CFD Review  
Serving the CFD Community with News, Articles, and Discussion
 
CFD Review

User Preferences
Site Sponsorship
Headline Feeds
Mobile Edition
Privacy Policy
Terms of Service
twitter

Submit a CFD Story

Site Sponsors
The Choice for CFD Meshing
CFD Review

Tell a Friend
Help this site to grow by sending a friend an invitation to visit this site.

CFD News by Email
Did you know that you can get today's CFD Review headlines mailed to your inbox? Just log in and select Email Headlines Each Night on your User Preferences page.

 
Learning 3D Flow for Interactive Aerodynamic Design
Posted Fri September 07, 2018 @08:53AM
Print version Email story Tweet story
News Researchers Nobuyuki Umetani and Bernd Bickel have published their work on a data-driven technique to instantly predict how fluid flows around various three-dimensional objects.

CFD simulation of new designs, even in the case of minor changes, is computationally expensive since it requires solving the Navier-Stokes equation for many time steps. To accelerate the process, Umetani and Bickel propose a machine learning framework which predicts aerodynamic forces and velocity and pressure fields given a 3D shape input.


Sponsor CFD Review

So far, it has been extremely challenging to apply machine learning to the problem of modeling flow fields around objects because of the restrictive requirements of the method. For machine learning, both the input and the output data need to be structured consistently. This structuring of information works well for 2D images, where a picture can be easily represented by a regular arrangement of pixels. But if a 3D object is represented by units that define its shape, such as a mesh of triangles, the arrangement of these units might change if the shape changes. Two objects that look very similar to a person might therefore appear very different to a computer, as they are represented by a different mesh, and the machine would therefore be unable to transfer the information about the one to the other.

The solution came from Nobuyuki Umetaniís idea to use so-called polycubes to make the shapes manageable for machine learning. This approach, which was originally developed to apply textures to objects in computer animations, has strict rules for representing the objects. A model starts with a small number of large cubes which are then refined and split up in smaller ones following a well-defined procedure. If represented in this way, objects with similar shapes will have a similar data structure that machine learning methods can handle and compare.

[ Post Comment ]

Early Bird Registrations for the NUMECA User Meeting 2018 Ending Soon | NUMECA International Acquires FlowKit  >

 

 
CFD Review Login
User name:

Password:

Create an Account

Related Links
  • Bernd Bickel
  • Nobuyuki Umetani
  • published their work
  • More on News
  • 'Learning 3D Flow for Interactive Aerodynamic Design' | Login/Create an Account | Search Discussion

    The following comments are owned by whoever posted them.
    We are not responsible for them in any way.

    Your sister swims out to meet troop ships. All content except comments
    ©2020, Viable Computing.

    [ home | submit story | search | polls | faq | preferences | privacy | terms of service | rss  ]