一种基于多模态OAM波束的目标特征智能识别方法

周宁宁 朱士涛 年毅恒 田春明 张安学

周宁宁, 朱士涛, 年毅恒, 等. 一种基于多模态OAM波束的目标特征智能识别方法[J]. 雷达学报, 2021, 10(5): 760–772. doi: 10.12000/JR21056
引用本文: 周宁宁, 朱士涛, 年毅恒, 等. 一种基于多模态OAM波束的目标特征智能识别方法[J]. 雷达学报, 2021, 10(5): 760–772. doi: 10.12000/JR21056
ZHOU Ningning, ZHU Shitao, NIAN Yiheng, et al. An intelligent target feature recognition method based on multi-mode OAM beams[J]. Journal of Radars, 2021, 10(5): 760–772. doi: 10.12000/JR21056
Citation: ZHOU Ningning, ZHU Shitao, NIAN Yiheng, et al. An intelligent target feature recognition method based on multi-mode OAM beams[J]. Journal of Radars, 2021, 10(5): 760–772. doi: 10.12000/JR21056

一种基于多模态OAM波束的目标特征智能识别方法

doi: 10.12000/JR21056
基金项目: 国家自然科学基金(62071371, 61801368, 61801366),超高速电路设计与电磁兼容教育部重点实验室(LHJJ/2020-04),雷达信号处理国防科技重点实验室
详细信息
    作者简介:

    周宁宁(1996–),女,河南周口人,西安交通大学信息与通信工程学院在读硕士研究生。主要研究方向为基于OAM的关联成像算法、传输超表面产生OAM

    朱士涛(1980–),男,河北沧州人,博士,西安交通大学信息与通信工程学院副研究员,硕士生导师。主要研究方向为新型雷达信号处理方法、人工智能成像算法、微波关联成像、超材料孔径天线及微波量子雷达

    年毅恒(1995–),男,安徽蚌埠人,硕士,西安交通大学信息与通信工程学院在读博士研究生。主要研究方向为微波关联成像、雷达信号处理

    田春明(1974–),男,吉林通化人,博士,西安交通大学信息与通信工程学院讲师,硕士生导师。主要研究方向为电磁场与微波技术、计算电磁学、高功率微波技术、电磁辐射和散射等

    张安学(1972–),男,河南安阳人,博士,西安交通大学电磁与信息技术研究所教授,博士生导师。主要研究方向为新型天线与分集技术、移动通信微波射频技术、智能雷达信号处理、多天线通信系统与阵列信号处理、微波测试理论与系统设计等

    通讯作者:

    朱士涛 shitaozhu@xjtu.edu.cn

  • 责任主编:沙威 Corresponding Editor: SHA Wei
  • 中图分类号: TN95

An Intelligent Target Feature Recognition Method Based on Multi-mode OAM Beams

Funds: The National Natural Science Foundation of China (62071371, 61801368, 61801366), The Key Laboratory of High-Speed Circuit Design and EMC Ministry of Education (LHJJ/2020-04), The National Key Lab of Radar Signal Processing
More Information
  • 摘要: 高效率目标探测需要借助探测信号的低相关性空间调制,调制数量大且具有时间独立性。携带轨道角动量(OAM)的涡旋波束具有无穷多种模态且不同模态之间相互正交,借助强色散材料可以实现频率域的多模态OAM波束产生。该文首先对OAM的传播特性进行推导,给出了符合探测需求的多模态OAM波束源特征;在此基础上,研究了不同模态的OAM波束在3种不同应用场景下目标反射回波信号特性,采用卷积神经网络对不同反射场景下的数据特征进行提取,实现了对未知场景的判断及场景内的目标识别,并进行了抗噪性能分析。实验结果表明:理想状态下,网络对目标场景判断的准确率可达$97.5\% $;各反射场景中的两个相邻目标的间隔大于某一阈值时,网络对目标位置的识别准确率均高于$80\% $。但目标识别效果有环境依赖性,当${\rm{SNR}} < 20\;{\rm{dB}}$时,3种场景内的目标识别准确率均大幅降低。

     

  • 图  1  均匀圆形阵列产生OAM波束的示意图

    Figure  1.  Structure diagram of OAM beam generated by uniform circular array

    图  2  2模态和3模态OAM波束的幅相分布

    Figure  2.  Amplitude and phase distribution of OAM beams with 2-mode and 3-mode

    图  3  3种观测面的场景示意图

    Figure  3.  Scene sketch of three observation planes

    图  4  3种观测面的观测结果

    Figure  4.  Observation results of three observation planes

    图  5  径向相位变化示意图

    Figure  5.  Schematic diagram of radial phase variation

    图  6  观测截面示意图

    Figure  6.  Schematic diagram of observation section

    图  7  传统波束与OAM波束经不同反射面的回波方向图

    Figure  7.  Echo pattern of traditional beam and OAM beam through different reflector

    图  8  3种反射场景示意图

    Figure  8.  Schematic diagram of three reflection scenes

    图  9  反射场景1中观测点处反射信息

    Figure  9.  Reflection information at observation point in reflection scene 1

    图  10  反射场景2中观测点处反射信息

    Figure  10.  Reflection information at observation point in reflection scene 2

    图  11  反射场景3中观测点处反射信息

    Figure  11.  Reflection information at observation point in reflection scene 3

    图  12  网络结构示意图

    Figure  12.  Schematic diagram of network structure

    图  13  损失函数的变化曲线

    Figure  13.  Variation curve of loss function

    图  14  信噪比为10 dB时,2模态OAM波束的幅相特性

    Figure  14.  Amplitude and phase characteristics of 2-mode OAM beam when SNR is 10 dB

    图  15  信噪比对场景判断的影响

    Figure  15.  Influence of SNR on scene judgment

    图  16  信噪比对准确判断数目的影响

    Figure  16.  Influence of SNR on number of correct judgments

    图  17  样本数据获取及标签设置示意图

    Figure  17.  Schematic diagram of sample data acquisition and label setting

    图  18  目标间隔对场景内目标位置识别准确率的影响

    Figure  18.  Influence of target interval on accuracy of target location recognition in scene

    图  19  信噪比对场景内目标位置识别准确率的影响

    Figure  19.  Influence of SNR on the accuracy of target position recognition in scene

    表  1  阵列的半径

    Table  1.   Radius of array

    模态$ l $阵列半径R (m)
    10.0450
    20.0747
    30.1026
    40.1302
    50.1569
    60.1836
    70.2097
    80.2361
    90.2619
    下载: 导出CSV

    表  2  OAM波束经反射面1的反射角

    Table  2.   Reflection angle of OAM beam passing through reflector 1

    $ l $$ \theta $ (°)$ \mathrm{\varphi } $ (°)
    111.252389.9940
    211.252389.9819
    311.252389.9819
    411.252389.9699
    511.252389.9579
    611.252389.9579
    711.252389.9458
    811.252389.9458
    下载: 导出CSV

    表  3  发射阵列及卷积神经网络的相关参数

    Table  3.   Parameters of transmit array and convolutional neural network

    实验参数参数值
    频率 (GHz)10
    阵元数目 (个)40
    反射面尺寸$10\lambda $
    迭代次数100
    反向传播学习率1
    下载: 导出CSV
  • [1] 郭桂蓉, 胡卫东, 杜小勇. 基于电磁涡旋的雷达目标成像[J]. 国防科技大学学报, 2013, 35(6): 71–76. doi: 10.3969/j.issn.1001-2486.2013.06.013

    GUO Guirong, HU Weidong, and DU Xiaoyong. Electromagnetic vortex based radar target imaging[J]. Journal of National University of Defense Technology, 2013, 35(6): 71–76. doi: 10.3969/j.issn.1001-2486.2013.06.013
    [2] POYNTING J H. The wave motion of a revolving shaft, and a suggestion as to the angular momentum in a beam of circularly polarised light[J]. Proceedings of the Royal Society of London. Series A, Containing Papers of a Mathematical and Physical Character, 1909, 82(557): 560–567. doi: 10.1098/rspa.1909.0060
    [3] ALLEN L, BEIJERSBERGEN M W, SPREEUW R J C, et al. Orbital angular momentum of light and the transformation of Laguerre-Gaussian laser modes[J]. Physical Review A, 1992, 45(11): 8185–8189. doi: 10.1103/PhysRevA.45.8185
    [4] 付维杰. 基于超表面及波导结构的多阶OAM生成[D]. [硕士论文], 浙江大学, 2019: 11–13.

    FU Weijie. Multi-order OAM generation based on metasurfaces and waveguide structure[D]. [Master dissertation], Zhejiang University, 2019: 11–13.
    [5] 孙学宏, 李强, 庞丹旭, 等. 轨道角动量在无线通信中的研究新进展综述[J]. 电子学报, 2015, 43(11): 2305–2314. doi: 10.3969/j.issn.0372-2112.2015.11.025

    SUN Xuehong, LI Qiang, PANG Danxu, et al. New research progress of the orbital angular momentum technology in wireless communication: A survey[J]. Acta Electronica Sinica, 2015, 43(11): 2305–2314. doi: 10.3969/j.issn.0372-2112.2015.11.025
    [6] 袁铁柱. 涡旋电磁波在雷达成像中的应用研究[D]. [博士论文], 国防科学技术大学, 2017: 94–101.

    YUAN Tiezhu. Research on radar imaging using electromagnetic vortex wave[D]. [Ph. D. dissertation], University of Defense Science and Technology, 2017: 94–101.
    [7] WANG Jianqiu, LIU Kang, CHENG Yongqiang, et al. Vortex SAR imaging method based on OAM beams design[J]. IEEE Sensors Journal, 2019, 19(24): 11873–11879. doi: 10.1109/JSEN.2019.2937976
    [8] LIU Hongyan, LIU Kang, CHENG Yongqiang, et al. Microwave vortex imaging based on dual coupled OAM beams[J]. IEEE Sensors Journal, 2020, 20(2): 806–815. doi: 10.1109/JSEN.2019.2943698
    [9] 杜永兴, 仝宗俊, 秦岭, 等. 基于改进BP算法的电磁涡旋成像方法[J]. 雷达科学与技术, 2020, 18(5): 539–545. doi: 10.3969/j.issn.1672-2337.2020.05.012

    DU Yongxing, TONG Zongjun, QIN Ling, et al. Electromagnetic vortex imaging method based on improved BP algorithm[J]. Radar Science and Technology, 2020, 18(5): 539–545. doi: 10.3969/j.issn.1672-2337.2020.05.012
    [10] LIU Hongyan, WANG Yu, WANG Jianqiu, et al. Electromagnetic vortex enhanced imaging using fractional OAM beams[J]. IEEE Antennas and Wireless Propagation Letters, 2021, 20(6): 948–952. doi: 10.1109/LAWP.2021.3067914
    [11] YU Meiping, HAN Yiping, CUI Zhiwei, et al. Electromagnetic scattering by multiple dielectric particles under the illumination of unpolarized high-order Bessel vortex beam[J]. Journal of Quantitative Spectroscopy and Radiative Transfer, 2017, 195: 107–113. doi: 10.1016/j.jqsrt.2017.01.005
    [12] YAO Yu, LIANG Xianling, ZHU Maohua, et al. Analysis and experiments on reflection and refraction of orbital angular momentum waves[J]. IEEE Transactions on Antennas and Propagation, 2019, 67(4): 2085–2094. doi: 10.1109/TAP.2019.2896760
    [13] LIU Kang, LIU Hongyan, SHA W E I, et al. Backward scattering of electrically large standard objects illuminated by OAM beams[J]. IEEE Antennas and Wireless Propagation Letters, 2020, 19(7): 1167–1171. doi: 10.1109/LAWP.2020.2993687
    [14] GOODFELLOW I, BENGIO Y, COURVILLE A, 赵申剑, 黎彧君, 符天凡, 等译. 深度学习[M]. 北京: 人民邮电出版社, 2017: 11–22.

    GOODFLOW I, BENGIO Y, COURVILLE A, ZHAO Shenjian, LI Yujun, FU Tianfan, et al. translation. Deep Learning[M]. Beijing: People’s Posts and Telecommunications Press, 2017: 11–22.
    [15] LECUN Y, BOTTOU L, BENGIO Y, et al. Gradient-based learning applied to document recognition[J]. Proceedings of the IEEE, 1998, 86(11): 2278–2324. doi: 10.1109/5.726791
    [16] KRIZHEVSKY A, SUTSKEVER I, and HINTON G E. ImageNet classification with deep convolutional neural networks[C]. The 25th International Conference on Neural Information Processing Systems, Red Hook, United States, 2012: 1097–1105.
    [17] KE Hengjin, CHEN Dan, LI Xiaoli, et al. Towards brain big data classification: Epileptic EEG identification with a lightweight VGGNet on global MIC[J]. IEEE Access, 2018, 6: 14722–14733. doi: 10.1109/ACCESS.2018.2810882
    [18] KIM Y G and CHA E Y. Streamlined GoogLeNet algorithm based on CNN for Korean character recognition[J]. Journal of the Korea Institute of Information and Communication Engineering, 2016, 20(9): 1657–1665. doi: 10.6109/jkiice.2016.20.9.1657
    [19] CHEN Hao, DOU Qi, YU Lequan, et al. VoxResNet: Deep voxelwise residual networks for brain segmentation from 3D MR images[J]. NeuroImage, 2018, 170: 446–455. doi: 10.1016/j.neuroimage.2017.04.041
    [20] SHI Hongyu, WANG Luyi, PENG Gantao, et al. Generation of multiple modes microwave vortex beams using active metasurface[J]. IEEE Antennas and Wireless Propagation Letters, 2019, 18(1): 59–63. doi: 10.1109/LAWP.2018.2880732
    [21] 陈亚南, 董晓龙. 基于轨道角动量的雷达关联成像技术研究[J]. 电子设计工程, 2018, 26(6): 109–113, 119. doi: 10.3969/j.issn.1674-6236.2018.06.024

    CHEN Ya’nan and DONG Xiaolong. Radar correlated imaging based on orbital angular momentum[J]. Electronic Design Engineering, 2018, 26(6): 109–113, 119. doi: 10.3969/j.issn.1674-6236.2018.06.024
    [22] 谢处方, 饶克谨. 电磁场与电磁波[M]. 3版. 北京: 高等教育出版社, 1999: 333–334.

    XIE Chufang and RAO Kejin. Electromagnetic Field and Electromagnetic Wave[M]. 3rd ed. Beijing: Higher Education Press, 1999: 333–334.
    [23] 李玉鑑, 沈成恺, 杨红丽, 等. 初始化卷积神经网络的主成分洗牌方法[J]. 北京工业大学学报, 2017, 43(1): 22–27. doi: 10.11936/bjutxb2016060070

    LI Yujian, SHEN Chengkai, YANG Hongli, et al. PCA shuffling initialization of convolutional neural networks[J]. Journal of Beijing University of Technology, 2017, 43(1): 22–27. doi: 10.11936/bjutxb2016060070
  • 加载中
图(19) / 表(3)
计量
  • 文章访问数:  391
  • HTML全文浏览量:  61
  • PDF下载量:  114
  • 被引次数: 0
出版历程
  • 收稿日期:  2021-04-30
  • 修回日期:  2021-07-09
  • 网络出版日期:  2021-07-20
  • 刊出日期:  2021-10-28

目录

    /

    返回文章
    返回