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

TL;DR

This paper introduces a multiscale computational approach combining finite element analysis with deep material networks to efficiently simulate fiber reinforced plastic components with varying fiber orientations, enabling faster industrial-scale predictions.

Contribution

The work develops a coupled multiscale strategy using DMNs for fiber orientation variation, with a simplified training sampling and efficient evaluation techniques for industrial applications.

Findings

Significant speed-ups in two-scale simulations.

Effective modeling of fiber orientation variations.

Successful application to an industrial-scale component.

Abstract

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.