Deep multimodal autoencoder for crack criticality assessment

DOI10.1002/NME.6905MaRDI QIDQ6089256zbMATH OpenFDO

Authors D. Ryckelynck, J. Besson, François Willot

Publication date 17 November 2023

Published in International Journal for Numerical Methods in Engineering (Search for Journal in Brave)

zbMATH Keywords

transfer learningfinite element methoddigital twinCNNmultimodal autoencoder

Mathematics Subject Classification ID

Material properties given special treatment (74Exx) Plastic materials, materials of stress-rate and internal-variable type (74Cxx)

Recommendations

• Machine learning aided phase field method for fracture mechanics
• A physics-informed variational DeepONet for predicting crack path in quasi-brittle materials
• Parametrized reduced order modeling for cracked solids
• Deep learning phase‐field model for brittle fractures
• A nonlocal energy‐informed neural network for isotropic elastic solids with cracks under thermomechanical loads

Cites work

• scientific article; zbMATH DE number 3596197 (Why is no real title available?)
• scientific article; zbMATH DE number 1487152 (Why is no real title available?)
• A machine learning based plasticity model using proper orthogonal decomposition
• Anisotropic additive plasticity in the logarithmic strain space: Modular kinematic formulation and implementation based on incremental minimization principles for standard materials.
• Large scale object-oriented finite element code design
• Model reduction of dynamical systems on nonlinear manifolds using deep convolutional autoencoders
• Modern multidimensional scaling. Theory and applications.
• Multidimensional scaling and visualization of patterns in distribution of nontrivial zeros of the zeta-function
• Non-convergence of stochastic gradient descent in the training of deep neural networks
• Object-oriented programming applied to the finite element method. I: General concepts
• Object-oriented programming applied to the finite element method. II: Application to material behaviors.
• Polymorphic constitutive equations in finite element codes
• Precise Hausdorff distance computation between polygonal meshes
• Reducing the Dimensionality of Data with Neural Networks

Cited in

(1)

• Comparison of machine learning methods for crack localization

This page was built for publication: Deep multimodal autoencoder for crack criticality assessment

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6089256)