Lockheed Martin Will Merge Machine Learning with 3D Printing

A U.S. Navy research contract could make complex metal additive manufacturing a reality both in production centers and deep in the field.

October 10, 2018

William Kucinski

Soon robots like this could make decisions on how to build more effective 3-D printed parts. This multi-axis printer uses laser beams to deposit material and make metal components, which could be important resources for people far from supply chains. (Image source: Lockheed Martin)

Lockheed Martin of Bethesda, Md. and the Office of Naval Research are exploring how to apply artificial intelligence to train robots to independently oversee and optimize additive manufacturing, also known as 3D printing, of complex parts.

A decade ago, engineers at CFM International, a joint venture between GE Aviation and France’s Safran Aircraft Engines, started designing a new, fuel-efficient jet engine for single-aisle passenger planes — the aircraft industry’s biggest market. A key to the breakthrough engine was the wildly complex interior of the of the engine’s fuel nozzles; however, the tips’ interior geometry was too complex. It had more than 20 parts that had to be welded and brazed together. With additive manufacturing, engineers were able to combined all 20 parts into a single unit that weighed 25 percent less than an ordinary nozzle and was more than five times as durable. (Image source: GE Aviation)

Through a two-year, $5.8 million contract, Lockheed Martin will study and further advance multi-axis robots that use laser beams to deposit material, developing software models and sensor modifications for the robots to build better components.

3D printing offers manufacturers a way to design and produce single components with complex geometries that would be impossible to make using traditional manufacturing techniques. These parts can drastically reduce part counts and weight of the ships, aircraft, ground vehicles, and spacecraft they wind up in.

But 3D printing also requires a lot of babysitting. High-value and intricate parts sometimes require constant monitoring by expert specialists to get them right. Furthermore, if any one section of a part is below par, it can render the whole part unusable.

“We will research ways machines can observe, learn, and make decisions by themselves to make better parts that are more consistent, which is crucial as 3-D printed parts become more and more common,” says Brian Griffith, Lockheed Martin's project manager. “Machines should monitor and make adjustments on their own during printing to ensure that they create the right material properties during production.”

Researchers will apply machine learning techniques to additive manufacturing so variables can be monitored and controlled by the robot during fabrication.

“When you can trust a robotic system to make a quality part, that opens the door to who can build usable parts and where you build them,” says Zach Loftus, Lockheed Martin fellow for additive manufacturing. “Think about sustainment and how a maintainer can print a replacement part at sea, or a mechanic print a replacement part for a truck deep in the desert. This takes 3-D printing to the next, big step of deployment.”

Currently, technicians spend many hours per build testing quality after fabrication, but that's not the only waste in developing a complex part. It's common practice to build each part compensating for the weakest section for a part and allowing more margin and mass in the rest of the structure. Lockheed Martin's research will help machines make decisions about how to optimize structures based on previously verified analysis.

That verified analysis and integration into a 3-D printing robotic system is core to this new contract. Lockheed Martin, along with its strong team, will vet common types of microstructures used in an additive build. Although invisible from the outside, a part could have slightly different microstructures on the inside. The team will measure the performance attributes of the machine parameters, these microstructures and align them to material properties before integrating this knowledge into a working system. With this complete set of information, machines will be able to make decisions about how to print a part that ensures good performance.

The team is starting with the most common titanium alloy, Ti-6AI-4V, and integrating the related research with seven industry, national lab, and university partners.

William Kucinski is content editor at SAE International, Aerospace Products Group in Warrendale, Pa. Previously, he worked as a writer at the NASA Safety Center in Cleveland, Ohio and was responsible for writing the agency’s System Failure Case Studies. His interests include literally anything that has to do with space, past and present military aircraft, and propulsion technology.

Contact him regarding any article or collaboration ideas by e-mail at This email address is being protected from spambots. You need JavaScript enabled to view it..