Prediction and optimization of stretch flangeability of advanced high strength steels utilizing machine learning approaches

Abstract Advanced high strength steels (AHSS) exhibit diverse mechanical properties due to their complex chemical compositions and microstructures. Existing machine learning (ML) studies often focus on specific steel grades, limiting generalizability in predicting and optimizing AHSS properties. Her...

Full description

Saved in:
Bibliographic Details
Main Authors: Tianyang Li, Zheng Yang, Junyi Cui, Wenjie Chen, Rami Almatani, Yingjie Wu
Format: Article
Language:English
Published: Nature Portfolio 2025-05-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-00786-w
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849728412578480128
author Tianyang Li
Zheng Yang
Junyi Cui
Wenjie Chen
Rami Almatani
Yingjie Wu
author_facet Tianyang Li
Zheng Yang
Junyi Cui
Wenjie Chen
Rami Almatani
Yingjie Wu
author_sort Tianyang Li
collection DOAJ
description Abstract Advanced high strength steels (AHSS) exhibit diverse mechanical properties due to their complex chemical compositions and microstructures. Existing machine learning (ML) studies often focus on specific steel grades, limiting generalizability in predicting and optimizing AHSS properties. Here, an ML framework was presented to predict and optimize the stretch-flangeability of AHSS based on composition-microstructure-property correlations, using datasets from 212 steel conditions. Support vector machine, symbolic regression, and extreme gradient boosting models accurately predicted hole expansion ratio (HER), ultimate tensile strength (UTS), and total elongation (TE). Shapley additive explanations revealed the importance of bainite volume fraction (VB), carbon content (C), and chromium content (Cr) for HER, UTS, and TE, respectively. Multi-objective optimization generated 252 optimized conditions with improved comprehensive mechanical properties. The best optimized chemical compositions (0.12wt.% C-1.10Mn-0.15Si-0.47Cr) along with the carbon equivalent (CE) of 0.44 wt.%, and microstructural features (7.2% ferrite, 44.5% bainite, 40.5% martensite, and 7.8% tempered martensite) yielded HER of 119.8%, UTS of 1013.5 MPa, and TE of 22.7%. This systematic framework enables efficient prediction and optimization of material properties (especially HER), with potential applications across various fields of materials science.
format Article
id doaj-art-aba82968ff394389ba3003da1e97afcc
institution DOAJ
issn 2045-2322
language English
publishDate 2025-05-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-aba82968ff394389ba3003da1e97afcc2025-08-20T03:09:34ZengNature PortfolioScientific Reports2045-23222025-05-0115112110.1038/s41598-025-00786-wPrediction and optimization of stretch flangeability of advanced high strength steels utilizing machine learning approachesTianyang Li0Zheng Yang1Junyi Cui2Wenjie Chen3Rami Almatani4Yingjie Wu5Sichuan University - Pittsburgh Institute (SCUPI), Sichuan UniversitySichuan University - Pittsburgh Institute (SCUPI), Sichuan UniversityDepartment of Materials Science and Engineering, National University of SingaporeSichuan University - Pittsburgh Institute (SCUPI), Sichuan UniversityAdvanced Materials Technologies Institute, King Abdulaziz City for Science and TechnologySichuan University - Pittsburgh Institute (SCUPI), Sichuan UniversityAbstract Advanced high strength steels (AHSS) exhibit diverse mechanical properties due to their complex chemical compositions and microstructures. Existing machine learning (ML) studies often focus on specific steel grades, limiting generalizability in predicting and optimizing AHSS properties. Here, an ML framework was presented to predict and optimize the stretch-flangeability of AHSS based on composition-microstructure-property correlations, using datasets from 212 steel conditions. Support vector machine, symbolic regression, and extreme gradient boosting models accurately predicted hole expansion ratio (HER), ultimate tensile strength (UTS), and total elongation (TE). Shapley additive explanations revealed the importance of bainite volume fraction (VB), carbon content (C), and chromium content (Cr) for HER, UTS, and TE, respectively. Multi-objective optimization generated 252 optimized conditions with improved comprehensive mechanical properties. The best optimized chemical compositions (0.12wt.% C-1.10Mn-0.15Si-0.47Cr) along with the carbon equivalent (CE) of 0.44 wt.%, and microstructural features (7.2% ferrite, 44.5% bainite, 40.5% martensite, and 7.8% tempered martensite) yielded HER of 119.8%, UTS of 1013.5 MPa, and TE of 22.7%. This systematic framework enables efficient prediction and optimization of material properties (especially HER), with potential applications across various fields of materials science.https://doi.org/10.1038/s41598-025-00786-wStretch-flangeabilityAdvanced high strength steelsComposition-structure-property relationshipMachine learningMultiple objective optimization
spellingShingle Tianyang Li
Zheng Yang
Junyi Cui
Wenjie Chen
Rami Almatani
Yingjie Wu
Prediction and optimization of stretch flangeability of advanced high strength steels utilizing machine learning approaches
Scientific Reports
Stretch-flangeability
Advanced high strength steels
Composition-structure-property relationship
Machine learning
Multiple objective optimization
title Prediction and optimization of stretch flangeability of advanced high strength steels utilizing machine learning approaches
title_full Prediction and optimization of stretch flangeability of advanced high strength steels utilizing machine learning approaches
title_fullStr Prediction and optimization of stretch flangeability of advanced high strength steels utilizing machine learning approaches
title_full_unstemmed Prediction and optimization of stretch flangeability of advanced high strength steels utilizing machine learning approaches
title_short Prediction and optimization of stretch flangeability of advanced high strength steels utilizing machine learning approaches
title_sort prediction and optimization of stretch flangeability of advanced high strength steels utilizing machine learning approaches
topic Stretch-flangeability
Advanced high strength steels
Composition-structure-property relationship
Machine learning
Multiple objective optimization
url https://doi.org/10.1038/s41598-025-00786-w
work_keys_str_mv AT tianyangli predictionandoptimizationofstretchflangeabilityofadvancedhighstrengthsteelsutilizingmachinelearningapproaches
AT zhengyang predictionandoptimizationofstretchflangeabilityofadvancedhighstrengthsteelsutilizingmachinelearningapproaches
AT junyicui predictionandoptimizationofstretchflangeabilityofadvancedhighstrengthsteelsutilizingmachinelearningapproaches
AT wenjiechen predictionandoptimizationofstretchflangeabilityofadvancedhighstrengthsteelsutilizingmachinelearningapproaches
AT ramialmatani predictionandoptimizationofstretchflangeabilityofadvancedhighstrengthsteelsutilizingmachinelearningapproaches
AT yingjiewu predictionandoptimizationofstretchflangeabilityofadvancedhighstrengthsteelsutilizingmachinelearningapproaches