WASHINGTON — The Office of Naval Research awarded Lockheed Martin Oct. 1 a two-year, $5.8 million contract to explore how machine learning and artificial intelligence can make complex 3-D printing more reliable and save hours of tedious post-production inspections.

In today’s factories, 3-D printing parts requires persistent monitoring by specialists to ensure intricate parts are produced without impurities and imperfections that can compromise the integrity of the part overall. To improve this laborious process, the Navy is tasking Lockheed Martin with developing multi-axis robots that use lasers to deposit material and oversee the printing of parts.

Lockheed Martin has multiple partners on the contract including Carnegie Mellon University, Iowa State University, Colorado School of Mines, America Makes, GKN and Wolf Robotics and Oak Ridge National Laboratory.

The contract covers what Glynn Adams, a senior engineer with Lockheed Martin, describes as the pre-flight model of the program’s development. Initial work will focus on developing computer models that can predict the microstructures and mechanical properties of 3-D printed materials to generate simulation data to train with. Adams said the Carnegie Mellon team will look at variables such as, “the spot size of the laser beam, the rate of feed of the titanium wire [and]the total amount energy density input into the material while it is being manufactured.” This information helps the team predict the microstructure, or organizational structure of a material on a very small scale, that influences the physical properties of the additive manufactured part.

This data will then be shared with Iowa State, who will plug the information into a model that predicts the mechanical properties of the printed component. By taking temperature and spot size measurements, the team can also ensure they are, “accurately controlling energy density, the power of both the laser and the hot wire that goes into the process,” Adams said..

“All of that is happening before you actually try to do any kind of machine learning or artificial neural networks with the robot itself. That’s just to try to train the models to the point where we have confidence in the models,” Adams said.

Sounds easy, right?

But one key problem could come in cleaning up the data and removing excess noise from the measurements.

“Thermal measurements are pretty easy and not data intensive, but when you start looking at optical measurements you can collect just an enormous amount of data that is difficult to manage,” Adams explained. Lockheed Martin wants to learn how shrink the size of that dataset without sacrificing key parameters. The Colorado School of Mines and America Makes will tackle the problem of compressing and manipulating this data to extract the key information needed to train the algorithms.

After this work has been completed, the algorithms then will be sent to Oak Ridge National Laboratory, where robots will begin producing 3-D titanium parts and learn how to reliably construct geometrically and structurally sound parts. This portion of the program will confront challenges from the additive manufacturing and AI components of the project.

On the additive manufacturing side, the team will work with new manufacturing process, “trying to understand exactly what the primary, secondary and tertiary interactions are between all those different process parameters,” Adams said. “If you think about it, as you are building the part depending on the geometric complexity, now those interactions change based on the path the robot has to take to manufacture that part. One of the biggest challenges is going to be to understand exactly which of those parameters are the primary, which are the tertiary and to what level of control we need to be able to manipulate or control those process parameters in order to generate the confidence in the parts that we want.”

At the same time, researchers also will tackle AI machine learning challenges. Like with other AI programs, it’s crucial the algorithm is learning the right information, the right way. The models will give the algorithms a good starting point, but Adams said this will be an iterative process that depends on the algorithm’s ability to self-correct. “At some point, there are some inaccuracies that could come into that model,” Adams explained. “So now, the system itself has to understand it may be getting into a regime that is not going to produce the mechanical properties or microstructures that you want, and be able to self-correct to make certain that instead of going into that regime it goes into a regime that produces the geometric part that you want.”

With a complete algorithm that can be trusted to produce structurally sound 3-D printed parts, time-consuming post-production inspections will become a thing of the past. Instead of nondestructive inspections and evaluations, if you “have enough control on the process, enough in situ measurements, enough models to show that that process and the robot performed exactly as you thought it would, and produced a part that you know what its capabilities are going to be, you can immediately deploy that part,” said Adams. “That’s the end game, that’s what we’re trying to get to, is to build the quality into the part instead of inspecting it in afterwards."

Confidence in 3-D printed parts could have dramatic consequences for soldiers are across the services. As opposed to waiting for replacement parts, service members could readily search a database of components, find the part they need and have a replacement they can trust in hours rather than days or weeks. “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 3-D printing to the next, big step of deployment.”