基于高次时频谱特征的LPI雷达信号识别

李世通; 金小萍; 孙杰; 汪晓锋

doi:10.13700/j.bh.1001-5965.2022.0993

基于高次时频谱特征的LPI雷达信号识别

doi: 10.13700/j.bh.1001-5965.2022.0993

1.
中国计量大学信息工程学院浙江省电磁波信息技术与计量检测重点实验室，杭州 310000
2.
浙江省计量科学研究院，杭州 310000

基金项目:

浙江省自然科学基金(LQ20F020021)；浙江省电磁波信息技术与计量检测重点实验室开放式项目(2019KF0003)

详细信息

通讯作者:
E-mail：jxp1023@cjlu.edu.cn

中图分类号: TN791
计量
- 文章访问数: 1060
- HTML全文浏览量: 499
- PDF下载量: 83
- 被引次数: 0
出版历程
- 收稿日期: 2022-12-13
- 录用日期: 2023-03-17
- 网络出版日期: 2023-04-03
- 整期出版日期: 2025-01-31

LPI radar signal recognition based on high-order time-frequency spectrum features

1.
Key Laboratory of Electromagnetic Wave Information Technology and Metrology of Zhejiang Province，College of Information Engineering，China Jiliang University，Hangzhou 310000，China
2.
Zhejiang Institute of Metrology，Hangzhou 310000，China

Funds:

Zhejiang Provincial Natural Science Foundation of China (LQ20F020021); Open Project Funding of the Key Laboratory of Electromagnetic Wave Information Technology and Metrology of Zhejiang Province (2019KF0003)

More Information

Corresponding author: E-mail：jxp1023@cjlu.edu.cn

摘要

摘要:
针对传统LPI雷达信号识别算法在低信噪比下识别率较低的问题，提出了一种基于高次时频特征的雷达信号识别算法。利用时频变换得到雷达信号的时频分布，时频谱做幂次化计算得到信号的高次时频图像，提取时频图像的灰度梯度共生矩阵和伪Zernike特征并组成联合特征向量，通过支持向量机实现雷达信号的分类识别。实验结果表明：在信噪比为−6 dB时，所提算法对8种典型雷达信号的整体识别准确率能达到95%以上。
- 雷达信号识别 /
- 时频变换 /
- 高次时频 /
- 特征提取 /
- 支持向量机
Abstract:
In view of the low recognition rate of traditional low probability of intercept (LPI) radar signal recognition algorithms under low signal-to-noise ratios, a radar signal recognition algorithm based on high-order time-frequency features was proposed. The proposed algorithm firstly obtained the time-frequency distribution of radar signals by time-frequency transform, and then the power calculation of the time-frequency spectrum was done to obtain the high-order time-frequency image of the signal. The gray gradient co-generation matrix and pseudo-Zernike features of the time-frequency image were extracted and formed into a joint feature vector, and finally, the classification recognition of the radar signal was realized by the support vector machine (SVM). The experimental results show that the overall recognition accuracy of the proposed algorithm can reach more than 95% for eight typical radar signals when the signal-to-noise ratio is −6 dB.
- radar signal recognition /
- time-frequency transform /
- high-order time-frequency /
- feature extraction /
- support vector machine

HTML全文

图 1 −6 dB下8种雷达信号CWD时频图像

Figure 1. CWD time-frequency images of eight radar signals with SNR of −6 dB

下载: 全尺寸图片幻灯片

图 2 −6 dB下8种雷达信号PCWD时频图像

Figure 2. PCWD time-frequency images of eight radar signals with SNR of −6 dB

下载: 全尺寸图片幻灯片

图 3 时频图像预处理流程

Figure 3. Time-frequency image preprocessing

下载: 全尺寸图片幻灯片

图 4 算法流程

Figure 4. Flow chart of algorithm

下载: 全尺寸图片幻灯片

图 5 总体识别率曲线

Figure 5. Overall recognition rate curve

下载: 全尺寸图片幻灯片

图 6 8种雷达信号识别率曲线

Figure 6. Recognition rate curve of eight radar signals

下载: 全尺寸图片幻灯片

图 7 分类结果的混淆矩阵

Figure 7. Confusion matrix for classification results

下载: 全尺寸图片幻灯片

图 8 不同识别算法对比

Figure 8. Comparison of different recognition algorithms

下载: 全尺寸图片幻灯片

表 1 仿真信号参数设置

Table 1. Simulation signal parameter setting

雷达信号	仿真参数	取值范围
LFM，NLFM	起始频率/Hz	$U(1/16,1/8)$
LFM，NLFM	带宽/Hz	$U(1/16,1/8)$
BPSK	巴克码长度/个	$ \{ 5,7,11,13\} $
BPSK	载波频率/Hz	$ U(1/8,1/4) $
Frank	步进频率/Hz	$ \{ 4,8\} $
Frank	载波频率/Hz	$ U(1/8,1/4) $
Costas	调频序列/Hz	[3,5]
Costas	基准频率/Hz	$U(1/24,1/20)$
LFM/BPSK	基准频率/Hz	$U(1/24,1/20)$
	带宽/Hz	$U(1/16,1/8)$
	巴克码长度/个	$ \{ 5,7,11,13\} $
LFM/FSK	基准频率/Hz	$U(1/24,1/20)$
LFM/FSK	子码带宽/Hz	$U(1/20,1/10)$
FSK/BPSK	巴克码长度/个	$ \{ 5,7,11,13\} $
FSK/BPSK	基准频率/Hz	$U(1/24,1/20)$

下载: 导出CSV

参考文献(17)

[1]	孙艺聪, 田润澜, 董会旭, 等. 基于SAMME+ResNet的多相码信号识别方法[J]. 系统工程与电子技术, 2020, 42(10): 2239-2245. SUN Y C, TIAN R L, DONG H X, et al. Polyphase code signal recognition method based on SAMME+ResNet[J]. Systems Engineering and Electronics, 2020, 42(10): 2239-2245(in Chinese).
[2]	徐卓君, 杨雯婷, 杨承志, 等. 雷达脉内调制识别的改进残差神经网络算法[J]. 吉林大学学报(工学版), 2021, 51(4): 1454-1460. XU Z J, YANG W T, YANG C Z, et al. Improved residual neural network algorithm for radar intrapulse modulation classification[J]. Journal of Jilin University (Engineering and Technology Edition), 2021, 51(4): 1454-1460(in Chinese).
[3]	徐帅, 刘鲁涛. P-Net框架下的小样本雷达信号识别算法[J]. 哈尔滨工程大学学报, 2022, 43(5): 739-744. XU S, LIU L T. Small sample radar signal recognition algorithm under the P-Net framework[J]. Journal of Harbin Engineering University, 2022, 43(5): 739-744(in Chinese).
[4]	万海东, 蔡伟, 刘则林. 基于图像化特征的雷达信号个体识别与工作模式识别方法[J]. 空天预警研究学报, 2022, 36(2): 79-84. WAN H D, CAI W, LIU Z L. Method of individual recognition and operating mode recognition of radar signal based on image features[J]. Journal of Air & Space Early Warning Research, 2022, 36(2): 79-84(in Chinese).
[5]	白航, 赵拥军, 胡德秀, 等. 基于Choi-Williams时频图像特征的雷达辐射源识别[J]. 数据采集与处理, 2012, 27(4): 480-485. BAI H, ZHAO Y J, HU D X, et al. Radar emitter recognition based on image feature of Choi-Williams time-frequency distribution[J]. Data Acquisition and Processing, 2012, 27(4): 480-485(in Chinese).
[6]	孟凡杰, 唐宏, 王义哲, 等. 基于时频图像纹理特征的雷达辐射源信号识别[J]. 弹箭与制导学报, 2017, 37(3): 152-156. MENG F J, TANG H, WANG Y Z, et al. Radar emitter signal recognition based on texture feature of time-frequency image[J]. Journal of Projectiles, Rockets, Missiles and Guidance, 2017, 37(3): 152-156(in Chinese).
[7]	刘歌, 张国毅, 汪洪艳. 基于特征融合的雷达信号脉内调制类型识别[J]. 航天电子对抗, 2016, 32(3): 36-41. LIU G, ZHANG G Y, WANG H Y. Intra-pulse modulation recognition of radar signal based on features fusion[J]. Aerospace Electronic Warfare, 2016, 32(3): 36-41(in Chinese).
[8]	王功明, 陈世文, 黄洁, 等. 基于多重同步压缩变换的雷达辐射源分选识别[J]. 现代雷达, 2020, 42(3): 49-56. WANG G M, CHEN S W, HUANG J, et al. Radar emitter sorting and recognition based on multi-synchrosqueezing transform[J]. Modern Radar, 2020, 42(3): 49-56(in Chinese).
[9]	关欣, 朱杭平, 张玉虎. 基于 FRFT 的雷达辐射源信号特征分析及提取[J]. 探测与控制学报, 2018, 40(2): 71-76. GUAN X, ZHU H P, ZHANG Y H. Analysis and extraction of radar emitter signal feature based on fractional Fourier transform[J]. Journal of Detection and control, 2018, 40(2): 71-76(in Chinese).
[10]	苑军见, 陈世文, 刘智鑫, 等. 基于高次频谱对称 Holder 系数的雷达信号分选方法[J]. 信号处理, 2020, 36(10): 1775-1783. YUAN J J, CHEN S W, LIU Z X, et al. Radar signal sorting method based on the symmetric holder coefficients of high-order spectrum[J]. Signal Processing, 2020, 36(10): 1775-1783(in Chinese).
[11]	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 & Information Technology, 2021, 43(8): 2300-2307(in Chinese).
[12]	简川霞, 林子嘉, 杜美剑, 等. 基于特征融合与降维的印刷套准识别方法[J]. 包装工程, 2019, 40(21): 242-249. JIAN C X, LIN Z J, DU M J, et al. Printing registration recognition method based on feature fusion and dimension reduction[J]. Packaging Engineering, 2019, 40(21): 242-249(in Chinese).
[13]	林龙, 王贤浪. 基于杂草算法优化的轴承时频谱图聚类识别研究[J]. 内燃机与配件, 2021(2): 117-120. LIN L, WANG X L. A time-frequency image recognition method based on IWO-KFCM algorithm[J]. Internal Combustion Engine & Parts, 2021(2): 117-120(in Chinese).
[14]	陈后金, 许文达, 郝晓莉. 基于灰度-梯度共生矩阵的钢轨表面缺陷检测方法[J]. 北京交通大学学报, 2015, 39(2): 7-12. CHEN H J, XU W D, HAO X L. Detection of rail track surface defects based on gray level-gradient co-occurrence matrix[J]. Journal of Beijing Jiaotong University, 2015, 39(2): 7-12(in Chinese).
[15]	杨棉绒, 牛丽平. 基于LGBM的Zernike特征选取及红外图像目标识别方法[J]. 红外与激光工程, 2022, 51(4): 415-420. YANG M R, NIU L P. Zernike’s feature selection based on LGBM and identification methods of infrared image target[J]. Infrared and Laser Engineering, 2022, 51(4): 415-420(in Chinese).
[16]	NAILA S, JJ Y, YANG N, et al. A rapid recognition method for rice false smut based on HOG features and SVM classification[J]. Journal of Physics: Conference Series, 2020, 1576(1): 012018.
[17]	NIU Y T, SHANG Y, TIAN Y J. Multi-view SVM classification with feature selection[J]. Procedia Computer Science, 2019, 162: 405-412.