基于时频图学习的北斗卫星导航系统干扰类型识别

中国民航大学学报 ›› 2024, Vol. 42 ›› Issue (5): 45-51.

基于时频图学习的北斗卫星导航系统干扰类型识别

刘瑞华 a ，张艳婷 a ，马赞 b

中国民航大学 a. 电子信息与自动化学院； b. 安全科学与工程学院，天津 300300

收稿日期:2023-09-14 修回日期:2023-12-01 出版日期:2024-12-21 发布日期:2025-04-08
作者简介:刘瑞华（1965— ），男，陕西蓝田人，教授，博士，研究方向为卫星导航在民航中的应用、卫星导航与组合导航
基金资助:
国家重点研发计划项目（2022YFB3904300）

Identification of interference type of Beidou navigation satellite system based on

learning from time-frequency graph

LIU Ruihuaa , ZHANG Yantinga , MA Zanb

a. College of Electronic Information and Automation; b. College of Safety Science and Engineering, CAUC, Tianjin 300300, China

Received:2023-09-14 Revised:2023-12-01 Online:2024-12-21 Published:2025-04-08

摘要/Abstract

摘要：

针对当前干扰识别算法依赖特征工程提取特征存在提取繁琐、识别准确率受干信比取值影响较大的问题，

本文提出在不同干信比情况下基于时频图学习的北斗卫星导航系统（BDS，Beidou navigation satellite system）干扰类型识别方法。以航空机载北斗卫星导航系统 B1I 信号为对象，对原始 B1I 信号、包含干扰的 B1I

信号进行短时傅里叶变换，将变换后获取的时频图作为支持向量机和卷积神经网络模型的输入向量，完成

干扰类型的检测与识别。仿真结果表明，两种机器学习识别算法的平均识别率均达到了 99%以上，识别结果

比传统决策树识别算法提升了 30%以上，解决了现有干扰识别算法需要严重依赖人工设计的特征工程手动

提取干扰信号特征以及识别率较低的问题。该研究结果可为后续的干扰抑制工作提供先验信息，提高航空

领域中北斗卫星导航系统的安全性。

关键词:

干扰识别, 短时傅里叶变换, 时频图, 支持向量机, 卷积神经网络

Abstract:

Aiming at the problem that existing interference identification algorithms rely on feature engineering to extract features, which is cumbersome and the identification accuracy is greatly affected by the value of signal-to-noise ratio,

the interference type identification method of Beidou navigation satellite system (BDS) based on learning from

time-frequency graph under different signal-to-noise ratio is proposed in this paper. Taking the B1I signal of the

airborne BDS as the object, the original B1I signal and the B1I signal containing interference are subjected to

short-time Fourier transform. The time-frequency graph obtained after the transform is used as the input vector of

the support vector machine and convolutional neural network model to complete the detection and identification of

interference types. The simulation results show that the average identification accuracy of both machine learning

identification algorithms has reached over 99%, which is about 30% higher than that of traditional decision tree

identification algorithms, solving the problem of existing interference identification algorithms that heavily rely on

manually designed feature engineering to extract interference signal features and have low accuracy. The research

results can provide prior information for subsequent interference suppression work and improve the safety of BDS

in the aviation field.

Key words:

interference identification, short -term Fourier transform, time -frequency graph, support vector machine,

convolutional neural network

中图分类号:

TN911.4

刘瑞华 a , 张艳婷 a , 马赞 b.

基于时频图学习的北斗卫星导航系统干扰类型识别

[J]. 中国民航大学学报, 2024, 42(5): 45-51.

LIU Ruihuaa , ZHANG Yantinga , MA Zanb.

Identification of interference type of Beidou navigation satellite system based on

learning from time-frequency graph

[J]. Journal of Civil Aviation University of China, 2024, 42(5): 45-51.

参考文献

[1]

FANG F, LI Y, NIU Y T, et al. Jamming signal recognition based on de－

cision tree algorithm[J]. Communications Technology, 2019, 52(11): 2617-

2623.

[2]

SHAN L, ZHANG J Y, SUN L. Deception jamming identification based

on original echo information[J]. Electronic Information Warfare Tech－

nology, 2016: 55-58.

[3] 孙殿星, 王国宏, 盛丹. 基于均值-方差联合检验的航迹欺骗干

扰识别[J]. 航空学报, 2016, 37(4): 1292-1304.

[4] 田晓, 唐斌. 基于归一化小波分解能量比的雷达有源欺骗干扰

识别[J]. 数据采集与处理, 2013, 28(4): 416-420.

[5] 李果, 文妮, 宫丰奎, 等. 部分频带干扰下的 OFDM 系统干扰检

测与分集抑制算法[J]. 通信学报, 2021, 42(9): 194-204.

[6]

LI Y Q, LI P, YAN X P, et al． Application of wavelet transform to radio

fuze jamming identification[C]//2008 4th International Conference on

Wireless Communications, Networking and Mobile Computing, October

12-14, 2008, Dalian, China． IEEE, 2008: 1-4.

[7]

CUI Y, WANG J F. Wideband LFM interference suppression based on

fractional Fourier transform and projection techniques[J]. Circuits, Systems, and Signal Processing, 2014, 33(2): 613-627．

[8]

FU R R． Compound jamming signal recognition based on neural networks

[C]//2016 6th International Conference on Instrumentation & Measurement, Computer, Communication and Control(IMCCC),July 21-23, 2016,

Harbin, China． IEEE, 2016: 737-740．

[9] 张婧, 冯振明. 基于神经网络和 SVM 的 GPS 干扰类型识别[J]. 信

息与电子工程, 2009, 7(5): 386-389.

[10] YANG Y, ZHU L D． An efficient way for satellite interference signal

recognition via incremental learning[C]//2019 International Symposium

on Networks, Computers and Communications(ISNCC), June 18-20,

2019, Istanbul, Turkey． IEEE, 2019: 1-5．

[11] 王亚．基于特征提取的多干扰检测与识别方法研究[D]．成都: 电

子科技大学, 2022: 39-40．

[12] 葛红妨. 卫星干扰信号的检测与识别[D]. 杭州: 杭州电子科技大学,

2022: 48-50.

[13] 陈起磊, 蒋亦悦, 唐瑶, 等. 基于时频图与改进图卷积神经网络的

异步电机故障诊断方法[J]. 振动与冲击, 2022, 41(24): 241-248.

[14] WANG Y X, HUANG Y, CHEN Z Y, et al． Complicated interference

identification via machine learning methods[C]//2021 IEEE 4th Inter－

national Conference on Electronic Information and Communication Technology (ICEICT), August 18-20, 2021, Xi’an, China． IEEE, 2021:

400-405．

[15] HOTFILTER T, HOEFER J, MERZ P, et al. Leveraging mixed-preci－

sion CNN inference for increased robustness and energy efficiency [C]//

2023 IEEE 36th International System -on -Chip Conference (SOCC),

September 5-8, 2023, Santa Clara, CA, USA. IEEE, 2023: 1-6.

[16] PANE S F, RAMDAN J, PUTRADA A G, et al. A hybrid CNN-LSTM

model with word-emoji embedding for improving the twitter sentiment

analysis on Indonesia’s PPKM policy[C]//2022 6th International Conference on Information Technology, Information Systems and Electrical

Engineering (ICITISEE), December 13-14, 2022, Yogyakarta, Indonesia.

IEEE, 2022: 51-56.

[17] CORTES C, VAPNIK V. Support vector networks[J]. Machine Learning,

1995, 20(3): 273-297.

[18] MATHUR A, FOODY G M. Multiclass and binary SVM classification:

implications for training and classification users[J].IEEE Geoscience and

Remote Sensing Letters, 2008, 5(2): 241-245．

[19] 朱鹏程. GNSS 干扰检测与识别技术研究[D]. 重庆: 重庆大学, 2018.

[20] DUVVURI K, KANISETTYPALLI H, JAYAN S． Detection of brain tu－

mor using CNN and CNN-SVM[C]//2022 3rd International Conference

for Emerging Technology(INCET), May 27-29, 2022, Belgaum, India．

IEEE, 2022: 1-7．

[21] LLUGSI R, YACOUBI S E, FONTAINE A, et al. Comparison between

adam, adamax and adam w optimizers to implement a weather forecast

based on neural networks for the Andean city of Quito[C]//2021 IEEE

Fifth Ecuador Technical Chapters Meeting (ETCM),October 12-15, 2021,

Cuenca, Ecuador. IEEE, 2021: 1-6.