Support vector regression models of reflectarray unit cell in a geometrical 4-D parallelotope domain around a rectangle of stability
Autor(es) y otros:
Palabra(s) clave:
Dual band
machine learning
orthotope
parallelotope
reflectarray antenna
support vector regression (SVR)
surrogate model
wideband
Fecha de publicación:
Editorial:
IEEE
Versión del editor:
Citación:
Resumen:
In this work, surrogate models based on support vector regression (SVR) of a multiresonant unit cell in a geometrical 4-D parallelotope domain are trained and used in a reflectarray antenna design. The multiple sharp resonances of the unit cell prevent a suitable training process in the whole orthotope defined by the available degrees of freedom (DoFs). Thus, a strategy to improve the training process and obtain highly accurate models is devised. It consists in defining a parallelotope around a rectangle of stability, which is in turn defined at a lower dimensionality. The SVR models with four geometrical DoF obtained in this parallelotope are shown to provide highly accurate results for the design of a large contoured-beam reflectarray for space applications. The direct optimization with the surrogate models allows to improve the cross-polarization performance by several decibels while considerably increasing computational performance. Furthermore, compared to lower dimensionality models, the 4-D models offer better results when applied to wideband and dual-band reflectarray direct optimization.
In this work, surrogate models based on support vector regression (SVR) of a multiresonant unit cell in a geometrical 4-D parallelotope domain are trained and used in a reflectarray antenna design. The multiple sharp resonances of the unit cell prevent a suitable training process in the whole orthotope defined by the available degrees of freedom (DoFs). Thus, a strategy to improve the training process and obtain highly accurate models is devised. It consists in defining a parallelotope around a rectangle of stability, which is in turn defined at a lower dimensionality. The SVR models with four geometrical DoF obtained in this parallelotope are shown to provide highly accurate results for the design of a large contoured-beam reflectarray for space applications. The direct optimization with the surrogate models allows to improve the cross-polarization performance by several decibels while considerably increasing computational performance. Furthermore, compared to lower dimensionality models, the 4-D models offer better results when applied to wideband and dual-band reflectarray direct optimization.
Patrocinado por:
This work was supported in part by the Ministerio de Ciencia, Innovación y Universidades under Project IJC2018-035696-I, in part by MICIN/AEI/10.13039/501100011033 under Project PID2020-114172RB-C21 (ENHANCE-5G), in part by the NextGenerationEU under the Recovery Plan for Europe under Project TED2021-130650B-C22, and in part by the Gobierno del Principado de Asturias under Project AYUD/2021/51706.