Gain and radiation pattern enhancement using ANN-based reflector antenna for full 5G Sub-6GHz applications

The development, analysis, fabrication, and measurements of an inset-feed frequency selective surface (FSS) monopole rectangular patch antenna based on the Fabry-Perot cavity (FPC) principle were discussed in this paper. The proposed antenna is fabricated on two pieces of flame retardant-4(FR4) substrate (FSS reflector) and RT Duroid 5880 substrate (main radiating patch) of equal size 49mm×49mm×1.6mm. The use of FR4 controls the cost of the antenna while the RT Durid maintains low losses and supports improvement in gain and radiation characteristics. The FPC principle is utilized to enhance antenna gain and directional radiation characteristics. The distance between the substrate and FSS layer is evaluated by developing a relationship using a machine learning artificial neural network (ANN) model-based method by speculating the output through iterations and it is validated by the high-frequency structure simulator (HFSS) optimization process. Equally spaced 15 dipole strips FSS layer is used as reflector surface which yields enhanced gain from 4.41dBi to 8.99dBi (∽4.58dBi improvement), unidirectional radiation patterns, and improved front-to-back-ratio (FBR) from 1.7dB to 17.5dB in the E-plane at the design frequency 5.5GHz. The antenna achieves a -10dB bandwidth from 1.12GHz to 8.64GHz (7.52GHz). The measured results are in close agreement with the simulated results. At the end, an electrical equivalent resistor, inductor, and capacitor (RLC) circuit of the proposed antenna has been generated from the antenna reflection coefficient. The reflection coefficient of the RLC equivalent circuit of the proposed antenna is validated using advanced design system (ADS) software. Since the antenna has ultra-wideband (UWB) performance, therefore it is most suitable for wireless 3G/4G/5G and Sub-6GHz lower frequency range (FR1), satellite, and RADAR communications.