A deep energy method for finite deformation hyperelasticity

DOI10.1016/j.euromechsol.2019.103874zbMath1472.74213OpenAlexW2982123645WikidataQ126983614 ScholiaQ126983614MaRDI QIDQ2292258

Xiaoying Zhuang, Vien Minh Nguyen-Thanh, Timon Rabczuk

Publication date: 3 February 2020

Published in: European Journal of Mechanics. A. Solids (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.euromechsol.2019.103874

zbMATH Keywords

loss functionmachine learningartificial neural networkpotential energy minimization

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Nonlinear elasticity (74B20) Energy minimization in equilibrium problems in solid mechanics (74G65) Numerical and other methods in solid mechanics (74S99)

Related Items

Force density-informed neural network for prestress design of tensegrity structures with multiple self-stress modes ⋮ The mixed deep energy method for resolving concentration features in finite strain hyperelasticity ⋮ Simulation of the 3D hyperelastic behavior of ventricular myocardium using a finite-element based neural-network approach ⋮ Physics informed neural networks for continuum micromechanics ⋮ SEM: a shallow energy method for finite deformation hyperelasticity problems ⋮ A deep learning energy method for hyperelasticity and viscoelasticity ⋮ Prediction of Early Compressive Strength of Ultrahigh-Performance Concrete Using Machine Learning Methods ⋮ Modeling the spatiotemporal intracellular calcium dynamics in nerve cell with strong memory effects ⋮ Three ways to solve partial differential equations with neural networks — A review ⋮ Wavelet neural operator for solving parametric partial differential equations in computational mechanics problems ⋮ Enhanced physics‐informed neural networks for hyperelasticity ⋮ On the use of graph neural networks and shape‐function‐based gradient computation in the deep energy method ⋮ Physics-informed radial basis network (PIRBN): a local approximating neural network for solving nonlinear partial differential equations ⋮ Adversarial deep energy method for solving saddle point problems involving dielectric elastomers ⋮ Transfer learning based physics-informed neural networks for solving inverse problems in engineering structures under different loading scenarios ⋮ A model for rubber-like materials with three parameters obtained from a tensile test ⋮ Brain MRI Images Classifications with Deep Fuzzy Clustering and Deep Residual Network ⋮ Predicting the Pore-Pressure and Temperature of Fire-Loaded Concrete by a Hybrid Neural Network ⋮ A complete physics-informed neural network-based framework for structural topology optimization ⋮ Optimum design of nonlinear structures via deep neural network-based parameterization framework ⋮ Deep energy method in topology optimization applications ⋮ CPINet: parameter identification of path-dependent constitutive model with automatic denoising based on CNN-LSTM ⋮ Physics-informed neural network for modelling the thermochemical curing process of composite-tool systems during manufacture ⋮ Parametric deep energy approach for elasticity accounting for strain gradient effects ⋮ The neural particle method - an updated Lagrangian physics informed neural network for computational fluid dynamics ⋮ A unified-implementation of smoothed finite element method (UI-SFEM) for simulating biomechanical responses of multi-materials orthodontics ⋮ Deep autoencoder based energy method for the bending, vibration, and buckling analysis of Kirchhoff plates with transfer learning ⋮ CENN: conservative energy method based on neural networks with subdomains for solving variational problems involving heterogeneous and complex geometries ⋮ A robust unsupervised neural network framework for geometrically nonlinear analysis of inelastic truss structures

Uses Software

• L-BFGS
• FEniCS
• TensorFlow
• FLagSHyP
• PyTorch
• Adam
• DGM

Cites Work

• Unnamed Item
• Unnamed Item
• Data-driven non-linear elasticity: constitutive manifold construction and problem discretization
• Automated solution of differential equations by the finite element method. The FEniCS book
• Isogeometric analysis: CAD, finite elements, NURBS, exact geometry and mesh refinement
• The reduced model multiscale method (R3M) for the nonlinear homogenization of hyperelastic media at finite strains
• On the limited memory BFGS method for large scale optimization
• Meshless methods: a review and computer implementation aspects
• Hidden physics models: machine learning of nonlinear partial differential equations
• Multilayer feedforward networks are universal approximators
• The Deep Ritz Method: a deep learning-based numerical algorithm for solving variational problems
• Two-stage data-driven homogenization for nonlinear solids using a reduced order model
• Reduced order modeling for nonlinear structural analysis using Gaussian process regression
• DGM: a deep learning algorithm for solving partial differential equations
• Isogeometric analysis: an overview and computer implementation aspects
• Self-consistent clustering analysis: an efficient multi-scale scheme for inelastic heterogeneous materials
• A framework for data-driven analysis of materials under uncertainty: countering the curse of dimensionality
• Data-driven computational mechanics
• An \textit{hp}-proper orthogonal decomposition-moving least squares approach for molecular dynamics simulation
• Computational homogenization of nonlinear elastic materials using neural networks
• Coarse-graining of multiscale crack propagation
• Multiscale aggregating discontinuities: A method for circumventing loss of material stability
• Element‐free Galerkin methods
• Neural Networks and Deep Learning
• Isogeometric Analysis
• Non-convex Optimization for Machine Learning
• Nonlinear Solid Mechanics for Finite Element Analysis: Statics