ORNL, U.S. Dept. of Energy
ORNL publishes new additive manufacturing datasets
The Department of Energy’s Oak Ridge National Laboratory has publicly issued free additive manufacturing datasets help verify and improve the quality of 3D printed components.
The data has been gathered over ten years at the DOE’s Manufacturing Demonstration Facility comprising early-stage research in advanced manufacturing and comprehensive analysis of printed components.
The datasets are now available online and are thought to ‘significantly boost efforts to verify the quality of additively manufactured parts’ using only information gathered during printing, without the need for costly and time-consuming post-production analysis.
“We are providing trustworthy datasets for industry to use toward certification of products,” said Vincent Paquit, head of the ORNL Secure and Digital Manufacturing section. “This is a data management platform structured to tell a complete story around an additively manufactured component. The goal is to use in-process measurements to predict the performance of the printed part.”
Additive manufacturing typically requires a non-traditional approach to quality control, relying heavily on expensive evaluation techniques such as destructive mechanical testing or non-destructive X-ray computed tomography. However, these techniques can be limited, particularly for larger 3D printed parts.
Read more: New developments in the automated quality control of 3D printed parts
ORNL’s comprehensive 230 GB datasets can be used to train machine learning models to improve quality assessment for printed components. The data covers the design, printing and testing of five sets of parts with different geometric shapes, all made using a laser powder bed technology. Researchers can access machine health sensor data, laser scan paths, 30,000 powder bed images and 6,300 tests of the material’s tensile strength. ORNL researchers have demonstrated how to apply the datasets by training a machine learning algorithm to reliably predict whether a mechanical test will be successful. It is also said to have made 61% fewer errors in predicting a part’s ultimate tensile strength.
“This is a key enabler to additive manufacturing at industry scale, because they can’t afford to characterise every piece,” Paquit said. “Using this data can help them capture the link between intent, manufacturing and outcomes.”