Exploring the 3D architectures of deep material network in data-driven multiscale mechanics

01/02/2019
by   Zeliang Liu, et al.
0

This paper extends the deep material network (DMN) proposed by Liu et al. (2018) to tackle general 3-dimensional (3D) problems with arbitrary material and geometric nonlinearities. The global framework of DMN for mechanistic data-driven multiscale material modeling is discussed in detail on the offline training and online extrapolation stages. Analytical solutions of the 3D building block with a two-layer structure in both small- and finite-strain formulations are derived based on interfacial equilibrium conditions and kinematic constraints. With linear elastic data generated by direct numerical simulations on a representative volume element (RVE), the network can be effectively trained in offline stage using stochastic gradient descent and advanced model compression algorithms. Efficiency and accuracy of DMN on addressing the long-standing 3D RVE challenges with complex morphologies and material laws are validated through numerical experiments, including 1) hyperelastic particle-reinforced rubber composite with Mullins effect; 2) polycrystalline materials with rate-dependent crystal plasticity; 3) carbon fiber reinforced polymer (CFRP) composites with fiber anisotropic elasticity and matrix plasticity. In particular, we demonstrate a three-scale homogenization procedure of CFRP system by concatenating the microscale and mesoscale material networks. The complete learning and extrapolation procedures of DMN establish a reliable data-driven framework for multiscale material modeling and design.

READ FULL TEXT
07/25/2018

A Deep Material Network for Multiscale Topology Learning and Accelerated Nonlinear Modeling of Heterogeneous Materials

The discovery of efficient and accurate descriptions for the macroscopic...
08/07/2019

Deep material network with cohesive layers: Multi-stage training and interfacial failure analysis

A fundamental issue in multiscale materials modeling and design is the c...
09/15/2022

Physically recurrent neural networks for path-dependent heterogeneous materials: embedding constitutive models in a data-driven surrogate

Driven by the need to accelerate numerical simulations, the use of machi...
01/18/2021

Cell division in deep material networks applied to multiscale strain localization modeling

Despite the increasing importance of strain localization modeling (e.g.,...
10/19/2020

A General, Implicit, Large-Strain FE^2 Framework for the Simulation of Dynamic Problems on Two Scales

In this paper we present a fully-coupled, two-scale homogenization metho...
08/29/2019

Multiscale modeling of vascularized tissues via non-matching immersed methods

We consider a multiscale approach based on immersed methods for the effi...
01/26/2021

Data-Driven simulation of inelastic materials using structured data sets, tangent space information and transition rules

Data-driven computational mechanics replaces phenomenological constituti...