Learning nonlocal constitutive models with neural networks

Abstract

Constitutive and closure models play important roles in computational mechanics and computational physics in general. Classical constitutive models for solid and fluid materials are typically local, algebraic equations or flow rules describing the dependence of stress on the local strain and/or strain-rate. Closure models such as those describing Reynolds stress in turbulent flows and laminar--turbulent transition can involve transport PDEs (partial differential equations). Such models play similar roles to constitutive relation, but they are often more challenging to develop and calibrate as they describe nonlocal mappings and often contain many submodels. Inspired by the structure of the exact solutions to linear transport PDEs, we propose a neural network representing a region-to-point mapping to describe such nonlocal constitutive models. The range of nonlocal dependence and the convolution structure are derived from the formal solution to transport equations. The neural network-based nonlocal constitutive model is trained with data. Numerical experiments demonstrate the predictive capability of the proposed method. Moreover, the proposed network learned the embedded submodel without using data from that level, thanks to its interpretable mathematical structure, which makes it a promising alternative to traditional nonlocal constitutive models.

References in corpus (38)

• Adam: A Method for Stochastic Optimization
• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• DeepONet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operators
• DGM: A deep learning algorithm for solving partial differential equations
• Solving high-dimensional partial differential equations using deep learning
• Turbulence Modeling in the Age of Data
• Fourier Neural Operator for Parametric Partial Differential Equations
• Surrogate Modeling for Fluid Flows Based on Physics-Constrained Deep Learning Without Simulation Data
• Deep learning-based numerical methods for high-dimensional parabolic partial differential equations and backward stochastic differential equations
• Data-driven computational mechanics
• A unified deep artificial neural network approach to partial differential equations in complex geometries
• A Physics Informed Machine Learning Approach for Reconstructing Reynolds Stress Modeling Discrepancies Based on DNS Data
• A Comprehensive Physics-Informed Machine Learning Framework for Predictive Turbulence Modeling
• Physics-Informed Machine Learning Approach for Augmenting Turbulence Models: A Comprehensive Framework
• Deep UQ: Learning deep neural network surrogate models for high dimensional uncertainty quantification
• Thermodynamics-based Artificial Neural Networks for constitutive modeling
• Optimal Subsampling for Large Sample Logistic Regression
• Discovery of Algebraic Reynolds-Stress Models Using Sparse Symbolic Regression
• Solving Many-Electron Schrödinger Equation Using Deep Neural Networks
• PDE-Net: Learning PDEs from Data
• Learning Constitutive Relations from Indirect Observations Using Deep Neural Networks
• Learning Constitutive Relations using Symmetric Positive Definite Neural Networks
• Neural Operator: Graph Kernel Network for Partial Differential Equations
• CFDNet: a deep learning-based accelerator for fluid simulations
• Solving Electrical Impedance Tomography with Deep Learning
• Not All Samples Are Created Equal: Deep Learning with Importance Sampling
• Uniformly Accurate Machine Learning Based Hydrodynamic Models for Kinetic Equations
• DeepCFD: Efficient Steady-State Laminar Flow Approximation with Deep Convolutional Neural Networks
• Learning nonlocal constitutive models with neural networks
• A Bi-fidelity Surrogate Modeling Approach for Uncertainty Propagation in Three-Dimensional Hemodynamic Simulations
• Machine learning based non-Newtonian fluid model with molecular fidelity
• Enforcing Boundary Conditions on Physical Fields in Bayesian Inversion
• A bi-fidelity method for the multiscale Boltzmann equation with random parameters
• Efficient Augmentation via Data Subsampling
• Optimal Sub-sampling with Influence Functions
• Solving Inverse Wave Scattering with Deep Learning
• Frame-independent vector-cloud neural network for nonlocal constitutive modeling on arbitrary grids

Cited by in corpus (14)

• Multiscale modeling of inelastic materials with Thermodynamics-based Artificial Neural Networks (TANN)
• Ensemble Kalman method for learning turbulence models from indirect observation data
• Learning nonlocal constitutive models with neural networks
• Machine Learning for Physics-Informed Generation of Dispersed Multiphase Flow Using Generative Adversarial Networks
• An iterative data-driven turbulence modeling framework based on Reynolds stress representation
• Discovering explicit Reynolds-averaged turbulence closures for turbulent separated flows through deep learning-based symbolic regression with non-linear corrections
• An equivariant neural operator for developing nonlocal tensorial constitutive models
• CGKN: A Deep Learning Framework for Modeling Complex Dynamical Systems and Efficient Data Assimilation
• Frame invariance and scalability of neural operators for partial differential equations
• Frame-independent vector-cloud neural network for nonlocal constitutive modeling on arbitrary grids
• UCNN: A Convolutional Strategy on Unstructured Mesh
• Turbulence closure modeling with data-driven techniques: Investigation of generalizable deep neural networks
• ML-based identification of the interface regions for coupling local and nonlocal models
• Rotational and Reflectional Equivariant Convolutional Neural Network for data-limited applications: Multiphase Flow demonstration