Toward Generalizable Graph Learning for 3D Engineering AI: Explainable Workflows for CAE Mode Shape Classification and CFD Field Prediction

TL;DR

This paper introduces a graph learning framework using GNNs for 3D engineering tasks like CAE mode classification and CFD prediction, emphasizing explainability, reusability, and efficiency.

Contribution

It presents a physics-aware graph representation and GNN-based workflow tailored for heterogeneous 3D engineering data, supporting classification and prediction with explainability.

Findings

Region-aware BiW graph enables explainable mode classification.

Physics-informed surrogate accurately predicts pressure and WSS.

Symmetry-preserving down sampling reduces computational cost without losing accuracy.

Abstract

Automotive engineering development increasingly relies on heterogeneous 3D data, including finite element (FE) models, body-in-white (BiW) representations, CAD geometry, and CFD meshes. At the same time, engineering teams face growing pressure to shorten development cycles, improve performance and accelerate innovation. Although artificial intelligence (AI) is increasingly explored in this domain, many current methods remain task-specific, difficult to interpret, and hard to reuse across development stages. This paper presents a practical graph learning framework for 3D engineering AI, in which heterogeneous engineering assets are converted into physics-aware graph representations and processed by Graph Neural Networks (GNNs). The framework is designed to support both classification and prediction tasks. The framework is validated on two automotive applications: CAE vibration mode shape classification and CFD aerodynamic field prediction. For CAE vibration mode classification, a region-aware BiW graph supports explainable mode classification across vehicle and FE variants under label scarcity. For CFD aerodynamic field prediction, a physics-informed surrogate predicts pressure and wall shear stress (WSS) across aerodynamic body shape variants, while symmetry preserving down sampling retains accuracy with lower computational cost. The framework also outlines data generation guidance that can help engineers identify which additional simulations or labels are valuable to collect next. These results demonstrate a practical and reusable engineering AI workflow for more trustworthy CAE and CFD decision support.