An Adaptive Evolutionary Algorithm for UWB Microstrip Antennas Optimization Using a Machine Learning Technique

Abstract

This article presents an application of a machine learning technique to enhance a multiobjective evolutionary algorithm to estimate fitness function behaviors from a set of experiments made in laboratory to analyze a microstrip antenna used in ultra wideband wireless devices. These function behaviors are related to three objectives: bandwidth, return loss, and central frequency deviation. Each objective is used inside an aggregate adaptive weighted fitness function that estimates the behavior in the algorithm. The machine learning technique enabled a dynamic estimation of an aggregated compound fitness function and made it possible to a prototype algorithm to learn and adapt with a set of experiments stored in a web system repository. The final results were then compared with the ones obtained with a similar antenna modeled in a simulator program and with the ones of a real prototype antenna built from the optimal values obtained after the optimization.

A comparative analysis of machine learning approach for optimizing antenna design

“…Also, in recent years, different optimization approaches have been analyzed with evolutionary algorithms such as genetic algorithms (GA) [25], swarm intelligence [26], and differential evolution (DE) algorithms, which are designed from the inspiration of nature and have been used to optimize the antenna design [27,28]. In [29], GAs have been combined with interpolation to design an ultrawide band ring monopole antenna. Also, in [30], GAs have been used to design unconventional antenna systems for 5G-based stations.…”

A review on the design and optimization of antennas using machine learning algorithms and techniques

“…Interpolation combined with GA used for the design of an UWB ring monopole antenna was presented in References 186 and 187 where fitness function behaviors such as the BW, the RL, and the central frequency division (CFD) were estimated. After optimizing those parameters, comparison was held between a simulated antenna and a real prototype manufactured from the obtained values.…”