基于改进残差神经网络的雷达信号识别方法

doi:10.12305/j.issn.1001-506X.2024.10.13

摘要/Abstract

摘要：

针对低信噪比情况下, 雷达信号特征提取困难, 导致识别准确率较低的问题, 提出一种基于改进残差神经网络的雷达信号调制识别方法。首先使用时频分析方法, 将时域信号转化为二维时频图像; 然后对图像进行灰度化、高斯滤波、双线性插值、归一化等预处理, 作为深度学习模型的输入; 最后搭建改进的残差神经网络, 利用空间和通道重构单元减少特征冗余, 提高特征提取精度, 从而提高低信噪比下雷达信号识别准确率。仿真实验结果表明, 信噪比为-8 dB时, 该方法对12类典型雷达信号的整体识别准确率达到96.67%, 具有较好的噪声鲁棒性与抗混淆能力。

关键词: 辐射源信号识别, 时频分析, 深度学习, 残差神经网络

Abstract:

In the case of low signal to noise ratio, radar signal feature extraction is difficult, resulting in low recognition accuracy, a radar signal modulation recognition method based on improved residual neural network is proposed. Firstly, the time-frequency analysis method is used to transform the time-domain signal into a two-dimensional time-frequency image. Then, the image is preprocessed by graying, Gaussian filtering, bilinear interpolation, normalization, etc., as the input of the deep learning model. Finally, an improved residual neural network is built, which uses space and channel reconstruction units to reduce feature redundancy and improve feature extraction accuracy, thereby improving radar signal recognition accuracy under low signal to noise ratio. Simulation results show that when the signal to noise ratio is -8 dB, the overall recognition accuracy of the proposed method for 12 typical radar signals reaches 96.67%, which has good noise robustness and anti-confusion ability.

Key words: emitter signal recognition, time-frequency analysis, deep learning, residual neural network

中图分类号:

TN971

聂千祁, 沙明辉, 朱应申. 基于改进残差神经网络的雷达信号识别方法[J]. 系统工程与电子技术, 2024, 46(10): 3356-3364.

Qianqi NIE, Minghui SHA, Yingshen ZHU. Radar signal recognition method based on improved residual neural network[J]. Systems Engineering and Electronics, 2024, 46(10): 3356-3364.

图/表 15

图1

图2

图3

图4

图5

图6

图7

表1

图8

图9

表2

图10

图11

表3

图12

参考文献 30

1	张国柱, 黄可生, 姜文利, 等. 基于信号包络的辐射源细微特征提取方法[J]. 系统工程与电子技术, 2006, 28 (6): 795- 797.
	ZHANG G Z , HUANG K S , JIANG W L , et al. Emitter feature extract method based on signal envelope[J]. Systems Engineering and Electronics, 2006, 28 (6): 795- 797.
2	YILDIRIM A . Method for estimating the central frequency of phase-coded radar signals[J]. IET Signal Processing, 2016, 10 (9): 1073- 1081. doi: 10.1049/iet-spr.2016.0237
3	王国涛, 姜秋喜, 刘方正, 等. 基于频谱和瞬时自相关的雷达信号调制识别[J]. 兵器装备工程学报, 2022, 43 (1): 200- 205.
	WANG G T , JIANG Q X , LIU F Z , et al. Radar signal modulation recognition based on spectrum and instaneous autocorrelation[J]. Journal of Ordnance Equipment Engineering, 2022, 43 (1): 200- 205.
4	AMIN V S, ZHANG Y D, HIMED B. Improved instaneous frequency estimation of multi-component FM signals[C]//Proc. of the IEEE Radar Conference, 2019.
5	ZHANG M , LIU L T , DIAO M . LPI radar waveform recognition based on time-frequency distribution[J]. Sensors, 2016, 16 (10): 1682. doi: 10.3390/s16101682
6	HELBERT S , KERISTA S , SYAHRUL H , et al. Time frequency signal classification using continuous wavelet transformation[J]. IOP Conference Series Materials Science and Engineering, 2020, 851 (1): 12045- 12051. doi: 10.1088/1757-899X/851/1/012045
7	QU Q Z, WANG Y L, DU Q L. Automatic modulation recognition for radar signals based on ACSE networks[C]//Proc. of the CIE International Conference on Radar, 2021: 1104-1107.
8	WANG G M, CHEN S W, HU X, et al. Radar emitter sorting and recognition based on time-frequency image union feature[C]//Proc. of the IEEE 4th International Conference on Signal and Image Processing, 2019: 165-170.
9	HAN L H , HUANG G M . Intrapulse modulation recognition of radar signals based on spectrum analysis[J]. Electronic Information Warfare Technology, 2011, 26 (3): 29- 32.
10	孟祥豪, 赵海旭, 梁言. 一种基于对角积分双谱的复合调制LPI雷达信号识别方法[J]. 航天电子对抗, 2021, 37 (5): 13-18, 24.
	MENG X H , ZHAO H X , LIANG Y . A compound modulated LPI radar signal recognition method based on diagonal integral bispectrum[J]. Aerospace Electronic Warfare, 2021, 37 (5): 13-18, 24.
11	刘赢, 田润澜, 王晓峰. 基于深层卷积神经网络和双谱特征的雷达信号识别方法[J]. 系统工程与电子技术, 2019, 41 (9): 1998- 2005.
	LIU Y , TIAN R L , WANG X F . Radar signal recognition method based on deep convolutional neural network and bispectrum feature[J]. Systems Engineering and Electronics, 2019, 41 (9): 1998- 2005.
12	MI X P , CHEN X H , LIU Q , et al. Radar signals modulation recognition based on bispectrum feature processing[J]. Journal of Physics: Conference Series, 2021, 1971 (1): 12099- 12110. doi: 10.1088/1742-6596/1971/1/012099
13	YUAN X Y , HE P , ZHU Q L , et al. Adversarial examples: attacks and defenses for deep learning[J]. IEEE Trans.on Neural Networks and Learning Systems, 2019, 30 (9): 2805- 2824. doi: 10.1109/TNNLS.2018.2886017
14	O'SHEA T J , ROY T , CLANCY T C . Over-the-air deep learning based radio signal classification[J]. IEEE Journal of Selected Topics in Signal Processing, 2018, 12 (1): 168- 179. doi: 10.1109/JSTSP.2018.2797022
15	XU Z Y . Research on deep learning in natural language processing[J]. Advances in Computer and Communication, 2023, 4 (3): 196- 200.
16	HU K J , LI H Y , XU S F , et al. Nonlinear signal classification based on wavelet transform and deep belief network[J]. Journal of Physics: Conference Series, 2021, 1948 (1): 12029- 12034.
17	ZHOU Z W , HUANG G M , CHEN H Y , et al. Automatic radar waveform recognition based on deep convolutional denoising auto-encoders[J]. Circuits, Systems, and Signal Processing, 2018, 37 (9): 4043- 4048.
18	LIU L T , LI X Y . Radar signal recognition based on triplet convolutional neural network[J]. EURASIP Journal on Advances in Signal Processing, 2021, 112.
19	杨洁, 张欢. 基于改进型AlexNet的LPI雷达信号识别[J]. 现代电子技术, 2020, 43 (5): 57- 60.
	YANG J , ZHANG H . LPI radar signal recognition based on improved AlexNet[J]. Modern Electronics Technique, 2020, 43 (5): 57- 60.
20	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.
21	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.
	QIN X , HUANG J , ZHA X , et al. Radar emitter signal recognition based on dilated residual network[J]. Acta Electronica Sinica, 2020, 48 (3): 456- 462.
22	QU Z Y , MAO X J , DENG Z A . Radar signal intra-pulse mo-dulation recognition based on convolutional neural network[J]. IEEE Access, 2018, 6, 43874- 43884.
23	HUANG D K , YAN X P , HAO X H , et al. Low SNR multi-emitter signal sorting and recognition method based on low-order cyclic statistics CWD time-frequency images and the YOLOv5 deep learning model[J]. Sensors, 2022, 22 (20): 7783- 7805.
24	肖易寒, 王亮, 郭玉霞. 基于去噪卷积神经网络的雷达信号调制类型识别[J]. 电子与信息学报, 2021, 43 (8): 2300- 2307.
	XIAO Y H , WANG L , GUO Y X . Radar signal modulation type recognition based on denoising convolutional neural network[J]. Journal of Electronics and Information Technology, 2021, 43 (8): 2300- 2307.
25	LI J , ZHANG H Q , OU J P , et al. A radar signal recognition approach via ⅡF-Net deep learning models[J]. Computational Intelligence and Neuroscience, 2020, 8858588.
26	SI W J , WAN C X , DENG Z A . An efficient deep convolutional neural network with features fusion for radar signal recognition[J]. Multimedia Tools and Applications, 2023, 82, 2871- 2885.
27	QUAN D Y , TANG Z Y , WANG X F , et al. LPI radar signal recognition based on dual-channel CNN and feature fusion[J]. Symmetry, 2022, 14 (3): 570- 582.
28	ZHANG X L , ZHANG J Z , LUO T Z , et al. Radar signal intrapulse modulation recognition based on a denoising-guided disentangled network[J]. Remote Sensing, 2022, 14 (5): 1252- 1266.
29	LI J F, WEN Y, HE L H. SCConv: spatial and channel reconstruction convolution for feature redundancy[C]//Proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023: 6153-6162.
30	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.

信号类型	参数	取值范围
LFM	起始频率/GHz	[4, 5]
NLFM	带宽/MHz	[30, 100]
BPSK	载频/GHz	[4, 5]
BPSK	巴克码长度	{7, 11, 13}
QPSK	载频/GHz	[4, 5]
LFM-BPSK	基准频率/GHz	[4, 5]
LFM-BPSK	子脉冲带宽/MHz	{2, 3, 4, 5, 6}
LFM-FSK	基准频率/MHz	[60, 150]
FSK-PSK	基准频率/MHz	[60, 150]
P1~P4	载频/MHz	[60, 150]
P1~P4	相位控制数	{4, 5, 6, 7, 8}(P2码取偶数)
Costas	基准频率/MHz	[60, 150]
Costas	跳频序列长度	{5, 6, 7, 10}

网络模型	空间复杂度/byte	时间复杂度/s
GoogleNet	6.31M	606.72
VGG19	139.63M	279.44
SENet	11.27M	403.86
ResNeXt50	14.61M	592.11
SCConv-ResNet18	11.03M	330.72

方法	空间复杂度/byte	时间复杂度/s
AlexNet	26.11M	172.70
ResNet	11.17M	364.24
DRN	15.89M	239.89
SCConv-ResNet18	11.03M	330.72

[1]	蔡伟, 王鑫, 蒋昕昊, 杨志勇, 陈栋. 基于解耦的小样本目标检测方法研究[J]. 系统工程与电子技术, 2024, 46(9): 2941-2950.
[2]	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.
[3]	陈晓萱, 徐书文, 胡绍海, 马晓乐. 基于卷积与自注意力的红外与可见光图像融合[J]. 系统工程与电子技术, 2024, 46(8): 2641-2649.
[4]	张瑞斌, 朱梦韬, 李云杰. 对调制识别网络隐身的雷达发射信号生成方法[J]. 系统工程与电子技术, 2024, 46(7): 2256-2268.
[5]	华煜明, 王东亚, 朱天林, 金胜, 王洋. 复合微多普勒信号的时频谐波分析方法[J]. 系统工程与电子技术, 2024, 46(7): 2301-2309.
[6]	汪强龙, 高晓光, 吴必聪, 胡子剑, 万开方. 受限玻尔兹曼机及其变体研究综述[J]. 系统工程与电子技术, 2024, 46(7): 2323-2345.
[7]	孙先涛, 江汪洋, 陈文杰, 陈伟海, 智亚丽. 基于感兴趣区域的物体抓取位姿检测[J]. 系统工程与电子技术, 2024, 46(6): 1867-1877.
[8]	牛闯, 林强, 段敏, 施端阳, 谷成刚. 脉内频率-时延捷变雷达抗间歇采样转发干扰方法[J]. 系统工程与电子技术, 2024, 46(5): 1583-1598.
[9]	陈雪梅, 刘志恒, 周绥平, 余航, 刘彦明. 基于HRNet的高分辨率遥感影像道路提取方法[J]. 系统工程与电子技术, 2024, 46(4): 1167-1173.
[10]	张天文, 张晓玲, 邵子康, 曾天娇. 基于掩模注意型交互的SAR舰船实例分割[J]. 系统工程与电子技术, 2024, 46(3): 831-838.
[11]	季然, 肖茂森, 李硕, 刘宇, 罗湛仪, 程嘉维. 基于机器学习的MRTD客观测试方法研究[J]. 系统工程与电子技术, 2024, 46(10): 3265-3270.
[12]	施端阳, 林强, 胡冰, 杜小帅. 基于YOLO的航管一次雷达目标检测方法[J]. 系统工程与电子技术, 2024, 46(1): 143-151.
[13]	汪萌, 诸兵. 不确定性建模在2D和3D目标检测中的应用[J]. 系统工程与电子技术, 2023, 45(8): 2370-2376.
[14]	王磊, 张志勇, 胥辉旗, 曾维贵, 曹司磊. 基于VMD分解和多域联合分布的雷达辐射源识别[J]. 系统工程与电子技术, 2023, 45(8): 2479-2488.
[15]	邵凯, 杜自群, 王光宇. 基于模型剪枝动态调整压缩率的CSI反馈方法[J]. 系统工程与电子技术, 2023, 45(8): 2615-2622.