Optimizing machine learning models for granular NdFeB magnets by very fast simulated annealing

Abstract The macroscopic properties of permanent magnets and the resultant performance required for real implementations are determined by the magnets’ microscopic features. However, earlier micromagnetic simulations and experimental studies required relatively a lot of work to gain any complete and...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Hyeon-Kyu Park, Jae-Hyeok Lee, Jehyun Lee, Sang-Koog Kim
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/aabaa86861e840049fcdb68fd9c3dac5
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:aabaa86861e840049fcdb68fd9c3dac5
record_format	dspace
spelling	oai:doaj.org-article:aabaa86861e840049fcdb68fd9c3dac52021-12-02T12:11:07ZOptimizing machine learning models for granular NdFeB magnets by very fast simulated annealing10.1038/s41598-021-83315-92045-2322https://doaj.org/article/aabaa86861e840049fcdb68fd9c3dac52021-02-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-83315-9https://doaj.org/toc/2045-2322Abstract The macroscopic properties of permanent magnets and the resultant performance required for real implementations are determined by the magnets’ microscopic features. However, earlier micromagnetic simulations and experimental studies required relatively a lot of work to gain any complete and comprehensive understanding of the relationships between magnets’ macroscopic properties and their microstructures. Here, by means of supervised learning, we predict reliable values of coercivity (μ 0 H c ) and maximum magnetic energy product (BH max) of granular NdFeB magnets according to their microstructural attributes (e.g. inter-grain decoupling, average grain size, and misalignment of easy axes) based on numerical datasets obtained from micromagnetic simulations. We conducted several tests of a variety of supervised machine learning (ML) models including kernel ridge regression (KRR), support vector regression (SVR), and artificial neural network (ANN) regression. The hyper-parameters of these models were optimized by a very fast simulated annealing (VFSA) algorithm with an adaptive cooling schedule. In our datasets of randomly generated 1,000 polycrystalline NdFeB cuboids with different microstructural attributes, all of the models yielded similar results in predicting both μ 0 H c and BH max. Furthermore, some outliers, which deteriorated the normality of residuals in the prediction of BH max, were detected and further analyzed. Based on all of our results, we can conclude that our ML approach combined with micromagnetic simulations provides a robust framework for optimal design of microstructures for high-performance NdFeB magnets.Hyeon-Kyu ParkJae-Hyeok LeeJehyun LeeSang-Koog KimNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-11 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Hyeon-Kyu Park Jae-Hyeok Lee Jehyun Lee Sang-Koog Kim Optimizing machine learning models for granular NdFeB magnets by very fast simulated annealing
description	Abstract The macroscopic properties of permanent magnets and the resultant performance required for real implementations are determined by the magnets’ microscopic features. However, earlier micromagnetic simulations and experimental studies required relatively a lot of work to gain any complete and comprehensive understanding of the relationships between magnets’ macroscopic properties and their microstructures. Here, by means of supervised learning, we predict reliable values of coercivity (μ 0 H c ) and maximum magnetic energy product (BH max) of granular NdFeB magnets according to their microstructural attributes (e.g. inter-grain decoupling, average grain size, and misalignment of easy axes) based on numerical datasets obtained from micromagnetic simulations. We conducted several tests of a variety of supervised machine learning (ML) models including kernel ridge regression (KRR), support vector regression (SVR), and artificial neural network (ANN) regression. The hyper-parameters of these models were optimized by a very fast simulated annealing (VFSA) algorithm with an adaptive cooling schedule. In our datasets of randomly generated 1,000 polycrystalline NdFeB cuboids with different microstructural attributes, all of the models yielded similar results in predicting both μ 0 H c and BH max. Furthermore, some outliers, which deteriorated the normality of residuals in the prediction of BH max, were detected and further analyzed. Based on all of our results, we can conclude that our ML approach combined with micromagnetic simulations provides a robust framework for optimal design of microstructures for high-performance NdFeB magnets.
format	article
author	Hyeon-Kyu Park Jae-Hyeok Lee Jehyun Lee Sang-Koog Kim
author_facet	Hyeon-Kyu Park Jae-Hyeok Lee Jehyun Lee Sang-Koog Kim
author_sort	Hyeon-Kyu Park
title	Optimizing machine learning models for granular NdFeB magnets by very fast simulated annealing
title_short	Optimizing machine learning models for granular NdFeB magnets by very fast simulated annealing
title_full	Optimizing machine learning models for granular NdFeB magnets by very fast simulated annealing
title_fullStr	Optimizing machine learning models for granular NdFeB magnets by very fast simulated annealing
title_full_unstemmed	Optimizing machine learning models for granular NdFeB magnets by very fast simulated annealing
title_sort	optimizing machine learning models for granular ndfeb magnets by very fast simulated annealing
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/aabaa86861e840049fcdb68fd9c3dac5
work_keys_str_mv	AT hyeonkyupark optimizingmachinelearningmodelsforgranularndfebmagnetsbyveryfastsimulatedannealing AT jaehyeoklee optimizingmachinelearningmodelsforgranularndfebmagnetsbyveryfastsimulatedannealing AT jehyunlee optimizingmachinelearningmodelsforgranularndfebmagnetsbyveryfastsimulatedannealing AT sangkoogkim optimizingmachinelearningmodelsforgranularndfebmagnetsbyveryfastsimulatedannealing
_version_	1718394648909578240

Optimizing machine learning models for granular NdFeB magnets by very fast simulated annealing

Ejemplares similares