Reproduce “BAT-NO: A Boundary-Condition-Aware Transformer Neural Operator for Crashworthiness Prediction of Vehicle Components” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Haoran Li, Yingxue Zhao, Haosu Zhou, Mustapha Ziane, Pierre Culiere, Tobias Pfaff, Nan Li
BAT-NO predicts crash deformation for a B-pillar side impact with varying shape, loading, and support stiffness. It combines boundary-aware slices for global interactions with a direct pathway that places conditions on the latent grid. On a 50-simulation validation set, its mean nodal displacement error was 0.4510 mm, versus 0.6689 mm for GINO, supporting prediction within this design space, not beyond it.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.