Resonant frequency calculation for circular microstrip antennas using artificial neural networks

Sagiroglu S., Guney K., Erler M.

INTERNATIONAL JOURNAL OF RF AND MICROWAVE COMPUTER-AIDED ENGINEERING, vol.8, no.3, pp.270-277, 1998 (SCI-Expanded) identifier identifier identifier


A new, simple approach for calculating bandwidth of electrically thin and thick rectangular microstrip patch antennas, based on multilayered perceptrons network, is presented. Four learning algorithms, backpropagation, delta-bar-delta, quick propagation, and extended-delta-bar-delta are used to train perceptrons. Theoretical bandwidth results obtained using the new approach are in agreement with experimental results available in the literature.

A new method based on artificial neural networks for calculating the resonant frequency of circular microstrip patch antennas is presented. This neural method is simple and is useful for the computer-aided design (CAD) of microstrip antennas. The theoretical resonant frequency results obtained by using the method are in very good agreement with the experimental results reported elsewhere. (C) 1998 John Wiley & Sons, Inc.