Prediction of martensite start temperature of steel combined with expert experience and machine learning

The martensite start temperature (MS) plays a pivotal role in formulating heat treatment regimes for steel. This paper, through the compilation of experimental data from literature and the incorporation of expert knowledge to construct features, employs machine learning algorithms to predict the MS...

Full description

Saved in:
Bibliographic Details
Main Authors: Chengcheng Liu, Hang Su
Format: Article
Language:English
Published: Taylor & Francis Group 2024-12-01
Series:Science and Technology of Advanced Materials
Subjects:
Online Access:https://www.tandfonline.com/doi/10.1080/14686996.2024.2354655
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846111263614042112
author Chengcheng Liu
Hang Su
author_facet Chengcheng Liu
Hang Su
author_sort Chengcheng Liu
collection DOAJ
description The martensite start temperature (MS) plays a pivotal role in formulating heat treatment regimes for steel. This paper, through the compilation of experimental data from literature and the incorporation of expert knowledge to construct features, employs machine learning algorithms to predict the MS of steel. The study highlights that the ETR algorithm attains optimal prediction accuracy, and the inclusion of atomic features enhances the model’s performance. Feature selection is accomplished by evaluating linear and nonlinear relationships between data using the Pearson correlation coefficient (PCC), variance inflation factor (VIF), and maximum information coefficient (MIC). Subsequently, the performance of machine learning models on unknown data is compared to validate the model’s generalization ability. The introduction of SHAP values for model interpretability analysis unveils the influencing mechanisms between features and the target variable. Finally, utilizing a specific steel type as an illustration, the paper underscores the practical value of the model.
format Article
id doaj-art-78ffdf1994d240408dbff53e69cdcd05
institution Kabale University
issn 1468-6996
1878-5514
language English
publishDate 2024-12-01
publisher Taylor & Francis Group
record_format Article
series Science and Technology of Advanced Materials
spelling doaj-art-78ffdf1994d240408dbff53e69cdcd052024-12-23T08:54:39ZengTaylor & Francis GroupScience and Technology of Advanced Materials1468-69961878-55142024-12-0125110.1080/14686996.2024.2354655Prediction of martensite start temperature of steel combined with expert experience and machine learningChengcheng Liu0Hang Su1Institute of Structural Steel, Central Iron and Steel Research Institute, Beijing, ChinaMaterial Digital R&D Center, China Iron and Steel Research Institute Group, Beijing, ChinaThe martensite start temperature (MS) plays a pivotal role in formulating heat treatment regimes for steel. This paper, through the compilation of experimental data from literature and the incorporation of expert knowledge to construct features, employs machine learning algorithms to predict the MS of steel. The study highlights that the ETR algorithm attains optimal prediction accuracy, and the inclusion of atomic features enhances the model’s performance. Feature selection is accomplished by evaluating linear and nonlinear relationships between data using the Pearson correlation coefficient (PCC), variance inflation factor (VIF), and maximum information coefficient (MIC). Subsequently, the performance of machine learning models on unknown data is compared to validate the model’s generalization ability. The introduction of SHAP values for model interpretability analysis unveils the influencing mechanisms between features and the target variable. Finally, utilizing a specific steel type as an illustration, the paper underscores the practical value of the model.https://www.tandfonline.com/doi/10.1080/14686996.2024.2354655Martensite start temperatureexpert experiencemachine learningsteel
spellingShingle Chengcheng Liu
Hang Su
Prediction of martensite start temperature of steel combined with expert experience and machine learning
Science and Technology of Advanced Materials
Martensite start temperature
expert experience
machine learning
steel
title Prediction of martensite start temperature of steel combined with expert experience and machine learning
title_full Prediction of martensite start temperature of steel combined with expert experience and machine learning
title_fullStr Prediction of martensite start temperature of steel combined with expert experience and machine learning
title_full_unstemmed Prediction of martensite start temperature of steel combined with expert experience and machine learning
title_short Prediction of martensite start temperature of steel combined with expert experience and machine learning
title_sort prediction of martensite start temperature of steel combined with expert experience and machine learning
topic Martensite start temperature
expert experience
machine learning
steel
url https://www.tandfonline.com/doi/10.1080/14686996.2024.2354655
work_keys_str_mv AT chengchengliu predictionofmartensitestarttemperatureofsteelcombinedwithexpertexperienceandmachinelearning
AT hangsu predictionofmartensitestarttemperatureofsteelcombinedwithexpertexperienceandmachinelearning