Neural network modeller for multilayered microstrip patch antennas

This paper presents the development of a neural network modeller for the optimisation of a dual band multilayer microstrip patch antenna. The multilayer antenna is built on an in-house semi-insulating GaAs substrate and poses a challenge to the EM based optimisation. The developed neural modeller speeds up design optimisation by replacing repeated EM simulations and retains good accuracy compared with the MoM modelling.