A deep learning driven pseudospectral PCE based FFT homogenization algorithm for complex microstructures

Abstract

This work is directed to uncertainty quantification of homogenized effective properties for composite materials with complex, three dimensional microstructure. The uncertainties arise in the material parameters of the single constituents as well as in the fiber volume fraction. They are taken into account by multivariate random variables. Uncertainty quantification is achieved by an efficient surrogate model based on pseudospectral polynomial chaos expansion and artificial neural networks. An artificial neural network is trained on synthetic binary voxelized unit cells of composite materials with uncertain three dimensional microstructures, uncertain linear elastic material parameters and different loading directions. The prediction goals of the artificial neural network are the corresponding effective components of the elasticity tensor, where the labels for training are generated via a fast Fourier transform based numerical homogenization method. The trained artificial neural network is then used as a deterministic solver for a pseudospectral polynomial chaos expansion based surrogate model to achieve the corresponding statistics of the effective properties. Three numerical examples deal with the comparison of the presented method to the literature as well as the application to different microstructures. It is shown, that the proposed method is able to predict central moments of interest while being magnitudes faster to evaluate than traditional approaches.

References in corpus (12)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• DeepONet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operators
• On the Convergence of Adam and Beyond
• Deep UQ: Learning deep neural network surrogate models for high dimensional uncertainty quantification
• An FFT-based Galerkin Method for Homogenization of Periodic Media
• Operator learning for predicting multiscale bubble growth dynamics
• Finite strain FFT-based non-linear solvers made simple
• A finite element perspective on non-linear FFT-based micromechanical simulations
• Dive into Deep Learning
• FFT-based homogenisation accelerated by low-rank tensor approximations
• Energy-based comparison between the Fourier--Galerkin method and the finite element method
• Generalized Joint Probability Density Function Formulation inTurbulent Combustion using DeepONet

Cited by in corpus (5)

• Physics informed neural networks for continuum micromechanics
• Deep Learning in Deterministic Computational Mechanics
• Three-dimensional microstructure generation using generative adversarial neural networks in the context of continuum micromechanics
• Two-stage 2D-to-3D reconstruction of realistic microstructures: Implementation and numerical validation by effective properties
• Inverse design of spinodoid structures using Bayesian optimization