A generalized neural simulator for computing different parameters of circular/triangular microstrip antennas simultaneously

Computation of different parameters using a generalized hardware/software approach leads to save time and resources. Keeping this concept in mind authors are proposed a generalized neural simulator for computing two parameters each of circular patch (i.e. resonance frequency and radius) and triangular patch (i.e. resonance frequency and side-length) microstrip antennas simultaneously. For the purpose nine different training algorithms are used and Levenberg-Marquardt (LM) backpropagation is proved to be the fastest converging training algorithm and producing the results with least error. The results thus obtained by this simulator are in conventionality and very good in agreement with their measured counterparts.