Defense Logistics Agency Awards Senvol Grant to Predict Mechanical Performance of 3D Printed Parts

New York-based Senvol, which provides data to companies to help them adopt 3D printing into their workflows, has been pretty focused on military applications as of late. The company joined the National Armaments Consortium in July, and it received a grant in August from the National Institute of Standards and Technology (NIST), a non-regulatory agency of the United States Department of Commerce, to use its Senvol ML data-driven machine learning software suite for 3D printing to set up Process-Structure-Property (PSP) relationships.

Senvol ML helps companies characterize or qualify 3D printing materials and processes fast, so users can select the appropriate process parameters, given the target mechanical performance, for specific 3D printers.

Continuing with this trend, Senvol has just received another grant from a military source – this time, it’s from the Defense Logistics Agency (DLA), which is the US combat logistics support agency.

The DLA manages the global supply chain, all the way from raw materials to end user and disposition, for the country’s Army, Navy, Air Force, Marine Corps, Coast Guard, several federal agencies, ten combatant commands, and partner and allied nations. The agency also manages a total of nine supply chains and roughly 5 million items, which includes the supply of 86% of the military’s total spare parts.

Recently, the DLA announced that it had awarded Senvol a grant for a new project, called “Additive Manufacturing Sensor Fusion Technologies for Process Monitoring and Control,” which will focus on accurately predicting a 3D printed part’s mechanical performance by analyzing additive manufacturing in-situ monitoring data. So Senvol’s ML software will be coming into play here to conduct the analyses for the project.

“The goal of this project is to demonstrate that parts of equivalent mechanical performance can be made on two different additive manufacturing machines, and that a suite of in-situ monitoring equipment is able to collectively provide sufficient data to monitor the process signatures and ensure that the additive manufacturing process will indeed yield equivalent parts,” said Annie Wang, the President of Senvol.

Senvol will work to demonstrate that a 3D printed part’s mechanical performance can be accurately predicted by using its ML software to analyze data from different 3D printing in-situ monitoring sensors.

By applying its ML software’s sensor fusion techniques to analyze all of the collected data, Senvol can accurately determine which specific suite of in-situ monitoring sensors should be installed into laser powder bed fusion 3D printing systems.

During the joint project with the DLA, Senvol will be working to implement, into one or more laser powder bed fusion 3D printing systems, what it calls its “advanced in-situ monitoring systems of various modalities.” Then, once the data has been collected from the 3D printers, Senvol will analyze it using its data-driven machine learning algorithms, in order to relate mechanical performance and material properties to process signatures. The company will also use its real-time data processing algorithms, which extract data such as process signatures, for analysis purposes.

What do you think? Discuss this story and other 3D printing topics at 3DPrintBoard.com or share your thoughts in the Facebook comments below.