Deep autoencoders for physics-constrained data-driven nonlinear materials modeling
From MaRDI portal
Publication:2237774
Abstract: Physics-constrained data-driven computing is an emerging computational paradigm that allows simulation of complex materials directly based on material database and bypass the classical constitutive model construction. However, it remains difficult to deal with high-dimensional applications and extrapolative generalization. This paper introduces deep learning techniques under the data-driven framework to address these fundamental issues in nonlinear materials modeling. To this end, an autoencoder neural network architecture is introduced to learn the underlying low-dimensional representation (embedding) of the given material database. The offline trained autoencoder and the discovered embedding space are then incorporated in the online data-driven computation such that the search of optimal material state from database can be performed on a low-dimensional space, aiming to enhance the robustness and predictability with projected material data. To ensure numerical stability and representative constitutive manifold, a convexity-preserving interpolation scheme tailored to the proposed autoencoder-based data-driven solver is proposed for constructing the material state. In this study, the applicability of the proposed approach is demonstrated by modeling nonlinear biological tissues. A parametric study on data noise, data size and sparsity, training initialization, and model architectures, is also conducted to examine the robustness and convergence property of the proposed approach.
Recommendations
- Efficient multiscale modeling of heterogeneous materials using deep neural networks
- Physically recurrent neural networks for path-dependent heterogeneous materials: embedding constitutive models in a data-driven surrogate
- A deep material network for multiscale topology learning and accelerated nonlinear modeling of heterogeneous materials
- Deep learned finite elements
- A physics-informed deep learning framework for inversion and surrogate modeling in solid mechanics
- Learning nonlocal constitutive models with neural networks
- Microstructure-guided deep material network for rapid nonlinear material modeling and uncertainty quantification
- Physics-informed multi-LSTM networks for metamodeling of nonlinear structures
- Modeling the dynamics of PDE systems with physics-constrained deep auto-regressive networks
Cites work
- \(\mathrm{SO}(3)\)-invariance of informed-graph-based deep neural network for anisotropic elastoplastic materials
- A deep material network for multiscale topology learning and accelerated nonlinear modeling of heterogeneous materials
- A manifold learning approach to data-driven computational elasticity and inelasticity
- A model of incompressible isotropic hyperelastic material behavior using spline interpolations of tension-compression test data
- A multilevel finite element method (FE\(^{2}\)) to describe the response of highly nonlinear structures using generalized continua.
- A multiscale multi-permeability poroplasticity model linked by recursive homogenizations and deep learning
- A new reliability-based data-driven approach for noisy experimental data with physical constraints
- A physics-constrained data-driven approach based on locally convex reconstruction for noisy database
- A survey of parametrized variational principles and applications to computational mechanics
- A topology optimization method for geometrically nonlinear structures with meshless analysis and independent density field interpolation
- Adaptive subgradient methods for online learning and stochastic optimization
- An unsupervised data completion method for physically-based data-driven models
- Artificial neural network as an incremental nonlinear constitutive model for a finite element code.
- Artificial neural networks in numerical modelling of composites
- Data driven computing with noisy material data sets
- Data-based derivation of material response
- Data-driven computational mechanics
- Data-driven problems in elasticity
- Deep learning
- Diffusion nets
- Exploring strategies for training deep neural networks
- Finite element analysis of V-ribbed belts using neural network based hyperelastic material model
- scientific article; zbMATH DE number 1322734 (Why is no real title available?)
- Laplacian Eigenmaps for Dimensionality Reduction and Data Representation
- Learning deep architectures for AI
- Model-free data-driven computational mechanics enhanced by tensor voting
- Model-free data-driven inelasticity
- Model-free data-driven methods in mechanics: material data identification and solvers
- Non-linear version of stabilized conforming nodal integration for Galerkin mesh-free methods
- Nonlinear Dimensionality Reduction
- Nonlinear finite elements for continua and structures
- Numerical implementation of a neural network based material model in finite element analysis
- Principal component analysis.
- Reducing the Dimensionality of Data with Neural Networks
- Reproducing kernel particle methods
- Reproducing kernel particle methods for large deformation analysis of nonlinear structures
- Stability of feed forward artificial neural networks versus nonlinear structural models in high speed deformations: a critical comparison
- THE PARTITION OF UNITY METHOD
- Variational framework for distance-minimizing method in data-driven computational mechanics
- What-you-prescribe-is-what-you-get orthotropic hyperelasticity
Cited in
(42)- A non-cooperative meta-modeling game for automated third-party calibrating, validating and falsifying constitutive laws with parallelized adversarial attacks
- Exploring the 3D architectures of deep material network in data-driven multiscale mechanics
- Physics-based self-learning recurrent neural network enhanced time integration scheme for computing viscoplastic structural finite element response
- Deep learning and self-consistent field theory: a path towards accelerating polymer phase discovery
- Inside the black box: a physical basis for the effectiveness of deep generative models of amorphous materials
- On physics-informed data-driven isotropic and anisotropic constitutive models through probabilistic machine learning and space-filling sampling
- Graph neural networks for simulating crack coalescence and propagation in brittle materials
- Microstructure-guided deep material network for rapid nonlinear material modeling and uncertainty quantification
- Data-driven tissue mechanics with polyconvex neural ordinary differential equations
- Physics-informed multi-LSTM networks for metamodeling of nonlinear structures
- Theory-guided auto-encoder for surrogate construction and inverse modeling
- Bayesian neural networks for uncertainty quantification in data-driven materials modeling
- FEA-Net: a physics-guided data-driven model for efficient mechanical response prediction
- Constrained neural network training and its application to hyperelastic material modeling
- Geometric learning for computational mechanics. II: Graph embedding for interpretable multiscale plasticity
- Strain energy density as a Gaussian process and its utilization in stochastic finite element analysis: application to planar soft tissues
- Thermodynamically consistent machine-learned internal state variable approach for data-driven modeling of path-dependent materials
- Parametric reduced-order modeling enhancement for a geometrically imperfect component via hyper-reduction
- Distance-preserving manifold denoising for data-driven mechanics
- Model-free data-driven identification algorithm enhanced by local manifold learning
- Molecular dynamics inferred transfer learning models for finite‐strain hyperelasticity of monoclinic crystals: Sobolev training and validations against physical constraints
- A neural network‐enhanced reproducing kernel particle method for modeling strain localization
- Solving nonconvex energy minimization problems in martensitic phase transitions with a mesh-free deep learning approach
- Recurrent and convolutional neural networks in structural dynamics: a modified attention steered encoder-decoder architecture versus LSTM versus GRU versus TCN topologies to predict the response of shock wave-loaded plates
- Intelligent stiffness computation for plate and beam structures by neural network enhanced finite element analysis
- Spiking recurrent neural networks for neuromorphic computing in nonlinear structural mechanics
- gLaSDI: parametric physics-informed greedy latent space dynamics identification
- Computation‐with‐confidence for static elasticity: Data‐driven approach with order statistics
- Physics-based self-learning spiking neural network enhanced time-integration scheme for computing viscoplastic structural finite element response
- A neural network-based enrichment of reproducing kernel approximation for modeling brittle fracture
- A framework for self-evolving computational material models inspired by deep learning
- Neural-integrated meshfree (NIM) method: a differentiable programming-based hybrid solver for computational mechanics
- A thermodynamically consistent physics-informed deep learning material model for short fiber/polymer nanocomposites
- A multi-resolution physics-informed recurrent neural network: formulation and application to musculoskeletal systems
- N-adaptive Ritz method: a neural network enriched partition of unity for boundary value problems
- Data-driven physics-constrained recurrent neural networks for multiscale damage modeling of metallic alloys with process-induced porosity
- Data-driven micromorphic mechanics for materials with strain localization
- Physics-constrained symbolic model discovery for polyconvex incompressible hyperelastic materials
- Solving engineering eigenvalue problems with neural networks using the Rayleigh quotient
- Material-embedding physics-augmented neural networks: a first application to constitutive law parameterization
- Data-driven based stable analysis algorithm for nonlinear truss structures with geometric instabilities
- Learning constitutive relations from indirect observations using deep neural networks
This page was built for publication: Deep autoencoders for physics-constrained data-driven nonlinear materials modeling
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2237774)
