We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
The effect of element characteristics on bainite transformation start temperature using a machine learning approach.
- Authors
Liu, Yangni; Hou, Tingping; Yan, Zhuang; Yu, Tao; Duan, Junwen; Xiao, Yuhui; Wu, Kaiming
- Abstract
Bainite transformation start temperature (Bs) is an important index to measure the properties of bainitic steel. Based on the experimental results of bainite transformation behavior, the atomic scale characteristics are introduced, and the influence and prediction of different component content on Bs are analyzed by machine learning algorithm. The results show that Bs decreased significantly with the increase in C content (0−0.6wt.%) and Si content (0−0.2 wt.%), while the tendence remains almost unchanged when the Si content is greater than 0.2 wt.%. Furthermore, according to the analysis of atomic scale features, Bs has the strongest dependence on the number of valence electrons and the radius change rate relative to iron. The combination with the above two atomic scale features show the best model performance. The relationship between these two features and Bs is positively proportional, and Bs rises with the increase in their values. Extracting the valuable information about the relationship between Bs and element characteristics from the collected experimental data is of great significance to provide theoretical foundation of possible direction for the advances of designing the excellent properties in steels.
- Subjects
MACHINE learning; BAINITE; BAINITIC steel; CONDUCTION electrons; TEMPERATURE; IRON
- Publication
Journal of Materials Science, 2023, Vol 58, Issue 1, p443
- ISSN
0022-2461
- Publication type
Article
- DOI
10.1007/s10853-022-08035-5