On Reduced-Cost Design-Oriented Constrained Surrogate Modeling of Antenna Structures

Abstract

Design of contemporary antenna structures heavily relies on full-wave electromagnetic simulation models. Such models are essential to ensure reliability of evaluating antenna characteristics, yet they are computationally expensive and, therefore, unsuitable for handling tasks that require multiple analyses, e.g., parametric optimization. The cost issue can be alleviated by using fast surrogate models. Conventional data-driven models are unsuitable for modeling of antenna characteristics if the number of geometry parameters exceeds a few. Here, a novel approach is proposed. It is based on restricting the region of surrogate model validity to a manifold spanned by a set of reference designs corresponding to antenna optimized for various operating frequencies and dielectric permittivity of the substrate material. By focusing the modeling process in the region containing designs that are close-to-optimum from the point of view of the aforementioned operating/material criteria, considerable savings can be achieved in terms of the number of the training samples necessary to set up a reliable surrogate. In the letter, a rigorous analytical formulation of the technique is provided along with a case study of a ring slot antenna. The results are validated through measurements of fabricated antenna prototypes.