Senvol ML Software Helps US Air Force Accelerate Qualification of New 3D Printing Materials

Additive Manufacturing Data Specialist Senvol showed how its machine learning (ML) technology can be used to accelerate the qualification of new aerospace 3D printing materials.

Work under a contract awarded by the US 3D Printing Accelerator America doesthe firm has rolled out its Senvol ML software to quickly and inexpensively identify allowable properties during hardware R&D. Funded by the United States Air Force (USAF), it is believed that the findings from the project could be key to producing a new generation of durable lightweight parts, with aerospace and commercial applications.

“I have been involved in qualifying several additive manufacturing processes and materials for flight,” said Dr. William E. Frazier, retired chief scientist at NAVAIR and project participant, “and in my opinion, the further development of this technology will positively impact the cost, schedule, and performance of the Department of Defense (DoD) and commercial platforms.”

“Senvol’s ML approach responds directly to a major industry challenge: the rapid and cost-effective development of allowable properties of additive manufacturing materials.”

The US Air Force has a long history of using Senvol’s ML software for aerospace part optimization. Photo via Mikayla Heineck, US Air Force.

The military potential of Senvol ML

Indeed, Senvol ML is a data-driven software that can be used to analyze the relationships between 3D printing parameters and the final performance of a material. Technology-neutral, the program, compatible with all known AM processes, allows users to generate a set of parameters for their system or material, based on a predefined target mechanical performance.

Senvol ML owes much of its predictive powers to its Computational Integrated Materials Engineering or ‘ICME’ framework. Divided into four modules, this ICME quantifies the relationship between collected parameter data, material properties, process signatures and mechanical performance, to generate predictions of how the resulting parts will perform at a rapid rate of knots.

In doing so, Senvol ML provides a vital quality assurance tool for users in the aerospace, defense, consumer, medical, automotive, and oil and gas industries, and the technology also finds more and more military applications. Since 2020 alone, Senvol has used its software to facilitate the printing of large format aeronautical parts and develop a missile qualification workflow, while securing DoD funding to continue R&D.

“Senvol’s data-driven machine learning technology has the potential to significantly reduce the cost of developing licensed materials,” said Senvol President Zach Simkin. “By demonstrating an entirely new – and significantly more efficient – ​​approach to permit development, Senvol aims to generate tremendous value for the US Air Force, America Makes members, and the additive manufacturing industry as a whole. “

An example of Senvol ML analysis - stainless steel powder and powder bed laser fusion.  Image via Senvol.
An example of Senvol ML analysis – stainless steel powder and powder bed laser fusion. Image via Senvol.

Material qualification at pace

Senvol’s America Makes research project focused on the process of identifying the “allowable properties” of a material. Also known as “design permit”, these values ​​essentially represent a statistically determined minimum durability property that materials must have, in order to make them viable in particularly demanding applications.

Specifically, the program tasked the company with showing how the machine learning algorithms in its Senvol ML software can be used as a means to speed up this process, while reducing the large amount of empirical data normally required to do so. which can be an obstacle to the wider military deployment of 3D printing.

“Additive manufacturing is a modern, digital manufacturing method with rapidly customizable processing,” says Dr. Brandon Ribic, Chief Technology Officer of America Makes. “Continuing to use traditional authorized materials development approaches is a bottleneck for broader materials and process options and capabilities for additive manufacturing.”

According to Ribic, Senvol managed to overcome this bottleneck by developing a qualification approach based on data analysis, which showed the capabilities of its software in a “very powerful” way. In fact, working with Northrop Grummanthe National Aeronautical Research Institute (NIAR), Stratasys Direct Manufacturing and Council Pilgrimthe company is said to have been able to identify substantiated material properties, while simultaneously optimizing its data generation requirements.

Although the program has seen Senvol focus its efforts on finding allowable properties for flame retardant nylon 11 processed via a powder bed fusion machine, it says its approach can be applied to “any process, machine and additive manufacturing material”, to qualify their parameters. faster, cheaper and more accurately than traditional methods allow.

“The results of this America Makes program have been incredibly successful,” Simkin concluded. “Additionally, we have identified several other areas of opportunity to deepen machine learning capabilities to address this critical industry need. We look forward to continuing to partner with the industry to advance this area. peak. “

The Alchemite engine interface.  Image via Intellegens.
Senvol ML faces competition from other ML-based algorithms such as “Alchemite” from Intellegens. Image via Intellegens.

A new approach to qualification?

Compared to conventional “trial and error” approaches to material qualification, machine learning-based algorithms offer a way to eliminate human error behind failed prints. Although many such programs remain at an experimental level, the benefits of software developed by companies like Senvol ML and Intellegensare now beginning to arrive on the factory floor.

Last year again, the latter worked with the University of Sheffield AMRC and Boeing, to provide a new, optimized approach to 3D printing aerospace parts. Using the company’s own Alchemite ML Platformthe project was set up with the aim of improving the powder bed fusion process, so as to ensure that components could be produced faster, cheaper and from more materials than ever before.

Likewise, the engineers of Massachusetts Institute of Technology (MIT) have developed an open-source ML algorithm designed to help a wider audience speed up the process of identifying 3D printable materials. Wrapped up in their’AutoOED‘, the team’s program is able to automatically identify viable materials with desired qualities such as toughness, stiffness and strength.

To stay up to date with the latest 3D printing news, don’t forget to subscribe to the 3D Printing Industry Bulletin or follow us on Twitter or like our page on Facebook.

To deepen your knowledge of additive manufacturing, you can now subscribe to our Youtube channel, with discussions, debriefs and photos of 3D printing in action.

Are you looking for a job in the additive manufacturing industry? To visit 3D printing works for a selection of roles in the industry.

Featured image shows a fleet of US Air Force aircraft. Photo via Mikayla Heineck, US Air Force.



Source link