A machine-learning-based alloy design platform that enables both forward and inverse predictions for thermo-mechanically controlled processed (TMCP) steel alloys

Abstract Predicting mechanical properties such as yield strength (YS) and ultimate tensile strength (UTS) is an intricate undertaking in practice, notwithstanding a plethora of well-established theoretical and empirical models. A data-driven approach should be a fundamental exercise when making YS/U...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Jin-Woong Lee, Chaewon Park, Byung Do Lee, Joonseo Park, Nam Hoon Goo, Kee-Sun Sohn
Formato: article
Lenguaje:EN
Publicado: Nature Portfolio 2021
Materias:
R
Q
Acceso en línea:https://doaj.org/article/4f8b5e5a22314369822c383ea96bedd5
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:4f8b5e5a22314369822c383ea96bedd5
record_format dspace
spelling oai:doaj.org-article:4f8b5e5a22314369822c383ea96bedd52021-12-02T16:53:00ZA machine-learning-based alloy design platform that enables both forward and inverse predictions for thermo-mechanically controlled processed (TMCP) steel alloys10.1038/s41598-021-90237-z2045-2322https://doaj.org/article/4f8b5e5a22314369822c383ea96bedd52021-05-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-90237-zhttps://doaj.org/toc/2045-2322Abstract Predicting mechanical properties such as yield strength (YS) and ultimate tensile strength (UTS) is an intricate undertaking in practice, notwithstanding a plethora of well-established theoretical and empirical models. A data-driven approach should be a fundamental exercise when making YS/UTS predictions. For this study, we collected 16 descriptors (attributes) that implicate the compositional and processing information and the corresponding YS/UTS values for 5473 thermo-mechanically controlled processed (TMCP) steel alloys. We set up an integrated machine-learning (ML) platform consisting of 16 ML algorithms to predict the YS/UTS based on the descriptors. The integrated ML platform involved regularization-based linear regression algorithms, ensemble ML algorithms, and some non-linear ML algorithms. Despite the dirty nature of most real-world industry data, we obtained acceptable holdout dataset test results such as R2 > 0.6 and MSE < 0.01 for seven non-linear ML algorithms. The seven fully trained non-linear ML models were used for the ensuing ‘inverse design (prediction)’ based on an elitist-reinforced, non-dominated sorting genetic algorithm (NSGA-II). The NSGA-II enabled us to predict solutions that exhibit desirable YS/UTS values for each ML algorithm. In addition, the NSGA-II-driven solutions in the 16-dimensional input feature space were visualized using holographic research strategy (HRS) in order to systematically compare and analyze the inverse-predicted solutions for each ML algorithm.Jin-Woong LeeChaewon ParkByung Do LeeJoonseo ParkNam Hoon GooKee-Sun SohnNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-18 (2021)
institution DOAJ
collection DOAJ
language EN
topic Medicine
R
Science
Q
spellingShingle Medicine
R
Science
Q
Jin-Woong Lee
Chaewon Park
Byung Do Lee
Joonseo Park
Nam Hoon Goo
Kee-Sun Sohn
A machine-learning-based alloy design platform that enables both forward and inverse predictions for thermo-mechanically controlled processed (TMCP) steel alloys
description Abstract Predicting mechanical properties such as yield strength (YS) and ultimate tensile strength (UTS) is an intricate undertaking in practice, notwithstanding a plethora of well-established theoretical and empirical models. A data-driven approach should be a fundamental exercise when making YS/UTS predictions. For this study, we collected 16 descriptors (attributes) that implicate the compositional and processing information and the corresponding YS/UTS values for 5473 thermo-mechanically controlled processed (TMCP) steel alloys. We set up an integrated machine-learning (ML) platform consisting of 16 ML algorithms to predict the YS/UTS based on the descriptors. The integrated ML platform involved regularization-based linear regression algorithms, ensemble ML algorithms, and some non-linear ML algorithms. Despite the dirty nature of most real-world industry data, we obtained acceptable holdout dataset test results such as R2 > 0.6 and MSE < 0.01 for seven non-linear ML algorithms. The seven fully trained non-linear ML models were used for the ensuing ‘inverse design (prediction)’ based on an elitist-reinforced, non-dominated sorting genetic algorithm (NSGA-II). The NSGA-II enabled us to predict solutions that exhibit desirable YS/UTS values for each ML algorithm. In addition, the NSGA-II-driven solutions in the 16-dimensional input feature space were visualized using holographic research strategy (HRS) in order to systematically compare and analyze the inverse-predicted solutions for each ML algorithm.
format article
author Jin-Woong Lee
Chaewon Park
Byung Do Lee
Joonseo Park
Nam Hoon Goo
Kee-Sun Sohn
author_facet Jin-Woong Lee
Chaewon Park
Byung Do Lee
Joonseo Park
Nam Hoon Goo
Kee-Sun Sohn
author_sort Jin-Woong Lee
title A machine-learning-based alloy design platform that enables both forward and inverse predictions for thermo-mechanically controlled processed (TMCP) steel alloys
title_short A machine-learning-based alloy design platform that enables both forward and inverse predictions for thermo-mechanically controlled processed (TMCP) steel alloys
title_full A machine-learning-based alloy design platform that enables both forward and inverse predictions for thermo-mechanically controlled processed (TMCP) steel alloys
title_fullStr A machine-learning-based alloy design platform that enables both forward and inverse predictions for thermo-mechanically controlled processed (TMCP) steel alloys
title_full_unstemmed A machine-learning-based alloy design platform that enables both forward and inverse predictions for thermo-mechanically controlled processed (TMCP) steel alloys
title_sort machine-learning-based alloy design platform that enables both forward and inverse predictions for thermo-mechanically controlled processed (tmcp) steel alloys
publisher Nature Portfolio
publishDate 2021
url https://doaj.org/article/4f8b5e5a22314369822c383ea96bedd5
work_keys_str_mv AT jinwoonglee amachinelearningbasedalloydesignplatformthatenablesbothforwardandinversepredictionsforthermomechanicallycontrolledprocessedtmcpsteelalloys
AT chaewonpark amachinelearningbasedalloydesignplatformthatenablesbothforwardandinversepredictionsforthermomechanicallycontrolledprocessedtmcpsteelalloys
AT byungdolee amachinelearningbasedalloydesignplatformthatenablesbothforwardandinversepredictionsforthermomechanicallycontrolledprocessedtmcpsteelalloys
AT joonseopark amachinelearningbasedalloydesignplatformthatenablesbothforwardandinversepredictionsforthermomechanicallycontrolledprocessedtmcpsteelalloys
AT namhoongoo amachinelearningbasedalloydesignplatformthatenablesbothforwardandinversepredictionsforthermomechanicallycontrolledprocessedtmcpsteelalloys
AT keesunsohn amachinelearningbasedalloydesignplatformthatenablesbothforwardandinversepredictionsforthermomechanicallycontrolledprocessedtmcpsteelalloys
AT jinwoonglee machinelearningbasedalloydesignplatformthatenablesbothforwardandinversepredictionsforthermomechanicallycontrolledprocessedtmcpsteelalloys
AT chaewonpark machinelearningbasedalloydesignplatformthatenablesbothforwardandinversepredictionsforthermomechanicallycontrolledprocessedtmcpsteelalloys
AT byungdolee machinelearningbasedalloydesignplatformthatenablesbothforwardandinversepredictionsforthermomechanicallycontrolledprocessedtmcpsteelalloys
AT joonseopark machinelearningbasedalloydesignplatformthatenablesbothforwardandinversepredictionsforthermomechanicallycontrolledprocessedtmcpsteelalloys
AT namhoongoo machinelearningbasedalloydesignplatformthatenablesbothforwardandinversepredictionsforthermomechanicallycontrolledprocessedtmcpsteelalloys
AT keesunsohn machinelearningbasedalloydesignplatformthatenablesbothforwardandinversepredictionsforthermomechanicallycontrolledprocessedtmcpsteelalloys
_version_ 1718382856127905792