Parameter Estimation of Two-Element Rectangular Microstrip Patch Antenna Using Artificial Neural Network

The process of estimating the parameters of rectangular patch microstrip antennas has so far had some shortcomings, such as the amount of error generated and the complexity of the method. Therefore, research is needed to develop a new method that can improve the results of estimating the parameters, reducing the error rate and simplifying the process. An estimator model based on Artificial Neural Network (ANN) is proposed to analyse and estimate the parameters of a two-element rectangular patch microstrip antenna, including directivity, resonant frequency, VSWR, gain, bandwidth, and return loss. The data values input into the ANN include the substrate's dielectric constant, the substrate's thickness, and the feed and patch's length and width. The results show that the ANN can estimate the parameters of a two-element rectangular patch microstrip antenna with a low error rate and good convergence with low Mean Squared Error (MSE) value for directivity, resonant frequency, VSWR, gain, bandwidth, and return loss parameters of 0.00862, 0.02440, 0.00228, 0.04352, 0.00004, and 0.10232, respectively. The evaluation results demonstrate that our proposed ANN model have increased the accuracy estimation rate of two-element rectangular patch microstrip antenna parameters.