StampFormer: A Physics-Guided Material-Geometry-Coupled Multimodal Model for Rapid Prediction of Physical Fields in Sheet Metal Stamping

2026-05-12

AI Summary

This study addresses the limitations of traditional sheet metal stamping simulations, which rely on time-consuming finite element analysis (FEA), and the inability of existing surrogate models to jointly incorporate geometric and material characteristics for accurate full-field prediction. To overcome these challenges, this work proposes a physics-informed multimodal deep learning framework that, for the first time, achieves hierarchical fusion of part geometry and material constitutive responses. The approach introduces a Material-Augmented Geometry Network (MAGN) and a Hierarchical Material Embedding Injection Unit (HMEIU), effectively circumventing the material-agnostic nature of image-based models. Built upon an enhanced Swin-UNet architecture, the method achieves average relative errors below 8.5% for 2D fields—including thinning ratio, major/minor strains, and plastic strain—and a mean squared error under 1.2 mm² for 3D displacement fields in cross-beam panel stamping tasks, with each prediction completed in under one second.

Abstract

Traditional sheet metal forming relies on time-consuming and expensive Finite Element Analysis (FEA) for design validation, a process that significantly prolongs design cycles. While surrogate models offer faster iteration, current approaches have limitations: scalar-based methods cannot capture comprehensive field-based FEA results, while existing image-based models often ignore the critical role of material properties by focusing solely on geometry. To address this gap, we develop a physics-guided deep learning framework, namely StampFormer, which simultaneously uses component geometry and material stress-strain responses to predict FEA outcomes. The StampFormer framework uses three core components to process data. A Material-Augmented Geometric Network (MAGN) first fuses geometric and material data. This information is then integrated at various levels by a Hierarchical Material Embedding Injection Unit (HMEIU) before being processed by the primary network backbone, an adapted Swin-UNet. We evaluated our model on the stamping of a crossmember panel with two simulation datasets for steel and aluminium panels, and results demonstrate that StampFormer provides high-fidelity predictions of critical physical fields - including thinning, major strain, minor strain, plastic strain, and displacement - in under a second. Compared with ground truth FEA, our model achieved an average relative error of less than 8.5% on the four 2D fields and a mean squared error of less than 1.2 mm2 for the 3D displacement field. In summary, we introduce a practical and efficient framework that integrates multimodal information, namely geometry and material properties, to provide fast and accurate predictions, enabling designers to perform real-time manufacturability assessments.

Problem

• sheet metal stamping
• Finite Element Analysis
• surrogate modeling
• material-geometry coupling
• physical field prediction

Innovation

• physics-guided deep learning
• material-geometry coupling
• multimodal surrogate model
• sheet metal stamping
• field prediction