Building Spacecraft parts and mission hardware is one of the most complex challenges every space agency faces while preparing for a mission. However, NASA engineers at NASA’s Goddard Space Flight Center in Maryland are currently using commercially available AI software to create bespoke parts named “evolved structures,” for future missions.
The officials describe the hardware design as something that looks like bones left by some alien species. The hardware parts are built to weigh less and accommodate higher structural loads. Since the job is being executed by Artificial Intelligence, it only requires a fraction of the time to complete.
But what did NASA hope to accomplish from this technology? How will it be used for future deep space missions? Continue reading to find out.
How NASA engineers are Using AI to Build complex spacecraft parts
NASA is one of the few space agencies advocating for crewed missions to deep space. In fact, the agency has attained several milestones in space exploration and still looking forward to setting new records for mankind. The need for spacecraft parts arises frequently. Since AI is becoming more sophisticated and better these days, NASA engineers decide to use the technology and create spacecraft parts for future missions.
“They look somewhat alien and weird,” Research Engineer Ryan McClelland said, “but once you see them in function, it really makes sense.”
McClelland is the NASA engineer who pioneered the design of specialized, one-off parts using commercially available AI software at NASA’s Goddard Space Flight Center in Greenbelt, Maryland. He uses the software to produce hardware parts which he named evolved structures.
A computer-assisted design (CAD) specialist begins with the design of these parts by exploring the mission’s requirements and draws in the surface where each part is attached to the spacecraft or instrument. The designer also considers adding any bolts or fittings for the parts to the initial design.
The specialist also proceeds to block out a path of the design to prevent the algorithm from blocking a laser beam or optical sensor. At last, technicians come in to handle more complex parts of the design to maneuver for assembly and alignment.
As soon as all off-limit areas are identified, the AI will proceed to connect the dots by creating complex structure designs within an hour or two.
“The algorithms do need a human eye,” McClelland said. “Human intuition knows what looks right, but left to itself, the algorithm can sometimes make structures too thin.”
McClelland went further to explain how the AI design parts weigh less than regular spacecraft parts.
“These evolved structures save up to two-thirds of the weight compared to traditional components, and can be milled by commercial vendors,” McClelland said. “You can perform the design, analysis, and fabrication of a prototype part, and have it in hand in as little as one week. It can be radically fast compared with how we’re used to working.”
He also explained that the parts are analyzed using NASA-standard validation software and processes to figure out potential points of failure.
“We found it actually 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,” McClelland said. “The stress factors are almost ten times lower than parts produced by an expert human.”
What NASA hopes to Accomplish with this AI design
NASA has already adopted McClelland’s evolved components in several of its missions in different stages of design and construction. These NASA missions include Earth-atmosphere scanners, space weather monitors, the Mars Sample Return mission, astrophysics balloon observatories, and planetary instruments.
NASA’s scientists entrusted the evolved structures so much that Goodard Physicist Peter Magler is taking advantage of the AI components to develop the EXoplanet Climate Infrared Telescope (EXCITE) mission. This mission involves a balloon-borne telescope built to study hot Jupiter-type exoplanets orbiting other stars in the Milky Way Galaxy.
The telescope is still undergoing construction and testing and NASA officials are hoping to use a near-infrared spectrograph to perform continuous observation of each targeted planet’s orbit around its host star.
“We have a couple of areas with very tricky design requirements,” Nagler said. “There were combinations of specific interfaces and exacting load specifications that were proving to be a challenge for our designers.”
McClelland created the titanium scaffold for the back of the EXCITE telescope. The IR receiver will be mounted at this point inside an aluminum cryogenic chamber which will connect a carbon fiber plate that supports the primary mirror. NASA is planning an engineering test flight of this mission in the early fall of 2023.
The Future of AI in Building complex spacecraft parts
The use of AI is growing in almost every industry. McClelland is confident that NASA will continue to explore this technology in building awesome technologies in the future.
“If you’re a motorcycle or car company,” McClelland said, “there may be only one chassis design that you’re going to produce, and then you’ll manufacture a bunch of them. Here at NASA, we make thousands of bespoke parts every year.”
McClelland is also confident that merging AI with 3D printing and other fascinating technologies could boost deep space exploration in the future.
“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 said.
NASA could take advantage of these technologies to advance its In-space Servicing, Assembly, and Manufacturing (ISAM) capabilities in the future.
Artificial Intelligence is gradually advancing every industry and NASA is already taking advantage of the awesome technologies to boost its deep space missions. In the future, we may be able to build advanced AI systems that will make space explorations to become more interesting and awesome. What do you think about this groundbreaking technology?