Predicting the Tensile Properties of Automotive Steels at Intermediate Strain Rates via Interpretable Ensemble Machine Learning
Evaluating the dynamic impact properties of automotive steels is critical for structural design and material selection, but physical testing methods result in high costs and long lead times. In this study, a dataset was constructed by collecting data from high-speed tensile experiments on 65 automot...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-02-01
|
| Series: | World Electric Vehicle Journal |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2032-6653/16/3/123 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850087665458741248 |
|---|---|
| author | Houchao Wang Fengyao Lv Zhenfei Zhan Hailong Zhao Jie Li Kangte Yang |
| author_facet | Houchao Wang Fengyao Lv Zhenfei Zhan Hailong Zhao Jie Li Kangte Yang |
| author_sort | Houchao Wang |
| collection | DOAJ |
| description | Evaluating the dynamic impact properties of automotive steels is critical for structural design and material selection, but physical testing methods result in high costs and long lead times. In this study, a dataset was constructed by collecting data from high-speed tensile experiments on 65 automotive steels. Five machine learning models, including ridge regression, support vector machine regression, gradient boosted regression tree, random forest, and adaptive boosting regression, were developed to predict the yield strength (YS), ultimate tensile strength (UTS), and fracture elongation (FE) of automotive steels at 100/s using the composition, sample size, and quasi-static mechanical properties of automotive steels as input variables. To further improve the prediction accuracy, stacked ensemble ideas were used to integrate these single models. The results show that the ensemble model has higher prediction accuracy and generalization performance for mechanical properties at 100/s compared to a single model. When predicting the YS, UTS, and FE at 100/s, their 10-fold cross-validated average <i>R</i><sup>2</sup> are 0.913, 0.92, and 0.8, respectively. Most importantly, the Shapley additive explanation (SHAP)-based method reveals major features that significantly affect tensile properties at intermediate strain rates. The proposed methodology facilitates reductions in physical test requirements and costs. |
| format | Article |
| id | doaj-art-bdd9b9197d57443aa8665f7ff811dcfa |
| institution | DOAJ |
| issn | 2032-6653 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | World Electric Vehicle Journal |
| spelling | doaj-art-bdd9b9197d57443aa8665f7ff811dcfa2025-08-20T02:43:10ZengMDPI AGWorld Electric Vehicle Journal2032-66532025-02-0116312310.3390/wevj16030123Predicting the Tensile Properties of Automotive Steels at Intermediate Strain Rates via Interpretable Ensemble Machine LearningHouchao Wang0Fengyao Lv1Zhenfei Zhan2Hailong Zhao3Jie Li4Kangte Yang5State Key Laboratory of Intelligent Vehicle Safety Technology, Chongqing 401120, ChinaState Key Laboratory of Intelligent Vehicle Safety Technology, Chongqing 401120, ChinaState Key Laboratory of Intelligent Vehicle Safety Technology, Chongqing 401120, ChinaSchool of Mechatronics and Vehicle Engineering, Chongqing Jiaotong University, Chongqing 400074, ChinaState Key Laboratory of Intelligent Vehicle Safety Technology, Chongqing 401120, ChinaState Key Laboratory of Intelligent Vehicle Safety Technology, Chongqing 401120, ChinaEvaluating the dynamic impact properties of automotive steels is critical for structural design and material selection, but physical testing methods result in high costs and long lead times. In this study, a dataset was constructed by collecting data from high-speed tensile experiments on 65 automotive steels. Five machine learning models, including ridge regression, support vector machine regression, gradient boosted regression tree, random forest, and adaptive boosting regression, were developed to predict the yield strength (YS), ultimate tensile strength (UTS), and fracture elongation (FE) of automotive steels at 100/s using the composition, sample size, and quasi-static mechanical properties of automotive steels as input variables. To further improve the prediction accuracy, stacked ensemble ideas were used to integrate these single models. The results show that the ensemble model has higher prediction accuracy and generalization performance for mechanical properties at 100/s compared to a single model. When predicting the YS, UTS, and FE at 100/s, their 10-fold cross-validated average <i>R</i><sup>2</sup> are 0.913, 0.92, and 0.8, respectively. Most importantly, the Shapley additive explanation (SHAP)-based method reveals major features that significantly affect tensile properties at intermediate strain rates. The proposed methodology facilitates reductions in physical test requirements and costs.https://www.mdpi.com/2032-6653/16/3/123automotive steelmachine learningmechanical propertyensemble model |
| spellingShingle | Houchao Wang Fengyao Lv Zhenfei Zhan Hailong Zhao Jie Li Kangte Yang Predicting the Tensile Properties of Automotive Steels at Intermediate Strain Rates via Interpretable Ensemble Machine Learning World Electric Vehicle Journal automotive steel machine learning mechanical property ensemble model |
| title | Predicting the Tensile Properties of Automotive Steels at Intermediate Strain Rates via Interpretable Ensemble Machine Learning |
| title_full | Predicting the Tensile Properties of Automotive Steels at Intermediate Strain Rates via Interpretable Ensemble Machine Learning |
| title_fullStr | Predicting the Tensile Properties of Automotive Steels at Intermediate Strain Rates via Interpretable Ensemble Machine Learning |
| title_full_unstemmed | Predicting the Tensile Properties of Automotive Steels at Intermediate Strain Rates via Interpretable Ensemble Machine Learning |
| title_short | Predicting the Tensile Properties of Automotive Steels at Intermediate Strain Rates via Interpretable Ensemble Machine Learning |
| title_sort | predicting the tensile properties of automotive steels at intermediate strain rates via interpretable ensemble machine learning |
| topic | automotive steel machine learning mechanical property ensemble model |
| url | https://www.mdpi.com/2032-6653/16/3/123 |
| work_keys_str_mv | AT houchaowang predictingthetensilepropertiesofautomotivesteelsatintermediatestrainratesviainterpretableensemblemachinelearning AT fengyaolv predictingthetensilepropertiesofautomotivesteelsatintermediatestrainratesviainterpretableensemblemachinelearning AT zhenfeizhan predictingthetensilepropertiesofautomotivesteelsatintermediatestrainratesviainterpretableensemblemachinelearning AT hailongzhao predictingthetensilepropertiesofautomotivesteelsatintermediatestrainratesviainterpretableensemblemachinelearning AT jieli predictingthetensilepropertiesofautomotivesteelsatintermediatestrainratesviainterpretableensemblemachinelearning AT kangteyang predictingthetensilepropertiesofautomotivesteelsatintermediatestrainratesviainterpretableensemblemachinelearning |