A deep learning framework for solution and discovery in solid mechanics

Abstract

We present the application of a class of deep learning, known as Physics Informed Neural Networks (PINN), to learning and discovery in solid mechanics. We explain how to incorporate the momentum balance and constitutive relations into PINN, and explore in detail the application to linear elasticity, and illustrate its extension to nonlinear problems through an example that showcases von~Mises elastoplasticity. While common PINN algorithms are based on training one deep neural network (DNN), we propose a multi-network model that results in more accurate representation of the field variables. To validate the model, we test the framework on synthetic data generated from analytical and numerical reference solutions. We study convergence of the PINN model, and show that Isogeometric Analysis (IGA) results in superior accuracy and convergence characteristics compared with classic low-order Finite Element Method (FEM). We also show the applicability of the framework for transfer learning, and find vastly accelerated convergence during network re-training. Finally, we find that honoring the physics leads to improved robustness: when trained only on a few parameters, we find that the PINN model can accurately predict the solution for a wide range of parameters new to the network---thus pointing to an important application of this framework to sensitivity analysis and surrogate modeling.

19 pages, 14 figures

References in corpus (6)

• Adam: A Method for Stochastic Optimization
• TensorFlow: A system for large-scale machine learning
• MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems
• Solving high-dimensional partial differential equations using deep learning
• Physics-Constrained Deep Learning for High-dimensional Surrogate Modeling and Uncertainty Quantification without Labeled Data
• Learning data driven discretizations for partial differential equations

Cited by in corpus (27)

• Deep Autoencoder based Energy Method for the Bending, Vibration, and Buckling Analysis of Kirchhoff Plates
• SciANN: A Keras/Tensorflow wrapper for scientific computations and physics-informed deep learning using artificial neural networks
• Physics-Informed Neural Network for Modelling the Thermochemical Curing Process of Composite-Tool Systems During Manufacture
• Unsupervised discovery of interpretable hyperelastic constitutive laws
• Stress field prediction in fiber-reinforced composite materials using a deep learning approach
• A Physics-Guided Neural Network Framework for Elastic Plates: Comparison of Governing Equations-Based and Energy-Based Approaches
• Simulation of multi-species flow and heat transfer using physics-informed neural networks
• NN-EUCLID: deep-learning hyperelasticity without stress data
• A nonlocal physics-informed deep learning framework using the peridynamic differential operator
• Physics-Informed Neural Networks for Nonhomogeneous Material Identification in Elasticity Imaging
• Accelerated multiscale mechanics modeling in a deep learning framework
• A Physics-informed Assembly of Feed-Forward Neural Network Engines to Predict Inelasticity in Cross-Linked Polymers
• Multi-Output Physics-Informed Neural Networks for Forward and Inverse PDE Problems with Uncertainties
• An unsupervised latent/output physics-informed convolutional-LSTM network for solving partial differential equations using peridynamic differential operator
• Energy-based error bound of physics-informed neural network solutions in elasticity
• NVIDIA SimNet^{TM}: an AI-accelerated multi-physics simulation framework
• Learning constitutive models from microstructural simulations via a non-intrusive reduced basis method
• Deep learning for solution and inversion of structural mechanics and vibrations
• IDRLnet: A Physics-Informed Neural Network Library
• POD-DL-ROM: enhancing deep learning-based reduced order models for nonlinear parametrized PDEs by proper orthogonal decomposition
• The mixed deep energy method for resolving concentration features in finite strain hyperelasticity
• Physics-informed Neural Networks for Solving Inverse Problems of Nonlinear Biot's Equations: Batch Training
• From Kepler to Newton: Explainable AI for Science
• Multi-Constitutive Neural Network for Large Deformation Poromechanics Problem
• Numerical simulation of transient heat conduction with moving heat source using Physics Informed Neural Networks
• On Theory-training Neural Networks to Infer the Solution of Highly Coupled Differential Equations
• Rapid feasibility assessment of components formed through hot stamping: A deep learning approach