{"title":"磁化分布估计的物理信息神经网络","authors":"Zhi Gong, Zuqi Tang, Abdelkader Benabou","doi":"10.1049/elp2.70047","DOIUrl":null,"url":null,"abstract":"<p>Accurately estimating the magnetization distribution in permanent magnets is critical for optimising their performance in various applications, such as electric motors, generators and magnetic sensors, where precise magnetic field control is essential. A physics-informed neural network (PINN) is demonstrated to solve the inverse problem of magnetization distribution within the volume of permanent magnets. A neural network is constructed to model the spatially dependent magnetization in the magnet. The physical model, based on the Biot–Savart law, is integrated into the PINN framework. The discrepancy between the magnetic field calculated by the physical model and the externally observed one is used to guide the network training, exhibiting both the model-based and data-driven characteristics of the PINN. The accuracy and robustness of the proposed PINN are demonstrated through numerical experiments with both uniform and nonuniform magnetization scenarios, as well as both noise-free and noisy observation data. This study provides a new approach for solving magnetization distribution estimation problems, benefiting the development of high-quality permanent magnets for electrical engineering applications.</p>","PeriodicalId":13352,"journal":{"name":"Iet Electric Power Applications","volume":"19 1","pages":""},"PeriodicalIF":1.5000,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/elp2.70047","citationCount":"0","resultStr":"{\"title\":\"Physics-Informed Neural Network for Magnetization Distribution Estimation\",\"authors\":\"Zhi Gong, Zuqi Tang, Abdelkader Benabou\",\"doi\":\"10.1049/elp2.70047\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p>Accurately estimating the magnetization distribution in permanent magnets is critical for optimising their performance in various applications, such as electric motors, generators and magnetic sensors, where precise magnetic field control is essential. A physics-informed neural network (PINN) is demonstrated to solve the inverse problem of magnetization distribution within the volume of permanent magnets. A neural network is constructed to model the spatially dependent magnetization in the magnet. The physical model, based on the Biot–Savart law, is integrated into the PINN framework. The discrepancy between the magnetic field calculated by the physical model and the externally observed one is used to guide the network training, exhibiting both the model-based and data-driven characteristics of the PINN. The accuracy and robustness of the proposed PINN are demonstrated through numerical experiments with both uniform and nonuniform magnetization scenarios, as well as both noise-free and noisy observation data. This study provides a new approach for solving magnetization distribution estimation problems, benefiting the development of high-quality permanent magnets for electrical engineering applications.</p>\",\"PeriodicalId\":13352,\"journal\":{\"name\":\"Iet Electric Power Applications\",\"volume\":\"19 1\",\"pages\":\"\"},\"PeriodicalIF\":1.5000,\"publicationDate\":\"2025-07-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://onlinelibrary.wiley.com/doi/epdf/10.1049/elp2.70047\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Iet Electric Power Applications\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://onlinelibrary.wiley.com/doi/10.1049/elp2.70047\",\"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}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Iet Electric Power Applications","FirstCategoryId":"5","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1049/elp2.70047","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}
Physics-Informed Neural Network for Magnetization Distribution Estimation
Accurately estimating the magnetization distribution in permanent magnets is critical for optimising their performance in various applications, such as electric motors, generators and magnetic sensors, where precise magnetic field control is essential. A physics-informed neural network (PINN) is demonstrated to solve the inverse problem of magnetization distribution within the volume of permanent magnets. A neural network is constructed to model the spatially dependent magnetization in the magnet. The physical model, based on the Biot–Savart law, is integrated into the PINN framework. The discrepancy between the magnetic field calculated by the physical model and the externally observed one is used to guide the network training, exhibiting both the model-based and data-driven characteristics of the PINN. The accuracy and robustness of the proposed PINN are demonstrated through numerical experiments with both uniform and nonuniform magnetization scenarios, as well as both noise-free and noisy observation data. This study provides a new approach for solving magnetization distribution estimation problems, benefiting the development of high-quality permanent magnets for electrical engineering applications.
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