Abstract
Abstract
Obtaining flow fields around airfoils is an essential process in aerodynamics design. With advanced technology, simulating the whole process for any given mesh became possible using numerical analysis rather than wind tunnel experiments with scaled models. However, computing high-accuracy solutions for flow fields requires considerably more powerful hardware and computation time. Deep learning models have shown outstanding performances in many fields in recent years, providing satisfactory predictions with much less inference time. Therefore, neural networks are a good alternative for simulations in situations where less accurate but quick solutions are needed, such as airfoil design. However, popular architectures like CNNs or RNNs are naturally unsuitable for those tasks. Hence, this thesis aims to utilize graph neural networks to predict physical properties around airfoils. Various airfoils with different angles of attack in near transonic regimes have been used as the dataset. Three experiments have been done regarding graph neural networks: (1) Different architectures have been compared using the abovementioned dataset, (2) the importance of the surface nodes in training has been analyzed using different weights in the loss function, and (3) a proposed mesh-independent adaptive mesh refinement has been integrated into a deep learning methodology and tested. Our experiments found that graph neural architectures perform similarly in this task, and surface nodes do not significantly affect prediction performance except for the pressure field. The third experiment resulted differently, showing that performance dropped with each refinement process with respect to loss metric. On the other hand, we observed that the decreased metrics are due to adding new nodes. Thus, we achieved an overall similar performance with more resolution in shock areas comparing to no-refined training.