Recurrent U-Net-Based Graph Neural Network (RUGNN) for Accurate Deformation Predictions in Sheet Material Forming

2025-07-10

AI Summary

Conventional AI surrogate models struggle to capture complex 3D spatial relationships and temporal dynamics in sheet metal forming, while lacking permutation invariance. Method: This paper proposes RUGNN, a graph neural network (GNN)-based surrogate model. It incorporates GRUs to model temporal deformation evolution; designs U-Net–style graph down-sampling and up-sampling modules to capture long-range spatial dependencies; and introduces a novel “node-to-face” contact representation to significantly accelerate large-scale contact computation. Results: Evaluated on cold and hot forming of aluminum alloys, RUGNN achieves highly accurate, multi-step deformation field predictions closely matching finite element simulations. It substantially outperforms multiple baseline GNN models in prediction accuracy, demonstrating superior precision, generalizability, and engineering applicability for formability prediction.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

Abstract

In recent years, various artificial intelligence-based surrogate models have been proposed to provide rapid manufacturability predictions of material forming processes. However, traditional AI-based surrogate models, typically built with scalar or image-based neural networks, are limited in their ability to capture complex 3D spatial relationships and to operate in a permutation-invariant manner. To overcome these issues, emerging graph-based surrogate models are developed using graph neural networks. This study developed a new graph neural network surrogate model named Recurrent U Net-based Graph Neural Network (RUGNN). The RUGNN model can achieve accurate predictions of sheet material deformation fields across multiple forming timesteps. The RUGNN model incorporates Gated Recurrent Units (GRUs) to model temporal dynamics and a U-Net inspired graph-based downsample/upsample mechanism to handle spatial long-range dependencies. A novel 'node-to-surface' contact representation method was proposed, offering significant improvements in computational efficiency for large-scale contact interactions. The RUGNN model was validated using a cold forming case study and a more complex hot forming case study using aluminium alloys. Results demonstrate that the RUGNN model provides accurate deformation predictions closely matching ground truth FE simulations and outperforming several baseline GNN architectures. Model tuning was also performed to identify suitable hyperparameters, training strategies, and input feature representations. These results demonstrate that RUGNN is a reliable approach to support sheet material forming design by enabling accurate manufacturability predictions.

Problem

• Predicts sheet material deformation fields accurately
• Overcomes limitations of traditional AI surrogate models
• Improves computational efficiency for contact interactions

Innovation

• Recurrent U-Net-based GNN for deformation predictions
• GRUs and U-Net handle temporal and spatial dynamics
• Node-to-surface method improves contact computation efficiency