Boosting US Fighter Jets – NASA research applies artificial intelligence to hypersonic engine simulations
National Aeronautics and Space Administration (NASA) researchers have teamed up with the US Department of Energy’s Argonne National Laboratory (ANL) to develop artificial intelligence (AI) to improve the speed of simulations to study the behavior of the air surrounding supersonic and hypersonic aircraft. engines.
Fighter jets such as the F-15s regularly exceed Mach 2 – twice the speed of sound – during flight, called the supersonic level. During hypersonic flight at Mach 5 and beyond, an aircraft flies at over 3,000 miles per hour.
Hypersonic speeds have been made possible since the 1950s by propulsion systems used for rockets however engineers and scientists are working on advanced jet engine designs to make hypersonic flight much cheaper than a rocket launch and more common as for commercial flight, space exploration and national defense purposes.
The recently published paper by a team of NASA and LNA researchers details machine learning techniques to reduce the memory and costs needed to perform computational fluid dynamics (CFD) simulations related to the combustion of fuel at supersonic and hypersonic speeds.
The paper was previously presented at the American Institute of Aeronautics and Astronautics SciTech Forum in January.
Before building and testing an aircraft, CFD simulations are used to determine how the various forces surrounding an aircraft in flight will interact with it. CFD consists of numerical expressions representing the behavior of fluids such as air and water.
When an aircraft breaks the sound barrier, which involves traveling at speeds greater than the speed of sound, it generates a “shock wave” which is a disturbance that makes the air around it warmer, warmer dense and at higher pressure, causing it to behave very violently.
At hypersonic speeds, the air friction created is so strong that it could melt parts of a conventional commercial aircraft.
Air-breathing jet engines draw in oxygen to burn fuel during flight, so CFD simulations must account for major changes in the behavior of the air, not only around the aircraft, but also as it moves through the engine and interacts with the fuel.
While a conventional aircraft has fan blades to push air, in aircraft approaching Mach 3 and above speeds, their motion itself compresses the air. These aircraft designs, known as scramjets, are important for achieving levels of fuel efficiency that rocket propulsion cannot achieve.
So when it comes to CFD simulations on an aircraft capable of breaking the sound barrier, all of the above factors add new levels of complexity to an already computationally intense exercise.
“Because the interactions between chemistry and turbulence are so complex in these engines, scientists had to develop advanced combustion models and CFD codes to accurately and efficiently describe the physics of combustion,” said Sibendu Som, co-author of the study and acting director of the Argonne center. Advanced Propulsion and Energy Research Center.
NASA has a hypersonic CFD code known as VULCAN-CFD, specifically designed to simulate the behavior of burnups in such a volatile environment.
This code uses what are called “flamelet tables” where each “flamelet” is a small unit of flame in the entire combustion model. This array of data consists of various snapshots of fuel combustion in a huge collection that takes a large amount of computer memory to process.
Therefore, NASA and LNA researchers are exploring the use of AI to simplify these CFD simulations by reducing memory-intensive requirements and computational costs, in order to accelerate the pace of aircraft-breaking development. barriers.
ANL computer scientists used a flamelet table generated by software developed by Argonne to train an artificial neural network that could be applied to NASA’s VULCAN-CFD code. The AI used flamelet table values to learn shortcuts on determining combustion behavior in supersonic engine environments.
“The partnership has enhanced the capability of our in-house VULCAN-CFD tool by leveraging Argonne’s research efforts, allowing us to analyze the combustion characteristics of fuel at a greatly reduced cost,” said Robert Baurle, researcher at NASA Langley Research. Center.
Countries around the world are racing to achieve hypersonic flight capability and an essential part of this race are simulation experiments where there is enormous potential for the application of emerging technologies such as AI and machine learning ( ML).
Last month, according to a recent report by the EurAsian Times, Chinese researchers led by a senior Chinese military adviser on hypersonic weapons technology, claimed a significant breakthrough in an AI system capable of designing new hypersonic vehicles autonomously.
Additionally, in February, a Chinese space company called Space Transportation announced plans for testing beginning next year on a hypersonic aircraft capable of 7,000 miles per hour.
The company claimed their plane could fly from Beijing to New York in an hour.