Analysis of tensile properties in tempered martensite steels with different cementite particle size distributions
In this study, the tensile properties of tempered martensite steel were analyzed using a combination of an experimental approach and deep learning. The martensite steels were tempered in two stages, and fine and coarse cementite particles were mixed through two-stage tempering. The samples were heat...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
AIMS Press
2024-11-01
|
| Series: | AIMS Materials Science |
| Subjects: | |
| Online Access: | https://www.aimspress.com/article/doi/10.3934/matersci.2024050 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832590259749126144 |
|---|---|
| author | Kengo Sawai Keiya Sugiura Toshio Ogawa Ta-Te Chen Fei Sun Yoshitaka Adachi |
| author_facet | Kengo Sawai Keiya Sugiura Toshio Ogawa Ta-Te Chen Fei Sun Yoshitaka Adachi |
| author_sort | Kengo Sawai |
| collection | DOAJ |
| description | In this study, the tensile properties of tempered martensite steel were analyzed using a combination of an experimental approach and deep learning. The martensite steels were tempered in two stages, and fine and coarse cementite particles were mixed through two-stage tempering. The samples were heated to 923 and 973 K and held isothermally for 30, 45, and 60 min. They were then cooled to 723, 773, and 823 K; held isothermally for 30, 45, and 60 min; and furnace-cooled to room temperature (296 ± 2 K). The combination of low tempering temperature and short holding time in the first stage resulted in high tensile strength. When the tempering temperature at the first stage was 923 K, the combination of low tempering temperature and long holding time at the second stage resulted in high total elongation. This means that decreasing the number of coarse cementite particles and increasing the number of fine cementite particles improve the strength–ductility balance. Using the results obtained by the experimental approach, an image-based regression model was constructed that can accurately suggest the relationship between the microstructure and tensile properties of tempered martensite steel. We succeeded in developing image-based regression models with high accuracy using a convolutional neural network (CNN). Moreover, gradient-weighted class activation mapping (Grad-CAM) suggested that fine cementite particles and coarse and spheroidal cementite particles are the dominant factors for tensile strength and total elongation, respectively. |
| format | Article |
| id | doaj-art-69bdb41638ea43d69be872c507381b68 |
| institution | Kabale University |
| issn | 2372-0484 |
| language | English |
| publishDate | 2024-11-01 |
| publisher | AIMS Press |
| record_format | Article |
| series | AIMS Materials Science |
| spelling | doaj-art-69bdb41638ea43d69be872c507381b682025-01-24T01:30:27ZengAIMS PressAIMS Materials Science2372-04842024-11-011151056106410.3934/matersci.2024050Analysis of tensile properties in tempered martensite steels with different cementite particle size distributionsKengo Sawai0Keiya Sugiura1Toshio Ogawa2Ta-Te Chen3Fei Sun4Yoshitaka Adachi5Department of Materials Design Innovation Engineering, Graduate School of Engineering, Nagoya University, Furo-cho, Chikusa-ku, Nagoya, Aichi 464-8603, JapanDepartment of Materials Design Innovation Engineering, Graduate School of Engineering, Nagoya University, Furo-cho, Chikusa-ku, Nagoya, Aichi 464-8603, JapanDepartment of Mechanical Engineering, Faculty of Engineering, Aichi Institute of Technology, 1247 Yachigusa, Yakusa-cho, Toyota, Aichi 470-0392, JapanDepartment of Materials Design Innovation Engineering, Graduate School of Engineering, Nagoya University, Furo-cho, Chikusa-ku, Nagoya, Aichi 464-8603, JapanDepartment of Materials Design Innovation Engineering, Graduate School of Engineering, Nagoya University, Furo-cho, Chikusa-ku, Nagoya, Aichi 464-8603, JapanDepartment of Materials Design Innovation Engineering, Graduate School of Engineering, Nagoya University, Furo-cho, Chikusa-ku, Nagoya, Aichi 464-8603, JapanIn this study, the tensile properties of tempered martensite steel were analyzed using a combination of an experimental approach and deep learning. The martensite steels were tempered in two stages, and fine and coarse cementite particles were mixed through two-stage tempering. The samples were heated to 923 and 973 K and held isothermally for 30, 45, and 60 min. They were then cooled to 723, 773, and 823 K; held isothermally for 30, 45, and 60 min; and furnace-cooled to room temperature (296 ± 2 K). The combination of low tempering temperature and short holding time in the first stage resulted in high tensile strength. When the tempering temperature at the first stage was 923 K, the combination of low tempering temperature and long holding time at the second stage resulted in high total elongation. This means that decreasing the number of coarse cementite particles and increasing the number of fine cementite particles improve the strength–ductility balance. Using the results obtained by the experimental approach, an image-based regression model was constructed that can accurately suggest the relationship between the microstructure and tensile properties of tempered martensite steel. We succeeded in developing image-based regression models with high accuracy using a convolutional neural network (CNN). Moreover, gradient-weighted class activation mapping (Grad-CAM) suggested that fine cementite particles and coarse and spheroidal cementite particles are the dominant factors for tensile strength and total elongation, respectively.https://www.aimspress.com/article/doi/10.3934/matersci.2024050tempered martensite steelcementitestrength–ductility balancedeep learningimage-based regression |
| spellingShingle | Kengo Sawai Keiya Sugiura Toshio Ogawa Ta-Te Chen Fei Sun Yoshitaka Adachi Analysis of tensile properties in tempered martensite steels with different cementite particle size distributions AIMS Materials Science tempered martensite steel cementite strength–ductility balance deep learning image-based regression |
| title | Analysis of tensile properties in tempered martensite steels with different cementite particle size distributions |
| title_full | Analysis of tensile properties in tempered martensite steels with different cementite particle size distributions |
| title_fullStr | Analysis of tensile properties in tempered martensite steels with different cementite particle size distributions |
| title_full_unstemmed | Analysis of tensile properties in tempered martensite steels with different cementite particle size distributions |
| title_short | Analysis of tensile properties in tempered martensite steels with different cementite particle size distributions |
| title_sort | analysis of tensile properties in tempered martensite steels with different cementite particle size distributions |
| topic | tempered martensite steel cementite strength–ductility balance deep learning image-based regression |
| url | https://www.aimspress.com/article/doi/10.3934/matersci.2024050 |
| work_keys_str_mv | AT kengosawai analysisoftensilepropertiesintemperedmartensitesteelswithdifferentcementiteparticlesizedistributions AT keiyasugiura analysisoftensilepropertiesintemperedmartensitesteelswithdifferentcementiteparticlesizedistributions AT toshioogawa analysisoftensilepropertiesintemperedmartensitesteelswithdifferentcementiteparticlesizedistributions AT tatechen analysisoftensilepropertiesintemperedmartensitesteelswithdifferentcementiteparticlesizedistributions AT feisun analysisoftensilepropertiesintemperedmartensitesteelswithdifferentcementiteparticlesizedistributions AT yoshitakaadachi analysisoftensilepropertiesintemperedmartensitesteelswithdifferentcementiteparticlesizedistributions |