AIDefense

Lockheed Martin and U.S. Navy explore AM machine learning in $5.8M contract

The partners aim to increase automation and optimization for industrial additive manufacturing

Most industries would agree that there is no going back on additive manufacturing. The technology, which is opening up new avenues and possibilities for manufacturing across the board, is here to stay. Still, that doesn’t mean that there aren’t still hurdles and challenges that manufacturers have to overcome, including driving costs down for the technology, establishing standards and, perhaps most crucially, increasing process automation.

That is, while additive manufacturing is being used to produce parts for a range of applications, AM experts are still largely relied upon to monitor the 3D printing process and ensure that there are no discrepancies that could compromise a part. Fortunately, many companies active in industrial AM are honing their processes and workflows to be more intelligent and automated to reduce the manual labour required in AM and to increase productivity.

The most recent company to join the effort is American defense giant Lockheed Martin, which has teamed up with the Office of Naval Research to investigate the use of artificial intelligence (AI) to train robots to not only oversee but also optimize the 3D printing process for complex industrial parts. The recent partnership consists of a two-year contract worth $5.8 million.

Working together, Lockheed Martin and the Office of Naval Research will customize multi-axis 3D printing robots to be controlled by new software and sensor modifications with the goal of improving the functionality and efficiency of the robots. Notably, the partners will integrate machine learning techniques in the AM process so that variables in the workflow can be monitored and controlled as a part is printed.

Lockheed Martin machine learning

“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,” explained 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.”

Presently, most additive manufacturing processes still depend on specialists and technicians to ensure that everything is going smoothly and to make sure that parts meet requirements after printing. The smart robotic system being developed by Lockheed Martin will reduce the need for this.

More than that, the company says its AI project could enable 3D printers to make smart decisions on how to optimize 3D printed structures based on previously verified analysis. This would simplify the pre-production process by automating structure optimization for a given part.

The integration of this verified analysis into a robotic 3D printing platform is reportedly the core of the new contract between Lockheed Martin and the Office of Naval Research. To establish it, Lockheed Martin will analyze different types of microstructures common in additive manufacturing to see different performance attributes based on machine parameters and material properties. The information from these tests will be introduced into the working system, enabling machines to learn and make decisions about printing an optimized part.

“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,” commented 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 3D printing to the next, big step of deployment.”

The first stage in the cooperation will see Lockheed Martin and the Office of Naval Research working with Ti-6AI-4V, the most commonly used titanium alloy. The partners will also collaborate with various members from industry, national labs and universities.

Tags

Related Articles

We use cookies to give you the best online experience. By agreeing you accept the use of cookies in accordance with our cookie policy.

Privacy Settings saved!
Privacy Settings

When you visit any web site, it may store or retrieve information on your browser, mostly in the form of cookies. Control your personal Cookie Services here.

These cookies are necessary for the website to function and cannot be switched off in our systems.

In order to use this website we use the following technically required cookies
  • PHPSESSID
  • wordpress_test_cookie
  • wordpress_logged_in_
  • wordpress_sec

Decline all Services
Accept all Services
Close
Close

STAY AHEAD

OF THE CURVE

Join industry leaders and receive the latest insights on what really matters in AM!

This information will never be shared with 3rd parties

I’ve read and accept the privacy policy.*

WELCOME ON BOARD!