Design of Zero Clearance SIW Endfire Antenna Array Using Machine Learning-Assisted Optimization

• Published in: IEEE transactions on antennas and propagation 2022-05, Vol.70 (5), p.3858-3863
• Main Authors: Zhang, Jin, Akinsolu, Mobayode O., Liu, Bo, Zhang, Shuai
• Format: Article
• Language: English
• Subjects: Antenna array; Antenna arrays; Antenna design; Antennas; Applications programs; Bandwidth; Clearances; design exploration; Dipole antennas; Evolutionary computation; Impedance matching; Load modeling; Loaded antennas; Machine learning; Mobile antennas; Mobile computing; Optimization; Resonant frequency; substrate integrated waveguide (SIW) end-fire antenna; Substrate integrated waveguides; surrogate modeling
• ISSN: 0018-926X; 1558-2221
• DOI: 10.1109/TAP.2021.3137500

In this communication, a substrate integrated waveguide (SIW) end-fire antenna array with zero clearance is proposed for fifth-generation (5G) mobile applications using machine learning-assisted optimization. In particular, a novel impedance matching architecture that involves three arbitrary pad-loading metallic vias is investigated and adopted for the antenna element. Due to the stringent design requirements, the locations and sizes of the vias and pads are obtained via a state-of-the-art machine learning assisted antenna design exploration method, parallel surrogate model-assisted hybrid differential evolution for antenna synthesis (PSADEA). Keeping a very low profile, the array optimized by PSADEA covers an operating frequency bandwidth from 36 to 40 GHz. The in-band total efficiency is generally better than 60% and the peak gain is above 5 dBi. The beam scanning range at 39 GHz covers from −20° to 35°.