Super-resolution of turbulent reacting flows on complex meshes using graph neural networks
This enables more accurate coarse-grained simulations of turbulent reacting flows on complex geometries, addressing a limitation of previous methods restricted to uniform meshes.
The authors tackled the problem of reconstructing small-scale turbulent flow structures from coarse-grained data on complex meshes, demonstrating that their graph neural network approach accurately reconstructs fine-scale features in reacting channel flow and hydrogen-fueled internal combustion engine cases with cumulative error reduction.
State-of-the-art deep learning models have been extensively utilized to reconstruct small-scale structures from coarse-grained data in turbulent flows. However, their application has predominantly been restricted to structured uniform meshes, limiting their applicability to data associated with complex geometries that are typically simulated on structured non-uniform or unstructured meshes. Machine learning (ML) models based on graph neural networks (GNNs), known for their ability to process unstructured data, offer a promising alternative. In this study, we leverage the inherent flexibility of GNNs featuring message passing layers to develop a methodology for reconstructing unresolved small-scale structures from low-resolution data on complex meshes. The accuracy of the proposed approach is demonstrated using two cases: a reacting channel flow on a structured non-uniform mesh, and a reacting hydrogen fueled internal combustion (IC) engine featuring an unstructured mesh. Evaluation of results based on visual agreement, statistical metrics, and cumulative error reduction indicates the effectiveness of the method in accurately reconstructing fine-scale features. Overall, this study provides a pathway for integrating data-driven small-scale reconstruction and subgrid-scale modeling to enhance the accuracy of coarse-grained simulations on complex meshes.