Intelligent prediction and oriented design of high-hardness high-entropy ceramics

High-entropy ceramics are considered vital candidate materials for applications in rail transportation and advanced manufacturing due to their exceptional hardness and wear resistance. However, the intricate relationship between their composition and mechanical properties presents challenges for on-...

Full description

Saved in:
Bibliographic Details
Main Authors: Anzhe Wang, Jicheng Liu, Linwei Guo, Kejie Qu, Haishen Xie, Yawei Li, Bin Du
Format: Article
Language:English
Published: Elsevier 2025-05-01
Series:Journal of Materials Research and Technology
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2238785425009846
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850176108428787712
author Anzhe Wang
Jicheng Liu
Linwei Guo
Kejie Qu
Haishen Xie
Yawei Li
Bin Du
author_facet Anzhe Wang
Jicheng Liu
Linwei Guo
Kejie Qu
Haishen Xie
Yawei Li
Bin Du
author_sort Anzhe Wang
collection DOAJ
description High-entropy ceramics are considered vital candidate materials for applications in rail transportation and advanced manufacturing due to their exceptional hardness and wear resistance. However, the intricate relationship between their composition and mechanical properties presents challenges for on-demand material design. This work utilizes machine learning and heuristic optimization algorithms to achieve accurate predictions of bulk high-entropy ceramics hardness (with validation set errors <10 %) and the oriented design of high-entropy ceramics with a hardness of 25 GPa (with an average error of 2.6 %). This achievement is attributed to three key innovations: the construction of the feature space based on the Pearson correlation coefficient and genetic algorithm, along with algorithm selection and optimization through hyperparameter tuning; the novel combination of reduced-dimensionality component compositions with atomic/precursor descriptors, achieving a model R2 value of up to 0.898; the optimization of constituent elements using genetic algorithm and principal component analysis, providing direct guidance for the design of high-hardness high-entropy ceramics. Through these methodologies, new high-entropy ceramics compositions, typically represented by (Ti0·25Zr0·25Nb0.25Hf0.25)C, were successfully designed, achieving hardness of up to 23.9–25.2 GPa. This oriented design methodology holds promise for accelerating the on-demand design of high-entropy ceramics.
format Article
id doaj-art-41d965cd6c054681804cec54005cab44
institution OA Journals
issn 2238-7854
language English
publishDate 2025-05-01
publisher Elsevier
record_format Article
series Journal of Materials Research and Technology
spelling doaj-art-41d965cd6c054681804cec54005cab442025-08-20T02:19:19ZengElsevierJournal of Materials Research and Technology2238-78542025-05-01366015602310.1016/j.jmrt.2025.04.163Intelligent prediction and oriented design of high-hardness high-entropy ceramicsAnzhe Wang0Jicheng Liu1Linwei Guo2Kejie Qu3Haishen Xie4Yawei Li5Bin Du6School of Materials Science and Engineering, Nanjing Institute of Technology, Nanjing, 211167, China; Jiangsu Key Laboratory of Advanced Structural Materials and Application Technology, Nanjing Institute of Technology, Nanjing, 211167, China; Corresponding author. School of Materials Science and Engineering, Nanjing Institute of Technology, Nanjing, 211167, China.School of Materials Science and Engineering, Nanjing Institute of Technology, Nanjing, 211167, ChinaSchool of Physics and Materials Science, Guangzhou University, Guangzhou, 510006, ChinaSchool of Materials Science and Engineering, Nanjing Institute of Technology, Nanjing, 211167, ChinaJointech Tooling &amp; Moulding Technology Co., Ltd., Suzhou, 215131, ChinaState Key Laboratory of Advanced Refractories, Wuhan University of Science and Technology, Wuhan, 430081, China; Corresponding author.School of Physics and Materials Science, Guangzhou University, Guangzhou, 510006, China; Corresponding author.High-entropy ceramics are considered vital candidate materials for applications in rail transportation and advanced manufacturing due to their exceptional hardness and wear resistance. However, the intricate relationship between their composition and mechanical properties presents challenges for on-demand material design. This work utilizes machine learning and heuristic optimization algorithms to achieve accurate predictions of bulk high-entropy ceramics hardness (with validation set errors <10 %) and the oriented design of high-entropy ceramics with a hardness of 25 GPa (with an average error of 2.6 %). This achievement is attributed to three key innovations: the construction of the feature space based on the Pearson correlation coefficient and genetic algorithm, along with algorithm selection and optimization through hyperparameter tuning; the novel combination of reduced-dimensionality component compositions with atomic/precursor descriptors, achieving a model R2 value of up to 0.898; the optimization of constituent elements using genetic algorithm and principal component analysis, providing direct guidance for the design of high-hardness high-entropy ceramics. Through these methodologies, new high-entropy ceramics compositions, typically represented by (Ti0·25Zr0·25Nb0.25Hf0.25)C, were successfully designed, achieving hardness of up to 23.9–25.2 GPa. This oriented design methodology holds promise for accelerating the on-demand design of high-entropy ceramics.http://www.sciencedirect.com/science/article/pii/S2238785425009846Machine learningHigh-entropy ceramicsHardnessMechanical properties predictionOriented design
spellingShingle Anzhe Wang
Jicheng Liu
Linwei Guo
Kejie Qu
Haishen Xie
Yawei Li
Bin Du
Intelligent prediction and oriented design of high-hardness high-entropy ceramics
Journal of Materials Research and Technology
Machine learning
High-entropy ceramics
Hardness
Mechanical properties prediction
Oriented design
title Intelligent prediction and oriented design of high-hardness high-entropy ceramics
title_full Intelligent prediction and oriented design of high-hardness high-entropy ceramics
title_fullStr Intelligent prediction and oriented design of high-hardness high-entropy ceramics
title_full_unstemmed Intelligent prediction and oriented design of high-hardness high-entropy ceramics
title_short Intelligent prediction and oriented design of high-hardness high-entropy ceramics
title_sort intelligent prediction and oriented design of high hardness high entropy ceramics
topic Machine learning
High-entropy ceramics
Hardness
Mechanical properties prediction
Oriented design
url http://www.sciencedirect.com/science/article/pii/S2238785425009846
work_keys_str_mv AT anzhewang intelligentpredictionandorienteddesignofhighhardnesshighentropyceramics
AT jichengliu intelligentpredictionandorienteddesignofhighhardnesshighentropyceramics
AT linweiguo intelligentpredictionandorienteddesignofhighhardnesshighentropyceramics
AT kejiequ intelligentpredictionandorienteddesignofhighhardnesshighentropyceramics
AT haishenxie intelligentpredictionandorienteddesignofhighhardnesshighentropyceramics
AT yaweili intelligentpredictionandorienteddesignofhighhardnesshighentropyceramics
AT bindu intelligentpredictionandorienteddesignofhighhardnesshighentropyceramics