ORNL, U.S. Dept. of Energy
3D printed part sliced into small test pieces and digital model by ORNL
The Department of Energy’s Oak Ridge National Laboratory (ORNL) has publicly released new additive manufacturing datasets to help industry and researchers to evaluate and improve 3D printed part quality.
The data is being shared publicly through an online platform to provide “a complete story” around additively manufactured parts using information gathered during printing rather than relying on costly time-consuming post-production analysis.
ORNL said it has captured a ‘vast of trove of information’ over the the last 10 years at its Manufacturing Demonstration Facility, combining early-stage research in advanced manufacturing and analysis of 3D printed components. The data is now being used to train machine learning models to improve quality assessment for any type of printed component. Paired with high-performance computing methods, ORNL says the trained algorithm can use measurements taken during the 3D printing process to reliably predict whether a mechanical test will be successful, and has made 61% fewer errors in predicting a part’s ultimate tensile strength.
“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 relies on expensive evaluation techniques such as destructive mechanical testing or non-destructive X-ray computed tomography, which offer detailed cross-sectional images of objects but can be limited when it comes to larger parts. This 230-gigabyte dataset covers the design, printing and testing of five sets of laser powder bed parts with different geometric shapes. 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. Paquit believes the data to be a “key enabler to additive manufacturing at industry scale” by helping manufacturers to “capture the link between intent, manufacturing and outcomes.”
This is the fourth and most extensive set of additive manufacturing datasets ORNL has made publicly available. The particular set was generated as part of the Advanced Materials and Manufacturing Technology Program, funded by DOE’s Office of Nuclear Energy, which is being used to accelerate the development of advanced manufacturing technologies for reliable and economical nuclear energy.
