Machine learning assisted prediction of the Young’s modulus of compositionally complex alloys

Abstract We identify compositionally complex alloys (CCAs) that offer exceptional mechanical properties for elevated temperature applications by employing machine learning (ML) in conjunction with rapid synthesis and testing of alloys for validation to accelerate alloy design. The advantages of this...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Hrishabh Khakurel, M. F. N. Taufique, Ankit Roy, Ganesh Balasubramanian, Gaoyuan Ouyang, Jun Cui, Duane D. Johnson, Ram Devanathan
Formato: article
Lenguaje:EN
Publicado: Nature Portfolio 2021
Materias:
R
Q
Acceso en línea:https://doaj.org/article/d6e2398d05ad4fa1a7a1bef2dc4dd12f
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:d6e2398d05ad4fa1a7a1bef2dc4dd12f
record_format dspace
spelling oai:doaj.org-article:d6e2398d05ad4fa1a7a1bef2dc4dd12f2021-12-02T16:35:06ZMachine learning assisted prediction of the Young’s modulus of compositionally complex alloys10.1038/s41598-021-96507-02045-2322https://doaj.org/article/d6e2398d05ad4fa1a7a1bef2dc4dd12f2021-08-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-96507-0https://doaj.org/toc/2045-2322Abstract We identify compositionally complex alloys (CCAs) that offer exceptional mechanical properties for elevated temperature applications by employing machine learning (ML) in conjunction with rapid synthesis and testing of alloys for validation to accelerate alloy design. The advantages of this approach are scalability, rapidity, and reasonably accurate predictions. ML tools were implemented to predict Young’s modulus of refractory-based CCAs by employing different ML models. Our results, in conjunction with experimental validation, suggest that average valence electron concentration, the difference in atomic radius, a geometrical parameter λ and melting temperature of the alloys are the key features that determine the Young’s modulus of CCAs and refractory-based CCAs. The Gradient Boosting model provided the best predictive capabilities (mean absolute error of 6.15 GPa) among the models studied. Our approach integrates high-quality validation data from experiments, literature data for training machine-learning models, and feature selection based on physical insights. It opens a new avenue to optimize the desired materials property for different engineering applications.Hrishabh KhakurelM. F. N. TaufiqueAnkit RoyGanesh BalasubramanianGaoyuan OuyangJun CuiDuane D. JohnsonRam DevanathanNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-10 (2021)
institution DOAJ
collection DOAJ
language EN
topic Medicine
R
Science
Q
spellingShingle Medicine
R
Science
Q
Hrishabh Khakurel
M. F. N. Taufique
Ankit Roy
Ganesh Balasubramanian
Gaoyuan Ouyang
Jun Cui
Duane D. Johnson
Ram Devanathan
Machine learning assisted prediction of the Young’s modulus of compositionally complex alloys
description Abstract We identify compositionally complex alloys (CCAs) that offer exceptional mechanical properties for elevated temperature applications by employing machine learning (ML) in conjunction with rapid synthesis and testing of alloys for validation to accelerate alloy design. The advantages of this approach are scalability, rapidity, and reasonably accurate predictions. ML tools were implemented to predict Young’s modulus of refractory-based CCAs by employing different ML models. Our results, in conjunction with experimental validation, suggest that average valence electron concentration, the difference in atomic radius, a geometrical parameter λ and melting temperature of the alloys are the key features that determine the Young’s modulus of CCAs and refractory-based CCAs. The Gradient Boosting model provided the best predictive capabilities (mean absolute error of 6.15 GPa) among the models studied. Our approach integrates high-quality validation data from experiments, literature data for training machine-learning models, and feature selection based on physical insights. It opens a new avenue to optimize the desired materials property for different engineering applications.
format article
author Hrishabh Khakurel
M. F. N. Taufique
Ankit Roy
Ganesh Balasubramanian
Gaoyuan Ouyang
Jun Cui
Duane D. Johnson
Ram Devanathan
author_facet Hrishabh Khakurel
M. F. N. Taufique
Ankit Roy
Ganesh Balasubramanian
Gaoyuan Ouyang
Jun Cui
Duane D. Johnson
Ram Devanathan
author_sort Hrishabh Khakurel
title Machine learning assisted prediction of the Young’s modulus of compositionally complex alloys
title_short Machine learning assisted prediction of the Young’s modulus of compositionally complex alloys
title_full Machine learning assisted prediction of the Young’s modulus of compositionally complex alloys
title_fullStr Machine learning assisted prediction of the Young’s modulus of compositionally complex alloys
title_full_unstemmed Machine learning assisted prediction of the Young’s modulus of compositionally complex alloys
title_sort machine learning assisted prediction of the young’s modulus of compositionally complex alloys
publisher Nature Portfolio
publishDate 2021
url https://doaj.org/article/d6e2398d05ad4fa1a7a1bef2dc4dd12f
work_keys_str_mv AT hrishabhkhakurel machinelearningassistedpredictionoftheyoungsmodulusofcompositionallycomplexalloys
AT mfntaufique machinelearningassistedpredictionoftheyoungsmodulusofcompositionallycomplexalloys
AT ankitroy machinelearningassistedpredictionoftheyoungsmodulusofcompositionallycomplexalloys
AT ganeshbalasubramanian machinelearningassistedpredictionoftheyoungsmodulusofcompositionallycomplexalloys
AT gaoyuanouyang machinelearningassistedpredictionoftheyoungsmodulusofcompositionallycomplexalloys
AT juncui machinelearningassistedpredictionoftheyoungsmodulusofcompositionallycomplexalloys
AT duanedjohnson machinelearningassistedpredictionoftheyoungsmodulusofcompositionallycomplexalloys
AT ramdevanathan machinelearningassistedpredictionoftheyoungsmodulusofcompositionallycomplexalloys
_version_ 1718383782046728192