LDACS系统基于循环谱和残差神经网络的频谱感知方法

doi:10.12305/j.issn.1001-506X.2024.09.34

摘要/Abstract

摘要：

针对L波段数字航空通信系统(L-band digital aeronautic communication system, LDACS)可用频谱资源有限且易受大功率测距仪(distance measuring equipment, DME)信号干扰的问题, 提出一种基于降维循环谱和残差神经网络的频谱感知方法。首先理论推导分析了DME信号的循环谱特征; 然后利用Fisher判别率(Fisher discriminant rate, FDR)提取循环频率能量最大的向量, 通过主成分分析(principal component analysis, PCA)进行预处理特征增强; 最后给出数据处理后的循环谱向量与卷积神经网络相结合的实现过程, 实现了DME信号的有效检测。仿真结果表明, 该方法对噪声不敏感, 当信噪比不低于-15 dB时, 平均检测概率大于90%。当信噪比不低于-14 dB, 检测概率接近100%。

关键词: L波段数字航空通信系统, 测距仪, 频谱感知, 循环谱, 残差神经网络

Abstract:

To solve the problem that the available spectrum resources of L-band digital aeronautic communication system (LDACS) are limited and vulnerable to interference from high-power distance measuring equipment (DME) signals, a spectrum sensing method based on reduced dimension cyclic spectrum and residual neural network is proposed. Firstly, the cyclic spectrum characteristics of DME signal are analyzed theoretically. Then Fisher discriminant rate (FDR) is used to extract the vector with the highest cycle frequency energy, and the pre-processing features are enhanced by principal component analysis (PCA). Finally, the process of combining the cyclic spectral vector and convolutional neural network after data processing is given, and the effective detection of DME signal is achieved. Simulation results show that the method is not sensitive to noise, and the average detection probability is greater than 90% when the signal-to-noise ratio is no less than -15 dB. When the signal-to-noise ratio is not less than -14 dB, the detection probability is close to 100%.

Key words: L-band digital aeronautic communication system (LDACS), distance measuring equipment (DME), spectrum sensing, cyclic spectrum, residual neural network

中图分类号:

TN925

王磊, 张劲, 叶秋炫. LDACS系统基于循环谱和残差神经网络的频谱感知方法[J]. 系统工程与电子技术, 2024, 46(9): 3231-3238.

Lei WANG, Jin ZHANG, Qiuxuan YE. Spectrum sensing method based on cyclic spectrum and residual neural network in LDACS system[J]. Systems Engineering and Electronics, 2024, 46(9): 3231-3238.

图/表 11

图1

图2

图3

图4

表1

图5

图6

表2

图7

图8

图9

参考文献 30

1	MAURER N , GRAUPL T , BELLIDO-MANGANELL M A , et al. Flight trial demonstration of secure GBAS via the L-band digital aeronautical communications system (LDACS)[J]. IEEE Aerospace and Electronic Systems Magazine, 2021, 36 (4): 8- 17. doi: 10.1109/MAES.2021.3052318
2	NEJI N , LACERDA R D , AZOULAY A , et al. Survey on the future aeronautical communication system and its development for continental communications[J]. IEEE Trans.on Vehicular Technology, 2013, 62 (1): 182- 191. doi: 10.1109/TVT.2012.2207138
3	洪观. 基于压缩感知的L-DACS1宽带频谱感知算法研究[D]. 重庆: 重庆大学, 2017.
	HONG G. Study on broadband spectrum sensing algorithm based on compressed sensing of L-DACS1[D]. Chongqing: Chongqing University, 2017.
4	ABD-ELATY E , ZEKRY A , EL-AGOOZ S , et al. Cognitive radio techniques for utilizing the primary L-band distance mea-suring equipment for aeronautical communications[J]. IEEE Access, 2020, 8, 124812- 124823. doi: 10.1109/ACCESS.2020.3007741
5	KOPYTO D, LINDNER S, SCHULZ L, et al. Deep learning-based dynamic spectrum access for coexistence of aeronautical communication systems[C]//Proc. of the IEEE 96th Vehicular Technology Conference, 2022.
6	SHREEJITH S , MATHEW L K , PRASAD V A , et al. Effi cient spectrum sensing for aeronautical LDACS using low-power correlators[J]. IEEE Trans.on Very Large Scale Integration (VLSI) Systems, 2018, 26 (6): 1183- 1191. doi: 10.1109/TVLSI.2018.2806624
7	MATHEW L K, VINOD A P, MADHUKUMAR A S. A cyclic prefix assisted spectrum sensing method for aeronautical communic ation systems[C]//Proc. of the IEEE International Symposium on Circuits and Systems, 2019.
8	XIE J D , FANG J , LIU C , et al. Deep learning-based spectrum sensing in cognitive radio: a CNN-LSTM approach[J]. IEEE Communications Letters, 2020, 24 (10): 2196- 2200. doi: 10.1109/LCOMM.2020.3002073
9	LIU C , WANG J , LIU X M , et al. Deep CM-CNN for spectrum sensing in cognitive radio[J]. IEEE Journal on Selected Areas in Communications, 2019, 37 (10): 2306- 2321. doi: 10.1109/JSAC.2019.2933892
10	SSKI K , LEDZINSKI D . ECG signal classification using deep learning techniques based on the PTB-XL dataset[J]. Entropy, 2021, 23 (9): 1121. doi: 10.3390/e23091121
11	SINDI H , NOUR M , RAWA M , et al. A novel hybrid deep learning approach including combination of 1D power signals and 2D signal images for power quality disturbance classification[J]. Expert Systems with Applications, 2021, 174, 114785. doi: 10.1016/j.eswa.2021.114785
12	SHAH P K, SULTANE D, SINGH P. Spectrum sensing mechanism for congnitive radio using deep learning[C]//Proc. of the International Conference on Artificial Intelligence in Information and Communication, 2023.
13	LIN Y , TUYA T , DOU Z , et al. Contour stella image and deep learning for signal recognition in the physical layer[J]. IEEE Trans.on Cognitive Communications and Networking, 2021, 7 (1): 34- 46. doi: 10.1109/TCCN.2020.3024610
14	WANG Q , SU B , WANG C X , et al. ConvLSTM based spectrum sensing at very low SNR[J]. IEEE Wireless Communications Letters, 2023, 12 (6): 967- 971. doi: 10.1109/LWC.2023.3254048
15	ZHANG Z F , LUO H , WANG C , et al. Automatic modulation classification using CNN-LSTM based dual-stream structure[J]. IEEE Trans.on Vehicular Technology, 2020, 69 (11): 3521- 13531.
16	KIM S H , KIM J W , NWADIUGWU W P , et al. Deep learn ing-based robust automatic modulation classification for cognitive radio networks[J]. IEEE Access, 2021, 9, 92386- 92393. doi: 10.1109/ACCESS.2021.3091421
17	TEKBIYIK K , AKBUNAR O , EKTI A R , et al. Spectrum sensing and signal identification with deep learning based on spectral correlation function[J]. IEEE Trans.on Vehicular Technology, 2021, 70 (10): 10514- 10527. doi: 10.1109/TVT.2021.3109236
18	RAZA A , MEHMOOD A , ULLAH S , et al. Heartbeat sound signal classification using deep learning[J]. Sensors, 2019, 19 (21): 4819. doi: 10.3390/s19214819
19	ALTAHERI H , MUHAMMAD G , ALSULAIMAN M , et al. Deep learning techniques for classification of electroencephalogram (EEG) motor imagery (MI) signals: a review[J]. Neural Computing and Applications, 2023, 35, 14681- 14722. doi: 10.1007/s00521-021-06352-5
20	束学渊, 汪立新. 联合循环平稳特征PCA与XGBoost的频谱感知[J]. 计算机应用与软件, 2020, 37 (4): 114-118, 126. doi: 10.3969/j.issn.1000-386x.2020.04.019
	SHU X Y , WANG L X . Spectrum sensing by combining cyclostationary features PCA with XGBoost[J]. Computer Applications and Software, 2020, 37 (4): 114-118, 126. doi: 10.3969/j.issn.1000-386x.2020.04.019
21	WANG D , LIN M Y , ZHANG X X , et al. Automatic modulation classification based on CNN-Transformer graph neural network[J]. Sensors, 2023, 23 (16): 7281. doi: 10.3390/s23167281
22	葛战, 伍警, 李兵, 等. 基于循环谱和深度神经网络的调制识别算法[J]. 无线电工程, 2022, 52 (10): 1718- 1725. doi: 10.3969/j.issn.1003-3106.2022.10.005
	GE Z , WU J , LI B , et al. Modulation recognition based on cyclic spectrum and deep neural network[J]. Radio Engineering, 2022, 52 (10): 1718- 1725. doi: 10.3969/j.issn.1003-3106.2022.10.005
23	李冬霞, 李思, 刘海涛. 载波偏置测距仪信号的循环平稳特性[J]. 系统工程与电子技术, 2016, 38 (8): 1935- 1938.
	LI D X , LI S , LIU H T . Cyclostationarity of carrier offset distance measure equipment signals[J]. Systems Engineering and Electronics, 2016, 38 (8): 1935- 1938.
24	张贤达, 保铮. 非平稳信号分析与处理[M]. 北京: 国防工业出版社, 1998.
	ZHANG X D , BAO Z . Analysis and processing of non-stationary signals[M]. Beijing: National Defence Industry Press, 1998.
25	GARDNER W A . Introduction to random process with application to signals and systems[M]. New York: Macmillan, 1989.
26	HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition[C]//Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, 2016.
27	陈月, 张希, 艾文宝. 基于残差神经网络的频谱感知算法[J]. 现代电子技术, 2022, 45 (7): 1- 5.
	CHEN Y , ZHANG X , AI W B . Spectrum sensing algorithm based on residual neural network[J]. Modern Electronic Technology, 2022, 45 (7): 1- 5.
28	EUROPEAN UNION, EUROCONTROL. PJ. 14-W2-60 TRL6 final LDACS A/G specification[EB/OL]. [2023-07-08]. https://www.ldacs.com/wp-content/uploads/2023/03/SESAR2020_PJ14-W2-60_TRL6_D3_1_230_3rd_LDACS_AG_Specification_v1.0.0.pdf.
29	TAN P S , LIM K M , TAN C H , et al. Pre-trained DenseNet-121 with multilayer perceptron for acoustic event classification[J]. IAENG International Journal of Computer Science, 2023, 50 (1): 51- 62.
30	FENG S , ZHAO L P , SHI H Y , et al. One-dimensional VGGNet for high-dimensional data[J]. Applied Soft Computing, 2023, 135, 1568- 4946.

参数	参数值
采样频率/MHz	2.5
上采样因子	4
传输带宽/kHz	498.05
信道编码	卷积编码
FFT点数	64
有效子载波数	50
循环前缀点数	11
信道类型	AWGN信道
DME信号数目	1
DME载波偏置/kHz	+500、－500
信干比/dB	－3
脉冲间隔/μs	12

参数	ResNet-50	DenseNet-121	VGG-19	CNN-LSTM
训练时间/s	2 637.70	2 768.12	1 521.24	530.97
测试时间/s	8.351 9	8.714 7	4.865 2	1.320 8
准确度	0.952	0.946	0.910	0.766

[1]	李冬霞, 王佳妮, 彭祥清, 刘海涛, 王磊. 基于cSVB算法的DME脉冲干扰抑制方法[J]. 系统工程与电子技术, 2024, 46(8): 2877-2885.
[2]	王全全, 顾志豪, 吴城坤, 宛汀. 基于HHO-SVM的抗SSDF攻击协作频谱感知方法[J]. 系统工程与电子技术, 2024, 46(6): 2146-2154.
[3]	邹涵, 张天骐, 马焜然, 杨宗方. 基于多特征融合的MIMO-OFDM系统单-混信号调制识别算法[J]. 系统工程与电子技术, 2024, 46(4): 1456-1465.
[4]	陈增茂, 汪楷淋, 孙志国, 孙溶辰, 阿尔斯楞. Alpha稳定分布噪声下基于特征值之差频谱感知算法[J]. 系统工程与电子技术, 2023, 45(9): 2949-2955.
[5]	汪锐, 张天骐, 安泽亮, 王雪怡, 方竹. 基于联合特征参数和一维CNN的MIMO-OFDM系统调制识别算法[J]. 系统工程与电子技术, 2023, 45(3): 902-912.
[6]	孙志国, 沙钰彭, 宁晓燕. 基于NFM-BOK波形的低检测概率通信技术[J]. 系统工程与电子技术, 2023, 45(12): 4030-4039.
[7]	苑申昊, 陈增茂, 刁鸣, 孙志国, 孙溶辰. 基于复合熵和证据理论的抗SSDF攻击协作频谱感知方法[J]. 系统工程与电子技术, 2023, 45(11): 3663-3670.
[8]	唐玺博, 张立民, 钟兆根. 基于ADASYN与改进残差网络的入侵流量检测识别[J]. 系统工程与电子技术, 2022, 44(12): 3850-3862.
[9]	谭思炜, 唐波, 张林森, 张森. 跳频电磁引信干扰感知技术方案研究[J]. 系统工程与电子技术, 2022, 44(11): 3330-3337.
[10]	李贺, 赵文静, 金明录. 基于特征值高阶矩的频谱感知增强技术[J]. 系统工程与电子技术, 2022, 44(10): 3243-3248.
[11]	赖涛, 魏玺章, 黄海风, 欧鹏飞, 智国平, 于东俊, 孙京海. 面向FAST馈源仓定位的微波测距系统设计[J]. 系统工程与电子技术, 2022, 44(1): 10-19.
[12]	李冬霞, 陈秋雨, 王磊, 刘海涛. 基于BSBL-BO算法的DME脉冲干扰抑制方法[J]. 系统工程与电子技术, 2021, 43(9): 2649-2656.
[13]	张天骐, 白杨柳, 胡延平, 张晓艳. 交替二进制偏移载波信号的多参数盲估计[J]. 系统工程与电子技术, 2021, 43(9): 2665-2672.
[14]	常虹, 赵小强, 石海杰. 基于FFT谱能量检测和互相关检测的快速频谱感知方法及其性能分析[J]. 系统工程与电子技术, 2021, 43(5): 1406-1412.
[15]	谢存祥, 张立民, 钟兆根. 基于时频特征提取和残差神经网络的雷达信号识别[J]. 系统工程与电子技术, 2021, 43(4): 917-926.