A finite-element-inspired bipartite graph learned simulator for manufacturability assessment in large-deformation sheet forming
CAtt-BiGNN, a cross-attention-based bipartite graph neural network for coupled nodal-elemental learning, encodes FE-guided state organisation and information flow without imposing equilibrium or constitutive constraints is proposed.
Ying Zhao, Hao-Ran Li, Hao-Su Zhou et al.
· 0 citations