基于五维联合特征的雷达信号脉内调制识别  

Intra-pulse Modulation Recognition of Radar Signal Based on Five-dimensional Joint Features

作　　者：樊依晨 胡学成[1] FAN Yichen;HU Xuecheng(The 14th Research Institute of China Electronic Technology Group Corporation,Nanjing 210000)

机构地区：[1]中国电子科技集团第十四研究所,南京210000

出　　处：《舰船电子工程》2021年第7期93-96,123,共5页Ship Electronic Engineering

基　　金：空装十三五预研课题“机载雷达探测与隐身技术”资助。

摘　　要：雷达信号脉内调制识别是接收机分析非合作目标的一项重要技术。针对现有单一脉内特征在低信噪比条件下识别能力差的问题,提出了一种基于五维联合特征的雷达信号脉内调制识别算法。论文选取信号的差分近似熵、信息维数、最大奇异值、频域偏度特征以及调和平均盒维数五类抗噪性能较好的特征,采用了基于支持向量机的分类方法。仿真结果表明论文所提出的方法在信噪比较低的情况下相对其他算法仍有较高的识别率,在信噪比4dB以上时所有信号均能达到95%的识别率。Intra-pulse modulation recognition of radar signal is an important technology for receivers to analyse non coopera⁃tive targets.In order to solve the problem that the recognition ability of single intra pulse feature is poor under low signal-to-noise ra⁃tio,this paper proposes an intra pulse modulation recognition algorithm based on five-dimensional joint feature.In this paper,five kinds of anti-noise characteristics of the signal are selected,which are difference approximate entropy,information dimension,maximum singular value,frequency-domain skewness and harmonic average box dimension,and support vector machine is used to realize radar signal classification and recognition.The simulation results show that the method proposed in this paper has higher rec⁃ognition rate than other methods and all signals can reach 95%correct recognition rate when SNR over 4dB.

关 键 词：联合特征 支持向量积 雷达 脉内调制识别 最大奇异值 

分 类 号：TN957.51[电子电信—信号与信息处理]