CEAINov 10, 2024

Foundation Model for Composite Microstructures: Reconstruction, Stiffness, and Nonlinear Behavior Prediction

arXiv:2411.06565v48 citationsh-index: 4Materials & Design
Originality Incremental advance
AI Analysis

This work addresses the challenge of efficient material property prediction for composite materials, offering a novel foundation model approach that is incremental in applying existing self-supervised methods to a new domain.

The paper tackles the problem of predicting material properties from composite microstructure images by introducing the Material Masked Autoencoder (MMAE), a self-supervised Vision Transformer pretrained on a large dataset, which achieves transferable latent representations for tasks like predicting stiffness components and inferring nonlinear stress-strain responses.

We present the Material Masked Autoencoder (MMAE), a self-supervised Vision Transformer pretrained on a large corpus of short-fiber composite images via masked image reconstruction. The pretrained MMAE learns latent representations that capture essential microstructural features and are broadly transferable across tasks. We demonstrate two key applications: (i) predicting homogenized stiffness components through fine-tuning on limited data, and (ii) inferring physically interpretable parameters by coupling MMAE with an interaction-based material network (IMN), thereby enabling extrapolation of nonlinear stress-strain responses. These results highlight the promise of microstructure foundation models and lay the groundwork for future extensions to more complex systems, such as 3D composites and experimental datasets.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes