Automated optimization for broadband flat‐gain antenna designs with artificial neural network

Abstract

An automated optimization process for designing and optimising high-performance single microstrip antennas is presented. It consists of the successive use of two optimization methods, bottom-up optimization (BUO) and Bayesian optimization (BO), which are applied sequentially, resulting in electromagnetic (EM)-based artificial neural network modelling. The BUO method is applied for the initial design of the structure of the antennas whereas the BO approach is successively implemented to predict suitable dimensional parameters, leading to broadband, high flat-gain antennas. The optimization process is performed automatically with the combination of an electronic design automation tool and a numerical analyser. The proposed method is easy to use; it allows one to perform the design with little experience, because both structure modelling and sizing are performed automatically. To verify the power of the proposed EM-based method experimentally, two single microstrip antennas have been designed, optimised, fabricated, and measured. The first antenna has flat-gain performance (6.9-7.2 dB) in a frequency band of 8.8-10 GHz. The second has been designed to perform in the 8.7-to 10-GHz band, where it exhibits flat-gain performance with reduced fluctuation in the range of 6.7-7 dB. The experimental results are in good agreement with the numerical data.This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

Overview of evolutionary algorithms and neural networks for modern mobile communication

“…With respect to the authors' experience, AI methods can be used as platforms for constructing reported optimization methods and optimizing system's output specifications in an efficient way. Kouhalvandi et al in various research papers have proved this idea where ANNs and deep neural networks (DNNs) are used as platforms for optimizing power amplifiers (PAs) and antennas' output specifications using diverse multi‐objective optimization methods 56,261,283 . This idea leads to optimize complex systems in an automated environment without depending to any human's experience.…”

“…Kouhalvandi et al in various research papers have proved this idea where ANNs and deep neural networks (DNNs) are used as platforms for optimizing power amplifiers (PAs) and antennas' output specifications using diverse multi-objective optimization methods. 56,261,283 This idea leads to optimize complex systems in an automated environment without depending to any human's experience.…”

Hybrid Evolutionary Computing Assisted Irregular-Shaped Patch Antenna Design for Wide Band Applications

“…They found the PSO-MANFIS model provided more accurate results than the GA-MANFIS model. Conversely, Mir et al [31] investigated an automated optimization procedure based on Bayesian-optimization (BO) and bottom-up-optimization (BUO) to design the MPA for broadband with high flat-gain features. The initial structure of the MPA is designed by the BUO approach while the BO process is applied to forecast appropriate dimensional parameters.…”

“…( 28)). Now, the other coordinates of the antenna radiators (i.e., p 1 , p 2 , p 3 , p 4 , and p 5 ) are obtained as per equations (28)(29)(30)(31)(32)(33)(34)(35)(36)(37)(38)(39), which are found using the GSA-QPSO algorithm. Though, MATLAB is applied as the key development tool; where HFSS has been utilized to validate the performance of reflection coefficients and radiation characteristics.…”

Deep Learning Assisted Automatic Methodology for Implanted MIMO Antenna Designs on Large Ground Plane

“…Due to the complexity of MIMO antennas, it is not straightforward to model and design these circuits, and optimization-based approaches are importantly required. Reported various optimization methods around radio frequency and antenna designs are particle swarm optimization [6,7], ant colony optimization [8,9], chicken swarm optimization [10], harmony search algorithm [11], and genetic algorithm [12]; however, when the design parameters are in a huge number these methods can not be successful and intelligent based optimization methods are required [13].…”