基于SE-ResNeXt网络的低信噪比LPI雷达辐射源信号识别

doi:10.12305/j.issn.1001-506X.2022.12.11

系统工程与电子技术 ›› 2022, Vol. 44 ›› Issue (12): 3676-3684.doi: 10.12305/j.issn.1001-506X.2022.12.11

基于SE-ResNeXt网络的低信噪比LPI雷达辐射源信号识别

徐桂光¹, 王旭东^1,*, 汪飞¹, 胡国兵², 高涌荇¹, 罗泽虎¹

1. 南京航空航天大学电子信息工程学院/集成电路学院, 江苏南京 211106
2. 金陵科技学院电子信息工程学院, 江苏南京 211169

收稿日期:2021-09-07 出版日期:2022-11-14 发布日期:2022-11-24
通讯作者: 王旭东
作者简介:徐桂光(1996—), 男, 硕士研究生, 主要研究方向为雷达信号处理|王旭东(1979—), 男, 副教授, 主要研究方向为信号检测、参数估计、FPGA设计应用|汪飞(1976—), 男, 副教授, 主要研究方向为飞机射频隐身技术与微弱信号检测|胡国兵(1978—), 男, 教授, 主要研究方向为信号检测、识别与参数估计|高涌荇(1996—), 男, 硕士研究生, 主要研究方向为气象雷达目标识别|罗泽虎(1997—), 男, 硕士研究生, 主要研究方向为气象雷达目标识别
基金资助:
江苏省高等学校自然科学研究重大项目(20KJA510008);江苏省基础研究计划(自然科学基金)(BK20161104)

LPI radar emitter signals recognition in low SNR based on SE-ResNeXt network

Guiguang XU¹, Xudong WANG^1,*, Fei WANG¹, Guobing HU², Yongxing GAO¹, Zehu LUO¹

1. College of Electronic and Information Engineering/College of Integrated Circuits, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, China
2. Jinling Institute of Technology, Nanjing 211169, China

Received:2021-09-07 Online:2022-11-14 Published:2022-11-24
Contact: Xudong WANG

摘要/Abstract

摘要：

针对低信噪比(signal to noise ratio, SNR)低截获概率(low probability of intercept, LPI)雷达脉内波形识别准确率低的问题，提出一种基于时频分析、压缩激励(squeeze excitation, SE)和ResNeXt网络的雷达辐射源信号识别方法。首先通过Choi-Williams分布(Choi-Williams distribution, CWD)获得雷达时域信号的二维时频图像(time-frequency image, TFI)；然后进行TFI预处理降低噪声干扰和频率维的位置分布差异，以适应深度学习网络输入；最后在ResNeXt基础上加入扩张卷积和SE结构提取TFI特征，实现雷达辐射源分类。实验结果表明，SNR低至-8 dB时，该方法对12类常见LPI雷达波形的整体识别准确率依然能达到98.08%。

关键词: 低截获概率雷达波形, 辐射源信号识别, 残差网络, 压缩激励结构, 时频分析

Abstract:

Aiming at the problem of low signal to noise ratio (SNR) and low probability of intercept (LPI) radar pulse waveform recognition accuracy, a radar emitter signal recognition method based on time-frequency analysis, squeeze-excitation (SE) and ResNeXt network is proposed. Firstly, the radar time domain signal is transformed into a two-dimensional time-frequency image (TFI) by Choi-Williams distribution (CWD); then, the TFI pre-processing is used to reduce the noise interference and the difference in frequency dimension location distribution, adapting to deep learning network input; finally, the TFI features are extracted by adding dilated convolution and SE structure on the basis of ResNeXt to achieve radar emitter classification. The experimental results show that when the SNR is as low as -8 dB, the overall recognition accuracy of the method for 12 types of common LPI radar waveforms can still reach 98.08%.

Key words: low probability of intercept (LPI) radar waveform, emitter signal recognition, residual network, squeeze excitation (SE) structure, time-frequency analysis

中图分类号:

TN957.5

徐桂光, 王旭东, 汪飞, 胡国兵, 高涌荇, 罗泽虎. 基于SE-ResNeXt网络的低信噪比LPI雷达辐射源信号识别[J]. 系统工程与电子技术, 2022, 44(12): 3676-3684.

Guiguang XU, Xudong WANG, Fei WANG, Guobing HU, Yongxing GAO, Zehu LUO. LPI radar emitter signals recognition in low SNR based on SE-ResNeXt network[J]. Systems Engineering and Electronics, 2022, 44(12): 3676-3684.

图/表 17

图1

图2

图3

图4

图5

图6

图7

图8

图9

图10

表1

表2

图11

图12

图13

图14

图15

参考文献 30

1	WANG C, WANG J, ZHANG X D. Automatic radar waveform recognition based on time-frequency analysis and convolutional neural network[C]//Proc. of the IEEE International Conference on Acoustics, Speech and Signal Processing, 2017: 2437-2441.
2	ZHANG M , DIAO M , GAO L P , et al. Neural networks for radar waveform recognition[J]. Symmetry, 2017, 9 (5): 75. doi: 10.3390/sym9050075
3	CHEN T , LIU L Z . LPI radar waveform recognition based on multi-branch MWC compressed sampling receiver[J]. IEEE Access, 2018, 6, 30342- 30354. doi: 10.1109/ACCESS.2018.2845102
4	ZHOU Z W , HUANG G M , CHEN H Y , et al. Automatic radar waveform recognition based on deep convolutional denoising autoencoders[J]. Circuits, Systems, and Signal Processing, 2018, 37 (9): 4034- 4048. doi: 10.1007/s00034-018-0757-0
5	KONG S H , KIM M , HOANG L M , et al. Automatic LPI radar waveform recognition using CNN[J]. IEEE Access, 2018, 6, 4207- 4219. doi: 10.1109/ACCESS.2017.2788942
6	黄颖坤, 金炜东, 余志斌, 等. 基于深度学习和集成学习的辐射源信号识别[J]. 系统工程与电子技术, 2018, 40 (11): 33- 38.
	HUANG Y K , JIN W D , YU Z B , et al. Radar emitter signal recognition based on deep learning and ensemble learning[J]. Systems Engineering and Electronics, 2018, 40 (11): 33- 38.
7	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
8	郭立民, 寇韵涵, 陈涛, 等. 基于栈式稀疏自编码器的低信噪比下低截获概率雷达信号调制类型识别[J]. 电子与信息学报, 2018, 40 (4): 875- 881.
	GUO L M , KOU Y H , CHEN T , et al. Low probability of intercept radar signal recognition based on stacked sparse auto-encoder[J]. Journal of Electronics & Information Technology, 2018, 40 (4): 875- 881.
9	QU Z Y , MAO X J , DENG Z A . Radar signal intra-pulse modulation recognition based on convolutional neural network[J]. IEEE Access, 2018, 6, 43874- 43884. doi: 10.1109/ACCESS.2018.2864347
10	叶文强, 俞志富, 张奎. 基于DAE+CNN辐射源信号识别算法[J]. 计算机应用研究, 2019, 36 (12): 3815- 3818.
	YE W Q , YU Z F , ZHANG K . Recognition algorithm of emitter signal based on DAE+CNN[J]. Application Research of Computers, 2019, 36 (12): 3815- 3818.
11	QU Z , HOU C F , HOU C B , et al. Radar signal intra-pulse modulation recognition based on convolutional neural network and deep Q-learning network[J]. IEEE Access, 2020, 8, 49125- 49136. doi: 10.1109/ACCESS.2020.2980363
12	RICHARD G , WILEY E . The interception and analysis of radar signals[M]. Boston: Artech House, 2006.
13	XIE S, GIRSHICK R, DOLLAR P, et al. Aggregated residual transformations for deep neural networks[C]//Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, 2017: 1492-1500.
14	YU F, KOLTUN V. Multi-scale context aggregation by dilated convolutions[EB/OL]. [2021-09-01]. https://arxiv.org/abs/1511.07122.
15	HU J, SHEN L, SUN G, et al. Squeeze-and-excitation networks[C]//Proc. of the IEEE conference on computer vision and pattern recognition, 2018: 7132-7141.
16	万磊, 佟鑫, 盛明伟, 等. Softmax分类器深度学习图像分类方法应用综述[J]. 导航与控制, 2019, 18 (6): 1- 9. doi: 10.3969/j.issn.1674-5558.2019.06.001
	WAN L , TONG X , SHENG M W , et al. Review of image classification based on softmax classifier in deep learning[J]. Navigation and Control, 2019, 18 (6): 1- 9. doi: 10.3969/j.issn.1674-5558.2019.06.001
17	FENG Z P , LIANG M , CHU F L . Recent advances in time-frequency analysis methods for machinery fault diagnosis: a review with application examples[J]. Mechanical Systems and Signal Processing, 2013, 38 (1): 165- 205. doi: 10.1016/j.ymssp.2013.01.017
18	WANG C, WANG J, ZHANG X D. Automatic radar waveform recognition based on time-frequency analysis and convolutional neural network[C]//Proc. of the IEEE international Conference on Acoustics, Speech and Signal Processing, 2017: 2437-2441.
19	胡丹. 低截获概率雷达辐射源信号降噪与检测技术研究[D]. 哈尔滨: 哈尔滨工业大学, 2017.
	HU D. Research on denoise and detection technology of low probability radar radiation source signal[D]. Harbin: Harbin Institute of Technology, 2017.
20	王旭东, 刘渝. 多通道自相关信号检测算法及其FPGA实现[J]. 仪器仪表学报, 2007, 28 (5): 875- 881. doi: 10.3321/j.issn:0254-3087.2007.05.021
	WANG X D , LIU Y . Multi-channel self-correlation signal detection algorithm and its FPGA implementation[J]. Chinese Journal of Scientific Instrument, 2007, 28 (5): 875- 881. doi: 10.3321/j.issn:0254-3087.2007.05.021
21	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.
22	SZEGEDY C, LIU W, JIA Y Q, et al. Going deeper with convolutions[C]//Proc. of the IEEE conference on computer vision and pattern recognition, 2015.
23	ABIEN F A. Deep learning using rectified linear units (relu)[EB/OL]. [2021-09-01]. https//arxiv.org/abs/1803.08375.
24	GLOROT X, BORDES A, BENGIO Y. Deep sparse rectifier neural networks[C]//Proc. of the 14th International Conference on Artificial Intelligence and Statistics, 2011: 315-323.
25	LOFFE S, SZEGEDY C. Batch normalization: accelerating deep network trainingby reducing internal covariate shift[C]//Proc. of the International Conference on Machine Learning, 2015: 448-456.
26	PASZKE A , GROSS S , MASSA F , et al. Pytorch: an imperative style, high performance deep learning library[J]. Advances in Neural Information Processing Systems, 2019, 32, 8026- 8037.
27	KINGMA D P, BA J. Adam: a method for stochastic optimization[EB/OL]. [2021-09-01]. https://arxiv.org/abs/1412.6980.
28	秦鑫, 黄洁, 查雄, 等. 基于扩张残差网络的雷达辐射源信号识别[J]. 电子学报, 2020, 48 (3): 456- 462. doi: 10.3969/j.issn.0372-2112.2020.03.006
	QIN X , HUANG J , ZHA X , et al. Radar emitter signal recognition based on dilated residual network[J]. Acta Electionica Sinica, 2020, 48 (3): 456- 462. doi: 10.3969/j.issn.0372-2112.2020.03.006
29	QIN X, ZHA X, HUANG J, et al. Radar waveform recognition based on deep residual network[C]//Proc. of the IEEE 8th Joint International Information Technology and Artificial Intelligence Conference, 2019: 892-896.
30	LAUREN V D M , HINTON G . Visualizing data using t-SNE[J]. Journal of Machine Learning Research, 2008, 9, 2579- 2605.

层名	输出尺寸	网络结构(16×4 d)
第1层	112×112	卷积, 7×7, 64, 步长2
第2层	56×56	最大值池化3×3, 步长2
第2层	56×56	$ \left[\begin{array}{l}\text { 卷积, } 1 \times 1, 64, 1 \\\text { 卷积, } 3 \times 3, 64, 16 \\\text { 卷积, } 1 \times 1, 128, 1 \\\mathrm{FC}, [8, 128]\end{array}\right]$
第3层	28×28	$\left[\begin{array}{l}\text { 卷积, } 1 \times 1, 128, 1 \\\text { 卷积, } 3 \times 3, 128, 16 \\\text { 卷积, } 1 \times 1, 256, 1 \\\mathrm{FC}, [16, 256]\end{array}\right] $
第4层	28×28	$ \left[\begin{array}{l}\text { 卷积, } 1 \times 1, 256, 1 \\\text { 卷积, } 3 \times 3, 256, 16 \\\text { 卷积, } 1 \times 1, 512, 1 \\\mathrm{FC}, [32, 512]\end{array}\right]$
第5层	28×28	$ \left[\begin{array}{l}\text { 卷积, } 1 \times 1, 512, 1 \\\text { 卷积, } 3 \times 3, 512, 16 \\\text { 卷积, } 1 \times 1, 1024, 1 \\\mathrm{FC}, [64, 1024]\end{array}\right]$
-	1×1	GAP, 12-d FC, Softmax

信号类型	参数	取值范围
LFM	载频f_c	U(1/10, 1/3)
LFM	带宽B	U(1/10, 1/5)
Costas	跳频序列L	{3, 4, 5, 6}
Costas	基准频率f_min	U(1/24, 1/20)
BPSK	载频f_c	U(1/10, 1/3)
BPSK	巴克码长度L_c	{7, 11, 13}
Frank P1, P2	载频f_c	U(1/10, 1/3)
	相位控制数M	^{[8, 12]} P2码M为偶数
	相位子波数cpp	^{[2, 5]}
P3, P4	载频f_c	U(1/10, 1/3)
	相位控制数M	{36, 64, 81, 100}
	相位子波数cpp	^{[2, 5]}
T1, T2	载频f_c	U(1/10, 1/3)
T1, T2	波形段数k	^{[4, 6]}
T3, T4	载频f_c	U(1/10, 1/3)
	波形段数k	^{[4, 6]}
	调制带宽B	U(1/20, 1/8)

[1]	秦博伟, 蒋磊, 许华, 齐子森. 基于残差生成对抗网络的调制识别算法[J]. 系统工程与电子技术, 2022, 44(6): 2019-2026.
[2]	侯召国, 王华伟, 周良, 付强. 基于改进深度残差网络的旋转机械故障诊断[J]. 系统工程与电子技术, 2022, 44(6): 2051-2059.
[3]	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.
[4]	何炜琨, 刘昂, 王晓亮, 张莹, 陈敏. 机载阵列雷达风轮机回波信号建模与分析[J]. 系统工程与电子技术, 2021, 43(3): 666-675.
[5]	高诗飏, 董会旭, 田润澜, 张歆东. 基于SRNN+Attention+CNN的雷达辐射源信号识别方法[J]. 系统工程与电子技术, 2021, 43(12): 3502-3509.
[6]	张良, 杨威, 李玮杰, 杨小琪, 刘永祥. 基于复数卷积-残差网络的雷达杂波幅度统计模型分类[J]. 系统工程与电子技术, 2021, 43(11): 3086-3097.
[7]	孙艺聪, 田润澜, 王晓峰, 董会旭, 戴普. 基于改进CLDNN的辐射源信号识别[J]. 系统工程与电子技术, 2021, 43(1): 42-47.
[8]	杨文彬, 李旦, 张建秋. 分量载频差极小时频信号的超分辨率分析方法[J]. 系统工程与电子技术, 2020, 42(9): 1881-1889.
[9]	周阳, 毕大平, 沈爱国. 基于IRT的大动态反射系数微动目标检测算法[J]. 系统工程与电子技术, 2020, 42(9): 1935-1944.
[10]	李亚兰, 金炜东, 葛鹏. 基于VMD和特征融合的辐射源信号识别[J]. 系统工程与电子技术, 2020, 42(7): 1499-1503.
[11]	李建周, 刘祥威. 基于时隙差的电磁散射机理分解技术[J]. 系统工程与电子技术, 2020, 42(3): 513-520.
[12]	石礼盟, 杨承志, 吴宏超. 基于深层残差网络和三元组损失的雷达信号识别方法[J]. 系统工程与电子技术, 2020, 42(11): 2506-2512.
[13]	张盛魁, 姚志成, 何岷, 范志良, 杨剑. 改进时频脊线的跳频参数盲估计算法[J]. 系统工程与电子技术, 2019, 41(12): 2885-2890.
[14]	李建周, 刘祥威, 范超群, 刘露, 齐玉涛. 多自由度飞行目标动态建模及其散射特性分析[J]. 系统工程与电子技术, 2019, 41(11): 2401-2407.
[15]	徐丹, 符吉祥, 孙光才, 邢孟道, 苏涛. 宽带弹道高速群目标运动精补偿方法[J]. 系统工程与电子技术, 2019, 41(10): 2205-2213.

基于SE-ResNeXt网络的低信噪比LPI雷达辐射源信号识别

LPI radar emitter signals recognition in low SNR based on SE-ResNeXt network

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 17

参考文献 30

相关文章 15

编辑推荐

Metrics

本文评价