基于信号指纹的无人机遥控端个体识别方法  

Individual identification method for drone remote control terminal based on signal fingerprint

作　　者：何兵 樊宽刚 欧阳清华 李娜 刘亚辉 HE Bing;FAN Kuangang;OUYANG Qinghua;LI Na;LIU Yahui(School of Mechanical and Electrical Engineering,Jiangxi University of Science and Technology,Ganzhou 341000,China;School of Electrical Engineering and Automation,Jiangxi University of Science and Technology,Ganzhou 341000,China)

机构地区：[1]江西理工大学机电工程学院,江西赣州341000 [2]江西理工大学电气工程与自动化学院,江西赣州341000

出　　处：《传感器与微系统》2022年第2期58-61,共4页Transducer and Microsystem Technologies

基　　金：国家自然科学基金资助项目(61763018);江西省“03专项及5G项目”(20193ABC03A058);江西省教育厅重点资助项目(GJJ170493)。

摘　　要：针对无人机遥控端个体间信号相似,难以识别的问题,提出了一种基于信号指纹的无人机遥控端个体识别方法。方法通过多项式拟合暂态信号瞬时幅值包络曲线,得到暂态信号特征,再提取稳态信号的瞬时频率特征,并采用K最近邻(KNN)等多种机器学习方法进行信号识别。对实际数据处理结果表明:能够有效识别2个无人机遥控端个体,仿真实验结果表明:对5个无人机遥控端个体在信噪比5 dB时平均识别正确率大于90%。Aiming at the difficult identification problem of drone remote control caused by signal similarity, a method based on signal fingerprint is proposed to identify the drone controllers.This method uses Hilbert transform to obtain the instantaneous amplitude and frequency of the transmitted signal.Transient signal features are obtained by polynomial fitting of transient signal envelope curves.The method further extracts the instantaneous frequency features of the steady-state signal.K-nearest neighbor(KNN)and other machine learning methods are applied for signal recognition.The signal processing results show that the proposed method can recognize two drone remote control terminal.The simulation experiment results show that the average recognition accuracy of 5 drone remote control terminal is above 90 % when the signal-to-noise ratio is 5 dB.

关 键 词：无人机信号 信号指纹 信号识别 

分 类 号：TN911.72[电子电信—通信与信息系统]