BMO-GNN: Bayesian mesh optimization for graph neural networks to enhance engineering performance prediction

Abstract

Surrogate models are commonly used in engineering design to reduce the computational costs of simulations by approximating design variables and geometric parameters from computer-aided design (CAD) models. However, traditional surrogate models often lose critical information when simplified to lower dimensions and face challenges in handling the complexity of 3D shapes, especially in industrial datasets. To address these limitations, we propose a Bayesian graph neural network (GNN) framework that directly learns geometric features from CAD mesh representations for accurate engineering performance prediction. Our framework leverages Bayesian optimization (BO) to dynamically determine the optimal mesh element size, significantly improving model accuracy while balancing computational efficiency. This approach optimizes mesh resolution to preserve critical geometric features in 3D deep-learning-based surrogate models, adapting mesh size based on the task for high flexibility across various engineering applications. Experimental results demonstrate that mesh quality directly impacts prediction accuracy. The proposed BO-EI GNN model outperforms state-of-the-art models, including 3D CNN, SubdivNet, GCN, and GNN, in predicting mass, rim stiffness, and disk stiffness. Our method also significantly reduces computational costs compared to traditional optimization techniques. The proposed framework shows promising potential for application in finite element analysis (FEA) and other mesh-based simulations, enhancing the utility of surrogate models across various engineering fields.