面向无人机型号分选的图传信号时频与循环谱融合识别方法

崔亚民; 王首斌; 沈雷

doi:10.11959/j.issn.1000-0801.DXKX260077

您当前的位置：

首页 >

文章列表页 >

面向无人机型号分选的图传信号时频与循环谱融合识别方法

更新时间：2026-05-11

- 面向无人机型号分选的图传信号时频与循环谱融合识别方法
- A fusion recognition method of video transmission signal time-frequency and cyclic spectrum for uav model classification
- 电信科学 2026年
- 作者机构：
  
  1.杭州电子科技大学通信工程学院，浙江杭州 310018
  2.中国电子科技集团公司第三十六研究所，浙江嘉兴 314033
- 作者简介：
  
  [ "崔亚民（1995——），男，研究生，杭州电子科技大学，学生，主要研究方向为信号处理。" ]
  [ "王首斌（1984——），男，博士，中国电子科技集团公司第三十六研究所，高级工程师，主要研究方向为电子战系统总体技术。" ]
  [ "沈雷（1979——），男，博士，杭州电子科技大学，教授，主要研究方向为图像处理和信号处理。" ]
- 基金信息：
- DOI：10.11959/j.issn.1000-0801.DXKX260077
  中图分类号： TN911.7
- 收稿：2026-01-28，
  
  修回：2026-03-23，
  
  录用：2026-04-16，
- 稿件说明：
移动端阅览
崔亚民, 王首斌, 沈雷. 面向无人机型号分选的图传信号时频与循环谱融合识别方法[J/OL]. 电信科学, 2026.

CUI Yamin, WANG Shoubin, SHEN Lei. A fusion recognition method of video transmission signal time-frequency and cyclic spectrum for uav model classification[J/OL]. Telecommunications Science, 2026.
崔亚民, 王首斌, 沈雷. 面向无人机型号分选的图传信号时频与循环谱融合识别方法[J/OL]. 电信科学, 2026. DOI： 10.11959/j.issn.1000-0801.DXKX260077.

CUI Yamin, WANG Shoubin, SHEN Lei. A fusion recognition method of video transmission signal time-frequency and cyclic spectrum for uav model classification[J/OL]. Telecommunications Science, 2026. DOI： 10.11959/j.issn.1000-0801.DXKX260077.

摘要

为解决多无人机飞行场景下识别准确率低的问题，提出一种基于图传信号的多域特征融合识别方法。图传信号具有连续、高带宽与硬件依赖性强等特点，更适合作为稳定信号源。为克服单一特征局限性，融合短时傅里叶变换（Short-Time Fourier Transform

STFT）与循环谱分析（Cyclic Spectral Analysis

CSA）进行多域建模。STFT从时频动态中提取功放非线性、本振频偏等硬件指纹；CSA利用信号周期平稳性挖掘I/Q失配、载波泄漏等谱相关特征，从而全面表征细微身份差异。为充分挖掘融合特征形成的高维多域射频指纹表征中的复杂非线性相关性，设计了Effiv2KAN模型（EfficientNetV2-based Network with KAN Classifier）。该模型前端以EfficientNetV2对融合特征进行多尺度特征提取，后端采用KAN分类器，通过可学习样条函数替代固定激活函数，以灵活拟合特征间复杂非线性关系，提升对细微指纹的判别能力。实验结果表明，该模型在不同信噪比下均优于经典深度学习模型，对信号高度相似的无人机型号具有更强的抗噪鲁棒性。

Abstract

To address the issue of low recognition accuracy in multi-UAV flight scenarios

a multi-domain feature fusion recognition method based on video transmission signals was proposed. The video transmission signal

characterized by its continuity

high bandwidth

and strong hardware dependence

was considered a more suitable stable signal source. To overcome the limitations of a single feature

short-time Fourier transform (STFT) and cyclic spectral analysis (CSA) were integrated for multi-domain modeling. STFT was employed to extract hardware fingerprints

such as power amplifier nonlinearity and local oscillator frequency offset

from time-frequency dynamics. CSA was utilized to mine spectral correlation features

including I/Q mismatch and carrier leakage

by leveraging the cyclostationarity of the signal

thereby comprehensively characterizing subtle identity differences. To fully exploit the complex nonlinear correlations within the high-dimensional multi-domain radio frequency fingerprint representation formed by the fused features

an Effiv2KAN model (EfficientNetV2-based Network with KAN Classifier) was designed. In this model

EfficientNetV2 was adopted at the front end for multi-scale feature extraction from the fused features

and a KAN classifier was employed at the back end. By replacing fixed activation functions with learnable spline functions

the model flexibly fit the complex nonlinear relationships among features

enhancing the discriminative capability for subtle fingerprints. Experimental results demonstrated that the proposed model outperformed classical deep learning models under different signal-to-noise ratios and exhibited stronger noise-robustness for discriminating UAV models with highly similar signals.

关键词

Keywords

references

Hussain S , Chaudhry S A , Alomari O A , et al . Amassing the security: An ECC-based authentication scheme for Internet of Drones [J ] . IEEE Systems Journal , 2021 , 15 ( 3 ): 4431 - 4438 .

Pham Q V , Huynh-The T , Alazab M , et al . Sum-rate maximization for UAV-assisted visible light communications using NOMA: Swarm intelligence meets machine learning [J ] . IEEE Internet of Things Journal , 2020 , 7 ( 10 ): 10375 - 10387 .

Yaacoub J P , Noura H , Salman O , et al . Security analysis of drones systems: Attacks, limitations, and recommendations [J ] . Internet of Things , 2020 , 11 : 100218 .

王豪 , 罗俊松 , 王惠明 . 无人机射频指纹识别方法综述 [J ] . 无线电工程 , 2024 , 54 ( 11 ): 2672 - 2684 .

WANG H , LUO J S , WANG H M . Review of UAV RF Fingerprint Identification Methods [J ] . Radio Engineering , 2024 , 54 ( 11 ): 2672 - 2684 .

邓涵方 . 基于深度学习的射频指纹识别技术研究 [D ] . 桂林电子科技大学 , 2022 .

DENG H F . Research on RF fingerprint identification technology based on deep learning [D ] . Guilin : Guilin University of Electronic Technology , 2022 .

Zhang Y . RF-based drone detection using machine learning [C ] // 2021 2nd International Conference on Computing and Data Science (CDS) . IEEE , 2021 : 425 - 428 .

李超群 , 王金明 . 基于短时傅里叶变换的无人机射频指纹分类识别 [J ] . 通信技术 , 2022 , 55 ( 9 ): 1202 - 1207 .

LI C Q , WANG J M . Classification and Identification of UAV RF Fingerprints Based on Short-Time Fourier Transform [J ] . Communication Technology , 2022 , 55 ( 9 ): 1202 - 1207 .

Swinney C J , Woods J C . Unmanned aerial vehicle flight mode classification using convolutional neural network and transfer learning [C ] // 2020 16th International Computer Engineering Conference (ICENCO) . IEEE , 2020 : 83 - 87 .

Zhang H , Li T , Su N , et al . Drone identification based on normalized cyclic prefix correlation spectrum [J ] . IEEE Transactions on Cognitive Communications and Networking , 2024 , 10 ( 4 ): 1241 - 1252 .

俞宁宁 , 毛盛健 , 周成伟 , 等 . DroneRFa:用于侦测低空无人机的大规模无人机射频信号数据集 [J ] . 电子与信息学报 , 2024 , 46 ( 4 ): 1147 - 1156 .

YU N N , MAO S J , ZHOU C W , et al . DroneRFa: A Large-Scale UAV RF Signal Dataset for Low-Altitude Drone Detection [J ] . Journal of Electronics & Information Technology , 2024 , 46 ( 4 ): 1147 - 1156 .

Shi R , Yu X , Wang S , et al . RFUAV: A Benchmark Dataset for Unmanned Aerial Vehicle Detection and Identification [J ] . arXiv preprint arXiv: 2503.09033 , 2025 .

Tan M , Le Q . Efficientnetv2: Smaller models and faster training [C ] // International conference on machine learning . PMLR , 2021 : 10096 - 10106 .

Dosovitskiy A , Beyer L , Kolesnikov A , et al . An image is worth 16x16 words: Transformers for image recognition at scale [J ] . arXiv preprint arXiv: 2010.11929 , 2020 .

Liu Z , Lin Y , Cao Y , et al . Swin transformer: Hierarchical vision transformer using shifted windows [C ] // Proceedings of the IEEE/CVF international conference on computer vision . 2021 : 10012 - 10022 .

Simonyan K , Zisserman A . Very deep convolutional networks for large-scale image recogni- tion [J ] . arXiv preprint arXiv: 1409.1556 , 2014 .

He K , Zhang X , Ren S , et al . Deep residual learning for image recognition [C ] // Proceedings of the IEEE conference on computer vision and pattern recognition . 2016 : 770 - 778 .

Howard A , Sandler M , Chu G , et al . Searching for mobilenetv3 [C ] // Proceedings of the IEEE/CVF international conference on computer vision . 2019 : 1314 - 1324 .

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

暂无数据