肖易寒^1,,,
王亮¹,
郭玉霞^{2, 3}
1.哈尔滨工程大学信息与通信工程学院先进船舶通信与信息技术工业和信息化部重点实验室 哈尔滨 150000
2.中国空空导弹研究院 洛阳 471009
3.航空制导武器航空科技重点实验室 洛阳 471009
基金项目:国家自然科学基金(61571146)，中央高校基本科研基金(3072020CF0810)，航空科学基金(201801P6004)

详细信息

作者简介:肖易寒：女，1980年生，副教授，研究方向为雷达信号识别、深度学习、图像处理
王亮：男，1995年生，硕士生，研究方向为雷达信号识别、深度学习
郭玉霞：女，1979年生，研究员，研究方向为雷达导引系统总体设计、信号处理

通讯作者:肖易寒　xiaoyihan@hrbeu.edu.cn

中图分类号:TN957.51

计量

文章访问数:401
HTML全文浏览量:132
PDF下载量:110
被引次数:0

出版历程

收稿日期:2020-06-19
修回日期:2021-04-10
网络出版日期:2021-05-06
刊出日期:2021-08-10

Radar Signal Modulation Type Recognition Based on Denoising Convolutional Neural Network

Yihan XIAO^1,,,
Liang WANG¹,
Yuxia GUO^{2, 3}
1. Key Laboratory of Advanced Marine Communication and Information Technology, Ministry of Industry and Information Technology, Harbin Engineering University, Harbin 150000, China
2. China Airborne Missile Academy, Luoyang 471009, China
3. Aviation Key Laboratory of Science and Technology on Airborne Guided Weapons, Luoyang 471009, China
Funds:The National Natural Science Foundation of China (61571146), The Basic Scientific Research business Fees of the Central University (3072020CF0810), The Aviation Science Foundation (201801P6004)


摘要
摘要:针对低截获概率雷达(LPI)信号处理复杂，低信噪比条件下识别率低的问题，该文提出一种基于去噪卷积神经网络和Inception网络的信号分类识别系统。首先对8种LPI雷达信号进行Choi-Williams分布(CWD)时频变换，得到2维时频图像，然后使用去噪卷积神经网络进行时频图像去噪处理，最后将图像发送到Inception-V4网络进行特征提取，并使用softmax分类器进行分类，实现LPI雷达信号的有效分类识别。仿真结果表明，该方法在–10 dB信噪比(SNR)下，识别率仍然可以达到90%以上。
关键词:低截获概率雷达信号/
Choi-Williams分布时频变换/
去噪卷积神经网络/
Inception-V4网络
Abstract:Considering the problems of Low Probability of Intercept (LPI) radar signal processing complexity and low recognition rate under the condition of low SNR, a signal classification and recognition system based on Denoising Convolution Neural Network (DnCNN) and Inception network is proposed. Firstly, eight kinds of LPI radar signals are transformed by Choi Williams Distribution (CWD) to obtain two-dimensional time-frequency images. Then, the denoising convolution neural network is used to denoise the time-frequency images. Finally, the images are sent to the Inception-v4 network for feature extraction, and the softmax classifier is used for classification to realize the effective classification and recognition of LPI radar signals. Simulation results show that the recognition rate of this method can still reach more than 90% under –10 dB Signal-Noise Ratio (SNR).
Key words:Low Probability of Intercept (LPI) radar signal/
Choi-Williams Distribution (CWD) time-frequency transform/
Denoising Convolutional Neural Network (DnCNN)/
Inception-V4 network



PDF全文下载地址:

https://jeit.ac.cn/article/exportPdf?id=99e3f159-cfea-4d59-b85a-3880c96bcac1