NASA is using artificial intelligence (AI) technology to design spacecraft and mission hardware that weighs less while simultaneously tolerating higher structural loads, the agency announced in a Feb 9 blog post.
According to NASA Research Engineer Ryan McClelland – who pioneered the design of specialized one-off parts using commercially available AI software at NASA’s Goddard Space Flight Center – the AI-designed product saves up to two-thirds of the weight of traditional components and can be milled by commercial vendors.
To create these parts, a computer-assisted design (CAD) specialist begins with the mission requirements and draws in the surfaces where the hardware parts connect to the instrument or spacecraft, in addition to any bolts or fittings for electronics and other hardware. The CAD specialist may also need to block a path to prevent AI from obstructing a laser or optical sensor. More complicated designs may require room for technicians’ hands to maneuver to help assemble and align the piece.
Once all off-limits areas are defined, the AI connects the dots to produce the design, which takes up to one to two hours. The entire process – design analysis, prototype fabrication, and the final product – can take about a week.
“Parts are also analyzed using NASA-standard validation software and processes to identify potential points of failure. We found it lowers risk. After these stress analyses, we find the parts generated by the algorithm don’t have the stress concentrations that you have with human designs. The stress factors are almost ten times lower than parts produced by an expert human,” McClelland said.
The algorithms, however, still require a human eye. Human intuition knows what looks right, but if the algorithm is left operating alone, it “can sometimes make structures too thin,” McClelland said.
These AI-assisted components have been adopted by NASA missions in different stages of design and construction, including astrophysics balloon observatories, Earth-atmosphere scanners, planetary instruments, space weather monitors, space telescopes, and even the Mars Sample Return mission.
“AI-assisted design is a growing industry, with everything from equipment parts to entire car and motorcycle chassis developed by computers. The use case for NASA is strong,” McClelland said.
“These techniques could enable NASA and commercial partners to build larger components in orbit that would not otherwise fit in a standard launch vehicle, they could even facilitate construction on the Moon or Mars using materials found in those locations,” he concluded.
