Bayesian Regularization Based ANN for the Design of Flexible Antenna for UWB Wireless Applications

Abstract

This paper presents a flexible pentagonal shape Ultra-Wide Band (UWB) antenna design using Artificial Neural Network (ANN) for WLAN, 5G, and WiMAX applications. The pentagonal patch is placed on top of flexible polyimide substrate and simulated using the well-known 3-D electromagnetic (EM) simulator HFSS, v.18.1. Due to large computing cluster required by the EM simulator to solve the design under consideration in addition to the time consumed, ANN is used to synthesize the design and reduce the cost and time consumed to analyze the aforementioned structure. Neural Network with 1 hidden layer of 10 neurons based on Bayesian Regularization algorithm is presented. An error of less 5% is produced during the learning, validation, and testing processes. Neural network is a good candidate to represent the pentagonal shape antenna used for UWB applications.