Two-stage variable-fidelity modeling of antennas with domain confinement

Pietrenko‐Dabrowska, Anna; Kozieł, Sławomir; Golunski, Lukasz

doi:10.1038/s41598-022-20495-y

Cited by 11 publications

(4 citation statements)

References 84 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another ML-assisted antenna optimization method employing the use of multifidelity or variable-fidelity models of the given antenna structure in the optimization process to further improve the efficiency of surrogate modeling and the overall optimization process has been proposed [29]. In [29], variablefidelity EM models are used for both the surrogate domain definition and the final rendering of the surrogate model employed in the optimization process. Co-kriging is then employed to blend the low-fidelity and high-fidelity simulation data to better manage model discrepancies.…”

Section: Multifidelity Optimizationmentioning

confidence: 99%

Automated Design of Antennas Using AI Techniques: A Review of Contemporary Methods and Applications

Akinsolu,

Hua,

Liu

2024

2024 18th European Conference on Antennas and Propagation (EuCAP)

View full text Add to dashboard Cite

The automated design of antennas made possible through the use of artificial intelligence (AI) techniques is attracting much attention. This development can be mainly attributed to the reduced design time and the higher quality of design solutions that AI-driven antenna optimization methods provide in comparison to their more traditional counterparts. Due to the growing need to fulfill more stringent design specifications and functional requirements for both present-day and future wireless communication systems, the design and development of antennas and antenna systems have increased both in scope and complexity, such that conventional methodologies are often not fit for an efficient practical implementation. In this paper, a brief overview of some of the latest AI-based techniques for the design and optimization of contemporary antennas is provided with the goal of providing information on recent research to researchers in this growing area of interest.

show abstract

Section: Multifidelity Optimizationmentioning

confidence: 99%

Automated Design of Antennas Using AI Techniques: A Review of Contemporary Methods and Applications

Akinsolu,

Hua,

Liu

2024

2024 18th European Conference on Antennas and Propagation (EuCAP)

View full text Add to dashboard Cite

show abstract

“…Traditional metamodeling methodologies cannot handle nonlinear antenna characteristics across a large range of system parameters due to the curse of dimensionality. Performance-driven modeling frameworks that build surrogates from antenna performance numbers rather than geometric factors can overcome this issue [ 38 ]. This method dramatically reduces model setup costs without losing design utility.…”

Section: Related Workmentioning

confidence: 99%

Improved Dipper-Throated Optimization for Forecasting Metamaterial Design Bandwidth for Engineering Applications

et al. 2023

View full text Add to dashboard Cite

Metamaterials have unique physical properties. They are made of several elements and are structured in repeating patterns at a smaller wavelength than the phenomena they affect. Metamaterials’ exact structure, geometry, size, orientation, and arrangement allow them to manipulate electromagnetic waves by blocking, absorbing, amplifying, or bending them to achieve benefits not possible with ordinary materials. Microwave invisibility cloaks, invisible submarines, revolutionary electronics, microwave components, filters, and antennas with a negative refractive index utilize metamaterials. This paper proposed an improved dipper throated-based ant colony optimization (DTACO) algorithm for forecasting the bandwidth of the metamaterial antenna. The first scenario in the tests covered the feature selection capabilities of the proposed binary DTACO algorithm for the dataset that was being evaluated, and the second scenario illustrated the algorithm’s regression skills. Both scenarios are part of the studies. The state-of-the-art algorithms of DTO, ACO, particle swarm optimization (PSO), grey wolf optimizer (GWO), and whale optimization (WOA) were explored and compared to the DTACO algorithm. The basic multilayer perceptron (MLP) regressor model, the support vector regression (SVR) model, and the random forest (RF) regressor model were contrasted with the optimal ensemble DTACO-based model that was proposed. In order to assess the consistency of the DTACO-based model that was developed, the statistical research made use of Wilcoxon’s rank-sum and ANOVA tests.

show abstract

“…Efforts in space‐mapping/knowledge‐based modeling methods have also been expressed 6–14 to help EM parametric modeling and optimization perform better. Various space‐mapping methods have been introduced to map pre‐existing knowledge such as crude models, onto the EM response of microwave devices 15–49 …”

Section: Introductionmentioning

confidence: 99%

Advances in hybrid format‐based neuro‐transfer function techniques for parametric modeling of microwave components

Zhang

Liu

et al. 2023

Int J Numerical Modelling

View full text Add to dashboard Cite

Electromagnetic (EM) parametric modeling has become significant for EM designs of microwave devices. This paper outlines recent advances in hybrid format‐based neuro‐transfer function (TF) techniques for EM parametric modeling of microwave devices. To solve the problem of high‐sensitivity, a novel decomposition approach is discussed to develop a rational‐based neuro‐TF model of EM behavior of microwave devices. To handle the issue of non‐smoothness and discontinuity, a parametric modeling technique incorporating pole‐residue/rational and neural network hybrid transfer function (short for rational/pole‐residue hybrid neuro‐TF) of EM behavior is reviewed. This technique effectively combines rational and residue‐pole formats of the transfer functions. Compared with the residue‐pole‐based neuro‐TF modeling approach and the rational‐based neuro‐TF modeling approach, the rational/pole‐residue hybrid neuro‐TF technique allows for better accuracy in large geometrical changes and high order applications. A parametric modeling method combining neural network and polynomial‐transfer function (neuro‐PTF) is further presented as an advanced version of the rational/pole‐residue hybrid neuro‐TF method. In this approach, the pole–residue‐based transfer function and the polynomial function are used together to describe the EM responses, and can produce more accurate models, especially with large geometrical variables. Following the modeling process, trained models can be used to provide fast and accurate EM response predictions and can subsequently be used for advanced circuit and system design.

show abstract

Two-stage variable-fidelity modeling of antennas with domain confinement

Cited by 11 publications

References 84 publications

Automated Design of Antennas Using AI Techniques: A Review of Contemporary Methods and Applications

Automated Design of Antennas Using AI Techniques: A Review of Contemporary Methods and Applications

Improved Dipper-Throated Optimization for Forecasting Metamaterial Design Bandwidth for Engineering Applications

Advances in hybrid format‐based neuro‐transfer function techniques for parametric modeling of microwave components

Contact Info

Product

Resources

About