系统工程与电子技术 ›› 2019, Vol. 41 ›› Issue (9): 1998-2005.doi: 10.3969/j.issn.1001-506X.2019.09.12

• 传感器与信号处理 • 上一篇    下一篇

基于深层卷积神经网络和双谱特征的雷达信号识别方法

刘赢, 田润澜, 王晓峰


  

  1. 空军航空大学航空作战勤务学院, 吉林 长春 130022

  • 出版日期:2019-08-27 发布日期:2019-08-20

Radar signal recognition method based on deep convolutional neural network and bispectrum feature

LIU Ying, TIAN Runlan, WANG Xiaofeng   

  1. School of Aviation Operations and Services,Aviation University of Air Force, Changchun 130022,China
  • Online:2019-08-27 Published:2019-08-20

摘要:

针对复杂电磁环境下利用人工提取特征识别雷达信号存在的主观性强、特征冗余的问题,提出了一种基于深层卷积神经网络的识别方法。该方法首先提取雷达信号的双谱信息作为深层卷积神经网络模型的输入,然后利用模型的自学习能力提取深层特征,实现对不同调制样式雷达信号的识别,最后对不同结构网络模型的识别结果进行对比。仿真实验结果表明,相比传统雷达信号识别方法,该方法对于不同调制类型信号的识别效果优异,并且在识别率、抗噪性上都有所提升。

关键词: 雷达信号识别, 深层卷积神经网络, 特征提取, 双谱

Abstract:

Aiming at the problem of strong subjectivity and feature redundancy of radar signal recognition in the complex electromagnetic environment, a recognition method based on deep convolutional neural network is proposed. By extracting the bispectrum information of the radar signal as the input of the network model, the network model is used to automatically learn the deep features, identify the different modulation pattern signals, and compare the recognition results of the deep network models with different structures. The results of simulation experiment show that compared with the traditional radar signal recognition method, the proposed method has improved recognition rate and noise immunity.

Key words: radar signal recognition, deep convolutional neural network, feature extraction, bispectrum