A Hybrid GNN approach for predicting node data for 3D meshes
This work addresses efficiency in metal forging process optimization for manufacturing, though it appears incremental as it builds on existing GNN methods for a specific domain.
The paper tackles the time-consuming process of predicting optimal metal forging parameters via finite element simulations by introducing a hybrid graph neural network approach that processes 3D meshes into graphs or point clouds for faster simulation generation, achieving low error compared to finite element methods and outperforming existing models like PointNet and simple GNNs.
Metal forging is used to manufacture dies. We require the best set of input parameters for the process to be efficient. Currently, we predict the best parameters using the finite element method by generating simulations for the different initial conditions, which is a time-consuming process. In this paper, introduce a hybrid approach that helps in processing and generating new data simulations using a surrogate graph neural network model based on graph convolutions, having a cheaper time cost. We also introduce a hybrid approach that helps in processing and generating new data simulations using the model. Given a dataset representing meshes, our focus is on the conversion of the available information into a graph or point cloud structure. This new representation enables deep learning. The predicted result is similar, with a low error when compared to that produced using the finite element method. The new models have outperformed existing PointNet and simple graph neural network models when applied to produce the simulations.