Novel machine learning driven design strategy for high strength Zn Alloys optimization with multiple constraints

Abstract Zinc (Zn) alloys offer advantages such as abundant resources and low cost. Nevertheless, their current mechanical properties limit application in more advanced fields. Due to the lack of clear compositional design methods, the development of high-performance Zn alloys is urgently needed. To...

Full description

Saved in:
Bibliographic Details
Main Authors: Chenfeng Pan, Wenwen Lin, Jianxing Zhou, Wei Jian, Ka Chun Chan, Yuk Lun Chan, Lu Ren
Format: Article
Language:English
Published: Nature Portfolio 2025-06-01
Series:npj Computational Materials
Online Access:https://doi.org/10.1038/s41524-025-01666-7
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849725068705267712
author Chenfeng Pan
Wenwen Lin
Jianxing Zhou
Wei Jian
Ka Chun Chan
Yuk Lun Chan
Lu Ren
author_facet Chenfeng Pan
Wenwen Lin
Jianxing Zhou
Wei Jian
Ka Chun Chan
Yuk Lun Chan
Lu Ren
author_sort Chenfeng Pan
collection DOAJ
description Abstract Zinc (Zn) alloys offer advantages such as abundant resources and low cost. Nevertheless, their current mechanical properties limit application in more advanced fields. Due to the lack of clear compositional design methods, the development of high-performance Zn alloys is urgently needed. To this end, this work proposes a fast and effective design strategy for Zn alloys based on machine learning (ML). The prediction models for the ultimate tensile strength, elongation, and hardness were successfully developed, with accuracies exceeding 90%. Interpretability analysis of the models was performed using the SHAP method with particle swarm optimization (PSO). Furthermore, a ML-based Zn alloy composition design system (ZACDS) was proposed by integrating the Bayesian optimization algorithm. A novel high-strength Zn alloy was successfully designed using ZACDS, demonstrating good agreement between predicted and experimental mechanical properties. This approach offers a new strategy for Zn alloy design under different compositional constraints and performance requirements.
format Article
id doaj-art-987fd38ab2ee4cab9cae68c7a682ec69
institution DOAJ
issn 2057-3960
language English
publishDate 2025-06-01
publisher Nature Portfolio
record_format Article
series npj Computational Materials
spelling doaj-art-987fd38ab2ee4cab9cae68c7a682ec692025-08-20T03:10:34ZengNature Portfolionpj Computational Materials2057-39602025-06-0111111110.1038/s41524-025-01666-7Novel machine learning driven design strategy for high strength Zn Alloys optimization with multiple constraintsChenfeng Pan0Wenwen Lin1Jianxing Zhou2Wei Jian3Ka Chun Chan4Yuk Lun Chan5Lu Ren6Faculty of Mechanical Engineering and Mechanics, Ningbo UniversityFaculty of Mechanical Engineering and Mechanics, Ningbo UniversityFaculty of Mechanical Engineering and Mechanics, Ningbo UniversityFaculty of Mechanical Engineering and Mechanics, Ningbo UniversityGenesis Alloys (Ningbo) LtdGenesis Alloys (Ningbo) LtdFaculty of Mechanical Engineering and Mechanics, Ningbo UniversityAbstract Zinc (Zn) alloys offer advantages such as abundant resources and low cost. Nevertheless, their current mechanical properties limit application in more advanced fields. Due to the lack of clear compositional design methods, the development of high-performance Zn alloys is urgently needed. To this end, this work proposes a fast and effective design strategy for Zn alloys based on machine learning (ML). The prediction models for the ultimate tensile strength, elongation, and hardness were successfully developed, with accuracies exceeding 90%. Interpretability analysis of the models was performed using the SHAP method with particle swarm optimization (PSO). Furthermore, a ML-based Zn alloy composition design system (ZACDS) was proposed by integrating the Bayesian optimization algorithm. A novel high-strength Zn alloy was successfully designed using ZACDS, demonstrating good agreement between predicted and experimental mechanical properties. This approach offers a new strategy for Zn alloy design under different compositional constraints and performance requirements.https://doi.org/10.1038/s41524-025-01666-7
spellingShingle Chenfeng Pan
Wenwen Lin
Jianxing Zhou
Wei Jian
Ka Chun Chan
Yuk Lun Chan
Lu Ren
Novel machine learning driven design strategy for high strength Zn Alloys optimization with multiple constraints
npj Computational Materials
title Novel machine learning driven design strategy for high strength Zn Alloys optimization with multiple constraints
title_full Novel machine learning driven design strategy for high strength Zn Alloys optimization with multiple constraints
title_fullStr Novel machine learning driven design strategy for high strength Zn Alloys optimization with multiple constraints
title_full_unstemmed Novel machine learning driven design strategy for high strength Zn Alloys optimization with multiple constraints
title_short Novel machine learning driven design strategy for high strength Zn Alloys optimization with multiple constraints
title_sort novel machine learning driven design strategy for high strength zn alloys optimization with multiple constraints
url https://doi.org/10.1038/s41524-025-01666-7
work_keys_str_mv AT chenfengpan novelmachinelearningdrivendesignstrategyforhighstrengthznalloysoptimizationwithmultipleconstraints
AT wenwenlin novelmachinelearningdrivendesignstrategyforhighstrengthznalloysoptimizationwithmultipleconstraints
AT jianxingzhou novelmachinelearningdrivendesignstrategyforhighstrengthznalloysoptimizationwithmultipleconstraints
AT weijian novelmachinelearningdrivendesignstrategyforhighstrengthznalloysoptimizationwithmultipleconstraints
AT kachunchan novelmachinelearningdrivendesignstrategyforhighstrengthznalloysoptimizationwithmultipleconstraints
AT yuklunchan novelmachinelearningdrivendesignstrategyforhighstrengthznalloysoptimizationwithmultipleconstraints
AT luren novelmachinelearningdrivendesignstrategyforhighstrengthznalloysoptimizationwithmultipleconstraints