SuperMeshing: A New Deep Learning Architecture for Increasing the Mesh Density of Metal Forming Stress Field With Attention Mechanism And Perceptual Features

Abstract

Abstract In stress field analysis, the finite element method is a crucial approach, in which the mesh-density has a significant impact on the results. High mesh density usually contributes authentic to simulation results but costs more computing resources, leading to curtailing efficiency. To eliminate this drawback, we propose a new data-driven mesh-density boost model named SuperMeshingNet that strengthens the advantages of finite element analysis (FEA) with low mesh-density as inputs to the deep learning model, which consisting of Res-UNet architecture, to acquire high-density stress field instantaneously, shortening computing time and cost automatically. Moreover, the attention mechanism and the perceptual features are utilized, enhancing the performance of SuperMeshingNet. Compared with the baseline that applied the linear interpolation method, SuperMeshingNet achieves a prominent reduction in the mean squared error (MSE) and mean absolute error (MAE) on the test data, which contains prior unseen cases. Based on the dataset of the plane stress fields in sheet metal forming, the comparative experiments are proceeded to demonstrate the high quality and superior precision of the reconstructed results generated by the proposed model. The well-trained model can successfully show more excellent performance than the baseline models on the multiple scaled mesh-density, including 2×, 4×, and 8×. Enhanced by SuperMeshingNet with broaden scaling of mesh density and high precision output, FEA can be accelerated with seldom computational time and cost. We publicly share our work with full detail of implementation at https://github.com/zhenguonie/2021_SuperMeshing_2D_Metal_Forming.