Application of machine learning to assess the influence of microstructure on twin nucleation in Mg alloys

Abstract

AbstractTwin nucleation in textured Mg alloys was studied by means of electron back-scattered diffraction in samples deformed in tension along different orientations in more than 3000 grains. In addition, 28 relevant parameters, categorized in four different groups (loading condition, grain shape, apparent Schmid factors, and grain boundary features) were also recorded for each grain. This information was used to train supervised machine learning classification models to analyze the influence of the microstructural features on the nucleation of extension twins in Mg alloys. It was found twin nucleation is favored in larger grains and in grains with high twinning Schmid factors, but also that twins may form in the grains with very low or even negative Schmid factors for twinning if they have at least one smaller neighboring grain and another one (or the same) that is more rigid. Moreover, twinning of small grains with high twinning Schmid factors is favored if they have low basal slip Schmid factors and have at least one neighboring grain with a high basal slip Schmid factor that will deform easily. These results reveal the role of many-body relationships, such as differences in stiffness and size between a given grain and its neighbors, to assess extension twin nucleation in grains unfavorably oriented for twinning.