Machine learning materials physics: Multi-resolution neural networks learn the free energy and nonlinear elastic response of evolving microstructures

Abstract

Many important multi-component crystalline solids undergo mechanochemical spinodal decomposition: a phase transformation in which the compositional redistribution is coupled with structural changes of the crystal, resulting in dynamically evolving microstructures. The ability to rapidly compute the macroscopic behavior based on these detailed microstructures is of paramount importance for accelerating material discovery and design. Here, our focus is on the macroscopic, nonlinear elastic response of materials harboring microstructure. Because of the diversity of microstructural patterns that can form, there is interest in taking a purely computational approach to predicting their macroscopic response. However, the evaluation of macroscopic, nonlinear elastic properties purely based on direct numerical simulations (DNS) is computationally very expensive, and hence impractical for material design when a large number of microstructures need to be tested. A further complexity of a hierarchical nature arises if the elastic free energy and its variation with strain is a small-scale fluctuation on the dominant trajectory of the total free energy driven by microstructural dynamics. To address these challenges, we present a data-driven approach, which combines advanced neural network (NN) models with DNS to predict the homogenized, macroscopic, mechanical free energy and stress fields arising in a family of multi-component crystalline solids that develop microstructure. The hierarchical structure of the free energy's evolution induces a multi-resolution character to the machine learning paradigm: We construct knowledge-based neural networks (KBNNs) with either pre-trained fully connected deep neural networks (DNNs), or pre-trained convolutional neural networks (CNNs) that describe the dominant characteristic of the data to fully represent the hierarchically evolving free energy.

arXiv comment24 pages, 15 figures

References in corpus (15)

• Discovering governing equations from data: Sparse identification of nonlinear dynamical systems
• A General-Purpose Machine Learning Framework for Predicting Properties of Inorganic Materials
• By-passing the Kohn-Sham equations with machine learning
• Meta-modeling game for deriving theoretical-consistent, micro-structural-based traction-separation laws via deep reinforcement learning
• Machine learning materials physics: Integrable deep neural networks enable scale bridging by learning free energy functions
• Machine learning materials physics: Surrogate optimization and multi-fidelity algorithms predict precipitate morphology in an alternative to phase field dynamics
• Variational system identification of the partial differential equations governing pattern-forming physics: Inference under varying fidelity and noise
• Three-dimensional iso-geometric solutions to general boundary value problems of Toupin's gradient elasticity theory at finite strains
• Mechano-chemical spinodal decomposition: A phenomenological theory of phase transformations in multi-component, crystalline solids
• A three dimensional field formulation, and isogeometric solutions to point and line defects using Toupin's theory of gradient elasticity at finite strains
• Unconditionally stable, second-order accurate schemes for solid state phase transformations driven by mechano-chemical spinodal decomposition
• Machine learning materials physics: Deep neural networks trained on elastic free energy data from martensitic microstructures predict homogenized stress fields with high accuracy
• Unconditionally stable, second-order schemes for gradient-regularized, non-convex, finite-strain elasticity modeling martensitic phase transformations
• Predicting the mechanical response of oligocrystals with deep learning
• Deep learning methods based on cross-section images for predicting effective thermal conductivity of composites

Cited by in corpus (13)

• Multiscale modeling of inelastic materials with Thermodynamics-based Artificial Neural Networks (TANN)
• Deep transfer operator learning for partial differential equations under conditional shift
• Data-driven Tissue Mechanics with Polyconvex Neural Ordinary Differential Equations
• Towards out of distribution generalization for problems in mechanics
• Neural Cellular Automata for Solidification Microstructure Modelling
• Bayesian neural networks for weak solution of PDEs with uncertainty quantification
• Ogden Material Calibration via Magnetic Resonance Cartography, Parameter Sensitivity, and Variational System Identification
• Morphological evolution via surface diffusion learned by convolutional, recurrent neural networks: extrapolation and prediction uncertainty
• Extreme time extrapolation capabilities and thermodynamic consistency of physics-inspired Neural Networks for the 3D microstructure evolution of materials via Cahn-Hilliard flow
• Reduced order models from computed states of physical systems using non-local calculus on finite weighted graphs
• Numerical analysis of non-local calculus on finite weighted graphs, with application to reduced-order modelling of dynamical systems
• Exploring the potential of transfer learning for metamodels of heterogeneous material deformation
• System inference via field inversion for the spatio-temporal progression of infectious diseases: Studies of COVID-19 in Michigan and Mexico