A few months NASA recently unveiled its next-generation space suit that astronauts will wear when they return to the moon in 2024 as part of the agency’s plan to establish a permanent human presence on the lunar surface. The Extravehicular Mobility Unit, or xEMU, is NASA’s first major upgrade to its space suit in nearly 40 years and is designed to make life easier for astronauts who will spend a lot of time kicking up dust from the moon. It will allow them to bend and stretch in a way they couldn’t before, easily put on and take off the suit, change components for a better fit, and go months without making a repair.
But the biggest improvements were not showcased at the suit presentation last fall. Instead, they’re hidden in the xEMU’s portable life-support system, the astro backpack that turns a bulky cloth piece’s spacesuit into a personal spaceship. It handles the power, communications, oxygen supply, and temperature regulation of the spacesuit so that astronauts can focus on important tasks like building concrete launch pads. And for the first time, some of the components of an astronaut life support system will be designed by artificial intelligence.
Jesse Craft is a senior design engineer at Jacobs, a major Dallas-based engineering firm that was hired by NASA to renovate the xEMU life support system. For Craft and the hundreds of other engineers working on the project, this requires a careful balancing act between competing priorities. The life support system must be safe, obviously, but it must also be light enough to fit within the weight limits of the lunar lander and strong enough to withstand the intense g forces and vibrations you will experience during launch. a rocket. “It is a great engineering challenge,” says Craft.
Squeezing more stuff in less space with reduced mass is the kind of complex optimization problem that aerospace engineers face all the time. But NASA wants boots on the moon by 2024, and sticking to that aggressive timeline meant Craft and his colleagues couldn’t spend weeks debating the ideal shape of each widget. Instead, they are testing new AI-powered design software that can quickly generate new component designs.
“We consider AI to be a technology that can do something faster and better than a trained human,” says Jesse Coors-Blankenship, vice president of technology for PTC, the US company that made the software. “Some of the software technologies are things that engineers are already familiar with, such as structural simulation and optimization. But with AI, we can do it faster. “This engineering approach is known as generative design. The basic idea is to feed the software with a set of requirements for the maximum size of a component, the weight it must support or the temperatures to which you will be exposed and let the algorithms discover the rest.
PTC software combines several different approaches to AI, such as generative confrontation networks and genetic algorithms. A generative confrontation network is a game-like approach in which two machine learning algorithms confront each other in a competition to design the most optimized component. It is the same technique used to generate photos of people who do not exist. Genetic algorithms, by contrast, are analogous to natural selection. They generate multiple designs, combine them, and then take the best new generation designs and repeat. In the past, NASA has used genetic algorithms to design strange and optimal antennas.
“The machine’s iterative process is 100 or 1,000 times more than we could do on our own, and it offers a solution that is ideally optimized within our limitations,” says Craft. It is especially useful since the final design of the spacesuit life support system is still constantly changing. Even a small change in requirements in the future could result in weeks of lost work on the part of the engineers.
.
