An FE-DMN method for the multiscale analysis of fiber reinforced plastic components

by   Sebastian Gajek, et al.

In this work, we propose a fully coupled multiscale strategy for components made from short fiber reinforced composites, where each Gauss point of the macroscopic finite element model is equipped with a deep material network (DMN) which covers the different fiber orientation states varying within the component. These DMNs need to be identified by linear elastic precomputations on representative volume elements, and serve as high-fidelity surrogates for full-field simulations on microstructures with inelastic constituents. We discuss how to extend direct DMNs to account for varying fiber orientation, and propose a simplified sampling strategy which significantly speeds up the training process. To enable concurrent multiscale simulations, evaluating the DMNs efficiently is crucial. We discuss dedicated techniques for exploiting sparsity and high-performance linear algebra modules, and demonstrate the power of the proposed approach on an industrial-scale three-dimensional component. Indeed, the DMN is capable of accelerating two-scale simulations significantly, providing possible speed-ups of several magnitudes.


page 2

page 7

page 22

page 25

page 26


An FE-DMN method for the multiscale analysis of thermomechanical composites

We extend the FE-DMN method to fully coupled thermomechanical two-scale ...

Intelligent multiscale simulation based on process-guided composite database

In the paper, we present an integrated data-driven modeling framework ba...

High performance reduction technique for multiscale finite element modeling (HPR-FE2): towards industrial multiscale FE software

The authors have shown in previous contributions that reduced order mode...

Multiscale Modeling of Elasto-Plasticity in Heterogeneous Geomaterials Based on Continuum Micromechanics

In this paper, we investigate some micromechanical aspects of elasto-pla...

Reduced-Order Multiscale Modeling of Plastic Deformations in 3D Cast Metallic Alloys with Spatially Varying Microstructures

Cast aluminum alloys are increasingly utilized as light-weight materials...

Data-Driven Calibration of Multi-Fidelity Multiscale Fracture Models

Fracture modeling of metallic alloys with microscopic pores relies on mu...

A Manifold Learning Approach to Accelerate Phase Field Fracture Simulations in the Representative Volume Element

The multiscale simulation of heterogeneous materials is a popular and im...