Exploration of ductility for refractory high entropy alloys via interpretive machine learning

Refractory high-entropy alloys (RHEAs) having excellent thermo-mechanical properties always suffer from room temperature brittleness, due to the inherent brittleness of refractory metal elements. RHEAs with compressive ductility ≥30 % hold particular commercial value. While ductility can be engineer...

Full description

Saved in:
Bibliographic Details
Main Authors: Shaolong Zheng, Lingwei Yang, Liyang Fang, Chenran Xu, Guanglong Xu, Yifang Ouyang, Xiaoma Tao
Format: Article
Language:English
Published: Elsevier 2025-07-01
Series:Journal of Materials Research and Technology
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2238785425015078
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850218333840867328
author Shaolong Zheng
Lingwei Yang
Liyang Fang
Chenran Xu
Guanglong Xu
Yifang Ouyang
Xiaoma Tao
author_facet Shaolong Zheng
Lingwei Yang
Liyang Fang
Chenran Xu
Guanglong Xu
Yifang Ouyang
Xiaoma Tao
author_sort Shaolong Zheng
collection DOAJ
description Refractory high-entropy alloys (RHEAs) having excellent thermo-mechanical properties always suffer from room temperature brittleness, due to the inherent brittleness of refractory metal elements. RHEAs with compressive ductility ≥30 % hold particular commercial value. While ductility can be engineered through alloying composition and processing condition optimization, this remains challenging due to the virtually infinite and vast unexplored compositional space. Data-driven machine learning (ML) can significantly reduce experimental costs and time by establishing robust correlations between RHEA compositions and ductility. This study constructs an ML model for accurate ductility prediction from sparse compositional data, accelerating the design of ductile RHEAs within infinite compositional space. Two ML algorithms, decision tree (DT) and CatBoost, are trained using physical parameters, with CatBoost demonstrating superior performance in RHEA ductility classification. Integration of the shapley additive explanations (SHAP) model with sample data reveals key relationships between physical parameters and RHEA ductility, providing theoretical insights for developing high-ductility RHEAs. The analysis identifies δχ, Tm, VEC, and ΔHmix as critical factors in RHEA ductility prediction, with a quasi-linear relationship observed between ΔHmix and ductility. Through the prediction and subsequent preparation of TiZrNbTax (x=0.3, 0.5, 0.7, 1) alloys, the experimental results confirmed the reliability of the proposed model and key parameters. This approach establishes a novel methodology for exploring and developing RHEAs with excellent ductility.
format Article
id doaj-art-ea768e342a164914979a1d50812bebae
institution OA Journals
issn 2238-7854
language English
publishDate 2025-07-01
publisher Elsevier
record_format Article
series Journal of Materials Research and Technology
spelling doaj-art-ea768e342a164914979a1d50812bebae2025-08-20T02:07:46ZengElsevierJournal of Materials Research and Technology2238-78542025-07-01371243125610.1016/j.jmrt.2025.06.085Exploration of ductility for refractory high entropy alloys via interpretive machine learningShaolong Zheng0Lingwei Yang1Liyang Fang2Chenran Xu3Guanglong Xu4Yifang Ouyang5Xiaoma Tao6School of Physical Science and Technology, Guangxi Key Laboratory for Relativistic Astrophysics, State Key Laboratory of Featured Metal Materials and Life-cycle Safety for Composite Structures, Guangxi University, Nanning, 530004, ChinaHypervelocity Aerodynamics Institute, China Aerodynamics Research and Development Center, Mianyang, 621000, China; National Key Laboratory of Aerospace Physics in Fluids, China Aerodynamics Research and Development Center, Mianyang, 621000, China; Corresponding author. Hypervelocity Aerodynamics Institute, China Aerodynamics Research and Development Center, Mianyang, 621000, China.School of Physical Science and Technology, Guangxi Key Laboratory for Relativistic Astrophysics, State Key Laboratory of Featured Metal Materials and Life-cycle Safety for Composite Structures, Guangxi University, Nanning, 530004, ChinaSchool of Physical Science and Technology, Guangxi Key Laboratory for Relativistic Astrophysics, State Key Laboratory of Featured Metal Materials and Life-cycle Safety for Composite Structures, Guangxi University, Nanning, 530004, ChinaTech Institute of Advanced Materials & College of Materials Science and Engineering, Nanjing Tech University, Nanjing, 211816, ChinaSchool of Physical Science and Technology, Guangxi Key Laboratory for Relativistic Astrophysics, State Key Laboratory of Featured Metal Materials and Life-cycle Safety for Composite Structures, Guangxi University, Nanning, 530004, ChinaSchool of Physical Science and Technology, Guangxi Key Laboratory for Relativistic Astrophysics, State Key Laboratory of Featured Metal Materials and Life-cycle Safety for Composite Structures, Guangxi University, Nanning, 530004, China; Corresponding author.Refractory high-entropy alloys (RHEAs) having excellent thermo-mechanical properties always suffer from room temperature brittleness, due to the inherent brittleness of refractory metal elements. RHEAs with compressive ductility ≥30 % hold particular commercial value. While ductility can be engineered through alloying composition and processing condition optimization, this remains challenging due to the virtually infinite and vast unexplored compositional space. Data-driven machine learning (ML) can significantly reduce experimental costs and time by establishing robust correlations between RHEA compositions and ductility. This study constructs an ML model for accurate ductility prediction from sparse compositional data, accelerating the design of ductile RHEAs within infinite compositional space. Two ML algorithms, decision tree (DT) and CatBoost, are trained using physical parameters, with CatBoost demonstrating superior performance in RHEA ductility classification. Integration of the shapley additive explanations (SHAP) model with sample data reveals key relationships between physical parameters and RHEA ductility, providing theoretical insights for developing high-ductility RHEAs. The analysis identifies δχ, Tm, VEC, and ΔHmix as critical factors in RHEA ductility prediction, with a quasi-linear relationship observed between ΔHmix and ductility. Through the prediction and subsequent preparation of TiZrNbTax (x=0.3, 0.5, 0.7, 1) alloys, the experimental results confirmed the reliability of the proposed model and key parameters. This approach establishes a novel methodology for exploring and developing RHEAs with excellent ductility.http://www.sciencedirect.com/science/article/pii/S2238785425015078Refractory high entropy alloysDuctilityMachine learningClassification
spellingShingle Shaolong Zheng
Lingwei Yang
Liyang Fang
Chenran Xu
Guanglong Xu
Yifang Ouyang
Xiaoma Tao
Exploration of ductility for refractory high entropy alloys via interpretive machine learning
Journal of Materials Research and Technology
Refractory high entropy alloys
Ductility
Machine learning
Classification
title Exploration of ductility for refractory high entropy alloys via interpretive machine learning
title_full Exploration of ductility for refractory high entropy alloys via interpretive machine learning
title_fullStr Exploration of ductility for refractory high entropy alloys via interpretive machine learning
title_full_unstemmed Exploration of ductility for refractory high entropy alloys via interpretive machine learning
title_short Exploration of ductility for refractory high entropy alloys via interpretive machine learning
title_sort exploration of ductility for refractory high entropy alloys via interpretive machine learning
topic Refractory high entropy alloys
Ductility
Machine learning
Classification
url http://www.sciencedirect.com/science/article/pii/S2238785425015078
work_keys_str_mv AT shaolongzheng explorationofductilityforrefractoryhighentropyalloysviainterpretivemachinelearning
AT lingweiyang explorationofductilityforrefractoryhighentropyalloysviainterpretivemachinelearning
AT liyangfang explorationofductilityforrefractoryhighentropyalloysviainterpretivemachinelearning
AT chenranxu explorationofductilityforrefractoryhighentropyalloysviainterpretivemachinelearning
AT guanglongxu explorationofductilityforrefractoryhighentropyalloysviainterpretivemachinelearning
AT yifangouyang explorationofductilityforrefractoryhighentropyalloysviainterpretivemachinelearning
AT xiaomatao explorationofductilityforrefractoryhighentropyalloysviainterpretivemachinelearning