Learning constitutive models from microstructural simulations via a non-intrusive reduced basis method

Abstract

In order to optimally design materials, it is crucial to understand the structure-property relations in the material by analyzing the effect of microstructure parameters on the macroscopic properties. In computational homogenization, the microstructure is thus explicitly modeled inside the macrostructure, leading to a coupled two-scale formulation. Unfortunately, the high computational costs of such multiscale simulations often render the solution of design, optimization, or inverse problems infeasible. To address this issue, we propose in this work a non-intrusive reduced basis method to construct inexpensive surrogates for parametrized microscale problems; the method is specifically well-suited for multiscale simulations since the coupled simulation is decoupled into two independent problems: (1) solving the microscopic problem for different (loading or material) parameters and learning a surrogate model from the data; and (2) solving the macroscopic problem with the learned material model. The proposed method has three key features. First, the microscopic stress field can be fully recovered. Second, the method is able to accurately predict the stress field for a wide range of material parameters; furthermore, the derivatives of the effective stress with respect to the material parameters are available and can be readily utilized in solving optimization problems. Finally, it is more data efficient, i.e. requiring less training data, as compared to directly performing a regression on the effective stress. For the microstructures in the two test problems considered, the mean approximation error of the effective stress is as low as 0.1% despite using a relatively small training dataset. Embedded into the macroscopic problem, the reduced order model leads to an online speed up of approximately three orders of magnitude while maintaining a high accuracy as compared to the FE${}^2$ solver.

References in corpus (13)

• An Energy Approach to the Solution of Partial Differential Equations in Computational Mechanics via Machine Learning: Concepts, Implementation and Applications
• A numerical method for computing the overall response of nonlinear composites with complex microstructure
• Data-driven computational mechanics
• MOOSE: Enabling Massively Parallel Multiphysics Simulation
• Thermodynamics-based Artificial Neural Networks for constitutive modeling
• Model-Free Data-Driven Inelasticity
• Data Driven Computing with Noisy Material Data Sets
• A machine learning based plasticity model using proper orthogonal decomposition
• Learning Constitutive Relations from Indirect Observations Using Deep Neural Networks
• Learning Constitutive Relations using Symmetric Positive Definite Neural Networks
• A deep learning framework for solution and discovery in solid mechanics
• Micromorphic Computational Homogenization for Mechanical Metamaterials with Patterning Fluctuation Fields
• Standardized Non-Intrusive Reduced Order Modeling Using Different Regression Models With Application to Complex Flow Problems

Cited by in corpus (7)

• Physically recurrent neural networks for path-dependent heterogeneous materials: embedding constitutive models in a data-driven surrogate
• A Generative Modeling Framework for Inferring Families of Biomechanical Constitutive Laws in Data-Sparse Regimes
• A reduced order model for geometrically parameterized two-scale simulations of elasto-plastic microstructures under large deformations
• Similarity Equivariant Graph Neural Networks for Homogenization of Metamaterials
• G2Φnet: Relating Genotype and Biomechanical Phenotype of Tissues with Deep Learning
• Learning constitutive models from microstructural simulations via a non-intrusive reduced basis method: Extension to geometrical parameterizations
• Bayesian learning with Gaussian processes for low-dimensional representations of time-dependent nonlinear systems