Machine Learning Augments 3D Design for Greater Precision
- By Dian Schaffhauser
Researchers from Purdue University and the University of Southern California have created a machine learning algorithm to improve quality control in 3D printing. The idea is that pieces of a car, for example, could fit together more precisely and be assembled with less testing and time, according to a profile of the project.
The new software addresses that aspect of additive manufacturing that continually poses a problem: producing components that require a "high degree of precision and reproducibility." The program uses a "model-building algorithm" to analyze the product data and correct the computer-aided design models for greater geometric accuracy. The result is that the printed part reflects that greater precision.
"This has applications for many industries, such as aerospace, where exact geometric dimensions are crucial to ensure reliability and safety," said Arman Sabbaghi, an assistant professor of statistics in Purdue's College of Science, who led the research team for Purdue. "This has been the first time where I've been able to see my statistical work really make a difference, and it's the most incredible feeling in the world."
He added that the innovation "is heading on the path to essentially allowing anyone to be a manufacturer."
The researchers are working with the Purdue Office of Technology Commercialization to patent the innovation, and they're seeking partners for continued development.
The project was supported with funding from the National Science Foundation.
Dian Schaffhauser is a senior contributing editor for 1105 Media's education publications THE Journal, Campus Technology and Spaces4Learning. She can be reached at firstname.lastname@example.org or on Twitter @schaffhauser.