Neural network based CAD model for the design of rectangular patch antennas

Vandana Vikas Thakare¹* and Pramod Singhal²

¹Department of Electronics and Instrumentation Engineering, Anand Engineering College, Keetham, Agra, India, 282007.

²Department of Electronics Engineering, Madhav Institute of Technology and Science, Gwalior, India

. 

*Corresponding author. E-mail: vandanavt_19@rediffmail.com.

Tel: +91-9411961534.

Accepted 14 June, 2010

   Abstract

A new method of calculation of patch dimensions of a rectangular microstrip patch antennas using Artificial Neural Network (ANN) has been adopted in this paper. An ANN model has been developed and tested for rectangular patch antenna design. It transforms the data containing the dielectric constant (ε_r), thickness of the substrate (h), and antenna’s dominant-mode resonant frequency (f_r) to the patch dimensions that is, length (l) and width (w) of the patch. The results obtained using ANNs are compared with the simulation findings. The simulated values are obtained by designing the microstrip antenna using IE3D electromagnetic simulator. The ANNs results are more in agreement with simulation findings.

Key words: Microstrip antenna, bandwidth, simulation, modelling, neural networks, CAD