Machine learning of heavy rare earth-based low-temperature magnetocaloric materials under complex classification methods

IF 2.5 3区 材料科学 Q3 MATERIALS SCIENCE, MULTIDISCIPLINARY
Zhang Yan , Gao Fei , Cui Guofeng , Kuang Yafei , Zong Shutong , Chen Fenghua , Liu Hongxia , Sun Zhigang , Shen Baogen
{"title":"Machine learning of heavy rare earth-based low-temperature magnetocaloric materials under complex classification methods","authors":"Zhang Yan ,&nbsp;Gao Fei ,&nbsp;Cui Guofeng ,&nbsp;Kuang Yafei ,&nbsp;Zong Shutong ,&nbsp;Chen Fenghua ,&nbsp;Liu Hongxia ,&nbsp;Sun Zhigang ,&nbsp;Shen Baogen","doi":"10.1016/j.jmmm.2025.173180","DOIUrl":null,"url":null,"abstract":"<div><div>Low-temperature magnetic refrigeration materials have important application value in the fields of aerospace, military defense, medical and health care, and low-temperature physics. Compared with the “stir-fry” material R&amp;D model, machine learning can accelerate the data analysis and R&amp;D of new materials. However, at present, the research on machine learning is limited to the simulation and prediction of a single type of material, and the research object is mainly focused on materials with high phase transition temperature. Obviously, the generalizability of this kind of research is low. In order to solve the above scientific problems, this paper uses the gradient boosted regression tree (GBRT) model to train the dataset of heavy rare earth-based alloys under different classification methods, taking the chemical composition as the characteristic attributes, and the Curie temperature and maximum magnetic entropy as the target attributes. It was found that the performance of heavy rare earth-based alloys was different under different classification methods. The prediction of Curie temperature under each classification method is very good, but the prediction effect of magnetic entropy change with non-intrinsic properties is completely different. Among them, the prediction effect of magnetic entropy change of the whole dataset is poor,and the training results of the hexagonal structure and ternary alloys dataset are excellent. The correlation coefficient (R<sup>2</sup>) of the hexagonal structure on the training set and the test set is 0.99 and 0.77, respectively. The fitting results for the ternary alloys also reached 0.97 and 0.80, respectively. However, the orthogonal structure and binary structure datasets performed extremely poor, and the R<sup>2</sup> value of the test set was only 0.31 and 0.17, respectively. For the first time, we obtained the good prediction results of magnetocaloric effect materials under complex classification methods through the GBRT machine learning model, and revealed the influence of different classification methods on the target and feature attributes of the dataset from the physical level. These results are helpful to accelerate the development of low-temperature magnetocaloric materials.</div></div>","PeriodicalId":366,"journal":{"name":"Journal of Magnetism and Magnetic Materials","volume":"628 ","pages":"Article 173180"},"PeriodicalIF":2.5000,"publicationDate":"2025-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Magnetism and Magnetic Materials","FirstCategoryId":"88","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0304885325004123","RegionNum":3,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"MATERIALS SCIENCE, MULTIDISCIPLINARY","Score":null,"Total":0}
引用次数: 0

Abstract

Low-temperature magnetic refrigeration materials have important application value in the fields of aerospace, military defense, medical and health care, and low-temperature physics. Compared with the “stir-fry” material R&D model, machine learning can accelerate the data analysis and R&D of new materials. However, at present, the research on machine learning is limited to the simulation and prediction of a single type of material, and the research object is mainly focused on materials with high phase transition temperature. Obviously, the generalizability of this kind of research is low. In order to solve the above scientific problems, this paper uses the gradient boosted regression tree (GBRT) model to train the dataset of heavy rare earth-based alloys under different classification methods, taking the chemical composition as the characteristic attributes, and the Curie temperature and maximum magnetic entropy as the target attributes. It was found that the performance of heavy rare earth-based alloys was different under different classification methods. The prediction of Curie temperature under each classification method is very good, but the prediction effect of magnetic entropy change with non-intrinsic properties is completely different. Among them, the prediction effect of magnetic entropy change of the whole dataset is poor,and the training results of the hexagonal structure and ternary alloys dataset are excellent. The correlation coefficient (R2) of the hexagonal structure on the training set and the test set is 0.99 and 0.77, respectively. The fitting results for the ternary alloys also reached 0.97 and 0.80, respectively. However, the orthogonal structure and binary structure datasets performed extremely poor, and the R2 value of the test set was only 0.31 and 0.17, respectively. For the first time, we obtained the good prediction results of magnetocaloric effect materials under complex classification methods through the GBRT machine learning model, and revealed the influence of different classification methods on the target and feature attributes of the dataset from the physical level. These results are helpful to accelerate the development of low-temperature magnetocaloric materials.
复杂分类方法下重稀土基低温磁热材料的机器学习
低温磁致冷材料在航空航天、军事国防、医疗卫生、低温物理等领域具有重要的应用价值。与“炒菜式”材料研发模型相比,机器学习可以加速新材料的数据分析和研发。但目前对机器学习的研究还局限于对单一类型材料的模拟和预测,研究对象主要集中在相变温度较高的材料上。显然,这类研究的通用性较低。为了解决上述科学问题,本文采用梯度增强回归树(GBRT)模型,以化学成分为特征属性,居里温度和最大磁熵为目标属性,对不同分类方法下的重稀土基合金数据集进行训练。研究发现,在不同的分类方法下,重稀土基合金的性能是不同的。每种分类方法对居里温度的预测效果都很好,但对具有非本征性质的磁熵变化的预测效果则完全不同。其中,整个数据集的磁熵变化预测效果较差,六边形结构和三元合金数据集的训练结果优异。六边形结构在训练集和测试集上的相关系数R2分别为0.99和0.77。三元合金的拟合结果也分别达到0.97和0.80。然而,正交结构和二元结构数据集表现极差,检验集的R2值分别仅为0.31和0.17。我们首次通过GBRT机器学习模型获得了复杂分类方法下对磁热效应材料的良好预测结果,并从物理层面上揭示了不同分类方法对数据集目标属性和特征属性的影响。这些结果有助于加快低温磁致热材料的发展。
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
Journal of Magnetism and Magnetic Materials
Journal of Magnetism and Magnetic Materials 物理-材料科学:综合
CiteScore
5.30
自引率
11.10%
发文量
1149
审稿时长
59 days
期刊介绍: The Journal of Magnetism and Magnetic Materials provides an important forum for the disclosure and discussion of original contributions covering the whole spectrum of topics, from basic magnetism to the technology and applications of magnetic materials. The journal encourages greater interaction between the basic and applied sub-disciplines of magnetism with comprehensive review articles, in addition to full-length contributions. In addition, other categories of contributions are welcome, including Critical Focused issues, Current Perspectives and Outreach to the General Public. Main Categories: Full-length articles: Technically original research documents that report results of value to the communities that comprise the journal audience. The link between chemical, structural and microstructural properties on the one hand and magnetic properties on the other hand are encouraged. In addition to general topics covering all areas of magnetism and magnetic materials, the full-length articles also include three sub-sections, focusing on Nanomagnetism, Spintronics and Applications. The sub-section on Nanomagnetism contains articles on magnetic nanoparticles, nanowires, thin films, 2D materials and other nanoscale magnetic materials and their applications. The sub-section on Spintronics contains articles on magnetoresistance, magnetoimpedance, magneto-optical phenomena, Micro-Electro-Mechanical Systems (MEMS), and other topics related to spin current control and magneto-transport phenomena. The sub-section on Applications display papers that focus on applications of magnetic materials. The applications need to show a connection to magnetism. Review articles: Review articles organize, clarify, and summarize existing major works in the areas covered by the Journal and provide comprehensive citations to the full spectrum of relevant literature.
×
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:481959085
Book学术官方微信