Optimizing casting process using a combination of small data machine learning and phase-field simulations

Abstract It has been a challenge to employ machine learning (ML) to optimize casting processes due to the scarcity of data and difficulty in feature expansion. Here, we introduce a nearest neighbor search method to optimize the stratified random sampling in Latin hypercube sampling (LHS) and propose...

Full description

Saved in:
Bibliographic Details
Main Authors: Xiaolong Pei, Jiaqi Pei, Hua Hou, Yuhong Zhao
Format: Article
Language:English
Published: Nature Portfolio 2025-02-01
Series:npj Computational Materials
Online Access:https://doi.org/10.1038/s41524-025-01524-6
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850067198331060224
author Xiaolong Pei
Jiaqi Pei
Hua Hou
Yuhong Zhao
author_facet Xiaolong Pei
Jiaqi Pei
Hua Hou
Yuhong Zhao
author_sort Xiaolong Pei
collection DOAJ
description Abstract It has been a challenge to employ machine learning (ML) to optimize casting processes due to the scarcity of data and difficulty in feature expansion. Here, we introduce a nearest neighbor search method to optimize the stratified random sampling in Latin hypercube sampling (LHS) and propose a new revised LHS coupled with Bayesian optimization (RLHS-BO). Using this method, we optimized the squeeze-casting process for mine fuel tank partition castings for the first time with an ultra-small dataset of 25 samples. Compared to traditional methods such as random sampling, interval sampling, orthogonal design (OD), and central composite design (CCD), our approach covers the process parameter space more, reduces the data volume by approximately 50%, and achieves process optimization beyond five factors-five levels with fewer data. Through RLHS and 6 iterations of experiments, the optimal process was identified, and the ultimate tensile strength (UTS) of partition casting under the optimal process reached 239.7 MPa, with an elongation (EL) of 12.2%, showing increases of 17.6% and 18.4% over the optimal values in the initial dataset. Finally, a combination of Shapley additive interpretation (SHAP) and phase-field method (PFM) of solidification dendrite growth was used to address the issue of weak physical interpretability in ML models.
format Article
id doaj-art-9dc2917c3f4c453cafc9f5bf9db39964
institution DOAJ
issn 2057-3960
language English
publishDate 2025-02-01
publisher Nature Portfolio
record_format Article
series npj Computational Materials
spelling doaj-art-9dc2917c3f4c453cafc9f5bf9db399642025-08-20T02:48:27ZengNature Portfolionpj Computational Materials2057-39602025-02-0111111210.1038/s41524-025-01524-6Optimizing casting process using a combination of small data machine learning and phase-field simulationsXiaolong Pei0Jiaqi Pei1Hua Hou2Yuhong Zhao3School of Materials Science and Engineering, Collaborative Innovation Center of Ministry of Education and Shanxi Province for High-performance Al/Mg Alloy Materials, North University of ChinaSchool of Materials Science and Engineering, Collaborative Innovation Center of Ministry of Education and Shanxi Province for High-performance Al/Mg Alloy Materials, North University of ChinaSchool of Materials Science and Engineering, Collaborative Innovation Center of Ministry of Education and Shanxi Province for High-performance Al/Mg Alloy Materials, North University of ChinaSchool of Materials Science and Engineering, Collaborative Innovation Center of Ministry of Education and Shanxi Province for High-performance Al/Mg Alloy Materials, North University of ChinaAbstract It has been a challenge to employ machine learning (ML) to optimize casting processes due to the scarcity of data and difficulty in feature expansion. Here, we introduce a nearest neighbor search method to optimize the stratified random sampling in Latin hypercube sampling (LHS) and propose a new revised LHS coupled with Bayesian optimization (RLHS-BO). Using this method, we optimized the squeeze-casting process for mine fuel tank partition castings for the first time with an ultra-small dataset of 25 samples. Compared to traditional methods such as random sampling, interval sampling, orthogonal design (OD), and central composite design (CCD), our approach covers the process parameter space more, reduces the data volume by approximately 50%, and achieves process optimization beyond five factors-five levels with fewer data. Through RLHS and 6 iterations of experiments, the optimal process was identified, and the ultimate tensile strength (UTS) of partition casting under the optimal process reached 239.7 MPa, with an elongation (EL) of 12.2%, showing increases of 17.6% and 18.4% over the optimal values in the initial dataset. Finally, a combination of Shapley additive interpretation (SHAP) and phase-field method (PFM) of solidification dendrite growth was used to address the issue of weak physical interpretability in ML models.https://doi.org/10.1038/s41524-025-01524-6
spellingShingle Xiaolong Pei
Jiaqi Pei
Hua Hou
Yuhong Zhao
Optimizing casting process using a combination of small data machine learning and phase-field simulations
npj Computational Materials
title Optimizing casting process using a combination of small data machine learning and phase-field simulations
title_full Optimizing casting process using a combination of small data machine learning and phase-field simulations
title_fullStr Optimizing casting process using a combination of small data machine learning and phase-field simulations
title_full_unstemmed Optimizing casting process using a combination of small data machine learning and phase-field simulations
title_short Optimizing casting process using a combination of small data machine learning and phase-field simulations
title_sort optimizing casting process using a combination of small data machine learning and phase field simulations
url https://doi.org/10.1038/s41524-025-01524-6
work_keys_str_mv AT xiaolongpei optimizingcastingprocessusingacombinationofsmalldatamachinelearningandphasefieldsimulations
AT jiaqipei optimizingcastingprocessusingacombinationofsmalldatamachinelearningandphasefieldsimulations
AT huahou optimizingcastingprocessusingacombinationofsmalldatamachinelearningandphasefieldsimulations
AT yuhongzhao optimizingcastingprocessusingacombinationofsmalldatamachinelearningandphasefieldsimulations