Key points are not available for this paper at this time.
Utilization of electromagnetic (EM) simulation tools is mandatory in the design of contemporary antenna structures. At the same time, conducting design procedures that require multiple evaluations of the antenna at hand, such as parametric optimization or yield-driven design, is hindered due to the high cost of accurate EM analysis. To a certain extent, this issue can be addressed using fast replacement models (also referred to as surrogates). Unfortunately, due to curse of dimensionality, traditional data-driven surrogate modeling methods are limited to antenna structures described by a few parameters with relatively narrow parameter ranges. This is by no means sufficient given the complexity of modern designs. In this paper, a novel technique for surrogate modeling of antenna structures is proposed. It involves a construction of two levels of surrogates, both realized as kriging interpolation models. The first model is based on a set of reference designs optimized for selected performance figures. It is used to establish a domain for the final (second level) surrogate. This formulation permits efficient modeling within wide ranges of antenna geometry parameters and wide ranges of performance figures (e.g., operating frequencies). At the same time, it allows uniform allocation of training data samples in a straightforward manner. Our approach is demonstrated using two microstrip antenna examples and is compared with conventional kriging and radial basis function modeling. Application examples for antenna optimization are also provided along with experimental validation.
Kozieł et al. (Thu,) studied this question.