Developing a Foundation Model for Predicting Material Failure

TL;DR

This paper introduces a large-scale foundation model for predicting material failure, capable of generalizing across materials and simulation conditions, significantly improving accuracy and flexibility over traditional methods.

Contribution

The paper presents the first foundation model for material failure prediction that leverages large datasets and high parameter counts to enhance accuracy and generalization across diverse conditions.

Findings

Model scale correlates with performance improvements (loss scales as N^{-1.6}).

The model generalizes across different materials and simulation setups.

Supports diverse input formats and simulation grids.

Abstract

Understanding material failure is critical for designing stronger and lighter structures by identifying weaknesses that could be mitigated. Existing full-physics numerical simulation techniques involve trade-offs between speed, accuracy, and the ability to handle complex features like varying boundary conditions, grid types, resolution, and physical models. We present the first foundation model specifically designed for predicting material failure, leveraging large-scale datasets and a high parameter count (up to 3B) to significantly improve the accuracy of failure predictions. In addition, a large language model provides rich context embeddings, enabling our model to make predictions across a diverse range of conditions. Unlike traditional machine learning models, which are often tailored to specific systems or limited to narrow simulation conditions, our foundation model is designed to generalize across different materials and simulators. This flexibility enables the model to handle a range of material properties and conditions, providing accurate predictions without the need for retraining or adjustments for each specific case. Our model is capable of accommodating diverse input formats, such as images and varying simulation conditions, and producing a range of outputs, from simulation results to effective properties. It supports both Cartesian and unstructured grids, with design choices that allow for seamless updates and extensions as new data and requirements emerge. Our results show that increasing the scale of the model leads to significant performance gains (loss scales as $N^{-1.6}$, compared to language models which often scale as $N^{-0.5}$).