US Army to Use Senvol Machine Learning for Qualification of 3D Printed Missile Parts

Senvol is building itself out to be a critical part of 3D printing infrastructure. Bit by bit, the company is making itself indispensable especially to the U.S. defense community. It previously made software for the Office of Naval Research, got a grant from the Defense Logistics Agency, obtained another grant from NIST, joined the National Armaments Consortium, and worked together with ORNL. You can learn more about company co-founder Annie Wang here.

Senvol is a data merchant for 3D printing. The firm started off simple with a searchable database of additive manufacturing data. They also now have an API through which your software can access the database, Senvol Indexes for materials properties, and Senvol ML. Senvol ML is machine learning software that helps analyze part properties and settings. Ideally, this can aid you in optimizing your machine settings, more quickly qualify parts and predict properties in advance.

Now, Senvol ML has gotten a U.S. Military contract via the United States Army Research Laboratory (ARL), the same organization working with 3D Systems on its new huge printer. The idea is that by, “leveraging ML algorithms, the qualification plan will also be notably more efficient than more traditional qualification plans (i.e. require fewer builds and less time).” Stephanie Koch, ARL’s Advanced Manufacturing, Materials, and Processes Program (AMMP) Manager, said of the partnership:

“Additive manufacturing is a promising technology that could be used to enable multiple Army Modernization Priorities applications. Despite the potential that additive manufacturing offers, the rate of adoption is very slow due to the high cost and time associated with the design, qualification, and certification of additively manufactured parts. We are very encouraged with Senvol’s approach, and look forward to seeing how we can leverage machine learning to improve processes.”

Senvol President Annie Wang said:

“Senvol will implement data-driven machine learning technology for the U.S. Army that will substantially reduce the cost of material and part qualification. The significant reduction in cost and the increase in speed will allow the Army to support warfighter readiness by unlocking the full transformative potential that additive manufacturing offers.”

A Lockheed HiMars a high mobility launch system.

Partners include Lockheed Martin Missiles and Fire Control (“35 years in delivering critical kill chain solutions”), as well as Pilgrim Consulting.

Dr. William E. Frazier,  President of Pilgrim Consulting, “The plan is to fabricate a missile part and evaluate how close the actual performance requirements are compared to those predicted by the Senvol ML software, and to ultimately determine whether or not the part should be qualified.”

In front of Lockheed and the Defense Department, Senvol will thus undergo a live-fire test in its accuracy. This is a big moment for the company. Any kind of proof or validation as to its efficacy could be a big driver for the Defense Department and contractor adoption of Senvol’s technology. Indeed they have the potential to become a standard or standardly used application for the broader defense community. For this to work, Senvol will have to stand up to the scrutiny that this program will bring, however.

Lockheed Martin GMLRS.

Given the complexities and time in qualifying materials, parts, machines, and processes, Senvol has positioned itself as just the right solution at the right time. Companies such as Lockheed are looking at mounting costs to qualify many different AM materials and processes for flight. Finicky settings, many different parameters, and a variety of other variables mean that costs balloon when qualifying AM parts. Any kind of reduction in the data required or any kind of help in identifying the correct settings would save them considerable time and money.

At the same time, it would be very compelling to have algorithms learn and improve as they crawl data, looking for the best settings for 3D printing processes and materials. It’s just the right newfangled sauce of awesome that policymakers are attracted to. Machine learning is more often idly bandied about than used correctly. So, based upon that, we can’t yet know if this approach, with that implementation, will work with this dataset for AM. But, if things like this can save time on finding new materials, finding new settings, and qualifying new parts then this will be a very in-demand product indeed.

A THAAD missile

By successfully navigating the Beltway and developing data-rich products for a select set of customers, Senvol is quickly positioning itself as a key partner for the U.S. Defense establishment. By connecting our AM world with AM implementations, the firm is a bridge toward implementation.

Lockheed and other firms have for decades developed and commercialized 3D printing technologies for military applications. Especially in missiles, launch vehicles, drones, and aircraft AM has played a much larger role than you probably have realized in the development in next-generation military products. Key leaders in our industry such as Fried Vancraen and Dr. Hans Langer have previously resisted implementing our technology for military applications. The value for global militaries in weight-saving new geometries for warheads, rockets, and nuclear weapons is obvious. 3D printing also gives them the ability to be more agile, make more iterations, and develop products faster. As the battlefield evolves so can their kit. We must be cognizant of the opportunities, drive, and influence of military applications on AM. 3D printing for the military is a huge financial opportunity but at the same time intertwines us with geopolitical realities, deaths, and destruction.