Machine learning depinning of dislocation pileups

TL;DR

This paper investigates a one-dimensional dislocation pileup model under external stress, demonstrating that machine learning models can predict the system's stress response and critical transition points with high accuracy, revealing insights into plastic deformation predictability.

Contribution

It introduces machine learning approaches to predict dislocation dynamics and critical stress points in a dislocation pileup model, highlighting the potential for predictive modeling in material deformation.

Findings

Stress-strain response can be predicted accurately.

Prediction of flow stress and critical transition points is feasible.

Machine learning models capture the non-monotonic correlation with strain.

Abstract

We study a one-dimensional model of a dislocation pileup driven by an external stress and interacting with random quenched disorder, focusing on predictability of the plastic deformation process. Upon quasistatically ramping up the externally applied stress from zero the system responds by exhibiting an irregular stress--strain curve consisting of a sequence of strain bursts, i.e., critical-like dislocation avalanches. The strain bursts are power-law distributed up to a cutoff scale which increases with the stress level up to a critical flow stress value. There, the system undergoes a depinning phase transition and the dislocations start moving indefinitely, i.e., the strain burst size diverges. Using sample-specific information about the pinning landscape as well as the initial dislocation configuration as input, we employ predictive models such as linear regression, simple neural networks and convolutional neural networks to study the predictability of the simulated stress--strain curves of individual samples. Our results show that the response of the system -- including the flow stress value -- can be predicted quite well, with the correlation coefficient between predicted and actual stress exhibiting a non-monotonic dependence on strain. We also discuss our attempts to predict the individual strain bursts.