留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

基于多域特征的多雷达信号自动识别方法

杨瑾 郝新红 陈齐乐

杨瑾,郝新红,陈齐乐. 基于多域特征的多雷达信号自动识别方法[J]. 北京航空航天大学学报,2024,50(3):931-939 doi: 10.13700/j.bh.1001-5965.2022.0294
引用本文: 杨瑾,郝新红,陈齐乐. 基于多域特征的多雷达信号自动识别方法[J]. 北京航空航天大学学报,2024,50(3):931-939 doi: 10.13700/j.bh.1001-5965.2022.0294
YANG J,HAO X H,CHEN Q L. Automatic recognition method of multi-radar signals based on multi-domain features[J]. Journal of Beijing University of Aeronautics and Astronautics,2024,50(3):931-939 (in Chinese) doi: 10.13700/j.bh.1001-5965.2022.0294
Citation: YANG J,HAO X H,CHEN Q L. Automatic recognition method of multi-radar signals based on multi-domain features[J]. Journal of Beijing University of Aeronautics and Astronautics,2024,50(3):931-939 (in Chinese) doi: 10.13700/j.bh.1001-5965.2022.0294

基于多域特征的多雷达信号自动识别方法

doi: 10.13700/j.bh.1001-5965.2022.0294
基金项目: 国家自然科学基金(61871414)
详细信息
    通讯作者:

    E-mail:haoxinhong@bit.edu.cn

  • 中图分类号: V221+.3;TB553

Automatic recognition method of multi-radar signals based on multi-domain features

Funds: National Natural Science Foundation of China (61871414)
More Information
  • 摘要:

    为解决复杂电磁环境中多台雷达在相似的频段上同时发射各自的信号,导致侦察接收信号在时域和频域上重叠的问题,提出一种低信噪比(SNR)下自动调制识别(MR)方法。通过接收脉冲间列快速傅里叶变换(FFT)将接收信号的能量集中在各自的多普勒频率上,以达到分离多个截获信号的目的;将每个信号的Wigner-Ville分布(WVD)和模糊函数(AF)作为一幅图像的2层同时发送到训练后的残差神经网络(ResNet),以解决某些类型的信号仅采用单一时频分布时识别精度低的问题。理论分析和仿真结果表明:所提方法不仅能有效分离时域和频域重叠的多个雷达信号,而且能在SNR为−10 dB的条件下准确识别其调制模式。

     

  • 图 1  侦察机的作战场景

    Figure 1.  Reconnaissance aircraft in action

    图 2  多雷达信号MR方法原理图

    Figure 2.  Schematic diagram of multi-radar signal MR method

    图 3  基于ResNet的雷达信号识别模型

    Figure 3.  Radar signal recognition model based on ResNet

    图 4  FFT结果

    Figure 4.  FFT results

    图 5  分离出的4个雷达信号

    Figure 5.  Four isolated radar signals

    图 6  8种雷达信号的WVD

    Figure 6.  WVD of eight radar signals

    图 7  不同码元宽度BPSK信号的WVD

    Figure 7.  WVD of BPSK signals with different bit widths

    图 8  不同码元宽度下HM信号的WVD

    Figure 8.  WVD of HM signal at different bit widths

    图 9  WVD下不同雷达信号的MR精度

    Figure 9.  MR accuracy of different radar signals with WVD

    图 10  8种雷达信号的AF

    Figure 10.  AF of eight radar signals

    图 11  WVD和AF下不同雷达信号的MR精度

    Figure 11.  MR accuracy of different radar signals with WVD and AF

    图 12  不同方法的调制识别精度

    Figure 12.  Modulation identification accuracy of different methods

    表  1  雷达信号的仿真参数

    Table  1.   Simulation parameters of radar signal

    雷达 种类 调制
    模式
    带宽/MHz 重复
    周期/μs
    脉冲
    宽度/μs
    径向速度/
    ( m·s−1)
    雷达 1 地面 LFM 50 20 4 200
    雷达 2 地面 BPSK 20 15.5 1.55 150
    雷达 3 空中 Pulse 0.5 20 2 500
    雷达 4 空中 FMCW 30 20 450
    下载: 导出CSV

    表  2  雷达信号的仿真参数

    Table  2.   Simulation parameters of radar signal

    调制类型 PW/μs 带宽/MHz 频率/kHz SNR/dB
    SinFM
    Pulse
    0.5~4 20~50 10~120 −10~10
    Pulse 0.5~4 1~10 10~120 −10~10
    LFM
    Pulse
    0.5~4 20~50 10~120 −10~10
    BPSK
    Pulse
    0.5~4
    10~50
    10~120
    −10~10
    BPSK
    CW
    10~50
    10~120
    −10~10
    TriFM
    CW
    20~50
    10~120
    −10~10
    RamFM
    CW
    20~50
    10~120
    −10~10
    HM
    CW
    20~50
    10~120
    −10~10
    下载: 导出CSV

    表  3  网络模型参数

    Table  3.   Network model parameters

    输入大小 输出大小
    Input 128×128×2 128×128×2
    Conv2D 128×128×2 128×128×32
    Residual Unit1 128×128×32 128×128×32
    Residual Unit2 128×128×32 64×64×32
    Residual Unit3 64×64×32 64×64×32
    Residual Unit4 64×64×32 64×64×32
    Residual Unit5 64×64×32 32×32×32
    Residual Unit6 32×32×32 32×32×32
    Residual Unit7 32×32×32 32×32×32
    Residual Unit8 32×32×32 32×32×32
    Average Pooling2D 32×32×32 4×4×32
    Flatten 4×4×32 512
    Dense 512 8
    Sigmoid 8 8
    下载: 导出CSV
  • [1] HAYKIN S. Cognitive radar: A way of the future[J]. IEEE Signal Processing Magazine, 2006, 23(1): 30-40. doi: 10.1109/MSP.2006.1593335
    [2] ZHANG G X, RONG H N, JIN W D, et al. Radar emitter signal recognition based on resemblance coefficient features[C]//Proceedings of the International Conference on Rough Sets and Current Trends in Computing. Berlin: Springer, 2004: 665-670.
    [3] HORNE C, RITCHIE M, GRIFFITHS H. Proposed ontology for cognitive radar systems[J]. IET Radar, Sonar & Navigation, 2018, 12(12): 1363-1370.
    [4] XU Z, SHI Q. Interference mitigation for automotive radar using orthogonal noise waveforms[J]. IEEE Geoscience and Remote Sensing Letters, 2018, 15(1): 137-141. doi: 10.1109/LGRS.2017.2777962
    [5] ZHANG G X, LI X. A new recognition system for radar emitter signals[J]. Kybernetes, 2012, 41(9): 1351-1360. doi: 10.1108/03684921211275405
    [6] WEST N E, O’SHEA T. Deep architectures for modulation recognition[C]//Proceedings of the 2017 IEEE International Symposium on Dynamic Spectrum Access Networks. Piscataway: IEEE Press, 2017: 1-6.
    [7] DANG H V, KINSNER W. An analytical multiobjective optimization of joint spectrum sensing and power control in cognitive radio networks[C]//Proceedings of the 2015 IEEE 14th International Conference on Cognitive Informatics & Cognitive Computing. Piscataway: IEEE Press, 2015: 39-48.
    [8] GRILO A, MACEDO M, SEBASTIÃO P, et al. Electronic protection and routing optimization of MANETs operating in an electronic warfare environment[J]. Ad Hoc Networks, 2007, 5(7): 1031-1045. doi: 10.1016/j.adhoc.2006.05.002
    [9] KONG S H, KIM M, HOANG L M, et al. Automatic LPI radar waveform recognition using CNN[J]. IEEE Access, 2018, 6: 4207-4219. doi: 10.1109/ACCESS.2017.2788942
    [10] ZHANG M, LIU L T, DIAO M. LPI radar waveform recognition based on time-frequency distribution[J]. Sensors, 2016, 16(10): 1682. doi: 10.3390/s16101682
    [11] GRANGER E, RUBIN M A, GROSSBERG S, et al. Radar ESM with a what-and-where fusion neural network[C]//Neural Networks for Signal Processing XI: Proceedings of the 2001 IEEE Signal Processing Society Workshop. Piscataway: IEEE Press, 2002: 539-548.
    [12] ZAERIN M, SEYFE B. Multiuser modulation classification based on cumulants in additive white Gaussian noise channel[J]. IET Signal Processing, 2012, 6(9): 815-823. doi: 10.1049/iet-spr.2011.0357
    [13] O’SHEA T J, ROY T, CLANCY T C. Over-the-air deep learning based radio signal classification[J]. IEEE Journal of Selected Topics in Signal Processing, 2018, 12(1): 168-179. doi: 10.1109/JSTSP.2018.2797022
    [14] ZHU J D, ZHAO Y J, TANG J. Automatic recognition of radar signals based on time-frequency image character[C]//Proceedings of the IET International Radar Conference. London: IET, 2013: 1-6.
    [15] YU H H, YAN X P, LIU S K, et al. Radar emitter multi-label recognition based on residual network[J]. Defence Technology, 2022, 18(3): 410-417.
    [16] QU Z Y, HOU C F, HOU C B, et al. Radar signal intra-pulse modulation recognition based on convolutional neural network and deep Q-learning network[J]. IEEE Access, 2020, 8: 49125-49136. doi: 10.1109/ACCESS.2020.2980363
    [17] WANG Q, DU P F, YANG J Y, et al. Transferred deep learning based waveform recognition for cognitive passive radar[J]. Signal Processing, 2019, 155: 259-267. doi: 10.1016/j.sigpro.2018.09.038
    [18] ZHU M T, LI Y J, PAN Z S, et al. Automatic modulation recognition of compound signals using a deep multi-label classifier: a case study with radar jamming signals[J]. Signal Processing, 2020, 169: 107393.
    [19] LIU S K, YAN X P, LI P, et al. Radar emitter recognition based on SIFT position and scale features[J]. IEEE Transactions on Circuits and Systems II: Express Briefs, 2018, 65(12): 2062-2066.
    [20] ZAMIR S W, ARORA A, KHAN S, et al. Multi-stage progressive image restoration[C]//Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE Press, 2021: 14816-14826.
    [21] PETROV N, JORDANOV I, ROE J. Radar emitter signals recognition and classification with feedforward networks[J]. Procedia Computer Science, 2013, 22: 1192-1200. doi: 10.1016/j.procs.2013.09.206
    [22] GOULDIEFF V, PALICOT J, DAUMONT S. Blind modulation classification for cognitive satellite in the spectral coexistence context[J]. IEEE Transactions on Signal Processing, 2017, 65(12): 3204-3217. doi: 10.1109/TSP.2017.2688976
    [23] GUO Q, NAN P L, WAN J. Signal classification method based on data mining for multi-mode radar[J]. Journal of Systems Engineering and Electronics, 2016, 27(5): 1010-1017. doi: 10.21629/JSEE.2016.05.09
    [24] CHEN K Y, ZHANG S N, ZHU L Z, et al. Modulation recognition of radar signals based on adaptive singular value reconstruction and deep residual learning[J]. Sensors, 2021, 21(2): 449. doi: 10.3390/s21020449
    [25] ZHOU Z W, HUANG G M, CHEN H Y, et al. Automatic radar waveform recognition based on deep convolutional denoising auto-encoders[J]. Circuits, Systems, and Signal Processing, 2018, 37(9): 4034-4048. doi: 10.1007/s00034-018-0757-0
    [26] PAN Z S, WANG S F, ZHU M T, et al. Automatic waveform recognition of overlapping LPI radar signals based on multi-instance multi-label learning[J]. IEEE Signal Processing Letters, 2020, 27: 1275-1279. doi: 10.1109/LSP.2020.3009195
    [27] LIU Z P, LI L C, XU H Y, et al. A method for recognition and classification for hybrid signals based on Deep Convolutional Neural Network[C]//Proceedings of the 2018 International Conference on Electronics Technology. Piscataway: IEEE Press, 2018: 325-330.
    [28] GUO Q, SUN J, XU J F, et al. EfficientDeRain: Learning pixel-wise dilation filtering for high-efficiency single-image deraining[C]//Proceedings of the AAAI Conference on Artificial Intelligence. Washton, D. C. : AAAI, 2021: 35(2): 1487-1495.
    [29] BAKO S, VOGELS T, MCWILLIAMS B, et al. Kernel-predicting convolutional networks for denoising Monte Carlo renderings[J]. ACM Transactions on Graphics, 2017, 36(4): 1-14.
  • 加载中
图(12) / 表(3)
计量
  • 文章访问数:  604
  • HTML全文浏览量:  93
  • PDF下载量:  3
  • 被引次数: 0
出版历程
  • 收稿日期:  2022-04-29
  • 录用日期:  2022-06-29
  • 网络出版日期:  2022-08-03
  • 整期出版日期:  2024-03-27

目录

    /

    返回文章
    返回
    常见问答