Universal Fourier Neural Operators for periodic homogenization problems in linear elasticity

Abstract

Solving cell problems in homogenization is hard, and available deep-learning frameworks fail to match the speed and generality of traditional computational frameworks. More to the point, it is generally unclear what to expect of machine-learning approaches, let alone single out which approaches are promising. In the work at hand, we advocate Fourier Neural Operators (FNOs) for micromechanics, empowering them by insights from computational micromechanics methods based on the fast Fourier transform (FFT). We construct an FNO surrogate mimicking the basic scheme foundational for FFT-based methods and show that the resulting operator predicts solutions to cell problems with arbitrary stiffness distribution only subject to a material-contrast constraint up to a desired accuracy. In particular, there are no restrictions on the material symmetry like isotropy, on the number of phases and on the geometry of the interfaces between materials. Also, the provided fidelity is sharp and uniform, providing explicit guarantees leveraging our physical empowerment of FNOs. To show the desired universal approximation property, we construct an FNO explicitly that requires no training to begin with. Still, the obtained neural operator complies with the same memory requirements as the basic scheme and comes with runtimes proportional to classical FFT solvers. In particular, large-scale problems with more than 100 million voxels are readily handled. The goal of this work is to underline the potential of FNOs for solving micromechanical problems, linking FFT-based methods to FNOs. This connection is expected to provide a fruitful exchange between both worlds.

Published in Journal of the Mechanics and Physics of Solids

References in corpus (13)

• DeepONet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operators
• A numerical method for computing the overall response of nonlinear composites with complex microstructure
• A physics-informed variational DeepONet for predicting the crack path in brittle materials
• Fourier-based schemes for computing the mechanical response of composites with accurate local fields
• Accelerating a FFT-based solver for numerical homogenization of periodic media by conjugate gradients
• Unifying the design space and optimizing linear and nonlinear truss metamaterials by generative modeling
• Computational Homogenization of Polycrystals
• An overview on deep learning-based approximation methods for partial differential equations
• A proof that rectified deep neural networks overcome the curse of dimensionality in the numerical approximation of semilinear heat equations
• Int-Deep: A Deep Learning Initialized Iterative Method for Nonlinear Problems
• Filtering material properties to improve FFT-based methods for numerical homogenization
• An FFT-based method for computing the effective crack energy of a heterogeneous material on a combinatorially consistent grid
• A Spectral-based Physics-informed Finite Operator Learning for Prediction of Mechanical Behavior of Microstructures