Learning Deep Implicit Fourier Neural Operators (IFNOs) with Applications to Heterogeneous Material Modeling

Abstract

Constitutive modeling based on continuum mechanics theory has been a classical approach for modeling the mechanical responses of materials. However, when constitutive laws are unknown or when defects and/or high degrees of heterogeneity are present, these classical models may become inaccurate. In this work, we propose to use data-driven modeling, which directly utilizes high-fidelity simulation and/or experimental measurements to predict a material's response without using conventional constitutive models. Specifically, the material response is modeled by learning the implicit mappings between loading conditions and the resultant displacement and/or damage fields, with the neural network serving as a surrogate for a solution operator. To model the complex responses due to material heterogeneity and defects, we develop a novel deep neural operator architecture, which we coin as the Implicit Fourier Neural Operator (IFNO). In the IFNO, the increment between layers is modeled as an integral operator to capture the long-range dependencies in the feature space. As the network gets deeper, the limit of IFNO becomes a fixed point equation that yields an implicit neural operator and naturally mimics the displacement/damage fields solving procedure in material modeling problems. We demonstrate the performance of our proposed method for a number of examples, including hyperelastic, anisotropic and brittle materials. As an application, we further employ the proposed approach to learn the material models directly from digital image correlation (DIC) tracking measurements, and show that the learned solution operators substantially outperform the conventional constitutive models in predicting displacement fields.

References in corpus (17)

• DeepONet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operators
• Machine learning and the physical sciences
• Deep Potential Molecular Dynamics: a scalable model with the accuracy of quantum mechanics
• Data-driven computational mechanics
• Bayesian Deep Convolutional Encoder-Decoder Networks for Surrogate Modeling and Uncertainty Quantification
• Prediction of Aerodynamic Flow Fields Using Convolutional Neural Networks
• Solving ill-posed inverse problems using iterative deep neural networks
• Ab-Initio Solution of the Many-Electron Schrödinger Equation with Deep Neural Networks
• A physics-informed variational DeepONet for predicting the crack path in brittle materials
• Physics-Informed Neural Networks for Multiphysics Data Assimilation with Application to Subsurface Transport
• A deep material network for multiscale topology learning and accelerated nonlinear modeling of heterogeneous materials
• Physics-Informed Probabilistic Learning of Linear Embeddings of Non-linear Dynamics With Guaranteed Stability
• Model-Free Data-Driven Methods in Mechanics: Material Data Identification and Solvers
• Interfacing Finite Elements with Deep Neural Operators for Fast Multiscale Modeling of Mechanics Problems
• Fast simulation of Gaussian random fields
• Simulating progressive intramural damage leading to aortic dissection using an operator-regression neural network
• A data-driven peridynamic continuum model for upscaling molecular dynamics

Cited by in corpus (2)

• SVD Perspectives for Augmenting DeepONet Flexibility and Interpretability
• Improved generalization with deep neural operators for engineering systems: Path towards digital twin