ANN Model of Parabolic Reflector Antenna with Variable Feed Point Position

In this paper, the influence of the axial displacement of the feeder on the directivity of the parabolic reflector antenna is investigated. Deep neural networks are used to model the directivity of the antenna based on the following parameters: frequency, antenna diameter, focal length to antenna diameter ratio and feed point position along the main lobe axis. The accuracy and computational efficiency of the developed neural model is investigated and compared with that of the conventional EM model.