Machine Learning-Based Surrogate Modelling of Reflectarray Unit Cell in a 4-D Parallelotope-Shaped Domain
Subject:
Surrogate modelling
machine learning
support vector regression
reflectarray unit cell
method of moments
Publication date:
Editorial:
IEEE
Abstract:
A novel strategy to define a high-dimensionality parallelotope-shaped domain is proposed to train surrogate models of reflectarray unit cells. The concept is based on the definition of a region or rectangle of stability where sharp resonances are avoided as much as possible. Then, a 4-D parallelotope is defined around the rectangle of stability, controlling its size in order to avoid new resonances that appear as a consequence of increasing the dimensionality of the domain. This methodology is applied to generate surrogate models of a multi-resonant unit cell based on support vector regression. Results show a high degree of agreement between the obtained surrogate models and simulations based on the method of moments based on local periodicity tool that was used to generate the training samples. Furthermore, the proposed method performs better than lower dimensionality methods for wideband optimization.
A novel strategy to define a high-dimensionality parallelotope-shaped domain is proposed to train surrogate models of reflectarray unit cells. The concept is based on the definition of a region or rectangle of stability where sharp resonances are avoided as much as possible. Then, a 4-D parallelotope is defined around the rectangle of stability, controlling its size in order to avoid new resonances that appear as a consequence of increasing the dimensionality of the domain. This methodology is applied to generate surrogate models of a multi-resonant unit cell based on support vector regression. Results show a high degree of agreement between the obtained surrogate models and simulations based on the method of moments based on local periodicity tool that was used to generate the training samples. Furthermore, the proposed method performs better than lower dimensionality methods for wideband optimization.
Description:
International Conference on Modern Circuits and Systems Technologies (MOCAST) on Electronics and Communications (2023. Athens, Greece)
Patrocinado por:
This work was supported in part by the Ministerio de Ciencia, Innovación y Universidades under project IJC2018-035696-I; by MICIN/AEI/10.13039/501100011033 under project PID2020-114172RB-C21 (ENHANCE-5G); by Gobierno del Principado de Asturias under project AYUD/2021/51706.
Collections
Files in this item
