Abstract
ABSTRACT Stacking fault energy (SFE) is of the most critical microstructure attribute for controlling the deformation mechanism and optimizing mechanical properties of austenitic steels, while there are no accurate and straightforward computational tools for modeling it. In this work, we applied both thermodynamic modeling and machine learning to predict the stacking fault energy (SFE) for more than 300 austenitic steels. The comparison indicates a high need of improving low-temperature CALPHAD (CALculation of PHAse Diagrams) databases and interfacial energy prediction to enhance thermodynamic model reliability. The ensembled machine learning algorithms provide a more reliable prediction compared with thermodynamic and empirical models. Based on the statistical analysis of experimental results, only Ni and Fe have a moderate monotonic influence on SFE, while many other elements exhibit a complex effect that their influence on SFE may change with the alloy composition.
Highlights
Alloy with high strength and excellent ductility is one of the ultimate goals for materials design
transformation-induced plasticity (TRIP) activates when Stacking fault energy (SFE) is lower than 20 mJ/m2 [4], and twinning-induced plasticity (TWIP) is achievable if the SFE lies between 20 – 40 mJ/m2 [5]
In summary, we evaluated the thermodynamic model for SFE prediction, analyzed the influence of alloying elements on SFE, and built an accurate SFE model using Machine learning (ML)
Summary
Alloy with high strength and excellent ductility is one of the ultimate goals for materials design. In most of the past research, the SFE model and Gibbs free energy functions for phases are designed for steels with 2-3 alloying elements [16,17,18,19], while modeling the multicomponent systems is challenging since it involves many parameters. They have not been verified for alloys with a wide composition range [16,19,20]. This work (i) assessed the quality of the CALPHAD-based thermodynamic model-prediction, and revealed the importance of robust CALPHAD database on accurate SFE prediction; (ii) discussed the influence of alloying elements on SFE through a statistical approach and found Ni and Fe have a moderate monotonic influence on SFE while other elements might have a complex effect; and (iii) predicted SFE using ML, and proved the performance of the ML model developed in this work was superior to the thermodynamic and empirical models
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
