Phase characterization of a reflectarray unit cell with Minkowski shape radiating element using Multilayer Perceptron Neural Network

In recent years reflectarray antennas have become very popular research area for scientists to overcome their limitations which are the narrow band of the radiating elements and the differential spatial phase delay between elements on the reflectarray. The recent aim of reflectarray antenna design is to have a smaller gradient (slower slope) of the reflected wave phase by varying the size of radiating element. In this work, a single layer reflectarray unit cell is designed by using Minkowski shape radiating element. The reflection phase of unit cell is simulated varying geometric parameters of patch and substrate thickness within range 10-12 (GHz). After that Multilayer Perceptron Neural Network (MLP NN) is carried out to predict the phase characterization of reflected wave. Results which are reconstructed by MLP show that MLP NN can be used as a very successful technique for defining phase characteristics of a reflectarray unit cell design.