Support Vector Regression to Accelerate Design and Crosspolar Optimization of Shaped-Beam Reflectarray Antennas for Space Applications

A machine learning technique is applied to the design and optimization of reflectarray antennas to considerably accelerate computing time without compromising accuracy. In particular, support vector machines (SVMs), automatic learning structures that are able to deal with regression problems, are employed to obtain surrogate models of the reflectarray element to substitute the full-wave analysis tool for the characterization of the unit cell in the design and optimization algorithms. The analysis, design, and optimization of a very large reflectarray antenna for Direct Broadcast Satellite applications are accelerated up to three orders of magnitude. This is here demonstrated with three examples: one showing the design of a reflectarray and two for the crosspolar optimization, one with one coverage for each linear polarization (Europe and the Middle East) and another with a Middle East coverage working in dual-linear polarization. The accuracy of the proposed approach is validated by means of a comparison of the final designs with full-wave simulations based on local periodicity obtaining good agreement. The crosspolar dicrimination and crosspolar isolation are greatly improved using the SVMs while considerably reducing computing time.

[1]  Erik Jorgensen,et al.  The Generalized Direct Optimization Technique for Printed Reflectarrays , 2014, IEEE Transactions on Antennas and Propagation.

[2]  P. Pirinoli,et al.  Neural Network characterization of microstrip patches for reflectarray optimization , 2009, 2009 3rd European Conference on Antennas and Propagation.

[3]  Fernando Las-Heras,et al.  Improved Reflectarray Phase-Only Synthesis Using the Generalized Intersection Approach with Dielectric Frame and First Principle of Equivalence , 2017 .

[4]  M. Orefice,et al.  Characterization of microstrip reflectarray square ring elements by means of an Artificial Neural Network , 2010, Proceedings of the Fourth European Conference on Antennas and Propagation.

[5]  Salih Demirel,et al.  Design and analysis of minkowski reflectarray antenna using 3‐D CST microwave studio‐based neural network model with particle swarm optimization , 2013 .

[6]  Fernando Las-Heras,et al.  Complex Reflection Coefficient Synthesis Applied to Dual-Polarized Reflectarrays With Cross-Polar Requirements , 2015, IEEE Transactions on Antennas and Propagation.

[7]  Changhua Wan,et al.  Efficient computation of generalized scattering matrix for analyzing multilayered periodic structures , 1995 .

[8]  Giuseppe D'Elia,et al.  Antenna pattern synthesis: a new general approach , 1994, Proc. IEEE.

[9]  Sean Victor Hum,et al.  Bifocal Design Procedure for Dual-Reflectarray Antennas in Offset Configurations , 2018, IEEE Antennas and Wireless Propagation Letters.

[10]  R. Gillard,et al.  Loss analysis of a reflectarray cell using ANNs with accurate magnitude prediction , 2017, 2017 11th European Conference on Antennas and Propagation (EUCAP).

[11]  G. Toso,et al.  Dual-polarization reflectarray in Ku-band based on two layers of dipole-arrays for a transmit-receive satellite antenna with South American coverage , 2017, 2017 11th European Conference on Antennas and Propagation (EUCAP).

[12]  Alexander J. Smola,et al.  Learning with kernels , 1998 .

[13]  P. Pirinoli,et al.  Modeling of reflectarray elements by means of MetaPSO-based Artificial Neural Network , 2013, 2013 7th European Conference on Antennas and Propagation (EuCAP).

[14]  Fernando Las-Heras,et al.  Fast and Accurate Modeling of Dual-Polarized Reflectarray Unit Cells Using Support Vector Machines , 2018, IEEE Transactions on Antennas and Propagation.

[15]  Fernando Las-Heras,et al.  An Efficient Calculation of the Far Field Radiated by Non-Uniformly Sampled Planar Fields Complying Nyquist Theorem , 2015, IEEE Transactions on Antennas and Propagation.

[16]  M. Arrebola,et al.  Dual-Polarization Dual-Coverage Reflectarray for Space Applications , 2006, IEEE Transactions on Antennas and Propagation.

[17]  J. Encinar,et al.  Reflectarray Antennas for Dual Polarization and Broadband Telecom Satellite Applications , 2015, IEEE Transactions on Antennas and Propagation.

[18]  Marco Mussetta,et al.  Neural Network Characterization of Reflectarray Antennas , 2012 .

[19]  P. Robustillo,et al.  ANN Characterization of Multi-Layer Reflectarray Elements for Contoured-Beam Space Antennas in the Ku-Band , 2012, IEEE Transactions on Antennas and Propagation.

[20]  Selahattin Nesil,et al.  Phase characterization of a reflectarray unit cell with Minkowski shape radiating element using Multilayer Perceptron Neural Network , 2011, 2011 7th International Conference on Electrical and Electronics Engineering (ELECO).

[21]  Fernando Las-Heras,et al.  Reflectarray antenna with reduced crosspolar radiation pattern , 2016, 2016 10th European Conference on Antennas and Propagation (EuCAP).

[22]  Jose A. Encinar,et al.  Enhanced MoM Analysis of the Scattering by Periodic Strip Gratings in Multilayered Substrates , 2013, IEEE Transactions on Antennas and Propagation.

[23]  M. Arrebola,et al.  Design of a Contoured-Beam Reflectarray for a EuTELSAT European Coverage Using a Stacked-Patch Element Characterized by an Artificial Neural Network , 2012, IEEE Antennas and Wireless Propagation Letters.

[24]  Erik Jorgensen,et al.  Direct Optimization of Printed Reflectarrays for Contoured Beam Satellite Antenna Applications , 2013, IEEE Transactions on Antennas and Propagation.

[25]  J. Encinar,et al.  Efficient computation of the reflectarray far fields in adaptive grids for speed improvement , 2017, 2017 IEEE International Symposium on Antennas and Propagation & USNC/URSI National Radio Science Meeting.

[26]  G. Toso,et al.  A Transmit-Receive Reflectarray Antenna for Direct Broadcast Satellite Applications , 2011, IEEE Transactions on Antennas and Propagation.

[27]  Andrea Massa,et al.  Efficient Prediction of the EM Response of Reflectarray Antenna Elements by an Advanced Statistical Learning Method , 2018, IEEE Transactions on Antennas and Propagation.

[28]  Andrea Massa,et al.  Advanced learning-based approaches for reflectarrays design , 2017, 2017 11th European Conference on Antennas and Propagation (EUCAP).

[29]  J. R. Mosig,et al.  Accurate characterization of multi-resonant reflectarray cells by artificial neural networks , 2014, The 8th European Conference on Antennas and Propagation (EuCAP 2014).

[30]  C. Tienda,et al.  Ka-band reflectarray antenna system for SAR applications , 2014, The 8th European Conference on Antennas and Propagation (EuCAP 2014).

[31]  Fernando Las-Heras,et al.  Efficient Crosspolar Optimization of Shaped-Beam Dual-Polarized Reflectarrays Using Full- Wave Analysis for the Antenna Element Characterization , 2017, IEEE Transactions on Antennas and Propagation.

[32]  J. Nourinia,et al.  Efficient, Accurate and Scalable Reflectarray Phase-Only Synthesis Based on the Levenberg-Marquardt Algorithm , 2015 .