On nature-inspired design optimization of antenna structures using variable-resolution EM models

Abstract

Numerical optimization has been ubiquitous in antenna design for over a decade or so. It is indispensable in handling of multiple geometry/material parameters, performance goals, and constraints. It is also challenging as it incurs significant CPU expenses, especially when the underlying computational model involves full-wave electromagnetic (EM) analysis. In most practical cases, the latter is imperative to ensure evaluation reliability. The numerical challenges are even more pronounced when global search is required, which is most often carried out using nature-inspired algorithms. Population-based procedures are known for their ability to escape from local optima, yet their computational efficiency is poor, which makes them impractical when applied directly to EM models. A common workaround is the utilization of surrogate modeling techniques, typically in the form of iterative prediction-correction schemes, where the accumulated EM simulation data is used to identify the promising regions of the parameter space and to refine the surrogate model predictive power at the same time. Notwithstanding, implementation of surrogate-assisted procedures is often intricate, whereas their efficacy may be hampered by the dimensionality issues and considerable nonlinearity of antenna characteristics. This work investigates the benefits of incorporating variable-resolution EM simulation models into nature-inspired algorithms for optimization of antenna structures, where the model resolution pertains to the level of discretization density of an antenna structure in the full-wave simulation model. The considered framework utilizes EM simulation models which share the same physical background and are selected from a continuous spectrum of allowable resolutions. The early stages of the search process are carried out with the use of the lowest fidelity model, which is subsequently automatically increased to finally reach the high-fidelity antenna representation (i.e., considered as sufficiently accurate for design purposes). Numerical validation is executed using several antenna structures of distinct types of characteristics, and a particle swarm optimizer as the optimization engine. The results demonstrate that appropriate resolution adjustment profiles permit considerable computational savings (reaching up to eighty percent in comparison to high-fidelity-based optimization) without noticeable degradation of the search process reliability. The most appealing features of the presented approach—apart from its computational efficiency—are straightforward implementation and versatility.

Applications of Machine Learning and Deep Learning in Antenna Design, Optimization, and Selection: A Review

“…Multiple research works are carried out to optimize antenna performance based on MLAO. In [25], [55], [57]- [63] Gaussian process regression (GPR), surrogate-based optimization (SBO), ANN, support vector machine (SVM), and master-apprentice board learning system (MABLS) are discussed. Different aspects of the current MLAO antenna design methods can be categorized, such as whether they are offline or online, local or global optimization, single or multi-objective optimization, or parallel optimization [25], [55], [57]- [60].…”

“…In [25], [55], [57]- [63] Gaussian process regression (GPR), surrogate-based optimization (SBO), ANN, support vector machine (SVM), and master-apprentice board learning system (MABLS) are discussed. Different aspects of the current MLAO antenna design methods can be categorized, such as whether they are offline or online, local or global optimization, single or multi-objective optimization, or parallel optimization [25], [55], [57]- [60]. The MLAO can be used for antenna design not only in the optimization stage but also sensitivity analysis (SA) and resilient design [64], [65].…”

Trust region framework-based design of sub-6 GHz m-MIMO antenna and evaluation of SAR

“…To overcome the aforementioned challenges in a more efficient and effective manner, new solutions and strategies in antenna design must be developed, with the integration of full-wave electromagnetic solvers and optimization methods being a promising approach (Mahoutı et al , 2022; Koziel and Pietrenko‐Dabrowska, 2022; Jiang et al , 2022). The effective use of optimization methods in antenna design has recently led to many successful outcomes (Mahoutı et al , 2022; Koziel and Pietrenko‐Dabrowska, 2022; Jiang et al , 2022; Kozieł and Pietrenko-Dabrowska, 2023; Koziel et al , 2023; Zhang et al , 2021). The main principle behind the use of optimizers is to obtain an optimal solution according to design requirements and objectives.…”

A Fast Surrogate Model-Based Algorithm Using Multilayer Perceptron Neural Networks for Microwave Circuit Design

“…Nonlinear phenomena present significant challenges when it comes to comprehending and predicting the behavior of complex systems. This holds true in various engineering fields, including microwave circuit design, medical engineering, industrial engineering, etc., wherein accurate modeling and analysis play a vital role in optimizing performance and ensuring reliability [12][13][14][15]. However, traditional analytical approaches often struggle to capture the intricate dynamics exhibited by nonlinear systems, prompting the exploration of alternative methods [16].…”