Analysis and design of microstrip antennas by Artificial Neural Networks

The most common methods of analysis and design of microstrip antennas are the transmission line and the cavity model (analytical), that introduce some simplifications in the mechanisms of radiation from antennas, therefore, some errors are introduced in the determination of its main parameters. On the other hand, numerical methods, which are more accurate, require large computational resources, high processing time and an advanced electromagnetic knowledge. This work deals with the use of Artificial Neural Network (ANN), to represent the relationship between the antenna parameters (frequency, size and dielectric constant) for the analysis and design of several shapes of microstrip antennas.