基于融合熵特征的辐射源信号识别  

Radar Emitter Signal Recognition Based on Fusion Entropy Features

作　　者：余志斌[1] 陈春霞[3] 金炜东[2] 

机构地区：[1]西南交通大学信息科学与技术学院,成都610031 [2]西南交通大学电气工程学院,成都610031 [3]成都电子机械高等专科学校机械工程系,成都610031

出　　处：《现代雷达》2010年第1期34-38,共5页Modern Radar

基　　金：国家自然科学基金(No.60702026;No.60971103)

摘　　要：针对相近雷达辐射源信号难以识别的问题,一种新的雷达辐射源信号识别方法被提出。该方法基于小波包分解,用主成分分析法融合含有信号类别特性的小波包重构系数特征,并将融合特征的能量熵和概率熵构成特征向量,基于支持向量机实现信号的分类识别。在较大信噪比(SNR)范围内,使用该方法能获得满意的正确识别率,当SNR为5dB时,十分近似的线性调频信号正确识别率达到了91%,实验结果证实了该方法的有效性。Aiming at the problem of low degree of recognition in closed radars emitter signal recognition,a novel approach is proposed.In this approach,the fusion feature of wavelet packet reconstruction coefficient（WPRC）including characteristics of radar signal is extracted with the principal component analysis（PCA）,and the fusion energy entropy（FEnEn）of the fusion feature and the fusion probability entropy（FPrEn）of the fusion feature are used to construct a feature vector,and the support vector machine is used to identify closed radar emitter signals（ARES）automatically.This approach can achieve very satisfying accurate recognition when signal-to-noise rate（SNR）varies in a large range.Even for SNR=5 dB,the accurate recognition rate of the approximate LFM is 91%.The validity of the approach is demonstrated by experiments.

关 键 词：小波包 PCA融合特征 雷达辐射源信号 概率熵 能量熵 

分 类 号：TN957.51[电子电信—信号与信息处理]