New interactive machine learning tool makes car designs more aerodynamic

August 15, 2018, Institute of Science and Technology Austria
The new software instantly shows stream lines as well as pressure on the surface (color-coded) of interactively deformable shapes. Credit: Nobuyuki Umetani

When engineers or designers 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. Nobuyuki Umetani from Autodesk research (now at the University of Tokyo) and Bernd Bickel from the Institute of Science and Technology Austria (IST Austria) have now significantly sped up this process, making streamlines and parameters available in real time. Their method, which is the first to use machine learning to model flow around continuously editable 3-D objects, will be presented at this year's prestigious SIGGRAPH conference in Vancouver, where IST Austria researchers are involved in a total of five presentations.

Machine learning can make extremely time-consuming methods a lot faster. Before, the computation of the aerodynamic properties of cars usually took a day. "With our machine learning tool, we are able to predict the flow in fractions of a second," says Nobuyuki Umetani. The idea to use machine learning came up in a discussion between the two long-time collaborators. "We both share the vision of making simulations faster," explains IST Austria Professor Bernd Bickel. "We want people to be able to design objects interactively, and therefore we work together to develop data-driven methods," he adds.

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 2-D images, where a picture can be easily represented by a regular arrangement of pixels. But if a 3-D 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 Umetani's 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.

The researchers also proved in their study that the machine learning achieves an impressive accuracy, a prerequisite for engineering. Nobuyuki Umetani explains: "When simulations are made in the classical way, the results for each tested are eventually thrown away after the computation. This means that every new computation starts from scratch. With , we make use of the data from previous calculations, and if we repeat a calculation, the accuracy increases."

Explore further: First machine learning method capable of accurate extrapolation

More information: Nobuyuki Umetani et al. Learning three-dimensional flow for interactive aerodynamic design, ACM Transactions on Graphics (2018). DOI: 10.1145/3197517.3201325

Related Stories

Deep learning stretches up to scientific supercomputers

August 14, 2018

Machine learning, a form of artificial intelligence, enjoys unprecedented success in commercial applications. However, the use of machine learning in high performance computing for science has been limited. Why? Advanced ...

Artificial intelligence may put private data at risk

August 3, 2018

Machine learning – a form of artificial intelligence in which computers use data to learn on their own – is rapidly growing and poised to transform the world. But current models are vulnerable to privacy leaks and other ...

New algorithm limits bias in machine learning

July 16, 2018

Machine learning—a form of artificial intelligence based on the idea that computers can learn from data and make determinations with little help from humans—has the potential to improve our lives in countless ways. From ...

Recommended for you

Two new planets discovered using artificial intelligence

March 26, 2019

Astronomers at The University of Texas at Austin, in partnership with Google, have used artificial intelligence (AI) to uncover two more hidden planets in the Kepler space telescope archive. The technique shows promise for ...

Infertility's roots in DNA packaging

March 26, 2019

Pathological infertility is a condition affecting roughly 7 percent of human males, and among those afflicted, 10 to 15 percent are thought to have a genetic cause. However, pinpointing the precise genes responsible for the ...

Facebook is free, but should it count toward GDP anyway?

March 26, 2019

For several decades, gross domestic product (GDP), a sum of the value of purchased goods, has been a ubiquitous yardstick of economic activity. More recently, some observers have suggested that GDP falls short because it ...

Droughts could hit aging power plants hard

March 26, 2019

Older power plants with once-through cooling systems generate about a third of all U.S. electricity, but their future generating capacity will be undercut by droughts and rising water temperatures linked to climate change. ...

0 comments

Please sign in to add a comment. Registration is free, and takes less than a minute. Read more

Click here to reset your password.
Sign in to get notified via email when new comments are made.