Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Wei, Ting-Ju, Chen, Chuin-Shan
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2411.06565
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866914106822361088
author Wei, Ting-Ju
Chen, Chuin-Shan
author_facet Wei, Ting-Ju
Chen, Chuin-Shan
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2411_06565
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Foundation Model for Composite Microstructures: Reconstruction, Stiffness, and Nonlinear Behavior Prediction
Wei, Ting-Ju
Chen, Chuin-Shan
Computational Engineering, Finance, and Science
Artificial Intelligence
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.
title Foundation Model for Composite Microstructures: Reconstruction, Stiffness, and Nonlinear Behavior Prediction
topic Computational Engineering, Finance, and Science
Artificial Intelligence
url https://arxiv.org/abs/2411.06565