FilDeep: Learning Large Deformations of Elastic-Plastic Solids with Multi-Fidelity Data

2026-01-15

AI Summary

This work proposes the first multi-fidelity deep learning framework tailored for large-deformation elastoplastic solid simulation, addressing the longstanding challenge of balancing high accuracy with computational efficiency in the presence of massive data. By integrating high- and low-fidelity datasets, the method introduces an attention mechanism–driven cross-fidelity module that effectively captures long-range physical interactions. Joint training across fidelity levels further enhances the model’s generalization capability. Extensive experiments on representative tensile and bending scenarios demonstrate that the proposed framework significantly outperforms existing approaches, achieving superior accuracy, computational efficiency, and robustness, thereby enabling direct deployment in real-world manufacturing applications.

Technology Category

• Search and Optimization: Sampling/Simulation-based Search
• Machine Learning: Deep Neural Architectures and Foundation Models
• Computer Vision: Multi-modal Vision

Application Category

• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

The scientific computation of large deformations in elastic-plastic solids is crucial in various manufacturing applications. Traditional numerical methods exhibit several inherent limitations, prompting Deep Learning (DL) as a promising alternative. The effectiveness of current DL techniques typically depends on the availability of high-quantity and high-accuracy datasets, which are yet difficult to obtain in large deformation problems. During the dataset construction process, a dilemma stands between data quantity and data accuracy, leading to suboptimal performance in the DL models. To address this challenge, we focus on a representative application of large deformations, the stretch bending problem, and propose FilDeep, a Fidelity-based Deep Learning framework for large Deformation of elastic-plastic solids. Our FilDeep aims to resolve the quantity-accuracy dilemma by simultaneously training with both low-fidelity and high-fidelity data, where the former provides greater quantity but lower accuracy, while the latter offers higher accuracy but in less quantity. In FilDeep, we provide meticulous designs for the practical large deformation problem. Particularly, we propose attention-enabled cross-fidelity modules to effectively capture long-range physical interactions across MF data. To the best of our knowledge, our FilDeep presents the first DL framework for large deformation problems using MF data. Extensive experiments demonstrate that our FilDeep consistently achieves state-of-the-art performance and can be efficiently deployed in manufacturing.

Problem

• large deformation
• elastic-plastic solids
• multi-fidelity data
• data accuracy
• data quantity

Innovation

• multi-fidelity learning
• large deformation
• elastic-plastic solids
• attention mechanism
• deep learning