|About this Abstract
||2019 TMS Annual Meeting & Exhibition
||Computational Approaches for Big Data, Artificial Intelligence and Uncertainty Quantification in Computational Materials Science
||Investigation of Deformation Twinning in Mg Alloy during In-situ Compression Using Clustering and Computer Vision
||Zhe Chen, Samantha Daly
|On-Site Speaker (Planned)
Deformation twinning during in-situ compression was analyzed by clustering and computer vision approaches. High-resolution, large field-of-view deformation measurements capturing statistically representative microstructures were performed by scanning electron microscopy – digital image correlation using an automated and customized imaging system. Clustering analysis was used in each grain to segment the strain maps into fragments corresponding to different deformation features. Clusters were further classified as twinned or non-twinned categories using classifiers that contained information on the similarity between the strains of cluster and predicted twins, the global Schmid factor of the most probable twin system, and the evolution of the cluster size and shape. The application and performance of these classifiers will be discussed, as well as correlations between local microstructure, twinning activity, and the local strain evolution.
||Planned: Supplemental Proceedings volume