When engineers want to test the aerodynamic properties of the newly designed shape of a car, airplane, or other object, they would normally model the flow of air around the object by having a computer solve a complex set of equations — a procedure that usually takes hours or even an entire day. Researchers have significantly sped up this process, making streamlines and parameters available in real time. The method uses machine learning to model flow around continuously editable 3D objects.
Previously, the computation of the aerodynamic properties of cars usually took a day. With the new tool, engineers can predict the flow in fractions of a second. 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 uses 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 that are then refined and split up into 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.