Machine learning-based Curie temperature prediction for magnetic 14:2:1 phases
The TM14RE2B-based phases (TM = transition metal, RE = rare earth metal; hereafter called 14:2:1) enable permanent magnets with outstanding magnetic properties. Novel chemical compositions that represent new 14:2:1 phases necessitate that they do not demagnetize at application-specific operating tem...
Main Authors: | , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
AIP Publishing LLC
2023-03-01
|
Series: | AIP Advances |
Online Access: | http://dx.doi.org/10.1063/5.0116650 |
_version_ | 1797771940083007488 |
---|---|
author | Amit Kumar Choudhary Anoop Kini Dominic Hohs Andreas Jansche Timo Bernthaler Orsolya Csiszár Dagmar Goll Gerhard Schneider |
author_facet | Amit Kumar Choudhary Anoop Kini Dominic Hohs Andreas Jansche Timo Bernthaler Orsolya Csiszár Dagmar Goll Gerhard Schneider |
author_sort | Amit Kumar Choudhary |
collection | DOAJ |
description | The TM14RE2B-based phases (TM = transition metal, RE = rare earth metal; hereafter called 14:2:1) enable permanent magnets with outstanding magnetic properties. Novel chemical compositions that represent new 14:2:1 phases necessitate that they do not demagnetize at application-specific operating temperatures. Therefore, an accurate knowledge of the Curie temperature (Tc) is important. For magnetic 14:2:1 phases, we present a machine learning model that predicts Tc by using merely chemical compositional features. Hyperparameter tuning on bagging and boosting models, as well as averaging predictions from individual models using the voting regressor, enables a low mean-absolute-error of 16 K on an unseen test set. The training set and a test set have been constructed by randomly splitting, in an 80:20 ratio, of a database that contains 449 phases (270 compositionally unique) mapped with their Tc, taken from distinct publications. The model correctly identifies the relative importance of key substitutional elements that influence Tc, especially in an Fe base such as Co, Mn, and Al. This paper is expected to serve as a basis for accurate Curie temperature predictions in the sought-after 14:2:1 permanent magnet family, particularly for transition metal substitution of within 20% in an Fe or Co base. |
first_indexed | 2024-03-12T21:43:52Z |
format | Article |
id | doaj.art-f71376f015db4e899a57be5834753a3d |
institution | Directory Open Access Journal |
issn | 2158-3226 |
language | English |
last_indexed | 2024-03-12T21:43:52Z |
publishDate | 2023-03-01 |
publisher | AIP Publishing LLC |
record_format | Article |
series | AIP Advances |
spelling | doaj.art-f71376f015db4e899a57be5834753a3d2023-07-26T14:03:58ZengAIP Publishing LLCAIP Advances2158-32262023-03-01133035112035112-810.1063/5.0116650Machine learning-based Curie temperature prediction for magnetic 14:2:1 phasesAmit Kumar Choudhary0Anoop Kini1Dominic Hohs2Andreas Jansche3Timo Bernthaler4Orsolya Csiszár5Dagmar Goll6Gerhard Schneider7Materials Research Institute, Aalen University, Beethovenstraße 1, 73430 Aalen, GermanyMaterials Research Institute, Aalen University, Beethovenstraße 1, 73430 Aalen, GermanyMaterials Research Institute, Aalen University, Beethovenstraße 1, 73430 Aalen, GermanyMaterials Research Institute, Aalen University, Beethovenstraße 1, 73430 Aalen, GermanyMaterials Research Institute, Aalen University, Beethovenstraße 1, 73430 Aalen, GermanyMaterials Research Institute, Aalen University, Beethovenstraße 1, 73430 Aalen, GermanyMaterials Research Institute, Aalen University, Beethovenstraße 1, 73430 Aalen, GermanyMaterials Research Institute, Aalen University, Beethovenstraße 1, 73430 Aalen, GermanyThe TM14RE2B-based phases (TM = transition metal, RE = rare earth metal; hereafter called 14:2:1) enable permanent magnets with outstanding magnetic properties. Novel chemical compositions that represent new 14:2:1 phases necessitate that they do not demagnetize at application-specific operating temperatures. Therefore, an accurate knowledge of the Curie temperature (Tc) is important. For magnetic 14:2:1 phases, we present a machine learning model that predicts Tc by using merely chemical compositional features. Hyperparameter tuning on bagging and boosting models, as well as averaging predictions from individual models using the voting regressor, enables a low mean-absolute-error of 16 K on an unseen test set. The training set and a test set have been constructed by randomly splitting, in an 80:20 ratio, of a database that contains 449 phases (270 compositionally unique) mapped with their Tc, taken from distinct publications. The model correctly identifies the relative importance of key substitutional elements that influence Tc, especially in an Fe base such as Co, Mn, and Al. This paper is expected to serve as a basis for accurate Curie temperature predictions in the sought-after 14:2:1 permanent magnet family, particularly for transition metal substitution of within 20% in an Fe or Co base.http://dx.doi.org/10.1063/5.0116650 |
spellingShingle | Amit Kumar Choudhary Anoop Kini Dominic Hohs Andreas Jansche Timo Bernthaler Orsolya Csiszár Dagmar Goll Gerhard Schneider Machine learning-based Curie temperature prediction for magnetic 14:2:1 phases AIP Advances |
title | Machine learning-based Curie temperature prediction for magnetic 14:2:1 phases |
title_full | Machine learning-based Curie temperature prediction for magnetic 14:2:1 phases |
title_fullStr | Machine learning-based Curie temperature prediction for magnetic 14:2:1 phases |
title_full_unstemmed | Machine learning-based Curie temperature prediction for magnetic 14:2:1 phases |
title_short | Machine learning-based Curie temperature prediction for magnetic 14:2:1 phases |
title_sort | machine learning based curie temperature prediction for magnetic 14 2 1 phases |
url | http://dx.doi.org/10.1063/5.0116650 |
work_keys_str_mv | AT amitkumarchoudhary machinelearningbasedcurietemperaturepredictionformagnetic1421phases AT anoopkini machinelearningbasedcurietemperaturepredictionformagnetic1421phases AT dominichohs machinelearningbasedcurietemperaturepredictionformagnetic1421phases AT andreasjansche machinelearningbasedcurietemperaturepredictionformagnetic1421phases AT timobernthaler machinelearningbasedcurietemperaturepredictionformagnetic1421phases AT orsolyacsiszar machinelearningbasedcurietemperaturepredictionformagnetic1421phases AT dagmargoll machinelearningbasedcurietemperaturepredictionformagnetic1421phases AT gerhardschneider machinelearningbasedcurietemperaturepredictionformagnetic1421phases |