Data-driven physics-constrained recurrent neural networks for multiscale damage modeling of metallic alloys with process-induced porosity

DOI10.1007/S00466-023-02429-1MaRDI QIDQ6584871zbMATHFDO

Authors Shiguang Deng, Shirin Hosseinmardi, Libo Wang, Diran Apelian, Ramin Bostanabad

Publication date 8 August 2024

Published in Computational Mechanics (Search for Journal in Brave)

zbMATH Keywords

path dependencemicroscale simulationdeep learning modelirreversible elasto-plastic hardening/softeningtraining data generation

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Artificial neural networks and deep learning (68T07) Fluid-solid interactions (including aero- and hydro-elasticity, porosity, etc.) (74F10) Anelastic fracture and damage (74R20) Numerical and other methods in solid mechanics (74S99)

Recommendations

• A deep material network for multiscale topology learning and accelerated nonlinear modeling of heterogeneous materials
• 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
• Exploring the 3D architectures of deep material network in data-driven multiscale mechanics
• Deep autoencoders for physics-constrained data-driven nonlinear materials modeling

Cites work

• scientific article; zbMATH DE number 1322734 (Why is no real title available?)
• A PCE-based multiscale framework for the characterization of uncertainties in complex systems
• A consistent characteristic length for smeared cracking models
• A finite element method for crack growth without remeshing
• A multiscale multi-permeability poroplasticity model linked by recursive homogenizations and deep learning
• A physics-informed deep learning framework for inversion and surrogate modeling in solid mechanics
• A recurrent neural network-accelerated multi-scale model for elasto-plastic heterogeneous materials subjected to random cyclic and non-proportional loading paths
• Accelerating multiscale finite element simulations of history-dependent materials using a recurrent neural network
• Accurate cyclic plastic analysis using a neural network material model
• An implicit/explicit integration scheme to increase computability of nonlinear material and contact/friction problems
• Clustering discretization methods for generation of material performance databases in machine learning and design optimization
• Deep learning
• Directional distortional hardening in metal plasticity within thermodynamics
• Efficient prediction of the effective nonlinear properties of porous material by FEM-cluster based analysis (FCA)
• Energy dissipation analysis of elastic-plastic materials
• From virtual clustering analysis to self-consistent clustering analysis: a mathematical study
• Latent map Gaussian processes for mixed variable metamodeling
• Mechanistically informed data-driven modeling of cyclic plasticity via artificial neural networks
• Microstructural material database for self-consistent clustering analysis of elastoplastic strain softening materials
• Modeling and simulation of quasi-brittle failure with continuous anisotropic stress-based gradient-enhanced damage models
• Multi-fidelity cost-aware Bayesian optimization
• Multidomain Topology Optimization for Structural and Material Designs
• Multilayer feedforward networks are universal approximators
• Multiscale computational homogenization: review and proposal of a new enhanced-first-order method
• Multiscale methods for composites: A review
• Multiscale modeling of nonlinear electric conductivity in graphene-reinforced nanocomposites taking into account tunnelling effect
• Non-planar 3D crack growth by the extended finite element and level sets-Part I: Mechanical model
• Numerical modelling of crack propagation: automatic remeshing and comparison of different criteria.
• Probabilistic neural data fusion for learning from an arbitrary number of multi-fidelity data sets
• Reduced-order multiscale modeling of plastic deformations in 3D alloys with spatially varying porosity by deflated clustering analysis
• Self-consistent clustering analysis: an efficient multi-scale scheme for inelastic heterogeneous materials
• Smart constitutive laws: inelastic homogenization through machine learning
• Strain- and stress-based continuum damage models. I. Formulation
• The phenomenon of rupture and flow in solids
• Transformation field analysis of inelastic composite materials
• Uncertainty quantification in multiscale simulation of woven fiber composites
• Unified analysis of enriched finite elements for modeling cohesive cracks
• \(FE^2\) multiscale approach for modelling the elastoviscoplastic behaviour of long fibre SiC/Ti composite materials

This page was built for publication: Data-driven physics-constrained recurrent neural networks for multiscale damage modeling of metallic alloys with process-induced porosity

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6584871)