An Energy Approach to the Solution of Partial Differential Equations in Computational Mechanics via Machine Learning: Concepts, Implementation and Applications

Abstract

Partial Differential Equations (PDE) are fundamental to model different phenomena in science and engineering mathematically. Solving them is a crucial step towards a precise knowledge of the behaviour of natural and engineered systems. In general, in order to solve PDEs that represent real systems to an acceptable degree, analytical methods are usually not enough. One has to resort to discretization methods. For engineering problems, probably the best known option is the finite element method (FEM). However, powerful alternatives such as mesh-free methods and Isogeometric Analysis (IGA) are also available. The fundamental idea is to approximate the solution of the PDE by means of functions specifically built to have some desirable properties. In this contribution, we explore Deep Neural Networks (DNNs) as an option for approximation. They have shown impressive results in areas such as visual recognition. DNNs are regarded here as function approximation machines. There is great flexibility to define their structure and important advances in the architecture and the efficiency of the algorithms to implement them make DNNs a very interesting alternative to approximate the solution of a PDE. We concentrate in applications that have an interest for Computational Mechanics. Most contributions that have decided to explore this possibility have adopted a collocation strategy. In this contribution, we concentrate in mechanical problems and analyze the energetic format of the PDE. The energy of a mechanical system seems to be the natural loss function for a machine learning method to approach a mechanical problem. As proofs of concept, we deal with several problems and explore the capabilities of the method for applications in engineering.

References in corpus (10)

• TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
• TensorFlow: A system for large-scale machine learning
• Physics Informed Deep Learning (Part I): Data-driven Solutions of Nonlinear Partial Differential Equations
• Data-driven computational mechanics
• Isogeometric analysis: an overview and computer implementation aspects
• A unified deep artificial neural network approach to partial differential equations in complex geometries
• Deep Hidden Physics Models: Deep Learning of Nonlinear Partial Differential Equations
• Non-convex Finite-Sum Optimization Via SCSG Methods
• Enhancing approximation abilities of neural networks by training derivatives
• Topological properties of the set of functions generated by neural networks of fixed size

Cited by in corpus (87)

• hp-VPINNs: Variational Physics-Informed Neural Networks With Domain Decomposition
• PhyGeoNet: Physics-Informed Geometry-Adaptive Convolutional Neural Networks for Solving Parameterized Steady-State PDEs on Irregular Domain
• A physics-informed variational DeepONet for predicting the crack path in brittle materials
• Physics-informed graph neural Galerkin networks: A unified framework for solving PDE-governed forward and inverse problems
• PhyCRNet: Physics-informed Convolutional-Recurrent Network for Solving Spatiotemporal PDEs
• Transfer learning based physics-informed neural networks for solving inverse problems in engineering structures under different loading scenarios
• A Physics-Guided Neural Network Framework for Elastic Plates: Comparison of Governing Equations-Based and Energy-Based Approaches
• Physics informed neural networks for continuum micromechanics
• Local Extreme Learning Machines and Domain Decomposition for Solving Linear and Nonlinear Partial Differential Equations
• Topology optimization of 2D structures with nonlinearities using deep learning
• Kolmogorov Arnold Informed neural network: A physics-informed deep learning framework for solving forward and inverse problems based on Kolmogorov Arnold Networks
• A Method for Representing Periodic Functions and Enforcing Exactly Periodic Boundary Conditions with Deep Neural Networks
• Multi-scale modeling in thermal conductivity of Polyurethane incorporated with Phase Change Materials using Physics-Informed Neural Networks
• Theory-guided hard constraint projection (HCP): a knowledge-based data-driven scientific machine learning method
• Physics-Informed Neural Network Method for Forward and Backward Advection-Dispersion Equations
• The Neural Particle Method -- An Updated Lagrangian Physics Informed Neural Network for Computational Fluid Dynamics
• Sequential Deep Operator Networks (S-DeepONet) for Predicting Full-field Solutions Under Time-dependent Loads
• Stochastic analysis of heterogeneous porous material with modified neural architecture search (NAS) based physics-informed neural networks using transfer learning
• Mixed formulation of physics-informed neural networks for thermo-mechanically coupled systems and heterogeneous domains
• SPINN: Sparse, Physics-based, and partially Interpretable Neural Networks for PDEs
• A deep learning energy-based method for classical elastoplasticity
• CENN: Conservative energy method based on neural networks with subdomains for solving variational problems involving heterogeneous and complex geometries
• Physics-informed radial basis network (PIRBN): A local approximating neural network for solving nonlinear PDEs
• An overview on deep learning-based approximation methods for partial differential equations
• Enhanced physics-informed neural networks for hyperelasticity
• Solving Forward and Inverse Problems of Contact Mechanics using Physics-Informed Neural Networks
• Probabilistic Deep Learning for Real-Time Large Deformation Simulations
• Analysis of three dimensional potential problems in non-homogeneous media with physics-informed deep collocation method using material transfer learning and sensitivity analysis
• Integrated Finite Element Neural Network (I-FENN) for non-local continuum damage mechanics
• BINN: A deep learning approach for computational mechanics problems based on boundary integral equations
• On Computing the Hyperparameter of Extreme Learning Machines: Algorithm and Application to Computational PDEs, and Comparison with Classical and High-Order Finite Elements
• Deep energy method in topology optimization applications
• MAgNET: A Graph U-Net Architecture for Mesh-Based Simulations
• On the use of graph neural networks and shape-function-based gradient computation in the deep energy method
• DCEM: A deep complementary energy method for solid mechanics
• A Modified Batch Intrinsic Plasticity Method for Pre-training the Random Coefficients of Extreme Learning Machines
• On quadrature rules for solving Partial Differential Equations using Neural Networks
• Reduced and All-at-Once Approaches for Model Calibration and Discovery in Computational Solid Mechanics
• A finite element-based physics-informed operator learning framework for spatiotemporal partial differential equations on arbitrary domains
• Physics-informed Deep Learning for Muscle Force Prediction with Unlabeled sEMG Signals
• Error estimates of residual minimization using neural networks for linear PDEs
• On the Use of Neural Networks for Full Waveform Inversion
• Physics informed deep learning for computational elastodynamics without labeled data
• Piezoelectric modulus prediction using machine learning and graph neural networks
• Applications of Scientific Machine Learning for the Analysis of Functionally Graded Porous Beams
• Numerical Approximation of Partial Differential Equations by a Variable Projection Method with Artificial Neural Networks
• Convolution, aggregation and attention based deep neural networks for accelerating simulations in mechanics
• Lab-scale Vibration Analysis Dataset and Baseline Methods for Machinery Fault Diagnosis with Machine Learning
• Exact imposition of boundary conditions with distance functions in physics-informed deep neural networks
• Learning constitutive models from microstructural simulations via a non-intrusive reduced basis method
• Variational operator learning: A unified paradigm marrying training neural operators and solving partial differential equations
• A priori and a posteriori error estimates for the Deep Ritz method applied to the Laplace and Stokes problem
• I-FENN for thermoelasticity based on physics-informed temporal convolutional network (PI-TCN)
• Bayesian neural networks for weak solution of PDEs with uncertainty quantification
• Towards fast weak adversarial training to solve high dimensional parabolic partial differential equations using XNODE-WAN
• Neural Networks to solve Partial Differential Equations: a Comparison with Finite Elements
• I-FENN with Temporal Convolutional Networks: expediting the load-history analysis of non-local gradient damage propagation
• Training multi-objective/multi-task collocation physics-informed neural network with student/teachers transfer learnings
• Multiple scattering simulation via physics-informed neural networks
• Fast Evaluation of Finite Element Weak Forms Using Python Tensor Contraction Packages
• Physics-informed attention-based neural network for solving non-linear partial differential equations
• A mixed formulation for physics-informed neural networks as a potential solver for engineering problems in heterogeneous domains: comparison with finite element method
• Physics-informed discrete element modeling for the bandgap engineering of cylinder chains
• Learning the random variables in Monte Carlo simulations with stochastic gradient descent: Machine learning for parametric PDEs and financial derivative pricing
• The mixed deep energy method for resolving concentration features in finite strain hyperelasticity
• Geometry-aware framework for deep energy method: an application to structural mechanics with hyperelastic materials
• Deep Physics Corrector: A physics enhanced deep learning architecture for solving stochastic differential equations
• Meshless physics-informed deep learning method for three-dimensional solid mechanics
• Monte Carlo Neural PDE Solver for Learning PDEs via Probabilistic Representation
• Phase-field modeling of microstructure evolution: Recent applications, perspectives and challenges
• Variational PINNs with tree-based integration and boundary element data in the modeling of multi-phase architected materials
• Physics-Informed Graph-Mesh Networks for PDEs: A hybrid approach for complex problems
• N-Adaptive Ritz Method: A Neural Network Enriched Partition of Unity for Boundary Value Problems
• Numerical Solution and Bifurcation Analysis of Nonlinear Partial Differential Equations with Extreme Learning Machines
• A divide and conquer method for symbolic regression
• Numerical simulation of transient heat conduction with moving heat source using Physics Informed Neural Networks
• Integrated intelligent Jaya Runge-Kutta method for solving Falkner-Skan equations for Various Wedge Angles
• A deep learning energy method for hyperelasticity and viscoelasticity
• Physics-Informed Kolmogorov-Arnold Networks for multi-material elasticity problems in electronic packaging
• A Physics-Data-Driven Bayesian Method for Heat Conduction Problems
• Active learning with physics-informed neural networks for optimal sensor placement in deep tunneling through transversely isotropic elastic rocks
• Developing Artificial Mechanics Intuitions from Extremely Small Data
• Multi-patch isogeometric neural solver for partial differential equations on computer-aided design domains
• A Variational Kolosov--Muskhelishvili Network for Elasticity and Fracture
• Paradigm Shift Through the Integration of Physical Methodology and Data Science
• Physics-informed neural networks for solving thermo-mechanics problems of functionally graded material
• Acquiring elastic properties of thin composite structure from vibrational testing data