A Heuristic Artificial Neural Network Design of Resonant Frequency of Rectangular Microstrip/Patch Antennas

Abstract

In this paper, both the synthesis and analysis of rectangular microstrip antenna models based on the artificial neural networks are presented to calculate accurately the resonant frequency of the rectangular microstrip antennas. Artificial neural networks are developed from neurophysiology by morphologically and computationally mimicking human brains The resonant frequency results obtained by using rectangular microstrip antenna characteristics and neural network models are very good agreement with the experimental results available in the literature, this paper presents a multilayer perceptron (MLP)modular neural network, training with the resilient back propagation algorithm which has been used for nonlinear device modeling in microwave band.