Data driven surrogate modeling of horn antennas for optimal determination of radiation pattern and size using deep learning

Abstract

Horn antenna designs are favored in many applications where ultra-wide-band operation range alongside of a high-performance radiation pattern characteristics are requested. Scattering-parameter characteristics of antennas is an important design metric, where inefficiency in the input would drastically lower the realized gain. However, satisfying the requirement for scattering parameters are not enough for having an antenna with high-performance results, where the radiation characteristic of the design can be changed independently than the scattering parameters behavior. A design might have a high-efficiency performance, but the radiation characteristics might not be acceptable. Furthermore, there are other design considerations such as size and volume of the design alongside of these conflicting characteristics, which directly affect the manufacturing cost and limits the possible applications. In this work, by using data-driven surrogate modeling, it is aimed to achieve a computationally efficient design optimization process for horn antennas with high radiation performance alongside of being small in or within the limits of the desired application limits. Here, the geometrical design variables, operation frequency, and radiation direction of the design will be taken as the input, while the realized gain of the design is taken as the output of the surrogate model. Series of powerful and commonly used artificial intelligence algorithms, including Deep Learning had been used to create a data-driven surrogate model representation for the handled problem, and 80% computational cost reduction had been obtained via proposed approach. As for the verification of the studied optimization problem, an optimally designed antenna is prototyped via the use of three-dimensional printer and the experimental results ware compared with the results of surrogate model.