A graph-based probabilistic geometric deep learning framework with online enforcement of physical constraints to predict the criticality of defects in porous materials
Preprint
Abstract
Stress prediction in porous materials and structures is challenging due to the high computational cost associated with direct numerical simulations. Convolutional Neural Network (CNN) based architectures have recently been proposed as surrogates to approximate and extrapolate the solution of such multiscale simulations. These methodologies are usually limited to 2D problems due to the high computational cost of 3D voxel based CNNs. We propose a novel geometric learning approach based on a Graph Neural Network (GNN) that efficiently deals with three-dimensional problems by performing convolutions over 2D surfaces only. Following our previous developments using pixel-based CNN, we train the GNN to automatically add local fine-scale stress corrections to an inexpensively computed coarse stress prediction in the porous structure of interest. Our method is Bayesian and generates densities of stress fields, from which credible intervals may be extracted. As a second scientific contribution, we propose to improve the extrapolation ability of our network by deploying a strategy of online physics-based corrections. Specifically, we condition the posterior predictions of our probabilistic predictions to satisfy partial equilibrium at the microscale, at the inference stage. This is done using an Ensemble Kalman algorithm, to ensure tractability of the Bayesian conditioning operation. We show that this innovative methodology allows us to alleviate the effect of undesirable biases observed in the outputs of the uncorrected GNN, and improves the accuracy of the predictions in general.Keywords
All Related Versions
This publication has 36 references indexed in Scilit:
- Domain adaptation based transfer learning approach for solving PDEs on complex geometriesEngineering with Computers, 2022
- A Bayesian multiscale CNN framework to predict local stress fields in structures with microscale featuresComputational Mechanics, 2021
- Protein structure prediction using multiple deep neural networks in the 13th Critical Assessment of Protein Structure Prediction (CASP13)Proteins: Structure, Function, and Bioinformatics, 2019
- Guaranteed error bounds in homogenisation: an optimum stochastic approach to preserve the numerical separation of scalesInternational Journal for Numerical Methods in Engineering, 2016
- Gmsh: A 3‐D finite element mesh generator with built‐in pre‐ and post‐processing facilitiesInternational Journal for Numerical Methods in Engineering, 2009
- A three-scale domain decomposition method for the 3D analysis of debonding in laminatesComputational Mechanics, 2009
- Non-intrusive and exact global/local techniques for structural problems with local plasticityComputational Mechanics, 2009
- Hyper‐reduction of mechanical models involving internal variablesInternational Journal for Numerical Methods in Engineering, 2008
- General introduction to asymptotic methods2008
- Concurrent multi-scale analysis of elastic composites by a multi-level computational modelComputer Methods in Applied Mechanics and Engineering, 2004