采用极化特征的通信辐射源个体识别方法Individual Identification Method of Communication Emitters Using Polarization Feature
张梓轩,齐子森,许华,史蕴豪,梁佳
摘要(Abstract):
针对现有方法在通信辐射源空、时、频、能域特征相近甚至相同情况下,个体分类识别效果不佳的问题,提出了一种采用极化特征的通信辐射源个体识别方法。通过分析通信辐射源双极化特征表征方法,对通信辐射源的极化信号建模,根据极化信号模型,借鉴幅度-相位法思路,构建了双极化接收系统实现极化信号接收和极化特征提取;通过对极化天线振动引起的通道不一致性进行分析,建立极化通道误差模型,得到含有时变幅相误差的极化信号表示,据此设计了基于自编码器的通道时变幅相误差校正算法,在扰动数据(含时变幅相误差和噪声的数据)与原始数据(只含噪声的数据)双驱动下,学习原始数据深层特征规律,实现对扰动数据的重构,克服了极化特征对通道噪声与时变幅相误差敏感的问题;经过设置的阈值规则进行通信辐射源个体的硬判决分类。仿真实验表明,在信噪比为10 dB时,所提方法对模拟辐射源的个体识别准确率达95%以上。实测数据表明:所提方法在暗室理想情况下,对辐射源个体的识别准确率达99%以上;在实采数据上叠加高斯白噪声、模拟信噪比为10 dB时,个体识别准确率达95%以上,所提方法的有效性得到了验证。
关键词(KeyWords): 极化;时变幅相误差;自编码器;个体识别
基金项目(Foundation): 国家自然科学基金重点资助项目(61971434);; 空军工程大学研究生创新实践基金资助项目(CXJ2022019)
作者(Author): 张梓轩,齐子森,许华,史蕴豪,梁佳
参考文献(References):
- [1] 俞佳宝,胡爱群,朱长明,等.无线通信设备的射频指纹提取与识别方法 [J].密码学报,2016,3(5):433-446.YU Jiabao,HU Aiqun,ZHU Changming,et al.RF fingerprinting extraction and identification of wireless communication devices [J].Journal of Cryptologic Research,2016,3(5):433-446.
- [2] DANEV B,ZANETTI D,CAPKUN S.On physical-layer identification of wireless devices [J].ACM Computing Surveys,2012,45(1):6.
- [3] 潘一苇.通信辐射源个体识别关键技术研究 [D].郑州:战略支援部队信息工程大学,2019.
- [4] WILLIAMS M D,TEMPLE M A,REISING D R.Augmenting bit-level network security using physical layer RF-DNA fingerprinting [C]//2010 IEEE Global Telecommunications Conference.Piscataway,NJ,USA:IEEE,2010:1-6.
- [5] REISING D R,TEMPLE M A,JACKSON J A.Authorized and rogue device discrimination using dimensionally reduced RF-DNA fingerprints [J].IEEE Transactions on Information Forensics and Security,2015,10(6):1180-1192.
- [6] 秦嘉.基于深度学习的辐射源个体识别技术 [D].北京:北京邮电大学,2019.
- [7] JAIN A,AWAN A A,ANTHONY Q,et al.Performance characterization of DNN training using TensorFlow and PyTorch on modern clusters [C]//2019 IEEE International Conference on Cluster Computing (CLUSTER).Piscataway,NJ,USA:IEEE,2019:1-11.
- [8] 任春辉.通信电台个体特征分析 [D].成都:电子科技大学,2006.
- [9] 黄渊凌,郑辉.通信辐射源指纹产生机理及其仿真 [J].电信技术研究,2012(1):1-12.HUANG Yuanling,ZHENG Hui.Communication radiation source fingerprint generation mechanism and its simulation [J].Research on Telecommunication Technology,2012(1):1-12.
- [10] 王炳程.通信设备指纹识别关键技术研究 [D].成都:电子科技大学,2019.
- [11] PAN Yiwei,YANG Sihan,PENG Hua,et al.Specific emitter identification based on deep residual networks [J].IEEE Access,2019,7:54425-54434.
- [12] SANKHE K,BELGIOVINE M,ZHOU Fan,et al.No radio left behind:radio fingerprinting through deep learning of physical-layer hardware impairments [J].IEEE Transactions on Cognitive Communications and Networking,2020,6(1):165-178.
- [13] 岳嘉颖,郑娜娥,蒋春启.Hilbert包络谱的熵特征在辐射源个体识别中的应用 [J].计算机应用研究,2020,37(12):3677-3680.YUE Jiaying,ZHENG Nae,JIANG Chunqi.Application of entropy characteristics of Hilbert envelope spectrum in specific emitter identification [J].Application Research of Computers,2020,37(12):3677-3680.
- [14] 李天琪,张玉,张进,等.基于时频与快速熵的IFF辐射源个体识别方法 [J].探测与控制学报,2020,42(1):87-93,103.LI Tianqi,ZHANG Yu,ZHANG Jin,et al.IFF radiation sources individual recognition method based in time-frequency and fast entropy [J].Journal of Detection &Control,2020,42(1):87-93,103.
- [15] 毛毅,胡远泽,王景琳,等.基于相空间重构的未知辐射源信号特征提取与盲聚类 [C]//第十届中国指挥控制大会论文集:上册.北京:兵器工业出版社,2022:726-732.
- [16] YUAN Yingjun,HUANG Zhitao,WANG Fenghua,et al.Radio specific emitter identification based on nonlinear characteristics of signal [C]//2015 IEEE International Black Sea Conference on Communications and Networking (BlackSeaCom).Piscataway,NJ,USA:IEEE,2015:77-81.
- [17] 谷晓鹏,谢树果,常青,等.一种基于压缩感知的同频多辐射源数量估计及定位方法 [J].电子学报,2018,46(5):1173-1178.GU Xiaopeng,XIE Shuguo,CHANG Qing,et al.A number estimation and location method of multiple radiation sources based on compressive sensing [J].Acta Electronica Sinica,2018,46(5):1173-1178.
- [18] 齐悦.雷达辐射源信号时频特征分析及分类 [D].西安:西安电子科技大学,2018.
- [19] 王晓晗,闫毅,范亚楠,等.基于多域融合的空间辐射源细微特征识别 [J/OL].中国空间科学技术:1-11 [2022-11-22].http://kns.cnki.net/kcms/detail/11.1859.V.20221109.1256.002.html.WANG Xiaohan,YAN Yi,FAN Yanan,et al.Space emitter fine feature identification based on multi-domain fusion [J/OL].Chinese Space Science and Technology:1-11 [2022-11-22].http://kns.cnki.net/kcms/detail/11.1859.V.20221109.1256.002.html.
- [20] 彭杰.多辐射源信号目标识别方法与系统实现 [D].南京:南京邮电大学,2021.
- [21] 贾永强.通信辐射源个体识别技术研究 [D].成都:电子科技大学,2017.
- [22] 岳嘉颖.辐射源指纹特征提取技术与分类器设计研究 [D].郑州:战略支援部队信息工程大学,2019.
- [23] 杨永杰.辐射源极化信息的检测和识别技术研究 [D].西安:西安电子科技大学,2012.
- [24] 马慧慧.先进极化阵列的稳健参数估计算法研究 [D].西安:西安电子科技大学,2020.
- [25] 曾清平,闫世强.雷达极化技术与极化信息应用 [M].北京:国防工业出版社,2006.
- [26] 肖顺平.雷达极化技术 [M].北京:清华大学出版社,2022:36-37.
- [27] 来杰,王晓丹,向前,等.自编码器及其应用综述 [J].通信学报,2021,42(9):218-230.LAI Jie,WANG Xiaodan,XIANG Qian,et al.Review on autoencoder and its application [J].Journal on Communications,2021,42(9):218-230.
- [28] VINCENT P,LAROCHELLE H,LAJOIE I,et al.Stacked denoising autoencoders:learning useful representations in a deep network with a local denoising criterion [J].The Journal of Machine Learning Research,2010,11:3371-3408.
- [29] 侯青松,郭英,王布宏,等.共形阵列天线振动条件下稳健的DOA估计及位置误差校正 [J].信号处理,2010,26(11):1756-1760.HOU Qingsong,GUO Ying,WANG Buhong,et al.Robust direction finding and position errors calibration for conformal array antenna in the presence of vibration [J].Signal Processing,2010,26(11):1756-1760.
- [30] GLOROT X,BORDES A,BENGIO Y.Deep sparse rectifier neural networks [C]//Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics.Chia Laguna Resort,Sardinia,Italy:PMLR,2011:315-323.