Efficient Modeling of Missile RCS Magnitude Responses by Gaussian Processes

被引:24
作者
Jacobs, Jan Pieter [1 ]
du Plessis, Warren Paul [1 ]
机构
[1] Univ Pretoria, ZA-0002 Pretoria, South Africa
来源
IEEE ANTENNAS AND WIRELESS PROPAGATION LETTERS | 2017年 / 16卷
基金
新加坡国家研究基金会;
关键词
Gaussian processes (GP); modeling; radar cross section (RCS);
D O I
10.1109/LAWP.2017.2771236
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
080906 [电磁信息功能材料与结构]; 082806 [农业信息与电气工程];
摘要
An efficient technique for modeling radar cross section magnitude responses versus frequency is presented. The technique is based on Gaussian process regression andmakes it possible to significantly reduce the number of expensive computer simulations required to accurately resolve these responses. Examples of two missiles are used to evaluate the proposed technique. Average predictive normalized root-mean-square errors (RMSEs) of 1.24% and 1.63% were obtained, with the worst RMSE being less than 2.2%. These results were significantly better than results obtained with alternative techniques, including geometric theory of diffraction-based modeling and support vector regression.
引用
收藏
页码:3228 / 3231
页数:4
相关论文
共 10 条
[1]
Microwave devices and antennas modelling by support vector regression machines [J].
Angiulli, G. ;
Cacciola, M. ;
Versaci, M. .
IEEE TRANSACTIONS ON MAGNETICS, 2007, 43 (04) :1589-1592
[2]
[Anonymous], FEKO US MAN
[3]
Black A. A., 1991, Journal of Electronic Defense, V14, P44
[4]
Two-Stage Framework for Efficient Gaussian Process Modeling of Antenna Input Characteristics [J].
Jacobs, J. P. ;
Koziel, S. .
IEEE TRANSACTIONS ON ANTENNAS AND PROPAGATION, 2014, 62 (02) :706-713
[5]
Jacobs J. P., 2015, PROC LOUGHBOROUGH AN, P1
[6]
Knott E.F., 2004, RADAR CROSS SECTION, DOI DOI 10.1049/SBRA026E
[7]
Lathi B.B. P., 2010, MODERN DIGITAL ANALO, V4th
[8]
Neri F., 2006, INTRO ELECT DEFENSE, V2nd
[9]
A GTD-BASED PARAMETRIC MODEL FOR RADAR SCATTERING [J].
POTTER, LC ;
CHIANG, DM ;
CARRIERE, R ;
GERRY, MJ .
IEEE TRANSACTIONS ON ANTENNAS AND PROPAGATION, 1995, 43 (10) :1058-1067
[10]
Rasmussen CE, 2005, ADAPT COMPUT MACH LE, P1