Physics-informed machine learning combining experiment and simulation for the design of neodymium-iron-boron permanent magnets with reduced critical-elements content
Rare-earth elements like neodymium, terbium and dysprosium are crucial to the performance of permanent magnets used in various green-energy technologies like hybrid or electric cars. To address the supply risk of those elements, we applied machine-learning techniques to design magnetic materials wit...
| Main Authors: | , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-01-01
|
| Series: | Frontiers in Materials |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fmats.2022.1094055/full |
| _version_ | 1797950690011643904 |
|---|---|
| author | Alexander Kovacs Alexander Kovacs Johann Fischbacher Johann Fischbacher Harald Oezelt Harald Oezelt Alexander Kornell Alexander Kornell Qais Ali Qais Ali Markus Gusenbauer Markus Gusenbauer Masao Yano Noritsugu Sakuma Akihito Kinoshita Tetsuya Shoji Akira Kato Yuan Hong Stéphane Grenier Thibaut Devillers Nora M. Dempsey Tetsuya Fukushima Hisazumi Akai Naoki Kawashima Takashi Miyake Thomas Schrefl Thomas Schrefl |
| author_facet | Alexander Kovacs Alexander Kovacs Johann Fischbacher Johann Fischbacher Harald Oezelt Harald Oezelt Alexander Kornell Alexander Kornell Qais Ali Qais Ali Markus Gusenbauer Markus Gusenbauer Masao Yano Noritsugu Sakuma Akihito Kinoshita Tetsuya Shoji Akira Kato Yuan Hong Stéphane Grenier Thibaut Devillers Nora M. Dempsey Tetsuya Fukushima Hisazumi Akai Naoki Kawashima Takashi Miyake Thomas Schrefl Thomas Schrefl |
| author_sort | Alexander Kovacs |
| collection | DOAJ |
| description | Rare-earth elements like neodymium, terbium and dysprosium are crucial to the performance of permanent magnets used in various green-energy technologies like hybrid or electric cars. To address the supply risk of those elements, we applied machine-learning techniques to design magnetic materials with reduced neodymium content and without terbium and dysprosium. However, the performance of the magnet intended to be used in electric motors should be preserved. We developed machine-learning methods that assist materials design by integrating physical models to bridge the gap between length scales, from atomistic to the micrometer-sized granular microstructure of neodymium-iron-boron permanent magnets. Through data assimilation, we combined data from experiments and simulations to build machine-learning models which we used to optimize the chemical composition and the microstructure of the magnet. We applied techniques that help to understand and interpret the results of machine learning predictions. The variables importance shows how the main design variables influence the magnetic properties. High-throughput measurements on compositionally graded sputtered films are a systematic way to generate data for machine data analysis. Using the machine learning models we show how high-performance, Nd-lean magnets can be realized. |
| first_indexed | 2024-04-10T22:19:06Z |
| format | Article |
| id | doaj.art-ba3de6b1961f495380a13d05ea592dea |
| institution | Directory Open Access Journal |
| issn | 2296-8016 |
| language | English |
| last_indexed | 2024-04-10T22:19:06Z |
| publishDate | 2023-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Materials |
| spelling | doaj.art-ba3de6b1961f495380a13d05ea592dea2023-01-18T05:20:12ZengFrontiers Media S.A.Frontiers in Materials2296-80162023-01-01910.3389/fmats.2022.10940551094055Physics-informed machine learning combining experiment and simulation for the design of neodymium-iron-boron permanent magnets with reduced critical-elements contentAlexander Kovacs0Alexander Kovacs1Johann Fischbacher2Johann Fischbacher3Harald Oezelt4Harald Oezelt5Alexander Kornell6Alexander Kornell7Qais Ali8Qais Ali9Markus Gusenbauer10Markus Gusenbauer11Masao Yano12Noritsugu Sakuma13Akihito Kinoshita14Tetsuya Shoji15Akira Kato16Yuan Hong17Stéphane Grenier18Thibaut Devillers19Nora M. Dempsey20Tetsuya Fukushima21Hisazumi Akai22Naoki Kawashima23Takashi Miyake24Thomas Schrefl25Thomas Schrefl26Christian Doppler Laboratory for magnet design through physics informed machine learning, Danube University Krems, Wiener Neustadt, AustriaDepartment for Integrated Sensor Systems, Danube University Krems, Wiener Neustadt, AustriaChristian Doppler Laboratory for magnet design through physics informed machine learning, Danube University Krems, Wiener Neustadt, AustriaDepartment for Integrated Sensor Systems, Danube University Krems, Wiener Neustadt, AustriaChristian Doppler Laboratory for magnet design through physics informed machine learning, Danube University Krems, Wiener Neustadt, AustriaDepartment for Integrated Sensor Systems, Danube University Krems, Wiener Neustadt, AustriaChristian Doppler Laboratory for magnet design through physics informed machine learning, Danube University Krems, Wiener Neustadt, AustriaDepartment for Integrated Sensor Systems, Danube University Krems, Wiener Neustadt, AustriaChristian Doppler Laboratory for magnet design through physics informed machine learning, Danube University Krems, Wiener Neustadt, AustriaDepartment for Integrated Sensor Systems, Danube University Krems, Wiener Neustadt, AustriaChristian Doppler Laboratory for magnet design through physics informed machine learning, Danube University Krems, Wiener Neustadt, AustriaDepartment for Integrated Sensor Systems, Danube University Krems, Wiener Neustadt, AustriaAdvanced Materials Engineering Division, Toyota Motor Corporation, Susono, JapanAdvanced Materials Engineering Division, Toyota Motor Corporation, Susono, JapanAdvanced Materials Engineering Division, Toyota Motor Corporation, Susono, JapanAdvanced Materials Engineering Division, Toyota Motor Corporation, Susono, JapanAdvanced Materials Engineering Division, Toyota Motor Corporation, Susono, JapanUniversité Grenoble Alpes, CNRS, Grenoble INP, Institut Néel, Grenoble, FranceUniversité Grenoble Alpes, CNRS, Grenoble INP, Institut Néel, Grenoble, FranceUniversité Grenoble Alpes, CNRS, Grenoble INP, Institut Néel, Grenoble, FranceUniversité Grenoble Alpes, CNRS, Grenoble INP, Institut Néel, Grenoble, FranceThe Institute for Solid State Physics, The University of Tokyo, Kashiwa, JapanThe Institute for Solid State Physics, The University of Tokyo, Kashiwa, JapanThe Institute for Solid State Physics, The University of Tokyo, Kashiwa, JapanNational Institute of Advanced Industrial Science and Technology, Tsukuba, JapanChristian Doppler Laboratory for magnet design through physics informed machine learning, Danube University Krems, Wiener Neustadt, AustriaDepartment for Integrated Sensor Systems, Danube University Krems, Wiener Neustadt, AustriaRare-earth elements like neodymium, terbium and dysprosium are crucial to the performance of permanent magnets used in various green-energy technologies like hybrid or electric cars. To address the supply risk of those elements, we applied machine-learning techniques to design magnetic materials with reduced neodymium content and without terbium and dysprosium. However, the performance of the magnet intended to be used in electric motors should be preserved. We developed machine-learning methods that assist materials design by integrating physical models to bridge the gap between length scales, from atomistic to the micrometer-sized granular microstructure of neodymium-iron-boron permanent magnets. Through data assimilation, we combined data from experiments and simulations to build machine-learning models which we used to optimize the chemical composition and the microstructure of the magnet. We applied techniques that help to understand and interpret the results of machine learning predictions. The variables importance shows how the main design variables influence the magnetic properties. High-throughput measurements on compositionally graded sputtered films are a systematic way to generate data for machine data analysis. Using the machine learning models we show how high-performance, Nd-lean magnets can be realized.https://www.frontiersin.org/articles/10.3389/fmats.2022.1094055/fullmachine learning–MLmaterials designNdFeB permanent magnetcombinatorial sputteringrare-earth element (REE)optimization |
| spellingShingle | Alexander Kovacs Alexander Kovacs Johann Fischbacher Johann Fischbacher Harald Oezelt Harald Oezelt Alexander Kornell Alexander Kornell Qais Ali Qais Ali Markus Gusenbauer Markus Gusenbauer Masao Yano Noritsugu Sakuma Akihito Kinoshita Tetsuya Shoji Akira Kato Yuan Hong Stéphane Grenier Thibaut Devillers Nora M. Dempsey Tetsuya Fukushima Hisazumi Akai Naoki Kawashima Takashi Miyake Thomas Schrefl Thomas Schrefl Physics-informed machine learning combining experiment and simulation for the design of neodymium-iron-boron permanent magnets with reduced critical-elements content Frontiers in Materials machine learning–ML materials design NdFeB permanent magnet combinatorial sputtering rare-earth element (REE) optimization |
| title | Physics-informed machine learning combining experiment and simulation for the design of neodymium-iron-boron permanent magnets with reduced critical-elements content |
| title_full | Physics-informed machine learning combining experiment and simulation for the design of neodymium-iron-boron permanent magnets with reduced critical-elements content |
| title_fullStr | Physics-informed machine learning combining experiment and simulation for the design of neodymium-iron-boron permanent magnets with reduced critical-elements content |
| title_full_unstemmed | Physics-informed machine learning combining experiment and simulation for the design of neodymium-iron-boron permanent magnets with reduced critical-elements content |
| title_short | Physics-informed machine learning combining experiment and simulation for the design of neodymium-iron-boron permanent magnets with reduced critical-elements content |
| title_sort | physics informed machine learning combining experiment and simulation for the design of neodymium iron boron permanent magnets with reduced critical elements content |
| topic | machine learning–ML materials design NdFeB permanent magnet combinatorial sputtering rare-earth element (REE) optimization |
| url | https://www.frontiersin.org/articles/10.3389/fmats.2022.1094055/full |
| work_keys_str_mv | AT alexanderkovacs physicsinformedmachinelearningcombiningexperimentandsimulationforthedesignofneodymiumironboronpermanentmagnetswithreducedcriticalelementscontent AT alexanderkovacs physicsinformedmachinelearningcombiningexperimentandsimulationforthedesignofneodymiumironboronpermanentmagnetswithreducedcriticalelementscontent AT johannfischbacher physicsinformedmachinelearningcombiningexperimentandsimulationforthedesignofneodymiumironboronpermanentmagnetswithreducedcriticalelementscontent AT johannfischbacher physicsinformedmachinelearningcombiningexperimentandsimulationforthedesignofneodymiumironboronpermanentmagnetswithreducedcriticalelementscontent AT haraldoezelt physicsinformedmachinelearningcombiningexperimentandsimulationforthedesignofneodymiumironboronpermanentmagnetswithreducedcriticalelementscontent AT haraldoezelt physicsinformedmachinelearningcombiningexperimentandsimulationforthedesignofneodymiumironboronpermanentmagnetswithreducedcriticalelementscontent AT alexanderkornell physicsinformedmachinelearningcombiningexperimentandsimulationforthedesignofneodymiumironboronpermanentmagnetswithreducedcriticalelementscontent AT alexanderkornell physicsinformedmachinelearningcombiningexperimentandsimulationforthedesignofneodymiumironboronpermanentmagnetswithreducedcriticalelementscontent AT qaisali physicsinformedmachinelearningcombiningexperimentandsimulationforthedesignofneodymiumironboronpermanentmagnetswithreducedcriticalelementscontent AT qaisali physicsinformedmachinelearningcombiningexperimentandsimulationforthedesignofneodymiumironboronpermanentmagnetswithreducedcriticalelementscontent AT markusgusenbauer physicsinformedmachinelearningcombiningexperimentandsimulationforthedesignofneodymiumironboronpermanentmagnetswithreducedcriticalelementscontent AT markusgusenbauer physicsinformedmachinelearningcombiningexperimentandsimulationforthedesignofneodymiumironboronpermanentmagnetswithreducedcriticalelementscontent AT masaoyano physicsinformedmachinelearningcombiningexperimentandsimulationforthedesignofneodymiumironboronpermanentmagnetswithreducedcriticalelementscontent AT noritsugusakuma physicsinformedmachinelearningcombiningexperimentandsimulationforthedesignofneodymiumironboronpermanentmagnetswithreducedcriticalelementscontent AT akihitokinoshita physicsinformedmachinelearningcombiningexperimentandsimulationforthedesignofneodymiumironboronpermanentmagnetswithreducedcriticalelementscontent AT tetsuyashoji physicsinformedmachinelearningcombiningexperimentandsimulationforthedesignofneodymiumironboronpermanentmagnetswithreducedcriticalelementscontent AT akirakato physicsinformedmachinelearningcombiningexperimentandsimulationforthedesignofneodymiumironboronpermanentmagnetswithreducedcriticalelementscontent AT yuanhong physicsinformedmachinelearningcombiningexperimentandsimulationforthedesignofneodymiumironboronpermanentmagnetswithreducedcriticalelementscontent AT stephanegrenier physicsinformedmachinelearningcombiningexperimentandsimulationforthedesignofneodymiumironboronpermanentmagnetswithreducedcriticalelementscontent AT thibautdevillers physicsinformedmachinelearningcombiningexperimentandsimulationforthedesignofneodymiumironboronpermanentmagnetswithreducedcriticalelementscontent AT noramdempsey physicsinformedmachinelearningcombiningexperimentandsimulationforthedesignofneodymiumironboronpermanentmagnetswithreducedcriticalelementscontent AT tetsuyafukushima physicsinformedmachinelearningcombiningexperimentandsimulationforthedesignofneodymiumironboronpermanentmagnetswithreducedcriticalelementscontent AT hisazumiakai physicsinformedmachinelearningcombiningexperimentandsimulationforthedesignofneodymiumironboronpermanentmagnetswithreducedcriticalelementscontent AT naokikawashima physicsinformedmachinelearningcombiningexperimentandsimulationforthedesignofneodymiumironboronpermanentmagnetswithreducedcriticalelementscontent AT takashimiyake physicsinformedmachinelearningcombiningexperimentandsimulationforthedesignofneodymiumironboronpermanentmagnetswithreducedcriticalelementscontent AT thomasschrefl physicsinformedmachinelearningcombiningexperimentandsimulationforthedesignofneodymiumironboronpermanentmagnetswithreducedcriticalelementscontent AT thomasschrefl physicsinformedmachinelearningcombiningexperimentandsimulationforthedesignofneodymiumironboronpermanentmagnetswithreducedcriticalelementscontent |