Deep learning assisted prediction of retained austenite in the carburized layer for evaluating the wear resistance of mild steel
The content, distribution and size of retained austenite (RA) affect its mechanical stability in carburized layers. The stability of RA plays a decisive role in cold work hardening and strain-induced martensitic transformation during sliding friction; these changes determine wear resistance. In this...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-11-01
|
| Series: | Journal of Materials Research and Technology |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2238785422014600 |
| _version_ | 1811292755656179712 |
|---|---|
| author | Mingming Shen Zhenlong Zhu Shaobo Li Cunhong Yin Jing Yang Ansi Zhang |
| author_facet | Mingming Shen Zhenlong Zhu Shaobo Li Cunhong Yin Jing Yang Ansi Zhang |
| author_sort | Mingming Shen |
| collection | DOAJ |
| description | The content, distribution and size of retained austenite (RA) affect its mechanical stability in carburized layers. The stability of RA plays a decisive role in cold work hardening and strain-induced martensitic transformation during sliding friction; these changes determine wear resistance. In this study, a database was established based on laser confocal metallographic images of carburized layers on 23CrNi3MoA steel after different carburizing treatments. Eight algorithms were used to identify and calculate the amounts of RA in the carburized layers. The tribolayers and wear on the surfaces that underwent three carburizing processes, P13, P15, and P17, were characterized and tested. The results showed that the U-Net algorithm with an attention module and drop block regularization was the most suitable for the database. Predictions of the RA contents of surfaces after P13, P15, and P17 treatments were 19.9%, 28.1%, and 40.1%, respectively. The errors of the predictions compared with experimental results were within 5%. The surface carburized by the P15 process contained moderate amounts of RA and had the best wear resistance because the friction strain induced the formation of nanolamellar structures and the transformation of RA to martensite. The results of this study support the use of deep learning to identify and calculate the amounts of RA in carburized layers and optimize carburizing processes of mild steel. |
| first_indexed | 2024-04-13T04:50:11Z |
| format | Article |
| id | doaj.art-e6c035678caf4ab9ab692f623b856663 |
| institution | Directory Open Access Journal |
| issn | 2238-7854 |
| language | English |
| last_indexed | 2024-04-13T04:50:11Z |
| publishDate | 2022-11-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Journal of Materials Research and Technology |
| spelling | doaj.art-e6c035678caf4ab9ab692f623b8566632022-12-22T03:01:42ZengElsevierJournal of Materials Research and Technology2238-78542022-11-0121353362Deep learning assisted prediction of retained austenite in the carburized layer for evaluating the wear resistance of mild steelMingming Shen0Zhenlong Zhu1Shaobo Li2Cunhong Yin3Jing Yang4Ansi Zhang5School of Mechanical Engineering, Guizhou University, Guiyang 550025, China; School of Mechanical & Electrical Engineering, Guizhou Normal University, Guiyang 550025 ChinaCollege of Materials and Metallurgy, Guizhou University, Guiyang 550025, ChinaSchool of Mechanical Engineering, Guizhou University, Guiyang 550025, China; State Key Laboratory of Public Big Data, Guizhou University, Guiyang 550025, China; Corresponding author.School of Mechanical Engineering, Guizhou University, Guiyang 550025, ChinaSchool of Mechanical Engineering, Guizhou University, Guiyang 550025, China; State Key Laboratory of Public Big Data, Guizhou University, Guiyang 550025, ChinaSchool of Mechanical Engineering, Guizhou University, Guiyang 550025, China; State Key Laboratory of Public Big Data, Guizhou University, Guiyang 550025, ChinaThe content, distribution and size of retained austenite (RA) affect its mechanical stability in carburized layers. The stability of RA plays a decisive role in cold work hardening and strain-induced martensitic transformation during sliding friction; these changes determine wear resistance. In this study, a database was established based on laser confocal metallographic images of carburized layers on 23CrNi3MoA steel after different carburizing treatments. Eight algorithms were used to identify and calculate the amounts of RA in the carburized layers. The tribolayers and wear on the surfaces that underwent three carburizing processes, P13, P15, and P17, were characterized and tested. The results showed that the U-Net algorithm with an attention module and drop block regularization was the most suitable for the database. Predictions of the RA contents of surfaces after P13, P15, and P17 treatments were 19.9%, 28.1%, and 40.1%, respectively. The errors of the predictions compared with experimental results were within 5%. The surface carburized by the P15 process contained moderate amounts of RA and had the best wear resistance because the friction strain induced the formation of nanolamellar structures and the transformation of RA to martensite. The results of this study support the use of deep learning to identify and calculate the amounts of RA in carburized layers and optimize carburizing processes of mild steel.http://www.sciencedirect.com/science/article/pii/S2238785422014600WearTribolayerCarburized layerRetained austeniteDeep learning |
| spellingShingle | Mingming Shen Zhenlong Zhu Shaobo Li Cunhong Yin Jing Yang Ansi Zhang Deep learning assisted prediction of retained austenite in the carburized layer for evaluating the wear resistance of mild steel Journal of Materials Research and Technology Wear Tribolayer Carburized layer Retained austenite Deep learning |
| title | Deep learning assisted prediction of retained austenite in the carburized layer for evaluating the wear resistance of mild steel |
| title_full | Deep learning assisted prediction of retained austenite in the carburized layer for evaluating the wear resistance of mild steel |
| title_fullStr | Deep learning assisted prediction of retained austenite in the carburized layer for evaluating the wear resistance of mild steel |
| title_full_unstemmed | Deep learning assisted prediction of retained austenite in the carburized layer for evaluating the wear resistance of mild steel |
| title_short | Deep learning assisted prediction of retained austenite in the carburized layer for evaluating the wear resistance of mild steel |
| title_sort | deep learning assisted prediction of retained austenite in the carburized layer for evaluating the wear resistance of mild steel |
| topic | Wear Tribolayer Carburized layer Retained austenite Deep learning |
| url | http://www.sciencedirect.com/science/article/pii/S2238785422014600 |
| work_keys_str_mv | AT mingmingshen deeplearningassistedpredictionofretainedausteniteinthecarburizedlayerforevaluatingthewearresistanceofmildsteel AT zhenlongzhu deeplearningassistedpredictionofretainedausteniteinthecarburizedlayerforevaluatingthewearresistanceofmildsteel AT shaoboli deeplearningassistedpredictionofretainedausteniteinthecarburizedlayerforevaluatingthewearresistanceofmildsteel AT cunhongyin deeplearningassistedpredictionofretainedausteniteinthecarburizedlayerforevaluatingthewearresistanceofmildsteel AT jingyang deeplearningassistedpredictionofretainedausteniteinthecarburizedlayerforevaluatingthewearresistanceofmildsteel AT ansizhang deeplearningassistedpredictionofretainedausteniteinthecarburizedlayerforevaluatingthewearresistanceofmildsteel |