Artificial Neural Network Model for Suspended Rectangular Microstrip Antennas

The broadband microstrip antenna is more commonly realized by fabricating the patch on lower dielectric constant thicker substrate. While using thicker substrate, close form expressions for calculating edge extension length due to fringing fields is not available. In this paper, an artificial neural network model for suspended rectangular microstrip antenna is proposed. The resonance frequency calculated by using the proposed neural network model closely agrees with simulated and measured results over wide frequency range and for varying thicker substrates. Thus the proposed model can be used to accurately calculate the side length of rectangular microstrip antenna.