Abstract
In this paper, the design of frequency reconfigurable planar antenna by incorporation of metasurface superstrate (FRPA-MSS) is presented using an artificial neural network. The dual-layer radiating structure is created on a 1.524 mm thick Rogers RO4350B substrate board (εr = 3.48, tan δ = 0.0037). The candidate antenna is designed and analyzed using a high-frequency structure simulator (HFSS) tool. The transfer matrix method is employed for the successful retrieval of electromagnetic properties of the metamaterial. Frequency reconfiguration is achieved by placing the metasurface superstrate onto the rectangular patch antenna. A simplified ANN approach has been employed for the design of metasurface incorporated proposed antenna. Presented prototypes are characterized through experimental measurements. It is found from the practical observations that the proposed antenna effectively reconfigures the tuning range from 5.03 to 6.13 GHz. Moreover, the presented antenna operates efficiently with agreeable gain, good impedance matching, and stable pattern characteristics across the entire operational bandwidth. The experimental results obtained validate the simulated performance.
Specially designed microstrip patch antenna parameter optimization by artificial neural network