The relations between the antennas' geometrical parameters and design specifications usually consist of linear and nonlinear components. Especially with the increase of the requested performance measures, the design procedure becomes much more complex due to the conflicting performance criteria or design limitations. To achieve a design with high performance with feasible design parameters, a fast, accurate, and reliable design optimization process is required. Herein, to have a fast, accurate, and high‐performance capacitive‐feed antenna model to be used in design optimization problems, a modified multi‐layer perceptron (M2LP) model has been proposed. The M2LP is an equivalent convolutional neural network (CNN) model of a standard multilayer perceptron (MLP), where instead of traditional training parameters of MLP, more advanced training parameters of CNN models such as batch‐norm layer, leaky‐rectified linear unit (ReLU) layer, and Adam training algorithm had been used. Furthermore, the M2LP model had been used in a design optimization process and the obtained optimal antenna had been prototyped using 3D printing technology for justification of the proposed M2LP model with experimental results. As can be seen from the results, the proposed M2LP model is a fast, accurate, and reliable regression model for design optimization of microwave antennas.

No abstract

No abstract

No abstract

Fast replacement models (or surrogates) have been widely applied in the recent years to accelerate simulation-driven design procedures in microwave engineering. The fundamental reason is a considerable-and often prohibitive-CPU cost of massive full-wave electromagnetic (EM) analyses related to solving common tasks such as parametric optimization or uncertainty quantification. The most popular class of surrogates are data-driven models, which are fast to evaluate, versatile, and easy to handle. Notwithstanding, the curse of dimensionality as well as the utility demands (e.g., so that the model covers sufficiently broad ranges of the system operating conditions), limit the applicability of conventional methods. A performance-driven modeling paradigm allows for mitigating these issue by focusing the surrogate setup process in a constrained domain encapsulating designs being of high quality w.r.t. the assumed figures of interest. The nested kriging framework capitalizing on this idea, renders the constrained surrogate using kriging interpolation, and has been shown to surpass traditional approaches. In pursuit of further accuracy improvements, this work incorporates the performance-driven concept into the fully-connected regression model (FRCM). The latter has been recently introduced in the context of frequency selective surfaces, and combined deep neural networks with Bayesian optimization, the latter employed to determine the network architecture and hyper-parameters. Using two examples of miniaturized microstrip couplers, our methodology is demonstrated to outperform both conventional modeling techniques and nested kriging, with reliable models constructed over multi-dimensional parameters spaces using just a few hundreds of samples.INDEX TERMS Dara-driven modeling; surrogate modeling; performance-driven surrogates; nested kriging; deep regression model; Bayesian optimization.