AutoHood3D: A Multi-Modal Benchmark for Automotive Hood Design and Fluid-Structure Interaction
This dataset enables physics-aware ML development and accelerates generative-design iteration for automotive engineering, though it is incremental as it builds on existing multiphysics simulation methods.
The study introduces AutoHood3D, a high-fidelity multi-modal dataset with over 16,000 geometric variants of automotive hoods for machine learning applications in design and multiphysics surrogates, addressing limitations in existing datasets by providing time-resolved physical fields and structured prompts, and validates it with quantitative baselines showing systematic surrogate errors in displacement and force predictions.
This study presents a new high-fidelity multi-modal dataset containing 16000+ geometric variants of automotive hoods useful for machine learning (ML) applications such as engineering component design and process optimization, and multiphysics system surrogates. The dataset is centered on a practical multiphysics problem-hood deformation from fluid entrapment and inertial loading during rotary-dip painting. Each hood is numerically modeled with a coupled Large-Eddy Simulation (LES)-Finite Element Analysis (FEA), using 1.2M cells in total to ensure spatial and temporal accuracy. The dataset provides time-resolved physical fields, along with STL meshes and structured natural language prompts for text-to-geometry synthesis. Existing datasets are either confined to 2D cases, exhibit limited geometric variations, or lack the multi-modal annotations and data structures - shortcomings we address with AutoHood3D. We validate our numerical methodology, establish quantitative baselines across five neural architectures, and demonstrate systematic surrogate errors in displacement and force predictions. These findings motivate the design of novel approaches and multiphysics loss functions that enforce fluid-solid coupling during model training. By providing fully reproducible workflows, AutoHood3D enables physics-aware ML development, accelerates generative-design iteration, and facilitates the creation of new FSI benchmarks. Dataset and code URLs in Appendix.