基于STFT‑SST和深度卷积网络的多相码雷达信号识别  

Polyphase Codes Radar Signal Recognition Based on STFT‑SST and Deep Convolu‑tional Network

作　　者：倪雪 王华力 徐志军 荣传振 NI Xue;WANG Huali;XU Zhijun;RONG Chuangzheng(College of Communications Engineering,Army Engineering University of PLA,Nanjing,210007,China)

机构地区：[1]陆军工程大学通信工程学院,南京210007

出　　处：《数据采集与处理》2020年第6期1090-1096,共7页Journal of Data Acquisition and Processing

摘　　要：多相码雷达信号特征相似,类间差距小,在低信噪比(Signal‑to‑noise ratio,SNR)下极易混淆。Choi‑Williams等时频分布由于受时频分辨率的约束,难以刻画多相码信号的细节特征。为此,本文提出了一种基于同步挤压短时傅里叶变换(Short‑time Fourier transform‑based synchrosqueezing transform,STFT‑SST)和深度卷积网络的自动分类识别算法。在特征选取上,采用STFT‑SST对多相码雷达信号进行时频分析,并提出一种频谱增强算法,用于提升低SNR下的时频特征表示,以获得高分辨率的时频特征图像;在分类网络上,设计了一个9层深度卷积网络,并引入Inception模块,提升网络对细节特征的捕获能力。仿真结果表明,当SNR为-8 dB时,该系统对5种特定多相码的平均识别率达91.8%,在低SNR下具有更好的识别性能。The radar signals of polyphase codes are similar,which is easy to be confused under low signalto-noise ratio(SNR).The classic Choi-Williams and other time-frequency distribution methods constrained by the time-frequency resolution are difficult to characterize the details of polyphase codes.Here,we propose an automatic recognition method based on the short-time Fourier transform-based synchrosqueezing transform(STFT-SST)and deep convolutional network.On the feature selection,the STFT-SST is used to radar signals for time-frequency analysis,and a spectrum enhancement algorithm is proposed to enhance the time-frequency features under low signal-to-noise ratio,then the high-resolution feature images are obtained.On the classification network,a nine-layer deep convolution network is designed,and the inception module is introduced to capture the signal’s detailed features.The simulation results show that when the SNR is-8 dB,the average recognition rate for five polyphase codes reaches 91.8%.The recognition performance of the proposed method is better at the low SNR.

关 键 词：多相码 同步挤压短时傅里叶变换(STFT‑SST) 深度卷积网络 频谱增强 

分 类 号：TN953[电子电信—信号与信息处理]