Crash Assessment via Mesh-Based Graph Neural Networks and Physics-Aware Attention

TL;DR

This paper introduces hybrid mesh-based graph neural network models with physics-aware attention for fast, accurate crash simulation predictions, balancing scalar accuracy and structural interpretability.

Contribution

It proposes novel hybrid architectures combining local mesh message passing and global attention, improving the accuracy and interpretability of crash surrogate models.

Findings

Hybrid models achieve a mean RMSE of 3.20 mm on test set.

Geometry-aware attention models are competitive but may introduce local noise.

Hybrid mesh-attention models balance accuracy, physical plausibility, and interpretability.

Abstract

Full-vehicle crash simulations are computationally expensive, limiting their use in iterative design exploration. This work investigates learned hybrid surrogate models (MeshTransolver, MeshGeoTransolver, and MeshGeoFLARE) for predicting time-resolved structural deformation fields in an industrial lateral pole-impact benchmark. We evaluate whether neural surrogates can reproduce full-field crash kinematics with sufficient accuracy, spatial regularity, and structural plausibility for engineering interpretation. The proposed architectures combine local mesh message passing, geometry-aware global attention, and sparse contact-aware correction for autoregressive crash rollout. We compare mesh-based graph neural networks, attention-based geometric models, and hybrid architectures under a common training and hyperparameter configuration. The hybrid models capture both short-range structural interactions and long-range deformation patterns, while a sparse contact-aware variant assesses the effect of dynamic proximity interactions during rollout. On a 25-sample full-vehicle test set, the best hybrid model achieves a temporal mean root-mean-square error of 3.20 mm. While geometry-aware attention baselines are quantitatively competitive, qualitative side-view inspection shows they can introduce local spatial noise and deformation irregularities that complicate structural interpretation. In contrast, hybrid mesh-attention models provide the best balance between scalar accuracy, survival-space consistency, and physically interpretable displacement fields. These results suggest that crash surrogate assessment should combine global error metrics with downstream safety-relevant quantities and qualitative field inspection. The proposed methodology enables fast full-field predictions while preserving essential structural information for industrial crash-engineering analysis.