Home Transports Boeing Uses AI Company to 3-D Print Parts for Jets

Boeing Uses AI Company to 3-D Print Parts for Jets

HRL Laboratories is a dedicated research center based in Malibu, California. As well as taking on projects for the likes of the Defense Advanced Research Project Agency (DARPA), the company also prints parts for Boeing jets using a 3-D metal printer.

Both General Motors and Boeing are parent companies of HRL Laboratories. Rivals Airbus has already installed 3-D printed parts on its planes, in the form of wing brackets. It’s pretty exciting as it is the first-ever company to use artificial intelligence (AI) for this exact purpose. However, there are limitations.

The first being that the 3-D printed part is only as good as the metal powder that’s used to print it. According to materials scientist Hunter Martin, a lot of alloys that we think would be great for 3-D printing aren’t useable as their powder grains just don’t hold together well enough.

To get around this problem, experts at HRL’s Sensors and Materials Laboratory simply altered the alloy’s composition so that it was suitable for the 3-D printer. And the way in which they did that was through the use of machine learning software developed by Citrine Informatics. The first sample the group managed to print took around 2 years to develop. In order to come up with the most printable and effective composition for the alloy, around 10 million recipes were explored before the right mix was found by Citrine’s AI.

MORE – Top 50 RPA Tools – A Comprehensive Guide

Anytime a company wants to upgrade a product it first needs to consider what material to use to do that. “Everything has to start with, what are we going to make it out of?”, said Liz Holm, a materials scientist at Carnegie Mellon University. The problem is that this process can take a long time. So in 2013, Citrine co-founders Bryce Meredig and Kyle Michel joined CEO of Citrine Greg Mulholland and together they figured out how to speed up that process through the use of advanced AI algorithms.

But there’s still a significant lack of data available for such projects. “We have to do some creative things to really make the most of the data available,” says Mulholland. “There are times when we have to scan papers and notebooks from our customers, which is truly awful.” Luckily, using the AI, the team managed to cut down the time it takes to find the correct metal composition to make the 3-D parts from years to days.

Having found the new powder, several prototypes were made and tested for strength. They all passed the test. “It shouldn’t take 100 years to have really advanced answers to a lot of these materials science questions,” commented Mulholland. “It should take five to 10 years. Or shorter in some cases.” Thanks to Citrine, that’s come down to just a number of days.

MORE – Data Science – 8 Powerful Applications

Source Wired

Subscribe to our newsletter

Signup today for free and be the first to get notified on the latest news and insights on artificial intelligence

KC Cheung
KC Cheung has over 18 years experience in the technology industry including media, payments, and software and has a keen interest in artificial intelligence, machine learning, deep learning, neural networks and its applications in business. Over the years he has worked with some of the leading technology companies, building and growing dynamic teams in a fast moving international environment.
- Advertisment -


AI Model Development isn’t the End; it’s the Beginning

AI model development isn’t the end; it’s the beginning. Like children, successful models need continuous nurturing and monitoring throughout their lifecycle. Parenting is exhilarating and, if...