About this Abstract |
Meeting |
2024 TMS Annual Meeting & Exhibition
|
Symposium
|
Advanced Characterization Techniques for Quantifying and Modeling Deformation
|
Presentation Title |
Application of Machine Learning to Assess the Influence of Microstructure on Twin Nucleation in Mg Alloys |
Author(s) |
Biaobiao Yang, Valentin Vassilev-Galindo, Javier Llorca |
On-Site Speaker (Planned) |
Javier Llorca |
Abstract Scope |
Mechanical twinning is an important deformation mode in Mg alloys. The experimental evidence indicates that {10-12} <10-11> extension twins tend to nucleate at the grain boundaries of large grains that a suitable oriented to accommodate plastic deformation by this mechanism. However, twins are also nucleated in small grains or in grains that are not suitably oriented for twinning, indicating that other microstructural factors play a significant role.
In this investigation, the nucleation of extension twins during deformation along different orientations was determined by means of in situ electron backscatterer diffraction in a textured AZ31 Mg alloy, leading to a large dataset. The microstructural features of the grain and of the neighbour grains (size, Schmid factors for slip and twinning, number of neighbour grains, grain boundary parameters, etc.) were included in the dataset which was analyzed using Bayesian networks to unveil the microstructural factors that control extension twin nucleation. |
Proceedings Inclusion? |
Planned: |
Keywords |
Machine Learning, Magnesium, Mechanical Properties |