Senvol is developing a software that analyzes the relationship between additive manufacturing process parameters and material performance.
There’s nothing that the U.S. government likes more than information—except, perhaps, turning that information into something actionable. For instance, that’s how the Internet itself was born: through the need to create intelligence from countless data collected in Southeast Asia during the country’s military campaigns in the mid-20th century.
Now, that data and how it’s used is taking on a completely different form. Senvol, a startup dedicated to data related to additive manufacturing (AM), has announced that it will be developing AM machine learning software for the U.S. Navy’s Office of Naval Research (ONR), funded through the Navy Phase II STTR N16A-002. The software analyzes the relationship between AM process parameters and material performance. Using the software, ONR aims to substantiate material properties statistically in order to reduce reliance on traditional material characterization and testing.
Senvol’s software relies on a modularized integrated computational materials engineering (ICME) probabilistic framework for AM data. The data is broken down into four modules: process parameters, process signatures, material properties, and mechanical performance. The software uses an algorithm that quantifies the relationships between these four modules, regardless of the AM material, machine and process used.
“We are very excited about our work with the Navy’s Office of Naval Research. Our software’s capabilities will allow ONR to select the appropriate process parameters on a particular additive manufacturing machine given a target mechanical performance. This presents a unique opportunity to reduce the high level of trial and error that is currently required, which would save a tremendous amount of time and money,” said Senvol President Annie Wang. “In addition to our machine learning capabilities, we have also developed a computer vision algorithm that analyzes, in real-time, in situ monitoring data. This enables us to detect irregularities in real-time and begin to quantify the relationships between irregularities in the build and the resulting mechanical performance.”
Senvol has already seen multiple government customers make use of its technology. Oak Ridge National Laboratory, for instance, is working with Senvol’s data collection procedures to evaluate best practices for data collection. The U.S. Air Force is integrating the Senvol Database, made up of AM materials and machines, into its materials research software platform, HyperThought.
The machine learning software currently being developed with ONR will be made commercially available for qualifying AM parts. Those interested in beta testing the software can contact Senvol. The startup will be presenting its work at Additive Manufacturing Users Group (AMUG) and RAPID + TCT, as well. To learn more, visit the Senvol website.