一种基于脉间特征与脉内特征融合的雷达辐射源分类方法  

A Radar Emitter Classification Method Based on Fusion of Inter-Pulse Features and Intra-Pulse Features

作　　者：王程昱 凌青 闫文君 WANG Chengyu;LING Qing;YAN Wenjun(Naval Aviation University,Yantai Shandong 264001,China)

机构地区：[1]海军航空大学,山东烟台264001

出　　处：《海军航空大学学报》2025年第2期278-284,共7页Journal of Naval Aviation University

基　　金：国家自然科学基金面上项目(62371465);山东省青创团队(2022KJ084);山东省泰山学者专项基金。

摘　　要：雷达辐射源个体识别技术是指通过提取雷达细微特征判定载体身份属性。其基础是在复杂电磁环境下将多路混叠接收信号进行正确分选。针对传统基于脉间参数的信号分选易造成脉冲分类不正确的问题,提出了一种脉间参数结合脉内双谱特征的聚类算法:首先,构建包含信号载频、脉冲宽度和脉冲围线积分形成的双谱波形熵的特征矩阵;然后,采用改进自适应DBSCAN聚类算法对特征矩阵进行聚类分析。仿真结果表明,所提算法通过真实数据采集验证,分类准确率较传统PRI分选算法提升6%左右,能够解决PRI抖动及重频、多径效应产生的影响,满足后续个体识别需要。The individual identification technology of radar emitter is to determine the identity attribute of the carrier by extracting the subtle features of the radar,and the basis of the individual identification of radar emitter signals is to correctly sort the multi-channel aliasing received signals in a complex electromagnetic environment.In order to solve the problem that the traditional signal sorting based on interpulse parameters is easy to cause incorrect pulse classification,a clustering algorithm based on interpulse parameters combined with intra-pulse bispectral features is proposed,which firstly constructs a feature matrix of bispectral waveform entropy composed of signal carrier frequency,pulse width and pulse enclosure integral,and then uses the improved adaptive DBSCAN clustering algorithm to cluster the feature matrix.The simulation results show that the proposed algorithm is verified by real data collection,and the classification accuracy is about 90%,which can meet the needs of subsequent individual identification.

关 键 词：雷达信号处理 聚类 高阶谱 信号分选 

分 类 号：TN951[电子电信—信号与信息处理] TN971.1[电子电信—信息与通信工程]