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

2024/11/10 by Ting-Ju Wei, Wei, Ting-Ju, Chuin-Shan +1 · 1 citation
Materials Science · #Artificial Intelligence (cs.AI) #Computational Engineering #FOS: Computer and information sciences #Finance #Material Properties and Applications #and Science (cs.CE)

paper · pdf · doi:10.48550/arxiv.2411.06565

openalex publication_date 2024/11/10 · openalex created_date 2024/11/15 · openalex updated_date 2026/08/04

Abstract

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.

Cited by

• A Parametric Multiscale Surrogate Framework Based on Texture-Generalizable Deep Material Networks for Polycrystal Modeling

Related

• Machine learning of evolving physics-based material models for multiscale solid mechanics
• Micrometer: Micromechanics Transformer for Predicting Mechanical Responses of Heterogeneous Materials
• Efficient Nonlinear Multiscale Prediction for Unseen Polycrystalline Textures via Self-Supervised Microstructure Pretraining
• Intelligent multiscale simulation based on process-guided composite database
• Physically Recurrent Neural Networks for Computational Homogenization of Composite Materials with Microscale Debonding