The Department of Energy’s Oak Ridge National Laboratory has released a new additive manufacturing dataset that industry and researchers can use to assess and improve the quality of 3D printed components. The breadth of the datasets can significantly enhance 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.
Data has been collected regularly for more than a decade at DOE’s Manufacturing Demonstration Facility (MDF) at ORNL, where early research into advanced manufacturing, combined with comprehensive analysis of the resulting components, has created a vast trove of information about 3D printer performance. 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 has centuries of experience in quality control. However, additive manufacturing is a newer, non-traditional approach that typically relies on expensive assessment techniques to monitor part quality. These techniques can include destructive mechanical testing or non-destructive X-ray computed tomography, which creates detailed cross-sectional images of objects without damaging them. While informative, these techniques have limitations—for example, they are difficult to implement on large parts. ORNL’s comprehensive 3D printing datasets can be used to train machine learning models to improve quality assessment of any type of component.
“We provide reliable data sets that industry can use for product certification,” said Vincent Paquit, ORNL’s Secure and Digital Manufacturing Section Manager. “This is a structured data management platform 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 230-gigabyte dataset covers the design, printing, and testing of five sets of parts with different geometric shapes, all manufactured using a laser powder bed printing system. Researchers can access data from machine condition sensors, laser scan paths, 30,000 images of the powder bed, and 6,300 material tensile strength tests.
This is the fourth and largest additive manufacturing dataset that ORNL has made publicly available. Previous datasets have focused on building parts manufactured with electron beam powder bed and binder jet printing on MDF. The datasets can be accessed for specific information needed to understand rare failure mechanisms, develop inline analysis software, or model material properties.
The MDF, supported by DOE’s Office of Advanced Materials and Manufacturing Technologies, is a national consortium of collaborators working with ORNL to innovate, inspire, and catalyze the transformation of American manufacturing.
ORNL researchers showed how to apply the datasets By training a machine learning algorithm from measurements taken during the 3D printing process, the trained algorithm, combined with high-performance computing methods, can reliably predict whether a mechanical test will pass. It also made 61% fewer errors in predicting the ultimate tensile strength of a part.
Correlating in-process measurements with the final product is critical to ensuring when additional testing of the part is needed – and when it isn’t. “This is a key part of industrial-scale additive manufacturing because they can’t afford to characterize every part,” Paquit said. “Using this data can help them understand the connection between intent, manufacturing, and outcomes.”
The data generated was collected as part of the Advanced Materials and Manufacturing Technology program, funded by DOE’s Office of Nuclear Energy. These and other smart manufacturing approaches are used to accelerate the development, qualification, demonstration, and deployment of advanced manufacturing technologies to enable reliable and cost-effective nuclear energy.
UT-Battelle manages ORNL 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 is working to address some of the most pressing challenges of our time. For more information, visit energy.gov/science.