Araqev Commercializes Purdue-Developed AM Quality-Control Software

April 28, 2022
0
Comments

Purdue-Araqev-quality-control-softwareA Purdue University-related company, Araqev, has commercialized quality-control software designed to benefits sectors such as aerospace, automotive, consumer products, medical devices and national defense that employ additive manufacturing (AM) technologies.

The software helps end users print products in only a few design iterations, according to company officials, leading to less scrap material and machining time, eliminating the frustrations with 3D printing, and improving satisfaction with the final printed products. 

"We estimate that the quality-control issue with AM can lead to nearly $2 billion in global losses annually, based on a model for the production costs of metal-AM systems,” says Arman Sabbaghi, Araqev president and CEO, and associate professor in Purdue's Department of Statistics in the College of Science.

To use the Araqev software, customers upload their nominal design files and scanned point-cloud data from their printed products.

"Our software uses these inputs to fit machine-learning (ML) models that can simulate shape deviations for future printed products," Sabbaghi explains. "Furthermore, the ML models enable our software to derive modifications to the nominal designs, known as compensation plans, so that when the modified designs are printed, they will exhibit fewer shape deviations compared to the case when the original designs are printed."

Araqev's algorithms also enable the transfer of knowledge encoded via ML models across different materials, printers and shapes in an AM system.

"This means that our software enables a comprehensive platform for a customer to improve quality for their entire system," says Sabbaghi.

Effectiveness of the algorithms most recently were demonstrated via two validation experiments for the Markforged Metal X 3D printer involving 17-4 PH stainless-steel products, according to Sabbaghi.

"Our algorithms reduced shape inaccuracies by 30 to 60 percent,” Sabbaghi says, “depending on the geometry in at most two iterations, with three training shapes and one or two test shapes for a specific geometry involved across the iterations."

Araqev, which has licensed the software from the Purdue Research Foundation Office of Technology Commercialization, is establishing direct partnerships with 3D printing manufacturers and companies using 3D printers that Sabbaghi says will enable the company to scale quickly.

Industry-Related Terms: Case, Model, Nominal, Scale, Transfer
View Glossary of Metalforming Terms

 

See also: Markforged

Technologies:

Comments

Must be logged in to post a comment.
There are no comments posted.

Related Content

Subscribe to the Newsletter

Start receiving newsletters.