Interpretable machine-learning strategy for soft-magnetic property and thermal stability in Fe-based metallic glasses

Abstract Fe-based metallic glasses (MGs) have been extensively investigated due to their unique properties, especially the outstanding soft-magnetic properties. However, conventional design of soft-magnetic Fe-based MGs is heavily relied on “trial and error” experiments, and thus difficult to balanc...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Zhichao Lu, Xin Chen, Xiongjun Liu, Deye Lin, Yuan Wu, Yibo Zhang, Hui Wang, Suihe Jiang, Hongxiang Li, Xianzhen Wang, Zhaoping Lu
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2020
Materias:	Materials of engineering and construction. Mechanics of materials TA401-492 Computer software QA76.75-76.765
Acceso en línea:	https://doaj.org/article/41ec3b121f114d65904cce3446f4e76f
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:41ec3b121f114d65904cce3446f4e76f
record_format	dspace
spelling	oai:doaj.org-article:41ec3b121f114d65904cce3446f4e76f2021-12-02T12:34:52ZInterpretable machine-learning strategy for soft-magnetic property and thermal stability in Fe-based metallic glasses10.1038/s41524-020-00460-x2057-3960https://doaj.org/article/41ec3b121f114d65904cce3446f4e76f2020-12-01T00:00:00Zhttps://doi.org/10.1038/s41524-020-00460-xhttps://doaj.org/toc/2057-3960Abstract Fe-based metallic glasses (MGs) have been extensively investigated due to their unique properties, especially the outstanding soft-magnetic properties. However, conventional design of soft-magnetic Fe-based MGs is heavily relied on “trial and error” experiments, and thus difficult to balance the saturation flux density (B s) and thermal stability due to the strong interplay between the glass formation and magnetic interaction. Herein, we report an eXtreme Gradient Boosting (XGBoost) machine-learning (ML) model for developing advanced Fe-based MGs with a decent combination of B s and thermal stability. While it is an attempt to apply ML for exploring soft-magnetic property and thermal stability, the developed XGBoost model based on the intrinsic elemental properties (i.e., atomic size and electronegativity) can well predict B s and T x (the onset crystallization temperature) with an accuracy of 93.0% and 94.3%, respectively. More importantly, we derived the key features that primarily dictate B s and T x of Fe-based MGs from the ML model, which enables the revelation of the physical origins underlying the high B s and thermal stability. As a proof of concept, several Fe-based MGs with high T x (>800 K) and high B s (>1.4 T) were successfully developed in terms of the ML model. This work demonstrates that the XGBoost ML approach is interpretable and feasible in the extraction of decisive parameters for properties of Fe-based magnetic MGs, which might allow us to efficiently design high-performance glassy materials.Zhichao LuXin ChenXiongjun LiuDeye LinYuan WuYibo ZhangHui WangSuihe JiangHongxiang LiXianzhen WangZhaoping LuNature PortfolioarticleMaterials of engineering and construction. Mechanics of materialsTA401-492Computer softwareQA76.75-76.765ENnpj Computational Materials, Vol 6, Iss 1, Pp 1-9 (2020)
institution	DOAJ
collection	DOAJ
language	EN
topic	Materials of engineering and construction. Mechanics of materials TA401-492 Computer software QA76.75-76.765
spellingShingle	Materials of engineering and construction. Mechanics of materials TA401-492 Computer software QA76.75-76.765 Zhichao Lu Xin Chen Xiongjun Liu Deye Lin Yuan Wu Yibo Zhang Hui Wang Suihe Jiang Hongxiang Li Xianzhen Wang Zhaoping Lu Interpretable machine-learning strategy for soft-magnetic property and thermal stability in Fe-based metallic glasses
description	Abstract Fe-based metallic glasses (MGs) have been extensively investigated due to their unique properties, especially the outstanding soft-magnetic properties. However, conventional design of soft-magnetic Fe-based MGs is heavily relied on “trial and error” experiments, and thus difficult to balance the saturation flux density (B s) and thermal stability due to the strong interplay between the glass formation and magnetic interaction. Herein, we report an eXtreme Gradient Boosting (XGBoost) machine-learning (ML) model for developing advanced Fe-based MGs with a decent combination of B s and thermal stability. While it is an attempt to apply ML for exploring soft-magnetic property and thermal stability, the developed XGBoost model based on the intrinsic elemental properties (i.e., atomic size and electronegativity) can well predict B s and T x (the onset crystallization temperature) with an accuracy of 93.0% and 94.3%, respectively. More importantly, we derived the key features that primarily dictate B s and T x of Fe-based MGs from the ML model, which enables the revelation of the physical origins underlying the high B s and thermal stability. As a proof of concept, several Fe-based MGs with high T x (>800 K) and high B s (>1.4 T) were successfully developed in terms of the ML model. This work demonstrates that the XGBoost ML approach is interpretable and feasible in the extraction of decisive parameters for properties of Fe-based magnetic MGs, which might allow us to efficiently design high-performance glassy materials.
format	article
author	Zhichao Lu Xin Chen Xiongjun Liu Deye Lin Yuan Wu Yibo Zhang Hui Wang Suihe Jiang Hongxiang Li Xianzhen Wang Zhaoping Lu
author_facet	Zhichao Lu Xin Chen Xiongjun Liu Deye Lin Yuan Wu Yibo Zhang Hui Wang Suihe Jiang Hongxiang Li Xianzhen Wang Zhaoping Lu
author_sort	Zhichao Lu
title	Interpretable machine-learning strategy for soft-magnetic property and thermal stability in Fe-based metallic glasses
title_short	Interpretable machine-learning strategy for soft-magnetic property and thermal stability in Fe-based metallic glasses
title_full	Interpretable machine-learning strategy for soft-magnetic property and thermal stability in Fe-based metallic glasses
title_fullStr	Interpretable machine-learning strategy for soft-magnetic property and thermal stability in Fe-based metallic glasses
title_full_unstemmed	Interpretable machine-learning strategy for soft-magnetic property and thermal stability in Fe-based metallic glasses
title_sort	interpretable machine-learning strategy for soft-magnetic property and thermal stability in fe-based metallic glasses
publisher	Nature Portfolio
publishDate	2020
url	https://doaj.org/article/41ec3b121f114d65904cce3446f4e76f
work_keys_str_mv	AT zhichaolu interpretablemachinelearningstrategyforsoftmagneticpropertyandthermalstabilityinfebasedmetallicglasses AT xinchen interpretablemachinelearningstrategyforsoftmagneticpropertyandthermalstabilityinfebasedmetallicglasses AT xiongjunliu interpretablemachinelearningstrategyforsoftmagneticpropertyandthermalstabilityinfebasedmetallicglasses AT deyelin interpretablemachinelearningstrategyforsoftmagneticpropertyandthermalstabilityinfebasedmetallicglasses AT yuanwu interpretablemachinelearningstrategyforsoftmagneticpropertyandthermalstabilityinfebasedmetallicglasses AT yibozhang interpretablemachinelearningstrategyforsoftmagneticpropertyandthermalstabilityinfebasedmetallicglasses AT huiwang interpretablemachinelearningstrategyforsoftmagneticpropertyandthermalstabilityinfebasedmetallicglasses AT suihejiang interpretablemachinelearningstrategyforsoftmagneticpropertyandthermalstabilityinfebasedmetallicglasses AT hongxiangli interpretablemachinelearningstrategyforsoftmagneticpropertyandthermalstabilityinfebasedmetallicglasses AT xianzhenwang interpretablemachinelearningstrategyforsoftmagneticpropertyandthermalstabilityinfebasedmetallicglasses AT zhaopinglu interpretablemachinelearningstrategyforsoftmagneticpropertyandthermalstabilityinfebasedmetallicglasses
_version_	1718393794739568640

Interpretable machine-learning strategy for soft-magnetic property and thermal stability in Fe-based metallic glasses

Ejemplares similares