基于放大器非线性的射频指纹特征估计技术  

Radio frequency fingerprint feature estimation technology based on amplifier nonlinearity

作　　者：张冠杰[1] 李艳斌[1] 畅鑫 ZHANG Guanjie;LI Yanbin;CHANG Xin(The 54th Research Institute of China Electronics Technology Corporation,Shijiazhuang,Hebei 050081,China)

机构地区：[1]中国电子科技集团公司第五十四研究所,河北石家庄050081

出　　处：《河北工业科技》2024年第6期399-408,共10页Hebei Journal of Industrial Science and Technology

基　　金：中国博士后科学基金(2021M693002)。

摘　　要：为了使功放射频指纹特征不受发射机硬件畸变特性引起的剩余载波频偏影响,提出了基于差分处理的功放射频指纹特征估计方法。首先,使用基于前向结构的解调方法对接收信号进行预处理;其次,将逐点差分处理与信号重构方法相结合,对比了接收差分信号与重构差分信号之间的差异,利用最大似然估计和权值归一化方法,实现了与剩余载波频偏无关的功放射频指纹特征的提取;然后,采用支持向量机(support vector machine,SVM)分类器实现了辐射源个体识别;最后,利用功放畸变信号模型进行了仿真试验。结果表明:基于差分处理的放大器指纹特征估计与识别方法能够消除剩余载波频偏引起的特征漂移,在信噪比32 dB,剩余载波频偏差值±6 Hz范围内,识别准确率相比传统方法提升了30个百分点以上,显著改善了特定辐射源识别性能。与传统方法相比,虽然增加了差分分析和权值归一化的处理步骤,但无需准确估计信号剩余载波频偏就能消除剩余载波频偏的影响。所提方法在功率放大器射频指纹特征估计方面,能够有效消除剩余载波频偏的影响,在辐射源个体识别领域具有一定的应用价值。In order to prevent the residual frequency offset caused by the transmitter hardware distortion from affecting the radio frequency(RF)fingerprint features of the power amplifier,a power amplifier radio frequency fingerprint estimation method based on differential processing was proposed.Firstly,the forward structure-based demodulation method was used to preprocess the received signal;Secondly,the point-by-point differential processing was combined with the signal reconstruction to compare the difference between the received differential signal and the reconstructed differential signal.The maximum likelihood estimation and normalization methods were used to realize the extraction of the RF fingerprint features of the power amplifier independent of residual frequency offset;Thirdly,the SVM classifier was used to realize the identification of emitters.Finally,the power amplifier distortion signal model was used for simulation experiments.The results showe that the amplifier fingerprint feature estimation and recognition method based on differential processing can effectively eliminate the feature drift caused by the residual frequency offset,and the recognition accuracy is increased by more than 30 percentage points under the signal-to-noise ratio of 32 dB and the residual frequency offset deviation of±6 Hz,significantly improving the recognition performance.Compared with the traditional method,although the processing steps of differential processing and normalization are added in the proposed method,it is not necessary to accurately estimate the residual frequency offset to eliminate the impact of the residual frequency offset.The proposed method can effectively eliminate the influence of the residual frequency offset in the estimation of radio frequency fingerprint of amplifier,and has certain application value in the specific emitter identification.

关 键 词：参数估计 特定辐射源识别 功放非线性畸变 差分分析 射频指纹 

分 类 号：TN911.7[电子电信—通信与信息系统]