-noise ratios, a dual channel convolutional neural network model based on Choi-Williams distribution (CWD) and multisynchrosqueezing transform (MSST) is proposed, which obtains two-dimensional time-frequency images by CWD and MSST time-frequency analyses on radar signals. Respectively, the time-frequency images are preprocessed and sequencely fed to a dual channel convolutional neural network for deep feature extraction. Finally, the features acquired by the two channels are fused, and the radar signal is classified and recognized through the convolutional neural network classifier. The simulation results show that when the signal-to-noise ratio is -10 dB, the overall recognition accuracy can reach above 96%, which is excellent at low signal-to-noise ratios.

Key words： low signal-to-noise ratios; Choi-Williams distribution (CWD); multisynchrosqueezing transform (MSST); dual-channel convolutional neural network

参考文献

[1] 王军锋, 刘兴钊. 合成孔径雷达运动目标检测的研究进展[J]. 上海交通大学学报, 2018, 52(10): 1273-1279.
[1] WANG Junfeng, LIU Xingzhao. Development in SAR moving-target detection[J]. Journal of Shanghai Jiao Tong University, 2018, 52(10): 1273-1279.
[2] IGLESIAS V, GRAJAL J, ROYER P, et al. Real-time low-complexity automatic modulation classifier for pulsed radar signals[J]. IEEE Transactions on Aerospace and Electronic Systems, 2015, 51(1): 108-126.
[3] 李波波, 幸涛. 基于报文数据的雷达侦察系统侦察能力评估[J]. 现代信息科技, 2020, 4(23): 54-57.
[3] LI Bobo, XING Tao. Evaluation on reconnaissance capability of radar reconnaissance system based on message data[J]. Modern Informationn Technology, 2020, 4(23): 54-57
[4] 孟磊, 曲卫, 蔡凯, 等. 基于机器学习的雷达辐射源识别方法综述[J]. 兵器装备工程学报, 2020, 41(10): 16-21.
[4] MENG Lei, QU Wei, CAI Kai, et al. Overview of radar emitter identification based on machine learning[J]. Journal of Ordnance Equipment Engineering, 2020, 41(10): 16-21.
[5] JIANG W, REN Y H, LIU Y, et al. A method of radar target detection based on convolutional neural network[J]. Neural Computing and Applications, 2021, 33(16): 9835-9847.
[6] ZHU J D, ZHAO Y J, TANG J. Automatic recognition of radar signals based on time-frequency image character[C]∥IET International Radar Conference 2013. Xi’an, China: IET, 2013: 1-6.
[7] LIU Z P, WANG L D, FENG Y T, et al. A recognition method for time-frequency overlapped waveform-agile radar signals based on matrix transformation and multi-scale center point detection[J]. Applied Acoustics, 2021, 175: 107855.
[8] 陈昌孝, 何明浩, 徐璟, 等. 基于模糊函数相像系数的雷达辐射源信号分选[J]. 电波科学学报, 2014, 29(2): 260-264.
[8] CHEN Changxiao, HE Minghao, XU Jing, et al. Radar emitter signal sorting based on resemblance coefficient of ambiguity function[J]. Chinese Journal of Radio Science, 2014, 29(2): 260-264.
[9] 王功明, 陈世文, 黄洁, 等. 基于多重同步压缩变换的雷达辐射源分选识别[J]. 现代雷达, 2020, 42(3): 49-56.
[9] WANG Gongming, CHEN Shiwen, HUANG Jie, et al. Radar emitter sorting and recognition based on multi-synchrosqueezing transform[J]. Modern Radar, 2020, 42(3): 49-56.
[10] VERMA S, AGRAWAL R. Deep neural network in medical image processing[M]∥Handbook of deep learning in biomedical engineering. Amsterdam, USA: Elsevier, 2021: 271-292.
[11] 王功明, 陈世文, 黄洁, 等. 基于迁移深度学习的雷达信号分选识别[J]. 计算机科学与应用, 2019, 9(9): 1761-1788.
[11] WANG Gongming, CHEN Shiwen, HUANG Jie, et al. Radar signal sorting and recognition based on transferred deep learning[J]. Computer Science and Application, 2019, 9(9): 1761-1788.
[12] 谢存祥, 张立民, 钟兆根. 基于时频特征提取和残差神经网络的雷达信号识别[J]. 系统工程与电子技术, 2021, 43(4): 917-926.
[12] XIE Cunxiang, ZHANG Limin, ZHONG Zhaogen. Radar signal recognition based on time-frequency feature extraction and residual neural network[J]. Systems Engineering and Electronics, 2021, 43(4): 917-926.
[13] WEI S J, QU Q Z, SU H, et al. Intra-pulse modulation radar signal recognition based on CLDN network[J]. IET Radar, Sonar & Navigation, 2020, 14(6): 803-810.
[14] ALASKAR H. Deep learning-based model architecture for time-frequency images analysis[J]. International Journal of Advanced Computer Science and Applications, 2018, 9(12): 486-494.
[15] FENG Z P, LIANG M, CHU F L. Recent advances in time-frequency analysis methods for machinery fault diagnosis: A review with application examples[J]. Mechanical Systems and Signal Processing, 2013, 38(1): 165-205.
[16] LIU Y J, XIAO P, WU H C, et al. LPI radar signal detection based on radial integration of Choi-Williams time-frequency image[J]. Journal of Systems Engineering and Electronics, 2015, 26(5): 973-981.
[17] YU G, WANG Z H, ZHAO P. Multisynchrosqueezing transform[J]. IEEE Transactions on Industrial Electronics, 2019, 66(7): 5441-5455.
[18] LI D X, JIA H Y, YE Y C, et al. High power microwave signal detection based on second order multisynchrosqueezing transform[J]. Journal of Physics: Conference Series, 2020, 1617(1): 012049.
[19] LI Z Y. Modulation recognition of communication signals based on deep learning joint model[J]. Journal of Physics: Conference Series, 2021, 1856(1): 012042.
Options
文章导航

/

〈 〉