The Department of Energy’s Oak Ridge National Laboratory has released a new set of additive manufacturing data that industry and researchers can use to evaluate and improve the quality of 3D-printed components. The breadth of the data sets could greatly enhance efforts to verify the quality of additively manufactured parts using only information collected during printing, without the need for expensive and time-consuming post-production analysis.
The data has been routinely captured for a decade at the Department of Energy’s Manufacturing Demonstration Facility, or MDF, at ORNL, where early-stage research into advanced manufacturing coupled with extensive analysis of the resulting components has created a vast trove of information about how 3D printers perform. Years of experience pushing the boundaries of 3D printing with new materials, machines, and controls have given ORNL the unique ability to develop and share comprehensive datasets. The latest dataset is Now available for free via an online platform..
Traditional manufacturing benefits from centuries of experience in quality control. However, additive manufacturing is a newer, unconventional approach that typically relies on expensive assessment techniques to monitor the quality of parts. These techniques may include destructive mechanical testing or nondestructive X-ray computed tomography, which creates detailed cross-sectional images of objects without damaging them. While useful, these techniques have limitations—for example, they are difficult to perform on large parts. ORNL’s extensive 3D printing datasets can be used to train machine learning models to improve quality assessment of any type of component.
“We provide trustworthy datasets for industry to use in the product certification process,” said Vincent Paquette, head of the Digital and Secure Manufacturing Division at Oakland National Laboratory. “It’s a data management platform designed to tell the complete story of an additively manufactured component. The goal is to use in-process measurements to predict the performance of the printed part.”
The 230GB dataset covers the design, printing and testing of five sets of parts with different geometries, all made using a laser powder printing system. Researchers have access to machine health sensor data, laser scan paths, 30,000 images of laser powder and 6,300 tests of the material’s tensile strength.
This is the fourth and largest in a series of additive manufacturing datasets that Oakland National Laboratory has made available to the public. Previous datasets have focused on the construction of parts made using electron beam powder and adhesive jet printing in medium density fiberboard. The datasets can be searched for specific information needed to understand rare failure mechanisms, develop online analysis programs, or model materials properties.
MDF, supported by the Department of Energy’s Advanced Materials and Manufacturing Technologies Office, is a national consortium of collaborators working with Oak Ridge National Laboratory to innovate, inspire, and catalyze the transformation of manufacturing in the United States.
Researchers at Oak Ridge National Laboratory Explain how to apply data sets. By training a machine learning algorithm using measurements taken during the 3D printing process, and using high-performance computing techniques, the trained algorithm could reliably predict whether a mechanical test would pass or fail. It also made 61% fewer errors in predicting the ultimate tensile strength of a part.
Linking in-process measurements to the final product is essential to providing confidence about when additional testing of a part is needed and when it isn’t. “This is a key enabler for industrial-scale additive manufacturing, because they can’t afford to characterize every part,” said Paquette. “Using this data can help them capture the link between intent, manufacturing, and outcomes.”
The resulting data was part of the Advanced Materials and Manufacturing Technologies program, funded by the Department of Energy’s Office of Nuclear Energy. These and other smart manufacturing approaches are being used to accelerate the development, qualification, demonstration, and deployment of advanced manufacturing technologies to enable reliable and economical nuclear energy.
The University of Texas at Battelle manages Oakland National Laboratory for the Department of Energy’s Office of Science, the largest supporter of basic research in the physical sciences in the United States. The Office of Science works to address some of the most pressing challenges of our time. For more information, please visit energy.gov/science.
