SuperMeshing: A New Deep Learning Architecture for Increasing the Mesh Density of Physical Fields in Metal Forming Numerical Simulation

Abstract

Abstract In metal forming physical field analysis, finite element method (FEM) is a crucial tool, in which the mesh-density has a significant impact on the results. High mesh density usually contributes authentic to an increase in accuracy of the simulation results but costs more computing resources. To eliminate this drawback, we propose a data-driven mesh-density boosting model named SuperMeshingNet that uses low mesh-density physical field as inputs, to acquire high-density physical field with 2D structured grids instantaneously, shortening computing time and cost automatically. Moreover, the Res-UNet architecture and attention mechanism 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. The well-trained model can successfully show an improved 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, FEM can be accelerated with seldom computational time and cost with little accuracy sacrificed.