Machine learning plastic deformation of crystals

Abstract

Plastic deformation of micron-scale crystalline solids exhibits stress-strain curves with significant sample-to-sample variations. It is a pertinent question if this variability is purely random or to some extent predictable. Here we show, by employing machine learning techniques such as regression neural networks and support vector machines that deformation predictability evolves with strain and crystal size. Using data from discrete dislocations dynamics simulations, the machine learning models are trained to infer the mapping from features of the pre-existing dislocation configuration to the stress-strain curves. The predictability vs strain relation is non-monotonic and exhibits a system size effect: larger systems are more predictable. Stochastic deformation avalanches give rise to fundamental limits of deformation predictability for intermediate strains. However, the large-strain deformation dynamics of the samples can be predicted surprisingly well.

Published version from https://www.nature.com/articles/s41467-018-07737-2. Supplementary material can also be found from the link

References in corpus (13)

• Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning
• Machine learning phases of matter
• Learning phase transitions by confusion
• Identifying structural flow defects in disordered solids using machine learning methods
• Machine learning quantum phases of matter beyond the fermion sign problem
• Multi-scale modeling of dislocation-precipitate interactions in Fe: from molecular dynamics to discrete dislocations
• Avalanches and Plastic Flow in Crystal Plasticity: An Overview
• Quenched pinning and collective dislocation dynamics
• Glassy features of crystal plasticity
• Comparison of the dislocation density obtained by HR-EBSD and X-ray profile analysis
• The stress statistics of the first pop-in or intermittent plastic event in cyrstal plasticity
• The role of weakest links and system size scaling in multiscale modeling of stochastic plasticity
• Learning crystal plasticity using digital image correlation: Examples from discrete dislocation dynamics

Cited by in corpus (20)

• Predicting the failure of two-dimensional silica glasses
• Deep Learning and Crystal Plasticity: A Preconditioning Approach for Accurate Orientation Evolution Prediction
• Accelerating discrete dislocation dynamics simulations with graph neural networks
• Plastic yielding and deformation bursts in the presence of disorder from coherent precipitates
• Identification of dislocation reaction kinetics in complex dislocation networks for continuum modeling using data-driven methods
• Machine learning depinning of dislocation pileups
• Machine learning and predicting the time dependent dynamics of local yielding in dry foams
• Predicting elastic and plastic properties of small iron polycrystals by machine learning
• An efficient implicit method for discrete dislocation dynamics simulations
• Social Inequality Analysis of Fiber Bundle Model Statistics and Prediction of Materials Failure
• Stress Predictions in Polycrystal Plasticity using Graph Neural Networks with Subgraph Training
• Machine learning reveals strain-rate-dependent predictability of discrete dislocation plasticity
• Avalanches and rate effects in strain-controlled discrete dislocation plasticity of Al single crystals
• Avalanche correlations and stress-strain curves in discrete dislocation plasticity
• Bayesian optimization of discrete dislocation plasticity of two-dimensional precipitation hardened crystals
• The effects of external noise on threshold induced correlations in ferromagnetic systems
• Machine learning predictions of COVID-19 second wave end-times in Indian states
• Avalanche Dynamics and the Effect of Straining in Dislocation Systems with Quenched Disorder
• Quantitative analysis of the prediction performance of a Convolutional Neural Network evaluating the surface elastic energy of a strained film
• Estimating predictability of depinning dynamics by machine learning