Advancements in Flexible Antenna Design: Enabling Tri-Band Connectivity for WLAN, WiMAX, and 5G Applications

Abstract

The use of flexible antennas has garnered significant interest in light of their wide-ranging applications inside contemporary wireless communication systems. The need for these antennas stems from the necessity for small, conformal, and versatile systems that can effectively function across many frequency ranges. The present study investigates designing and optimizing a universal triband antenna, focusing on meeting the distinct demands of Wireless Local Area Networks (WLAN), Worldwide Interoperability for Microwave Access (WiMAX), and 5G applications. The current methodologies often need help attaining maximum efficiency over a wide range of frequency bands, resulting in concerns such as subpar radiation patterns and restricted bandwidth. To address the obstacles, this research proposes a novel approach known as the Triband Antenna Design using the Artificial Neural Network (3AD-ANN) method. This method utilizes machine learning techniques to devise and enhance the attributes of the antenna effectively. The 3AD-ANN approach presents several notable characteristics, such as heightened adaptability, increased radiation patterns, and a condensed physical structure. The mean values for far-field radiation gain are around -37.4 dB in simulated scenarios and -39.9 dB in actual observations. The average return loss is roughly -23.8 dB in simulations and -25.8 dB in experimental measurements. The numerical findings illustrate the effectiveness of this methodology, exhibiting exceptional return loss and gain sizes over a range of frequencies, including WLAN, WiMAX, and 5G.