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

TL;DR

SuperMeshingNet is a deep learning model that rapidly enhances mesh density in stress field analysis, significantly reducing computational costs while maintaining high accuracy, thus improving efficiency in metal forming simulations.

Contribution

The paper introduces SuperMeshingNet, a novel Res-UNet based deep learning architecture with attention and perceptual features for instant high-density stress field reconstruction from low-density inputs.

Findings

SuperMeshingNet outperforms linear interpolation in accuracy.

The model achieves high-quality results at multiple mesh scaling factors.

It significantly reduces computational time and resources.

Abstract

In stress field analysis, the finite element analysis 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 during the design process. 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 to 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 test data, which contains prior unseen cases. Based on the data set of metal forming, the comparable experiments are proceeded to demonstrate the high quality and superior precision of the reconstructed results generated by our model. The well-trained model can successfully show more excellent performance than the baseline and other methods on the multiple scaled mesh-density, including $2\times$, $4\times$, and $8\times$. With the refined result owning broaden scaling of mesh density and high precision, the FEA process can be accelerated with seldom cost on computation resources. We publicly share our work with full detail of implementation at https://github.com/zhenguonie/2021_SuperMeshing_2D_Metal_Forming