An Artificial Neural Network Model for Feed Position of the Microstrip Antenna
The current work deals with the development of an artificial neural network for fixing the feed position of a microstrip antenna, given the desired parameters like resonant frequency f0, substrate thickness, and relative permittivity εr. The network is first trained by varying patch dimensions at a fixed frequency. Next it is trained with all the three varying parameters, the patch dimensions (W and L) together with the frequency, to obtain the suitable position of the feed. Ill. 2, bibl. 5 (in English; summaries in Lithuanian, English and Russian).