Description: In part I of this presentation, we present our work of using Deep Neural Networks to learn fluid dynamics. We show three examples of applying such methods: (1) predicting flow and forces on a 2D wing, (2) predicting force coefficients on a 3D helicopter wing during a complex maneuver, (3) predicting Reynolds stresses in a turbulence model. In these examples, we have not yet enforced the physics within the neural network, which will be covered in part II of this talk.
Presenter(s): Dr. Wes Brewer - PET GDIT
Location: Webinar
Date & Time: March 24, 2020, 3:00p - 4:30p ET
Additional Notes: Part of the HPDA Seminar Series (2020).
Distribution Statement D. Distribution authorized to the Department of Defense and U.S. DoD contractors only, Administrative or Operational Use, 24 March 2020. Other requests for this document shall be referred to the High Performance Computing Modernization Office, 3909 Halls Ferry Road, Vicksburg, MS 39180.