基于主成分分析的雷达辐射源信号数量估计

陈韬伟; 金炜东

基于主成分分析的雷达辐射源信号数量估计

陈韬伟^1,2,
金炜东^3, ,

基金项目:

国家自然科学基金资助项目(60572143)

详细信息

作者简介:
陈韬伟(1976- ),博士研究生,研究方向为信号处理与智能信息处理,E-mail:cctw33@sina.com

通讯作者:
金炜东(1962- ),男,教授,博士,主要研究方向为优化理论与优化控制、智能信息处理、系统仿真等, E-mail: wdjin@home.swjtu.edu.cn

计量
- 文章访问数: 1546
- HTML全文浏览量: 74
- PDF下载量: 56
- 被引次数: 0
出版历程
- 收稿日期: 2007-11-05

Radar Emitter Number Estimation Based on Principal Component Analysis

CHEN Taowei^1,2,
JIN Weidong^{3
, ,}

摘要

摘要: 针对复杂电磁环境中雷达辐射源数的估计问题,提出了一种新的信息论准则.这种方法通过对接收到的脉冲信号包络向量进行主成分分析提取包络的特征值,并利用特征值按降序排列的曲线分布特点构造新的信息论准则,估计雷达辐射源数目.计算机仿真实验表明,与已有的信息论准则相比,在低信噪比(4~8 dB)下,雷达辐射源数的估计正确率平均提高29%,运行效率平均提高0.09 s.
- 主成分分析 /
- 信息论准则 /
- 雷达信号分选
Abstract: To estimate the number of radar emitters in a complex electromagnetic condition,a novel information-theoretic criterion was formulated based on the characteristic of eigenvalues extracted from the principal component analysis of received pulse envelope vectors and arranged in a decreasing order.Computer simulation shows that compared with the existing information-theoretic criterion,the proposed criterion has a 29% improvement in average correct estimation rate and a 0.09 s improvement in average computational efficiency when SNR(signal-to-noise ratio) varies from 4 to 8 dB.
- principal component analysis(PCA) /
- information-theoretic criterion /
- radar signal deinterleaving

HTML全文

参考文献(1)

WILEY R G.Electronic intelligence[M].2nd ed.Norwood:Artech House,1993.[2] 李合生,韩宇,蔡英武,等.雷达信号分选关键技术研究综述[J].系统工程与电子技术,2005,27(12):2035-2040.LI Hesheng,HAN Yu,CAI Yingwu,et al.Overview of the crucial technology research for radar signal sorting[J].Systems Engineering and Electronics,2005,27(12):2035-2040.[3] 魏东升,巫胜洪,唐斌.雷达脉内提取方法的研究[J].舰船科学技术,1994(3):23-30.[4] GRANGER E,SAVARIA Y,LAVOIE P,et al.Comparison of self-organizing neural networks for fast clustering of radar pulses[J].Signal Processing,1998,64(3):249-269.[5] KAMGAR P B,SCIORTINO J C.Automatic data sorting using neural network techniques,A744403[R].Washington DC:The Defense Technical Information Center,1996.[6] ZHOU Y,LEE J A.Minimum description length emitter number detection approach for intra-pulse analysis[C]∥Proceedings of the 1999 IEEE Pacific Rim Conference on Communications,Computers and Signal Processing(PACRIM'99).Victoria:IEEE Press,1999:548-551.[7] LIU J,GAO S W,LUO Z Q,et al.The minimum description length criterion applied to emitter number detection andpulse classification[C]∥Proceedings of IEEE Workshop Statistical Signal and Array Processing.Portland:IEEE Press,1998:172-175.[8] JOLLIFFE I T.Principal component analysis[M].New York:Springer,1986.[9] LINHART H,ZUCCHINI W.Model selection[M]∥Probability and Mathematical Statistics.New York:Wiley,1986.[10] TIPPING M E,BISHOP C M.Probabilistic principle component analysis[J].Journal of the Royal Statistical Society,1999,61(3):611-622.[11] MINKA T.Automatic choice of dimensionality for PCA,Technical Report 514[R].Cambridge:Massachusetts Institute of Technology,2000.[12] 张国柱,黄可生,姜文利,等.基于信号包络的辐射源细微特征提取方法[J].系统工程与电子技术,2006,28(6):795-798.ZHANG Guozhu,HUANG Kesheng,JIANG Wenli,et al.Emitter feature extract method based on signal envelop[J].Systems Engineering and Electronics,2006,28(6):795-798.[13] AKAIKE H.A new look at the statistical model identification[J].IEEE Trans.on Automatic Control,1974,19(6):716-723.[14] RISSANEN J.Modeling by the shortest description[J].Automatica,1978,14(5):465-471.[15] SCHWARTZ G.Estimating the dimension of a model[J].Annals of Statistics,1978,6(2):461-464.[16] 马建仓,牛奕龙,陈海洋.盲信号处理[M].北京:国防工业出版社,2006:42-46.

施引文献

附加材料(0)

访问统计

点击查看大图

计量

文章访问数: 1546
HTML全文浏览量: 74
PDF下载量: 56
被引次数: 0