Hybrid Electromagnetic Modelling of Tubular Permanent Magnet Linear Motors Based on Transfer Learning Physics-Informed Neural Networks

IF 1.5 4区 工程技术 Q3 ENGINEERING, ELECTRICAL & ELECTRONIC
Jiale Guo, Tao Wu, Xinmei Wang, Xiongbo Wan
{"title":"Hybrid Electromagnetic Modelling of Tubular Permanent Magnet Linear Motors Based on Transfer Learning Physics-Informed Neural Networks","authors":"Jiale Guo,&nbsp;Tao Wu,&nbsp;Xinmei Wang,&nbsp;Xiongbo Wan","doi":"10.1049/elp2.70057","DOIUrl":null,"url":null,"abstract":"<p>Due to the inherent nonlinearity and saturation in the magnetic circuits of tubular permanent magnet linear motors, the analytical method (AM), while computationally efficient, often fails to capture complex electromagnetic behaviours accurately. In contrast, the finite element analysis (FEA) offers high precision but is time consuming. The nonlinearity of magnetic materials introduces strong input–output coupling, while saturation leads to localised deviations in field distributions, both of which reduce the effectiveness and generalisability of conventional modelling approaches. To overcome these challenges, a physics-informed, data-driven modelling approach is proposed. Initially, a novel hybrid modelling framework based on physics-informed neural networks (PINNs) is introduced. In this framework, AM is incorporated into both the input-output layers and the relevant variables, thereby enabling the direct embedding of physical constraints into the loss function. Consequently, the network's training process is rigorously guided in accordance with established physical principles. To further enhance prediction accuracy and generalisation, a transfer learning framework is integrated into PINN, utilising pre-trained datasets from AM and fine-tuning the model using high-accuracy datasets derived from FEA. Additionally, to optimise the physical information-related hyperparameters that impact model accuracy, functional analysis of variance is employed to quantitatively assess their importance and determine the optimal hyperparameter values. Experimental results show that, with training sample sizes representing only 5% of the FEA data, TL-PINN achieves significant improvements over DNN, including a 74.25% reduction in (1 − <i>R</i><sup>2</sup>), a 49.51% reduction in RMSE, and a 50.46% reduction in MAE. These findings demonstrate that TL-PINN delivers superior accuracy while utilising substantially fewer FEA datasets.</p>","PeriodicalId":13352,"journal":{"name":"Iet Electric Power Applications","volume":"19 1","pages":""},"PeriodicalIF":1.5000,"publicationDate":"2025-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/elp2.70057","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Iet Electric Power Applications","FirstCategoryId":"5","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1049/elp2.70057","RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"ENGINEERING, ELECTRICAL & ELECTRONIC","Score":null,"Total":0}
引用次数: 0

Abstract

Due to the inherent nonlinearity and saturation in the magnetic circuits of tubular permanent magnet linear motors, the analytical method (AM), while computationally efficient, often fails to capture complex electromagnetic behaviours accurately. In contrast, the finite element analysis (FEA) offers high precision but is time consuming. The nonlinearity of magnetic materials introduces strong input–output coupling, while saturation leads to localised deviations in field distributions, both of which reduce the effectiveness and generalisability of conventional modelling approaches. To overcome these challenges, a physics-informed, data-driven modelling approach is proposed. Initially, a novel hybrid modelling framework based on physics-informed neural networks (PINNs) is introduced. In this framework, AM is incorporated into both the input-output layers and the relevant variables, thereby enabling the direct embedding of physical constraints into the loss function. Consequently, the network's training process is rigorously guided in accordance with established physical principles. To further enhance prediction accuracy and generalisation, a transfer learning framework is integrated into PINN, utilising pre-trained datasets from AM and fine-tuning the model using high-accuracy datasets derived from FEA. Additionally, to optimise the physical information-related hyperparameters that impact model accuracy, functional analysis of variance is employed to quantitatively assess their importance and determine the optimal hyperparameter values. Experimental results show that, with training sample sizes representing only 5% of the FEA data, TL-PINN achieves significant improvements over DNN, including a 74.25% reduction in (1 − R2), a 49.51% reduction in RMSE, and a 50.46% reduction in MAE. These findings demonstrate that TL-PINN delivers superior accuracy while utilising substantially fewer FEA datasets.

Abstract Image

基于迁移学习物理信息神经网络的管状永磁直线电机混合电磁建模
由于管状永磁直线电机磁路固有的非线性和饱和,分析方法虽然计算效率高,但往往不能准确地捕捉复杂的电磁行为。相比之下,有限元分析(FEA)精度高,但耗时长。磁性材料的非线性引入了强的输入输出耦合,而饱和导致了场分布的局部偏差,这两者都降低了传统建模方法的有效性和通用性。为了克服这些挑战,提出了一种物理信息,数据驱动的建模方法。首先,介绍了一种基于物理信息神经网络(pinn)的混合建模框架。在这个框架中,AM被合并到输入-输出层和相关变量中,从而能够将物理约束直接嵌入到损失函数中。因此,网络的训练过程严格按照既定的物理原理进行指导。为了进一步提高预测准确性和泛化性,将迁移学习框架集成到PINN中,利用AM的预训练数据集,并使用源自FEA的高精度数据集对模型进行微调。此外,为了优化影响模型准确性的物理信息相关超参数,采用方差的功能分析定量评估其重要性并确定最优超参数值。实验结果表明,在训练样本量仅占FEA数据的5%的情况下,TL-PINN比DNN取得了显著的改进,包括(1−R2)降低74.25%,RMSE降低49.51%,MAE降低50.46%。这些发现表明,TL-PINN在利用更少的有限元数据集的同时提供了更高的精度。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
Iet Electric Power Applications
Iet Electric Power Applications 工程技术-工程:电子与电气
CiteScore
4.80
自引率
5.90%
发文量
104
审稿时长
3 months
期刊介绍: IET Electric Power Applications publishes papers of a high technical standard with a suitable balance of practice and theory. The scope covers a wide range of applications and apparatus in the power field. In addition to papers focussing on the design and development of electrical equipment, papers relying on analysis are also sought, provided that the arguments are conveyed succinctly and the conclusions are clear. The scope of the journal includes the following: The design and analysis of motors and generators of all sizes Rotating electrical machines Linear machines Actuators Power transformers Railway traction machines and drives Variable speed drives Machines and drives for electrically powered vehicles Industrial and non-industrial applications and processes Current Special Issue. Call for papers: Progress in Electric Machines, Power Converters and their Control for Wave Energy Generation - https://digital-library.theiet.org/files/IET_EPA_CFP_PEMPCCWEG.pdf
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信