3 papers
cs.LG2026
Mask-Morph Graph U-Net: A Generalisable Mesh-Based Surrogate for Crashworthiness Field Prediction under Large Geometric Variation
Haoran Li, Tobias Lehrer, Yingxue Zhao +5
Nonlinear finite element crash simulations are accurate but computationally expensive, limiting their use in iterative design optimisation. Machine-learning surrogate models based…
cs.CE2026
A finite-element-inspired bipartite graph learned simulator for manufacturability assessment in large-deformation sheet forming
Yingxue Zhao, Haoran Li, Haosu Zhou +2
Explicit dynamic finite element (FE) simulations are widely used for large deformation engineering analysis, but repeated simulations remain costly during design space exploration…
cs.LG2025
Recurrent U-Net-Based Graph Neural Network (RUGNN) for Accurate Deformation Predictions in Sheet Material Forming
Yingxue Zhao, Qianyi Chen, Haoran Li +5
In recent years, various artificial intelligence-based surrogate models have been proposed to provide rapid manufacturability predictions of material forming processes. However, tr…