An energy approach to the solution of partial differential equations in computational mechanics via machine learning: concepts, implementation and applications

From MaRDI portal

Publication:2310233

Jump to:navigation, search

DOI10.1016/j.cma.2019.112790zbMath1439.74466arXiv1908.10407OpenAlexW2998847955WikidataQ126349025 ScholiaQ126349025MaRDI QIDQ2310233

Somdatta Goswami, Khader M. Hamdia, Hongwei Guo, Esteban Samaniego, Cosmin Anitescu, Xiaoying Zhuang, Vien Minh Nguyen-Thanh, Timon Rabczuk

Publication date: 6 April 2020

Published in: Computer Methods in Applied Mechanics and Engineering (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1908.10407

zbMATH Keywords

energy approach deep neural networks physics informed

Mathematics Subject Classification ID

Spectral, collocation and related methods for boundary value problems involving PDEs (65N35) Finite element methods applied to problems in solid mechanics (74S05) Energy minimization in equilibrium problems in solid mechanics (74G65) PDEs in connection with mechanics of deformable solids (35Q74)

Related Items

Recent Advances and Emerging Applications of the Singular Boundary Method for Large-Scale and High-Frequency Computational Acoustics, A method for representing periodic functions and enforcing exactly periodic boundary conditions with deep neural networks, PhyGeoNet: physics-informed geometry-adaptive convolutional neural networks for solving parameterized steady-state PDEs on irregular domain, A New Artificial Neural Network Method for Solving Schrödinger Equations on Unbounded Domains, A modified batch intrinsic plasticity method for pre-training the random coefficients of extreme learning machines, SPINN: sparse, physics-based, and partially interpretable neural networks for PDEs, The mixed deep energy method for resolving concentration features in finite strain hyperelasticity, An open-source implementation of a phase-field model for brittle fracture using Gridap in Julia, On quadrature rules for solving partial differential equations using neural networks, A general neural particle method for hydrodynamics modeling, A sample-efficient deep learning method for multivariate uncertainty qualification of acoustic-vibration interaction problems, Physics informed neural networks for continuum micromechanics, A novel hybrid machine learning framework for the prediction of diabetes with context-customized regularization and prediction procedures, SEM: a shallow energy method for finite deformation hyperelasticity problems, A mesh-free method using piecewise deep neural network for elliptic interface problems, Learning finite element convergence with the multi-fidelity graph neural network, Accelerating phase-field predictions via recurrent neural networks learning the microstructure evolution in latent space, A feed-forwarded neural network-based variational Bayesian learning approach for forensic analysis of traffic accident, A novel localized collocation solver based on a radial Trefftz basis for thermal conduction analysis in FGMs with exponential variations, Size-dependent nonlinear vibration of functionally graded composite micro-beams reinforced by carbon nanotubes with piezoelectric layers in thermal environments, Physically motivated structuring and optimization of neural networks for multi-physics modelling of solid oxide fuel cells, Nonlinear transient thermo-elastoplastic analysis of temperature-dependent FG plates using an efficient 3D meshless model, Numerical approximation of partial differential equations by a variable projection method with artificial neural networks, Probabilistic deep learning for real-time large deformation simulations, Application of Haar wavelet discretization and differential quadrature methods for free vibration of functionally graded micro-beam with porosity using modified couple stress theory, A Deep Learning Method for Elliptic Hemivariational Inequalities, Dynamic Loadings Induced Vibration of Third Order Shear Deformable FG-CNTRC Beams: Gram-Schmidt-Ritz Method, Solving flows of dynamical systems by deep neural networks and a novel deep learning algorithm, Effects of residual stress and viscous and hysteretic dampings on the stability of a spinning micro-shaft, Structural fatigue life prediction considering model uncertainties through a novel digital twin-driven approach, A physics-informed variational DeepONet for predicting crack path in quasi-brittle materials, Adaptive deep neural networks methods for high-dimensional partial differential equations, Towards fast weak adversarial training to solve high dimensional parabolic partial differential equations using XNODE-WAN, On computing the hyperparameter of extreme learning machines: algorithm and application to computational PDEs, and comparison with classical and high-order finite elements, A deep learning energy method for hyperelasticity and viscoelasticity, Size dependent torsional electro-mechanical analysis of flexoelectric micro/nanotubes, Dynamics of imperfect inhomogeneous nanoplate with exponentially-varying properties resting on viscoelastic foundation, Deep Neural Network Surrogates for Nonsmooth Quantities of Interest in Shape Uncertainty Quantification, The MLS-based numerical manifold method for Darcy flow in heterogeneous porous media, Aerothermoelastic analysis of GPL-reinforced composite lattice sandwich beams based on a refined equivalent model, Experimental and numerical analysis of hyperelastic plates using Mooney-Rivlin strain energy function and meshless collocation method, A data-driven multi-flaw detection strategy based on deep learning and boundary element method, A physics-informed neural network technique based on a modified loss function for computational 2D and 3D solid mechanics, A neural network-based approach for bending analysis of strain gradient nanoplates, Wave propagation analysis in viscoelastic Timoshenko nanobeams under surface and magnetic field effects based on nonlocal strain gradient theory, Machine Learning Surrogate Modeling for Meshless Methods: Leveraging Universal Approximation, Prediction of Early Compressive Strength of Ultrahigh-Performance Concrete Using Machine Learning Methods, Nonlocal strain gradient model for thermal buckling analysis of functionally graded nanobeams, A VDQ approach to nonlinear vibration analysis of functionally graded porous circular plates resting on elastic foundation under hygrothermal shock, Integrated finite element neural network (I-FENN) for non-local continuum damage mechanics, Wavelet neural operator for solving parametric partial differential equations in computational mechanics problems, Rapid calculation of large-scale acoustic scattering from complex targets by a dual-level fast direct solver, Adaptive quadrature/cubature rule: application to polytopes, Surrogate modeling for Bayesian inverse problems based on physics-informed neural networks, Long-time integration of parametric evolution equations with physics-informed DeepONets, A deep Fourier residual method for solving PDEs using neural networks, Transfer learning based physics-informed neural networks for solving inverse problems in engineering structures under different loading scenarios, Stochastic projection based approach for gradient free physics informed learning, QBoost for regression problems: solving partial differential equations, Deep physics corrector: a physics enhanced deep learning architecture for solving stochastic differential equations, MFLP-PINN: a physics-informed neural network for multiaxial fatigue life prediction, Deep energy method in topology optimization applications, An overview on deep learning-based approximation methods for partial differential equations, Finite element analysis of shock absorption of porous soles established by Grasshopper and UG secondary development, Geometrically nonlinear postbuckling behavior of imperfect FG-CNTRC shells under axial compression using isogeometric analysis, Isogeometric analysis of bending, vibration, and buckling behaviors of multilayered microplates based on the non-classical refined shear deformation theory, A refined quasi-3D logarithmic shear deformation theory-based effective meshfree method for analysis of functionally graded plates resting on the elastic foundation, Dual BEM for wave scattering by an H-type porous barrier with nonlinear pressure drop, A unified adaptive approach for membrane structures: form finding and large deflection isogeometric analysis, Numerical solution and bifurcation analysis of nonlinear partial differential equations with extreme learning machines, A physics-guided neural network framework for elastic plates: comparison of governing equations-based and energy-based approaches, Learning constitutive models from microstructural simulations via a non-intrusive reduced basis method, A phase-field thermomechanical framework for modeling failure and crack evolution in glass panes under fire, Free vibration response of smart sandwich plates with porous CNT-reinforced and piezoelectric layers, Parametric deep energy approach for elasticity accounting for strain gradient effects, Local extreme learning machines and domain decomposition for solving linear and nonlinear partial differential equations, A variational formulation for 2-D vibro-acoustic analysis of a circular ring in unbounded domain, The smoothed finite element method for time-dependent mechanical responses of MEE materials and structures around Curie temperature, The neural particle method - an updated Lagrangian physics informed neural network for computational fluid dynamics, \textit{hp}-VPINNs: variational physics-informed neural networks with domain decomposition, Adaptive surrogate-based harmony search algorithm for design optimization of variable stiffness composite materials, Interface immersed particle difference method for weak discontinuity in elliptic boundary value problems, Unnamed Item, A unified-implementation of smoothed finite element method (UI-SFEM) for simulating biomechanical responses of multi-materials orthodontics, Free vibration of irregular plates via indirect differential quadrature and singular convolution techniques, Analytical and meshless numerical approaches to unified gradient elasticity theory, Numerical solution of the parametric diffusion equation by deep neural networks, Mesh refinement procedures for the phase field approach to brittle fracture, Multi-fidelity meta modeling using composite neural network with online adaptive basis technique, Two novel Bessel matrix techniques to solve the squeezing flow problem between infinite parallel plates, Exact imposition of boundary conditions with distance functions in physics-informed deep neural networks, PhyCRNet: physics-informed convolutional-recurrent network for solving spatiotemporal PDEs, Physics-informed graph neural Galerkin networks: a unified framework for solving PDE-governed forward and inverse problems, A local meshless method for transient nonlinear problems: preliminary investigation and application to phase-field models, CENN: conservative energy method based on neural networks with subdomains for solving variational problems involving heterogeneous and complex geometries, A priori and a posteriori error estimates for the deep Ritz method applied to the Laplace and Stokes problem, A mixed formulation for physics-informed neural networks as a potential solver for engineering problems in heterogeneous domains: comparison with finite element method, Multi-Objective Optimization of Laminated Functionally Graded Carbon Nanotube-Reinforced Composite Plates Using Deep Feedforward Neural Networks-NSGAII Algorithm, Deep learning for gas sensing using MOFs coated weakly-coupled microbeams, Deep learning-accelerated computational framework based on physics informed neural network for the solution of linear elasticity, On the order of derivation in the training of physics-informed neural networks: case studies for non-uniform beam structures, Modeling the spatiotemporal intracellular calcium dynamics in nerve cell with strong memory effects, Physics-Informed Neural Networks for Solving Dynamic Two-Phase Interface Problems, A neural network‐enhanced reproducing kernel particle method for modeling strain localization, Enhanced physics‐informed neural networks for hyperelasticity, Deep learning phase‐field model for brittle fractures, Deep capsule encoder–decoder network for surrogate modeling and uncertainty quantification, A nonlocal energy‐informed neural network for isotropic elastic solids with cracks under thermomechanical loads, A highly accurate artificial neural networks scheme for solving higher multi‐order fractal‐fractional differential equations based on generalized Caputo derivative, A stepwise physics‐informed neural network for solving large deformation problems of hypoelastic materials, Phase-field DeepONet: physics-informed deep operator neural network for fast simulations of pattern formation governed by gradient flows of free-energy functionals, On the use of graph neural networks and shape‐function‐based gradient computation in the deep energy method, BINN: a deep learning approach for computational mechanics problems based on boundary integral equations, On the use of neural networks for full waveform inversion, Physics-informed radial basis network (PIRBN): a local approximating neural network for solving nonlinear partial differential equations, Physically informed deep homogenization neural network for unidirectional multiphase/multi-inclusion thermoconductive composites, Topology optimization of light structures using the natural neighbour radial point interpolation method, Physics informed WNO, A novel physics-informed deep learning strategy with local time-updating discrete scheme for multi-dimensional forward and inverse consolidation problems, Adversarial deep energy method for solving saddle point problems involving dielectric elastomers, A nonlocal strain gradient model for buckling analysis of laminated composite nanoplates using CLPT and TSDT, Deep convolutional Ritz method: parametric PDE surrogates without labeled data, A posteriori error control of approximate solutions to boundary value problems found by neural networks, Regularized singular boundary method for calculating wave forces on three-dimensional large offshore structure, A Novel Deep Neural Network Algorithm for the Helmholtz Scattering Problem In the Unbounded Domain, Label-free learning of elliptic partial differential equation solvers with generalizability across boundary value problems, Physics-informed neural network frameworks for crack simulation based on minimized peridynamic potential energy, A connection element method: both a new computational method and a physical data-driven framework -- take subsurface two-phase flow as an example, Convolution hierarchical deep-learning neural network (C-HiDeNN) with graphics processing unit (GPU) acceleration, Divide and Conquer: A Quick Scheme for Symbolic Regression, Brain MRI Images Classifications with Deep Fuzzy Clustering and Deep Residual Network, Distributed PINN for Linear Elasticity — A Unified Approach for Smooth, Singular, Compressible and Incompressible Media, Predicting the Pore-Pressure and Temperature of Fire-Loaded Concrete by a Hybrid Neural Network, A Machine Learning-Based Approach for the Design of Lower Limb Exoskeleton, Engineered Interphase Mechanics in Single Lap Joints: Analytical and PINN Formulations, Multiscale Modeling of Metal-Ceramic Spatially Tailored Materials via Gaussian Process Regression and Peridynamics, An Assumed Strain Finite Element for Composite Plates Analysis, Optimization Design of Laminated Functionally Carbon Nanotube-Reinforced Composite Plates Using Deep Neural Networks and Differential Evolution, Learning the random variables in Monte Carlo simulations with stochastic gradient descent: Machine learning for parametric PDEs and financial derivative pricing, The anisotropic graph neural network model with multiscale and nonlinear characteristic for turbulence simulation, A neural network-based enrichment of reproducing kernel approximation for modeling brittle fracture, Reduced order isogeometric boundary element methods for CAD-integrated shape optimization in electromagnetic scattering, A novel numerical approach for the stability of nanobeam exposed to hygro‐thermo‐magnetic environment embedded in elastic foundation, A complete physics-informed neural network-based framework for structural topology optimization, A weighted-upwind generalized finite difference (WU-GFD) scheme with high-order accuracy for solving convection-dominated problems, Error assessment of an adaptive finite elements -- neural networks method for an elliptic parametric PDE

Uses Software

Cites Work

Retrieved from "https://portal.mardi4nfdi.de/w/index.php?title=Publication:2310233&oldid=14898533"