Abstract
In this paper, an artificial neural network (ANN)-based prediction model has been demonstrated to analyse microstrip transmission line (MTL) for the characteristic impedance, Z0. The ANN prediction model will overcome the time and effort required to design MTL using costly radio frequency (RF) software tools. The ANN model has been developed using feed forward back propagation (F-F B-P) algorithm with three hidden layers and optimized by gradient descent (GD) optimizer. ANN model has been developed on the dataset built using analytical formulation. The training, validation and test error obtained for the model are \( 7.197 \times 10^{ - 5} \), \( 6.189 \times 10^{ - 5} \) and 0.66, respectively, demonstrating high accuracy.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have