An approximation model based on convolutional neural networks (CNNs) is proposed for flow field predictions. The CNN is used to predict the velocity and pressure field in unseen flow conditions and geometries given the pixelated shape of the object. In particular, we consider Reynolds Averaged Navier–Stokes (RANS) flow solutions over airfoil shapes as training data. The CNN can automatically detect essential features with minimal human supervision and is shown to effectively estimate the velocity and pressure field orders of magnitude faster than the RANS solver, making it possible to study the impact of the airfoil shape and operating conditions on the aerodynamic forces and the flow field in near-real time. The use of specific convolution operations, parameter sharing, and gradient sharpening are shown to enhance the predictive capabilities of the CNN. We explore the network architecture and its effectiveness in predicting the flow field for different airfoil shapes, angles of attack, and Reynolds numbers.
Bibliographical noteFunding Information:
This work was supported by General Motors Corporation under a contract titled “Deep Learning and Reduced Order Modeling for Automotive Aerodynamics.” Computing resources were provided by the NSF via grant 1531752 MRI: Acquisition of Conflux, A Novel Platform for Data-Driven Computational Physics (Tech. Monitor: Stefan Robila).
- Convolutional neural networks
- Deep learning