基于多级跳线残差网络的雷达辐射源识别

doi:10.12305/j.issn.1001-506X.2022.07.10

摘要/Abstract

摘要：

针对复杂体制雷达辐射源的识别问题, 提出了一种基于时频特征提取与多级跳线残差网络(multi-level jumper residual network, MLJ-RN)结合的识别方法。首先，计算辐射源信号的平滑伪Wigner-Ville时频分布生成时频图像以表达信号本质特征, 将图像进行预处理以保留信号细微特征差异。然后，设计多级跳线连接的残差单元, 在此基础上构造MLJ-RN, 对时频图像相邻卷积层的细微特征进行学习和识别, 并使用随机梯度下降法训练网络。最后，通过对网络进行参数优化, 强化对信号的深层特征提取能力。仿真结果表明, 信噪比为－5 dB时, 该方法对12类雷达辐射源信号的整体识别概率达到95.1%, 从而验证了该方法在低信噪比下识别雷达信号的有效性。

关键词: 时频特征, 辐射源识别, 深度学习, 多级跳线

Abstract:

Aiming at the problem of complex radar emitter recognition, a recognition method based on time-frequency feature extraction and multi-level jumper residual network (MLJ-RN) is proposed. Firstly, the smoothed pseudo Wigner-Ville distribution (SPWVD) of emitter signals is calculated, a time-frequency image is generated to express the essential characteristics of the signal, and the image is preprocessed to retain the subtle differences of the signal features. Then a residual unit connected by multi-level jumpers is designed, a multi-level jumper residual network is constructed on this basis, the fine features of the adjacent convolution layers of the time-frequency image are learned and recognized, and the random gradient descent method is used to train the residual network. Finally, through the adjustment of the network, the parameters of the network are optimized to enhance the deep feature extraction ability of the signal. The simulation results show that when the signal-to-noise ratio (SNR) is －5 dB, the overall recognition probability of the method for 12 types of radar emitter signals reaches 95.1%, which verifies the effectiveness of the method in identifying radar signals at low SNRs.

Key words: time frequency feature, emitter recognition, deep learning, multi-level jumper

中图分类号:

TN971

张立民, 谭凯文, 闫文君, 张聿远. 基于多级跳线残差网络的雷达辐射源识别[J]. 系统工程与电子技术, 2022, 44(7): 2148-2156.

Limin ZHANG, Kaiwen TAN, Wenjun YAN, Yuyuan ZHANG. Radar emitter recognition based on multi-level jumper residual network[J]. Systems Engineering and Electronics, 2022, 44(7): 2148-2156.

图/表 15

表1

表2

图1

图2

图3

图4

图5

图6

图7

图8

图9

图10

图11

表3

表4

参考文献 29

1	WU L W , ZHAO Y Q , FENG M F , et al. Specific emitter identification using IMF-DNA with a joint feature selection algorithm[J]. Electronics, 2019, 8 (9): 934. doi: 10.3390/electronics8090934
2	WANG Y H , ZHANG S C , ZHANG Y W , et al. A cooperative spectrum sensing method based on empirical mode decomposition and information geometry in complex electromagnetic environment[J]. Complexity, 2019, (7): 1- 13.
3	周志文, 黄高明, 王雪宝, 等. 基于联合协作表示的特定辐射源识别[J]. 系统工程与电子技术, 2019, 41 (4): 724- 729.
	ZHOU Z W , HUANG G M , WANG X B , et al. Specific emitter recognition based on joint collaborative representation[J]. Systems Engineering and Electronics, 2019, 41 (4): 724- 729.
4	FU W H , HU Z , LI D . A sorting algorithm for multiple frequency-hopping signals in complex electromagnetic environments[J]. Circuits, Systems, and Signal Processing, 2020, 39 (1): 245- 267. doi: 10.1007/s00034-019-01160-8
5	HUANG S , CHAI L , LI Z N , et al. Automatic modulation classification using compressive convolutional neural network[J]. IEEE Access, 2019, 7, 79636- 79643. doi: 10.1109/ACCESS.2019.2921988
6	LI R D , LI L Z , YANG S Y , et al. Robust automated VHF modulation recognition based on deep convolutional neural networks[J]. IEEE Communications Letters, 2018, 22 (5): 946- 949. doi: 10.1109/LCOMM.2018.2809732
7	PENG S L , JIANG H Y , WANG H X , et al. Modulation classification based on signal constellation diagrams and deep learning[J]. IEEE Trans.on Neural Networks and Learning System, 2019, 30 (3): 718- 727. doi: 10.1109/TNNLS.2018.2850703
8	KULIN M , KAZAZ T , MOERMAN I , et al. End-to-end learning from spectrum data: a deep learning approach for wireless signal identification in spectrum monitoring applications[J]. IEEE Access, 2018, 6, 18484- 18501. doi: 10.1109/ACCESS.2018.2818794
9	KONG S H , KIM M , HOANG L M . Automatic LPI radar waveform recognition using CNN[J]. IEEE Access, 2018, 6, 4207- 4219. doi: 10.1109/ACCESS.2017.2788942
10	PENG S L , JIANG H Y , WANG H X , et al. Modulation classification based on signal constellation diagrams and deep learning[J]. IEEE Trans.on Neural Networks and Learning Systems, 2019, 30 (3): 718- 727. doi: 10.1109/TNNLS.2018.2850703
11	KONG M X, ZHANG J, LIU W F, et al. Radar emitter identification based on deep convolutional neural network[C]//Proc. of the International Conference on Control, Automation and Information Sciences, 2018.
12	ZHANG M , DIAO M , GUO L M . Convolutional neural networks for automatic cognitive radio waveform recognition[J]. IEEE Access, 2017, 5, 11074- 11082. doi: 10.1109/ACCESS.2017.2716191
13	ZHOU Z W , HUANG G M , WANG X B . Ensemble convolutional neural networks for automatic fusion recognition of multi-platform radar emitters[J]. ETRI Journal, 2019, 41 (6): 750- 759. doi: 10.4218/etrij.2017-0327
14	GAO J P , SHEN L X , GAO L P . Modulation recognition for radar emitter signals based on convolutional neural network and fusion features[J]. Transactions on Emerging Telecommunications Technologies, 2019, 30 (12): e3612.
15	SZEGEDY C, LIU W, JIA Y, et al. Going deeper with convolutions[C]//Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, 2015.
16	CHEN P H , LIN C J , SCHLKOPF B . A tutorial on ν-support vector machines[J]. Applied Stochastic Models in Business and Industry, 2005, 21 (2): 111- 136. doi: 10.1002/asmb.537
17	CHEN K Y , ZHANG S N , ZHU L Z , et al. Modulation recognition of radar signals based on adaptive singular value reconstruction and deep residual learning[J]. Sensors, 2021, 21 (2): 449. doi: 10.3390/s21020449
18	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: 770-778.
19	WANG Y , WU X , LI W Z , et al. Analysis of micro-Doppler signatures of vibration targets using EMD and SPWVD[J]. Neurocomputing, 2016, 171, 48- 56. doi: 10.1016/j.neucom.2015.06.005
20	YUAN Q Q , ZHANG Q , LI J , et al. Hyperspectral image denoising employing a spatial-spectral deep residual convolutional neural network[J]. IEEE Trans.on Geoscience and Remote Sensing, 2019, 57 (2): 1205- 1218. doi: 10.1109/TGRS.2018.2865197
21	孙伟峰, 戴永寿. 采用多级残差滤波的非局部均值图像去噪方法[J]. 电子与信息学报, 2016, 38 (8): 1999- 2006.
	SUN W F , DAI Y S . Non local mean image denoising method based on multistage residual filtering[J]. Journal of Electronics and Information Technology, 2016, 38 (8): 1999- 2006.
22	ZHOU D W , SHEN X L , DONG W M . Image zooming using directional cubic convolution interpolation[J]. IET Image Processing, 2012, 6 (6): 627- 634. doi: 10.1049/iet-ipr.2011.0534
23	SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[EB/OL]. [2021-01-05]. https://arxiv.org/abs/1409.155.
24	ALEX K , ILYA S , GEOFFREY E . ImageNet classification with deep convolutional neural networks[J]. Communications of the ACM, 2017, 60 (6): 84- 90. doi: 10.1145/3065386
25	HUANG H , PU C Y , LI Y , et al. Adaptive residual convolutional neural network for hyperspectral image classification[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2020, 13, 2520- 2531. doi: 10.1109/JSTARS.2020.2995445
26	LEE S J , CHEN T L , YU L , et al. Image classification based on the boost convolutional neural network[J]. IEEE Access, 2018, 6, 12755- 12768. doi: 10.1109/ACCESS.2018.2796722
27	PAN Y W , YANG S H , PENG H , et al. Specific emitter identification based on deep residual networks[J]. IEEE Access, 2019, 7, 54425- 54434. doi: 10.1109/ACCESS.2019.2913759
28	WANG X B, HUANG G M, ZHOU Z W, et al. Radar emitter recognition based on the short time Fourier transform and convolutional neural networks[C]//Proc. of the 10th IEEE International Congress on Image and Signal Processing, Biomedical Engineering and Informatics, 2017.
29	WANG X B , HUANG G M , ZHOU Z W , et al. Radar emitter recognition based on the energy cumulant of short time Fourier transform and reinforced deep belief network[J]. Sensors, 2018, 18 (9): 3103. doi: 10.3390/s18093103

调制方式	信号模型	参数
CW	$s(t)=A(t) \mathrm{e}^{\mathrm{j} 2 \pi f_{c} t}$	载频f_c
LFM	$s(t)=A(t) \mathrm{e}^{\mathrm{j} 2 \pi\left(f_{c} t-50 B f_{s} t^{2}\right)}$	带宽B
BFSK	$s(t)=A(t) \mathrm{e}^{\mathrm{j} 2 \pi f_{1} t}+A(t) \mathrm{e}^{\mathrm{j} 2 \pi f_{2} t}$	载频f₁, f₂
QFSK	$s(t)=\sum\limits_{i=1}^{4} A(t) \mathrm{e}^{\mathrm{j} 2 \pi f_{i} t}$	载频f_i
P1码-P4码	$s(t)=A(t) \mathrm{e}^{\mathrm{j}\left(2 \pi f_{c} t+\varphi_{m, n}+\theta\right)}$	载频f_c
2ASK	$s(t)=A(t) \mathrm{e}^{\mathrm{j} 2 \pi f_{c} t}$	载频f_c
QPSK	$s(t)=\sum\limits_{i=1}^{N} A(t) \mathrm{e}^{\mathrm{j}\left(2 \pi f_{c} t+\varphi_{m, n}\right)}$	相位φ_m,n 载频f_c
BPSK	$s(t)=\sum\limits_{i=1}^{N} A(t) \mathrm{e}^{\mathrm{j}\left(2 \pi f_{c} t+\pi C_{n}\right)}$	巴克码组C_n
BPSK+LFM	$s(t)=\sum\limits_{i=1}^{N} A(t) \mathrm{e}^{\mathrm{j}\left(2 \pi f_{c} t+\pi C_{n}-50 B f_{s} t^{2}\right)}$	带宽B 巴克码组C_n

码型	相位φ_m,n
P1	$\varphi_{m, n}=-\frac{\pi}{N}(N-(2 n-1))((n-1) N+m-1)$,$m=1,2, \cdots, N ; n=1,2, \cdots, N$
P2	$\varphi_{m, n}=\frac{\pi}{2 N}(N-(2 n-1))^{2}$,$n=1,2, \cdots, N,(N 为偶数)$
P3	$\varphi_{m}=\frac{\pi(m-1)^{2}}{N^{2}}, m=1,2, \cdots, N^{2}$
P4	$\varphi_{m}=\frac{\pi(m-1)^{2}}{N^{2}}-\pi(m-1)$,$m=1,2, \cdots, N^{2}$
QPSK	$\varphi_{m, n}=\frac{\pi}{8}(m-1)(n-1), m, n=1,2, \cdots, 16$

网络模型	空间复杂度
MLJ-RN	13.4×10⁶
ResNet-101	42.6×10⁶
AlexNet	52.0×10⁶
VGG-16	138.3×10⁶
GoogLeNet	10.3×10⁶

网络模型	每轮迭代时间	平均识别时间
MLJ-RN	116	15
ResNet-101	297	21
AlexNet	48	9
VGG-16	427	38
GoogLeNet	131	14

[1]	韩啸, 陈世文, 陈蒙, 杨锦程. 基于互易点学习的LPI信号开集识别[J]. 系统工程与电子技术, 2022, 44(9): 2752-2759.
[2]	金国栋, 薛远亮, 谭力宁, 许剑锟. 基于孪生神经网络的目标跟踪算法进展研究[J]. 系统工程与电子技术, 2022, 44(6): 1805-1822.
[3]	赵晓枫, 徐叶斌, 吴飞, 牛家辉, 蔡伟, 张志利. 基于全局感知机制的地面红外目标检测方法[J]. 系统工程与电子技术, 2022, 44(5): 1461-1467.
[4]	邹虹, 白陈阳, 何鹏, 崔亚平, 王汝言, 吴大鹏. 基于分布式深度学习的边缘服务放置策略[J]. 系统工程与电子技术, 2022, 44(5): 1728-1737.
[5]	陈冬, 句彦伟. 基于语义分割实现的SAR图像舰船目标检测[J]. 系统工程与电子技术, 2022, 44(4): 1195-1201.
[6]	孙晶明, 虞盛康, 孙俊. 基于深度学习的HRRP识别姿态敏感性分析[J]. 系统工程与电子技术, 2022, 44(3): 802-807.
[7]	姚云翔, 陈莹. 注意力机制下双模态交互融合的目标跟踪网络[J]. 系统工程与电子技术, 2022, 44(2): 410-419.
[8]	高涌荇, 王旭东, 汪玲, 朱岱寅, 郭军, 孟凡旺. 基于RCNN的双极化气象雷达天气信号检测[J]. 系统工程与电子技术, 2022, 44(11): 3380-3387.
[9]	曲凌志, 杨俊安, 刘辉, 黄科举. 嵌入注意力机制的通信辐射源个体识别方法[J]. 系统工程与电子技术, 2022, 44(1): 20-27.
[10]	周毅恒, 杨军, 夏赛强, 吕明久. 闪烁现象下旋翼目标微动参数估计方法[J]. 系统工程与电子技术, 2022, 44(1): 54-63.
[11]	付蓉, 黄天耀, 刘一民. 基于深度学习的捷变相参雷达1-Bit块稀疏重构[J]. 系统工程与电子技术, 2022, 44(1): 70-75.
[12]	张聿远, 张立民, 闫文君. 基于互相关特征图和扩张稠密卷积网络的SFBC-OFDM识别方法[J]. 系统工程与电子技术, 2021, 43(9): 2657-2664.
[13]	王彩云, 李阳雨, 李晓飞, 王佳宁, 魏文怡. 基于稀疏性深度学习的航拍图像超分辨重构[J]. 系统工程与电子技术, 2021, 43(8): 2045-2050.
[14]	黄月平, 李小锋, 杨小冈, 齐乃新, 卢瑞涛, 张胜修. 基于相关滤波的视觉目标跟踪算法新进展[J]. 系统工程与电子技术, 2021, 43(8): 2051-2065.
[15]	王彬, 王国宇. 基于改进的深度学习网络的SAR图像瞬时海岸线自动提取算法[J]. 系统工程与电子技术, 2021, 43(8): 2108-2115.