A Review of Data-Driven Models for Electromagnetic Devices Design and Analysis

In recent years, the design and optimization of electromagnetic devices have grown increasingly complex, driven by the demand for higher efficiency, greater power density, and cost-effectiveness. Traditional approaches such as finite element analysis (FEA) offer precise simulations but can be time-c...

Full description

Saved in:
Bibliographic Details
Main Authors: Zihan Li, Mengyu Cheng, Andy Tyrrell, Xing Zhao
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11091428/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849340563661258752
author Zihan Li
Mengyu Cheng
Andy Tyrrell
Xing Zhao
author_facet Zihan Li
Mengyu Cheng
Andy Tyrrell
Xing Zhao
author_sort Zihan Li
collection DOAJ
description In recent years, the design and optimization of electromagnetic devices have grown increasingly complex, driven by the demand for higher efficiency, greater power density, and cost-effectiveness. Traditional approaches such as finite element analysis (FEA) offer precise simulations but can be time-consuming and computationally intensive. To address these challenges, data-driven methods have gained traction as efficient alternatives. This review, focusing on recent deep learning advances, presents a comprehensive review on the application of data-driven models in the design and optimization of electromagnetic devices, summarizing the statistical models such as Response Surface Methodology (RSM) and recent popular machine learning (ML) methods in handling multiple variables, as well as the deep learning (DL) models, in predicting various electromagnetic device parameters and optimizing electromagnetic models. This paper highlights the latest advances in DL models for electromagnetic device applications, including motors, transformers, and electrical wires. It discusses their potential to assist FEA to accelerate design and optimization. Future key directions are proposed to improve efficiency and expand the versatility of data-driven models.
format Article
id doaj-art-d42841fce3084e8bbfac6bc7cb777622
institution Kabale University
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-d42841fce3084e8bbfac6bc7cb7776222025-08-20T03:43:52ZengIEEEIEEE Access2169-35362025-01-011314216114218510.1109/ACCESS.2025.359196511091428A Review of Data-Driven Models for Electromagnetic Devices Design and AnalysisZihan Li0https://orcid.org/0009-0006-2289-5353Mengyu Cheng1https://orcid.org/0000-0002-6483-4480Andy Tyrrell2https://orcid.org/0000-0002-8533-2404Xing Zhao3https://orcid.org/0000-0003-4000-0446School of Physics, Engineering and Technology, University of York, York, U.K.School of Physics, Engineering and Technology, University of York, York, U.K.School of Physics, Engineering and Technology, University of York, York, U.K.School of Physics, Engineering and Technology, University of York, York, U.K.In recent years, the design and optimization of electromagnetic devices have grown increasingly complex, driven by the demand for higher efficiency, greater power density, and cost-effectiveness. Traditional approaches such as finite element analysis (FEA) offer precise simulations but can be time-consuming and computationally intensive. To address these challenges, data-driven methods have gained traction as efficient alternatives. This review, focusing on recent deep learning advances, presents a comprehensive review on the application of data-driven models in the design and optimization of electromagnetic devices, summarizing the statistical models such as Response Surface Methodology (RSM) and recent popular machine learning (ML) methods in handling multiple variables, as well as the deep learning (DL) models, in predicting various electromagnetic device parameters and optimizing electromagnetic models. This paper highlights the latest advances in DL models for electromagnetic device applications, including motors, transformers, and electrical wires. It discusses their potential to assist FEA to accelerate design and optimization. Future key directions are proposed to improve efficiency and expand the versatility of data-driven models.https://ieeexplore.ieee.org/document/11091428/Data-driven modelsdeep learningelectromagnetic devicemachine learningoptimizationsurrogate model
spellingShingle Zihan Li
Mengyu Cheng
Andy Tyrrell
Xing Zhao
A Review of Data-Driven Models for Electromagnetic Devices Design and Analysis
IEEE Access
Data-driven models
deep learning
electromagnetic device
machine learning
optimization
surrogate model
title A Review of Data-Driven Models for Electromagnetic Devices Design and Analysis
title_full A Review of Data-Driven Models for Electromagnetic Devices Design and Analysis
title_fullStr A Review of Data-Driven Models for Electromagnetic Devices Design and Analysis
title_full_unstemmed A Review of Data-Driven Models for Electromagnetic Devices Design and Analysis
title_short A Review of Data-Driven Models for Electromagnetic Devices Design and Analysis
title_sort review of data driven models for electromagnetic devices design and analysis
topic Data-driven models
deep learning
electromagnetic device
machine learning
optimization
surrogate model
url https://ieeexplore.ieee.org/document/11091428/
work_keys_str_mv AT zihanli areviewofdatadrivenmodelsforelectromagneticdevicesdesignandanalysis
AT mengyucheng areviewofdatadrivenmodelsforelectromagneticdevicesdesignandanalysis
AT andytyrrell areviewofdatadrivenmodelsforelectromagneticdevicesdesignandanalysis
AT xingzhao areviewofdatadrivenmodelsforelectromagneticdevicesdesignandanalysis
AT zihanli reviewofdatadrivenmodelsforelectromagneticdevicesdesignandanalysis
AT mengyucheng reviewofdatadrivenmodelsforelectromagneticdevicesdesignandanalysis
AT andytyrrell reviewofdatadrivenmodelsforelectromagneticdevicesdesignandanalysis
AT xingzhao reviewofdatadrivenmodelsforelectromagneticdevicesdesignandanalysis