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.
出处
《现代雷达》
CSCD
北大核心
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)
关键词
小波包
PCA融合特征
雷达辐射源信号
概率熵
能量熵
wavelet package PCA fusion feature radar emitter signal probability entropy energy entropy
