Marrying machine learning with 3D printing for more reliable parts

DENVER. Lockheed Martin and the Office of Naval Research (ONR) are embarking on a project that aims to explore how to apply artificial intelligence (AI) to train robots to independently oversee and optimize 3D printing of complex parts.

The two-year, $5.8 million -- led by a team from 's Advanced Technology Center -- plans to develop software models, enhance sensors, and customize multi-axis robots that use laser beams to more accurately deposit materials, thereby resulting in better components.

Brian Griffith, Lockheed Martin's project manager, said of the project: "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 3D printed parts become more and more common. 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 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," said 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 to the next big step of deployment."

At present, technicians spend many hours per build testing quality after fabrication, but waste is also found in the practice of building each part in a way that compensates for the weakest section for a part and allows more margin and mass in the rest of the structure; team members say that the new research will help machines make decisions about how to optimize structures based on previously verified analysis.

This verified analysis and integration into a 3D printing robotic system is core to this new contract: The team will measure the performance attributes of the machine parameters, examine the microstructures used in an additive build, and align them to material properties before integrating this knowledge into a working system, which will then allow the to make decisions about how to print a part that ensures good performance.

The team -- along with seven industry, national lab and university partners -- will initially begin its research build with the most common titanium alloy, Ti-6AI-4V.