Efficient AI-Driven Design of Microwave Antennas Using PSADEA

Nowadays, artificial intelligence plays a very significant role in the optimal design of microwave devices such as antennas. In particular, antenna design automation via surrogate model-based optimization (SMBO) methods is attracting a lot of interest due to the efficiency improvement in terms of computational cost. The parallel surrogate model-assisted hybrid differential evolution for antenna optimisation (PSADEA) method is a state-of-the-art SMBO method. In this paper, PSADEA is used to synthesize a compact slotted monopole antenna for ultra wide band body-centric applications. The performance of PSADEA is compared with 2019 Computer Simulation Technology - Microwave Studio (CST-MWS) optimizers: trust region framework (TRF) and particle swarm optimisation (PSO). Results from the comparisons show that PSADEA obtains very satisfactory design solutions for the monopole antenna in all runs using an affordable optimization time in each, whereas the alternative optimizers fail to obtain a satisfactory design solution in all runs. A close agreement between the simulated and measured results for the fabricated prototype of a typical PSADEA synthesized design for the monopole antenna validates the design solution quality of PSADEA.