Argonne National Laboratory and NASA researchers have published a paper on the use of artificial intelligence to speed up simulations of air behavior surrounding supersonic and hypersonic aircraft propulsion systems.
The partners trained a neural network to find shortcuts to answers about fuel combustion at environments faster than sound, reducing the memory and cost required to conduct computational fluid dynamics simulations, Argonne said Wednesday.
The AI technology is expected to enhance the current process of running massive tables of combustion data through NASA’s VULCAN-CFD hypersonic code and accelerate the development of barrier-breaking engines for supersonic and hypersonic aircraft.
“Working with NASA gave us the opportunity to integrate our novel developments in a state-of-the-art CFD code, and also to further improve the developments for more efficient design and optimization of hypersonic jets,” explained Sinan Demir, an Argonne computational scientist.
The research paper was previously presented at the American Institute of Aeronautics and Astronautics SciTech Forum in January.