Deep learning base modified MLP model for precise scattering parameter prediction of capacitive feed antenna

Abstract

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.