Learning Constitutive Relations from Indirect Observations Using Deep Neural Networks

Abstract

We present a new approach for predictive modeling and its uncertainty quantification for mechanical systems, where coarse-grained models such as constitutive relations are derived directly from observation data. We explore the use of a neural network to represent the unknown constitutive relations, compare the neural networks with piecewise linear functions, radial basis functions, and radial basis function networks, and show that the neural network outperforms the others in certain cases. We analyze the approximation error of the neural networks using a scaling argument. The training and predicting processes in our framework combine the finite element method, automatic differentiation, and neural networks (or other function approximators). Our framework also allows uncertainty quantification in the form of confidence intervals. Numerical examples on a multiscale fiber-reinforced plate problem and a nonlinear rubbery membrane problem from solid mechanics demonstrate the effectiveness of our framework.

40 pages, 21 figures

References in corpus (13)

• Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning
• Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)
• Deep learning-based numerical methods for high-dimensional parabolic partial differential equations and backward stochastic differential equations
• Data-driven computational mechanics
• Self-Normalizing Neural Networks
• Active subspace methods in theory and practice: applications to kriging surfaces
• Deep UQ: Learning deep neural network surrogate models for high dimensional uncertainty quantification
• Cross-Covariance Functions for Multivariate Geostatistics
• Data Driven Computing with Noisy Material Data Sets
• All you need is a good init
• Learning Parameters and Constitutive Relationships with Physics Informed Deep Neural Networks
• The Neural Network Approach to Inverse Problems in Differential Equations
• Calibrating Multivariate Lévy Processes with Neural Networks

Cited by in corpus (47)

• Differentiable modeling to unify machine learning and physical models and advance Geosciences
• Uncertainty Quantification in Scientific Machine Learning: Methods, Metrics, and Comparisons
• Thermodynamics-based Artificial Neural Networks for constitutive modeling
• Intelligent Computing: The Latest Advances, Challenges and Future
• Unsupervised discovery of interpretable hyperelastic constitutive laws
• Transfer learning based physics-informed neural networks for solving inverse problems in engineering structures under different loading scenarios
• Geometric deep learning for computational mechanics Part I: Anisotropic Hyperelasticity
• Learning Constitutive Relations using Symmetric Positive Definite Neural Networks
• Multiscale modeling of inelastic materials with Thermodynamics-based Artificial Neural Networks (TANN)
• NN-EUCLID: deep-learning hyperelasticity without stress data
• Automated discovery of generalized standard material models with EUCLID
• Deep Learning in Deterministic Computational Mechanics
• Recent Advances and Applications of Machine Learning in Experimental Solid Mechanics: A Review
• Hybrid FEM-NN models: Combining artificial neural networks with the finite element method
• Discovering plasticity models without stress data
• MAgNET: A Graph U-Net Architecture for Mesh-Based Simulations
• Learning nonlocal constitutive models with neural networks
• SINDy-BVP: Sparse Identification of Nonlinear Dynamics for Boundary Value Problems
• A Computationally Tractable Framework for Nonlinear Dynamic Multiscale Modeling of Membrane Fabric
• Physics Constrained Learning for Data-driven Inverse Modeling from Sparse Observations
• Image Inversion and Uncertainty Quantification for Constitutive Laws of Pattern Formation
• Learning constitutive models from microstructural simulations via a non-intrusive reduced basis method
• HyperCAN: Hypernetwork-Driven Deep Parameterized Constitutive Models for Metamaterials
• ADCME: Learning Spatially-varying Physical Fields using Deep Neural Networks
• Bayesian neural networks for weak solution of PDEs with uncertainty quantification
• Inverse Modeling of Viscoelasticity Materials using Physics Constrained Learning
• A Generative Modeling Framework for Inferring Families of Biomechanical Constitutive Laws in Data-Sparse Regimes
• Physics-informed deep learning for flow and deformation in poroelastic media
• Single-test evaluation of directional elastic properties of anisotropic structured materials
• Learning orbital dynamics of binary black hole systems from gravitational wave measurements
• G2Φnet: Relating Genotype and Biomechanical Phenotype of Tissues with Deep Learning
• An equivariant neural operator for developing nonlocal tensorial constitutive models
• Solving Inverse Problems in Steady-State Navier-Stokes Equations using Deep Neural Networks
• Mechanics Informatics: A paradigm for efficiently learning constitutive models
• Multi-Constitutive Neural Network for Large Deformation Poromechanics Problem
• How machine learning can help the design and analysis of composite materials and structures?
• Distributed Machine Learning for Computational Engineering using MPI
• Frame-independent vector-cloud neural network for nonlocal constitutive modeling on arbitrary grids
• Online learning in idealized ocean gyres
• Improve Unscented Kalman Inversion With Low-Rank Approximation and Reduced-Order Model
• Living in the Physics and Machine Learning Interplay for Earth Observation
• A deep learning energy method for hyperelasticity and viscoelasticity
• Unscented Kalman Inversion: Efficient Gaussian Approximation to the Posterior Distribution
• Bayesian-EUCLID: discovering hyperelastic material laws with uncertainties
• Probabilistic partition of unity networks for high-dimensional regression problems
• Bayesian Calibration for Large-Scale Fluid Structure Interaction Problems Under Embedded/Immersed Boundary Framework
• Trust Region Method for Coupled Systems of PDE Solvers and Deep Neural Networks