Prediction of aerodynamic flow fields using convolutional neural networks

Saakaar Bhatnagar, Yaser Afshar, Shaowu Pan, Karthik Duraisamy, Shailendra Kaushik

Research output: Contribution to journalArticlepeer-review

25 Scopus citations

Abstract

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.

Original languageEnglish (US)
Pages (from-to)525-545
Number of pages21
JournalComputational Mechanics
Volume64
Issue number2
DOIs
StatePublished - Aug 15 2019

Bibliographical note

Funding 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).

Keywords

  • Aerodynamics
  • Airfoils
  • Convolutional neural networks
  • Deep learning
  • RANS

Fingerprint Dive into the research topics of 'Prediction of aerodynamic flow fields using convolutional neural networks'. Together they form a unique fingerprint.

Cite this