Predicting plastic deformation of crystalline materials by deciphering acoustic emission

Acoustic emission signals have been shown to accompany avalanche-like events in materials, such as dislocation avalanches in crystalline solids, collapse of voids in porous matter or domain wall movement in ferroics. The data provided by acoustic emission measurements are tremendously rich, but it is rather challenging to precisely connect them to the characteristics of the triggering avalanche. In our work, we derive various frequency-dependent and independent descriptors with which one can infer microscopic details of dislocation avalanches in micropillar compression tests from merely acoustic emission data. We present a machine learning approach suitable for the prediction of the force-time response of single crystalline metals as it provides outstanding prediction for the temporal location of avalanches and also predicts the magnitude of individual deformation events. The transferability of the method to other specimen sizes is demonstrated and the possible application in more generic settings is discussed.