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

• URL: http://arxiv.org/abs/2605.18835v1
• Date: Wed, 13 May 2026 01:13:39 GMT
• Title: StampFormer: A Physics-Guided Material-Geometry-Coupled Multimodal Model for Rapid Prediction of Physical Fields in Sheet Metal Stamping
• Abstract summary: StampFormer is a framework that simultaneously uses component geometry and material stress-strain responses to predict FEA outcomes.<n>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.
• Score: 9.998824681546477
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• Influence of Extruded Filament Shape on Buildability in 3D Concrete Printing: A Geometry-Informed Deep Learning-FEM Approach [0.601977707672242]
  The geometric morphology of deposited filaments can significantly influence the structural performance and stability of 3D concrete-printed structures.<n>FEM-based approaches for buildability assessment represent printed layers as simplified, potentially limiting predictive accuracy.<n>This study proposes a geometry-informed modelling framework that integrates the deep-learning-based filament shape prediction tool ShapeGen3DCP.
  arXiv  Detail & Related papers  (2026-09-03T16:08:19Z)
• Robust and Interpretable Adaptation of Equivariant Materials Foundation Models via Sparsity-promoting Fine-tuning [48.04423567569116]
  We propose a sparsity-promoting fine-tuning method that selectively updates model parameters.<n>On energy and force prediction tasks, our method matches or surpasses full fine-tuning and equivariant low-rank adaptation.<n>Our results establish sparsity-promoting fine-tuning as a flexible and interpretable method for domain specialization of equivariant materials foundation models.
  arXiv  Detail & Related papers  (2026-06-17T05:10:18Z)
• CatalyticMLLM: A Graph-Text Multimodal Large Language Model for Catalytic Materials [61.546562658308005]
  We propose QE-Catalytic-V2, a unified graph--text multimodal large language model for catalytic materials.<n>It integrates property prediction and inverse design within the same model and shared representation space.<n>Under this unified framework, QE-Catalytic-V2 can not only perform reliable property prediction but also generate and screen physically feasible CIF candidates.
  arXiv  Detail & Related papers  (2026-05-17T04:31:46Z)
• SLAT-Phys: Fast Material Property Field Prediction from Structured 3D Latents [55.26273954022457]
  Estimating the material property field of 3D assets is critical for physics-based simulation, robotics, and digital twin generation.<n>We present SLAT-Phys, an end-to-end method that predicts spatially varying material property fields of 3D assets directly from a single RGB image without explicit 3D reconstruction.
  arXiv  Detail & Related papers  (2026-03-25T06:14:03Z)
• AutoHood3D: A Multi-Modal Benchmark for Automotive Hood Design and Fluid-Structure Interaction [0.0]
  The dataset is centered on a practical multiphysics problem-hood deformation from fluid entrapment and inertial loading during rotary-dip painting.<n>Each hood is numerically modeled with a coupled Large-Eddy Simulation (LES)-Finite Element Analysis (FEA) using 1.2M cells in total.<n>The dataset provides time-resolved physical fields, along with STL meshes and structured natural language prompts for text-to-geometry.
  arXiv  Detail & Related papers  (2025-11-05T14:09:03Z)
• A Foundation Model for Material Fracture Prediction [37.06207593775499]
  We present a data-driven foundation model for fracture prediction.<n>It operates across simulators, a wide range of materials, and diverse loading conditions.<n>It can be fine-tuned with minimal data on diverse downstream tasks.
  arXiv  Detail & Related papers  (2025-07-30T20:23:36Z)
• MatDecompSDF: High-Fidelity 3D Shape and PBR Material Decomposition from Multi-View Images [20.219010684946888]
  MatDecompSDF is a framework for recovering high-fidelity 3D shapes and decomposing their physically-based material properties from multi-view images.<n>Our method produces editable and relightable assets that can be seamlessly integrated into standard graphics pipelines.
  arXiv  Detail & Related papers  (2025-07-07T08:22:32Z)
• Text to Band Gap: Pre-trained Language Models as Encoders for Semiconductor Band Gap Prediction [9.325818199739759]
  We investigate transformer-based language models, including RoBERTa, T5, Llama-3, and MatSciBERT, for predicting band gaps of semiconductor materials.<n>The inputs encode key material features, such as chemical composition, crystal system, space group, and other structural and electronic properties.
  arXiv  Detail & Related papers  (2025-01-07T00:56:26Z)
• IDArb: Intrinsic Decomposition for Arbitrary Number of Input Views and Illuminations [64.07859467542664]
  Capturing geometric and material information from images remains a fundamental challenge in computer vision and graphics.<n>Traditional optimization-based methods often require hours of computational time to reconstruct geometry, material properties, and environmental lighting from dense multi-view inputs.<n>We introduce IDArb, a diffusion-based model designed to perform intrinsic decomposition on an arbitrary number of images under varying illuminations.
  arXiv  Detail & Related papers  (2024-12-16T18:52:56Z)
• PhyRecon: Physically Plausible Neural Scene Reconstruction [81.73129450090684]
  We introduce PHYRECON, the first approach to leverage both differentiable rendering and differentiable physics simulation to learn implicit surface representations. Central to this design is an efficient transformation between SDF-based implicit representations and explicit surface points. Our results also exhibit superior physical stability in physical simulators, with at least a 40% improvement across all datasets.
  arXiv  Detail & Related papers  (2024-04-25T15:06:58Z)
• FAENet: Frame Averaging Equivariant GNN for Materials Modeling [123.19473575281357]
  We introduce a flexible framework relying on frameaveraging (SFA) to make any model E(3)-equivariant or invariant through data transformations. We prove the validity of our method theoretically and empirically demonstrate its superior accuracy and computational scalability in materials modeling.
  arXiv  Detail & Related papers  (2023-04-28T21:48:31Z)
• Machine-learning accelerated identification of exfoliable two-dimensional materials [0.0]
  Two-dimensional (2D) materials have been a central focus of recent research because they host a variety of properties. It is crucial to be able to identify accurately and efficiently if bulk three-dimensional (3D) materials are formed by layers held together by a weak binding energy. We develop a machine-learning (ML) approach that, combined with a fast preliminary geometrical screening, is able to efficiently identify potentially exfoliable materials.
  arXiv  Detail & Related papers  (2022-07-18T14:48:53Z)
• How to See Hidden Patterns in Metamaterials with Interpretable Machine Learning [82.67551367327634]
  We develop a new interpretable, multi-resolution machine learning framework for finding patterns in the unit-cells of materials. Specifically, we propose two new interpretable representations of metamaterials, called shape-frequency features and unit-cell templates.
  arXiv  Detail & Related papers  (2021-11-10T21:19:02Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.