A surrogate model for computational homogenization of elastostatics at finite strain using high‐dimensional model representation‐based neural network

Abstract

We propose a surrogate model for two-scale computational homogenization of elastostatics at finite strains. The macroscopic constitutive law is made numerically available via an explicit formulation of the associated macroenergy density. This energy density is constructed by using a neural network architecture that mimics a high-dimensional model representation. The database for training this network is assembled through solving a set of microscopic boundary value problems with the prescribed macroscopic deformation gradients (input data) and subsequently retrieving the corresponding averaged energies (output data). Therefore, the two-scale computational procedure for nonlinear elasticity can be broken down into two solvers for microscopic and macroscopic equilibrium equations that work separately in two stages, called the offline and online stages. The finite element method is employed to solve the equilibrium equation at the macroscale. As for microscopic problems, an FFT-based collocation method is applied in tandem with the Newton-Raphson iteration and the conjugate-gradient method. Particularly, we solve the microscopic equilibrium equation in the Lippmann-Schwinger form without resorting to the reference medium. In this manner, the fixed-point iteration that might require quite strict numerical stability conditions in the nonlinear regime is avoided. In addition, we derive the projection operator used in the FFT-based method for homogenization of elasticity at finite strain. K E Y W O R D S computational homogenization, data-driven, FFT-based methods, nonlinear elasticity 1 INTRODUCTION Multiscale techniques are important for man-made and natural materials; one such approach is homogenization. Roughly speaking, homogenization is a rigorous version of what is known as averaging. It is a powerful tool to study the heterogeneous materials and composites. Based on the knowledge of the microstructure of materials, the objective is to Abbreviations: HDMR, high-dimensional model representation; FFT, fast Fourier transform; FEM, finite element method; NN, neural network.

Feed-Forward Neural Networks for Failure Mechanics Problems

“…DL has many architectures, especially in mechanics, and research is focused mainly on using the feed-forward neural network (FFNN), recurrent neural network (RNN), and convolutional neural network (CNN). So far, applications of these types of neural networks devoted to the field of mechanics can be seen in the recent works of [27][28][29][30][31][32][33][34][35][36][37][38][39][40][41][42][43]. A detailed description of those approaches is summarized as follows:…”

Solving Partial Differential Equations Using Deep Learning and Physical Constraints

“…(7) So far, there have been many promising applications of neural networks in computational engineering. For example, one very interesting work is that neural networks have been used to construct constitutive laws as a surrogate model replacing the two-scale computational approaches [72,73]. These valuable works will guide us in further exploring the applications of neural networks in scientific computing.…”

Optimizing the neural network hyperparameters utilizing genetic algorithm

“…‡ Corresponding author ORCID: Saeid NIKBAKHT, https://orcid.org/0000-0003-2398-3962; Timon RABCZUK, https://orcid.org/0000-0002-7150-296X c Zhejiang University Press 2021 Moreover, numerous studies using NN have been carried out. Nguyen-Thanh et al (2019) implemented a deep neural network (DNN) method to find the stress and displacement distributions through mechanical structures such as 2D and 3D cantilever beams under bending and twisting T-shaped bars. The total potential energy of the system was considered as the loss function which was minimized using Adam and limited-memory Broyden-Fletcher-Goldfarb-Shanno (L-BFGS) optimization methods.…”