کنفرانس مهندسی برق ایران

صفحه اصلی / سی و دومین کنفرانس بین المللی مهندسی برق

Design of Fresnel-Region Millimeter-Wave Metasurface Beam Shaper Using Deep Learning

نویسندگان :

Mohammad Hossein Koohi Ghamsari¹ Ehsan Imanbeygi² Mehdi Ahmadi-Boroujeni³

1- دانشگاه صنعتی شریف 2- دانشگاه صنعتی شریف 3- دانشگاه صنعتی شریف

کلمات کلیدی :

Beam shaping،Fresnel region،metasurface،deep-learning،flat-top beam shaper

چکیده :

In this paper, we present a new approach for designing a metasurface structure that leverages deep learning techniques for beam shaping of a millimeter-wave source in the Fresnel region. The selection of unit cell geometry is crucial to attain accurate control over the phasefront of the incident wave. We show that our selection of unit cells enables the metasurface to produce the desired beam intensity on the target plane. To train our neural network, we generate datasets using analytical solutions of the beam shaping problem. The efficiency of our suggested method is evaluated by designing the phase profile of the metasurface to generate flat-top irradiation at a specific distance from the metasurface. The results demonstrate the feasibility of the proposed deep learning approach for designing beam shaper metasurfaces.