Modeling and design of an equilateral triangular patch antenna on suspended and single substrate are accomplished in this paper. The spectral domain approach is important due to its accuracy, but has a high computational cost. On the other hand, the Artificial Neural Networks (ANNs) have recently become a fast and flexible vehicle for modeling and designing microwave antennas. This paper introduces electromagnetic knowledge combined with ANNs to compute the resonant frequency of the fundamental and higher order modes and to eliminate the difficulties of handling the singularity points encountered in the numerical evaluation of integrals. The resonant frequency results obtained from the neural model are in very good agreement with the experimental and theoretical results available in the literature.
Read full abstract