Fast and Accurate Modeling of Dual-Polarized Reflectarray Unit Cells Using Support Vector Machines
- 5 January 2018
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Antennas and Propagation
- Vol. 66 (3) , 1258-1270
Abstract
This paper describes the characterization of reflectarray unit cells using support vector machines (SVMs) to obtain fast and accurately the full matrix of reflection coefficients, which is used for an analysis of dual-polarized reflectarrays, demonstrating the performance of the model. First, a surrogate model of the reflectarray unit cell is obtained using SVMs. To this end, a set of random samples of the reflection coefficient matrix with a full-wave method of moments based on local periodicity (MoM-LP) is used to train the SVMs. To efficiently obtain the surrogate model, a novel strategy to accelerate the training process is presented, remarkably reducing computing time. Next, the model is tested against a different set of samples, obtaining an excellent agreement between the SVM model and MoM-LP simulations for all reflection coefficients, including the cross-coefficients. The surrogate model is then used for an efficient analysis of three reflectarrays with pencil beam for point-to-point communications, isoflux pattern for global Earth coverage, and a shaped beam for local multipoint distribution service application, showing excellent agreement in both copolar and crosspolar patterns between the SVM and MoM-LP simulations. Finally, the analysis is accelerated by a factor larger than three orders of magnitude using SVMs instead of MoM-LP.Keywords
Funding Information
- European Space Agency (ESTEC/AO/1-7064/12/NL/MH)
- Ministerio de Economía y Competitividad, Spanish Government (MIRIIEM TEC2014-54005-P, MYRADA TEC2016-75103-C2-1-R)
- Gobierno del Principado de Asturias/FEDER (GRUPIN14-114)
This publication has 43 references indexed in Scilit:
- Loss analysis of a reflectarray cell using ANNs with accurate magnitude prediction2017
- An Efficient Numerical Solution Method for Reflectarrays of Varying Element SizesIEEE Transactions on Antennas and Propagation, 2015
- Reflectarray Antennas for Dual Polarization and Broadband Telecom Satellite ApplicationsIEEE Transactions on Antennas and Propagation, 2015
- Accurate characterization of multi-resonant reflectarray cells by artificial neural networks2014
- Design of a Contoured-Beam Reflectarray for a EuTELSAT European Coverage Using a Stacked-Patch Element Characterized by an Artificial Neural NetworkIEEE Antennas and Wireless Propagation Letters, 2012
- Neural Network Characterization of Reflectarray AntennasInternational Journal of Antennas and Propagation, 2012
- Computer tool for designing reflectarray antennas2012
- LIBSVMACM Transactions on Intelligent Systems and Technology, 2011
- Multiple Support Vector Regression for Antenna Array Characterization and SynthesisIEEE Transactions on Antennas and Propagation, 2007
- Broadband design of three-layer printed reflectarraysIEEE Transactions on Antennas and Propagation, 2003