Prediction of dynamic recrystallization behavior of SAE52100 large section bearing steel based on machine learning
Abstract This paper investigates the dynamic recrystallization characteristics of SAE52100 large section bearing steel under hot compression, focusing on both the center and surface. Using data from thermal simulation experiments the physical models were developed. Four machine learning algorithms i...
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley-VCH
2024-12-01
|
| Series: | Materials Genome Engineering Advances |
| Subjects: | |
| Online Access: | https://doi.org/10.1002/mgea.75 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841543276546490368 |
|---|---|
| author | Peiheng Ding Changqing Shu Shasha Zhang Zhaokuan Zhang Xingshuai Liu Jicong Zhang Qian Chen Shuaipeng Yu Xiaolin Zhu Zhengjun Yao |
| author_facet | Peiheng Ding Changqing Shu Shasha Zhang Zhaokuan Zhang Xingshuai Liu Jicong Zhang Qian Chen Shuaipeng Yu Xiaolin Zhu Zhengjun Yao |
| author_sort | Peiheng Ding |
| collection | DOAJ |
| description | Abstract This paper investigates the dynamic recrystallization characteristics of SAE52100 large section bearing steel under hot compression, focusing on both the center and surface. Using data from thermal simulation experiments the physical models were developed. Four machine learning algorithms including support vector regression, k‐nearest neighbors, random forest, and extreme gradient boosting were then employed to develop dynamic recrystallization prediction models based on the experimental data and inferred values from the physical model. The results show that the machine learning methods provide a better numerical description of the model, provided these are fed with extensive data. To enhance the scope of application, we obtained data from the dynamic recrystallization models for both the center and surface of SAE52100 steel in the as‐cast state, as well as extrapolated values from the literature regarding the hot‐rolled condition. When the SHAP method was introduced to reveal the mechanism of the influence of each input feature on the prediction results of the machine learning model, it was found that the test results of the Cr element did not match the theory, mainly because of the small scale of Cr elemental data and the strong dependence on grain size and secondary dendrite spacing. |
| format | Article |
| id | doaj-art-c31699c94d7345a8aa547bc349eced71 |
| institution | Kabale University |
| issn | 2940-9489 2940-9497 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Wiley-VCH |
| record_format | Article |
| series | Materials Genome Engineering Advances |
| spelling | doaj-art-c31699c94d7345a8aa547bc349eced712025-01-13T15:15:32ZengWiley-VCHMaterials Genome Engineering Advances2940-94892940-94972024-12-0124n/an/a10.1002/mgea.75Prediction of dynamic recrystallization behavior of SAE52100 large section bearing steel based on machine learningPeiheng Ding0Changqing Shu1Shasha Zhang2Zhaokuan Zhang3Xingshuai Liu4Jicong Zhang5Qian Chen6Shuaipeng Yu7Xiaolin Zhu8Zhengjun Yao9College of Materials Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing ChinaCollege of Materials Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing ChinaCollege of Materials Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing ChinaInstitute for Materials Research Tohoku University Ibaraki JapanCollege of Materials Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing ChinaCollege of Materials Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing ChinaCollege of Materials Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing ChinaCollege of Materials Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing ChinaJiangsu Product Quality Testing & Inspection Institute Nanjing ChinaCollege of Materials Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing ChinaAbstract This paper investigates the dynamic recrystallization characteristics of SAE52100 large section bearing steel under hot compression, focusing on both the center and surface. Using data from thermal simulation experiments the physical models were developed. Four machine learning algorithms including support vector regression, k‐nearest neighbors, random forest, and extreme gradient boosting were then employed to develop dynamic recrystallization prediction models based on the experimental data and inferred values from the physical model. The results show that the machine learning methods provide a better numerical description of the model, provided these are fed with extensive data. To enhance the scope of application, we obtained data from the dynamic recrystallization models for both the center and surface of SAE52100 steel in the as‐cast state, as well as extrapolated values from the literature regarding the hot‐rolled condition. When the SHAP method was introduced to reveal the mechanism of the influence of each input feature on the prediction results of the machine learning model, it was found that the test results of the Cr element did not match the theory, mainly because of the small scale of Cr elemental data and the strong dependence on grain size and secondary dendrite spacing.https://doi.org/10.1002/mgea.75dynamic recrystallizationlarge section bearing steelmachine learningrecrystallization kinetics |
| spellingShingle | Peiheng Ding Changqing Shu Shasha Zhang Zhaokuan Zhang Xingshuai Liu Jicong Zhang Qian Chen Shuaipeng Yu Xiaolin Zhu Zhengjun Yao Prediction of dynamic recrystallization behavior of SAE52100 large section bearing steel based on machine learning Materials Genome Engineering Advances dynamic recrystallization large section bearing steel machine learning recrystallization kinetics |
| title | Prediction of dynamic recrystallization behavior of SAE52100 large section bearing steel based on machine learning |
| title_full | Prediction of dynamic recrystallization behavior of SAE52100 large section bearing steel based on machine learning |
| title_fullStr | Prediction of dynamic recrystallization behavior of SAE52100 large section bearing steel based on machine learning |
| title_full_unstemmed | Prediction of dynamic recrystallization behavior of SAE52100 large section bearing steel based on machine learning |
| title_short | Prediction of dynamic recrystallization behavior of SAE52100 large section bearing steel based on machine learning |
| title_sort | prediction of dynamic recrystallization behavior of sae52100 large section bearing steel based on machine learning |
| topic | dynamic recrystallization large section bearing steel machine learning recrystallization kinetics |
| url | https://doi.org/10.1002/mgea.75 |
| work_keys_str_mv | AT peihengding predictionofdynamicrecrystallizationbehaviorofsae52100largesectionbearingsteelbasedonmachinelearning AT changqingshu predictionofdynamicrecrystallizationbehaviorofsae52100largesectionbearingsteelbasedonmachinelearning AT shashazhang predictionofdynamicrecrystallizationbehaviorofsae52100largesectionbearingsteelbasedonmachinelearning AT zhaokuanzhang predictionofdynamicrecrystallizationbehaviorofsae52100largesectionbearingsteelbasedonmachinelearning AT xingshuailiu predictionofdynamicrecrystallizationbehaviorofsae52100largesectionbearingsteelbasedonmachinelearning AT jicongzhang predictionofdynamicrecrystallizationbehaviorofsae52100largesectionbearingsteelbasedonmachinelearning AT qianchen predictionofdynamicrecrystallizationbehaviorofsae52100largesectionbearingsteelbasedonmachinelearning AT shuaipengyu predictionofdynamicrecrystallizationbehaviorofsae52100largesectionbearingsteelbasedonmachinelearning AT xiaolinzhu predictionofdynamicrecrystallizationbehaviorofsae52100largesectionbearingsteelbasedonmachinelearning AT zhengjunyao predictionofdynamicrecrystallizationbehaviorofsae52100largesectionbearingsteelbasedonmachinelearning |