Predicting mechanical properties of bainitic rail steels based on microstructure digitalization and machine learning
It is usually quite challenging to establish a quantitative chemical composition-microstructure-mechanical property relationship for bainitic steels. In this study, digital information was extracted based on EBSD data of bainitic rail steels, and two machine learning models were built to predict str...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-03-01
|
| Series: | Journal of Materials Research and Technology |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2238785425001553 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832583073459339264 |
|---|---|
| author | L.Q. Bai Z.Y. Ding J.L. Wang Z.J. Xie Z.N. Yang C.J. Shang |
| author_facet | L.Q. Bai Z.Y. Ding J.L. Wang Z.J. Xie Z.N. Yang C.J. Shang |
| author_sort | L.Q. Bai |
| collection | DOAJ |
| description | It is usually quite challenging to establish a quantitative chemical composition-microstructure-mechanical property relationship for bainitic steels. In this study, digital information was extracted based on EBSD data of bainitic rail steels, and two machine learning models were built to predict strength and impact energy based on chemical compositions and digitalized microstructural features. The models showed excellent prediction accuracy (R2 > 84%) for yield strength, tensile strength and impact energy. All predicted values were within the error range of experimental measured values. Feature importance analysis suggested that C has a beneficial and detrimental effect on the strength and toughness, respectively; while a high block boundary density proved to have a positive effect on toughness, which agrees well with previous experimental observations. The obtained quantitative relationship between chemical composition, microstructure and mechanical properties can serve as a good guideline for the design of bainitic rail steels with an optimized combination of high strength and toughness. |
| format | Article |
| id | doaj-art-29a56a1bb3e84641930c775b16cb0085 |
| institution | Kabale University |
| issn | 2238-7854 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Journal of Materials Research and Technology |
| spelling | doaj-art-29a56a1bb3e84641930c775b16cb00852025-01-29T05:01:21ZengElsevierJournal of Materials Research and Technology2238-78542025-03-013521362143Predicting mechanical properties of bainitic rail steels based on microstructure digitalization and machine learningL.Q. Bai0Z.Y. Ding1J.L. Wang2Z.J. Xie3Z.N. Yang4C.J. Shang5Collaborative Innovation Center of Steel Technology, University of Science and Technology Beijing, 100083, ChinaState Key Laboratory for Advanced Metals and Materials, University of Science and Technology Beijing, 100083, ChinaState Key Laboratory for Advanced Metals and Materials, University of Science and Technology Beijing, 100083, ChinaState Key Laboratory for Advanced Metals and Materials, University of Science and Technology Beijing, 100083, China; Corresponding author.National Engineering Research Center for Equipment and Technology of Cold Rolled Strip, Yanshan University, Qinhuangdao, 066004, China; Hebei Iron and Steel Laboratory, North China University of Science and Technology, Tangshan, 063210, ChinaState Key Laboratory for Advanced Metals and Materials, University of Science and Technology Beijing, 100083, ChinaIt is usually quite challenging to establish a quantitative chemical composition-microstructure-mechanical property relationship for bainitic steels. In this study, digital information was extracted based on EBSD data of bainitic rail steels, and two machine learning models were built to predict strength and impact energy based on chemical compositions and digitalized microstructural features. The models showed excellent prediction accuracy (R2 > 84%) for yield strength, tensile strength and impact energy. All predicted values were within the error range of experimental measured values. Feature importance analysis suggested that C has a beneficial and detrimental effect on the strength and toughness, respectively; while a high block boundary density proved to have a positive effect on toughness, which agrees well with previous experimental observations. The obtained quantitative relationship between chemical composition, microstructure and mechanical properties can serve as a good guideline for the design of bainitic rail steels with an optimized combination of high strength and toughness.http://www.sciencedirect.com/science/article/pii/S2238785425001553Machine learningMicrostructure digitalizationCrystallographic featureMechanical propertiesBainitic rail steels |
| spellingShingle | L.Q. Bai Z.Y. Ding J.L. Wang Z.J. Xie Z.N. Yang C.J. Shang Predicting mechanical properties of bainitic rail steels based on microstructure digitalization and machine learning Journal of Materials Research and Technology Machine learning Microstructure digitalization Crystallographic feature Mechanical properties Bainitic rail steels |
| title | Predicting mechanical properties of bainitic rail steels based on microstructure digitalization and machine learning |
| title_full | Predicting mechanical properties of bainitic rail steels based on microstructure digitalization and machine learning |
| title_fullStr | Predicting mechanical properties of bainitic rail steels based on microstructure digitalization and machine learning |
| title_full_unstemmed | Predicting mechanical properties of bainitic rail steels based on microstructure digitalization and machine learning |
| title_short | Predicting mechanical properties of bainitic rail steels based on microstructure digitalization and machine learning |
| title_sort | predicting mechanical properties of bainitic rail steels based on microstructure digitalization and machine learning |
| topic | Machine learning Microstructure digitalization Crystallographic feature Mechanical properties Bainitic rail steels |
| url | http://www.sciencedirect.com/science/article/pii/S2238785425001553 |
| work_keys_str_mv | AT lqbai predictingmechanicalpropertiesofbainiticrailsteelsbasedonmicrostructuredigitalizationandmachinelearning AT zyding predictingmechanicalpropertiesofbainiticrailsteelsbasedonmicrostructuredigitalizationandmachinelearning AT jlwang predictingmechanicalpropertiesofbainiticrailsteelsbasedonmicrostructuredigitalizationandmachinelearning AT zjxie predictingmechanicalpropertiesofbainiticrailsteelsbasedonmicrostructuredigitalizationandmachinelearning AT znyang predictingmechanicalpropertiesofbainiticrailsteelsbasedonmicrostructuredigitalizationandmachinelearning AT cjshang predictingmechanicalpropertiesofbainiticrailsteelsbasedonmicrostructuredigitalizationandmachinelearning |