The Department of Energy’s Oak Ridge National Laboratory (ORNL) continues to show its dedication to advancing more industrialized additive manufacturing in the United States. And it’s not just 3D printed parts and materials coming out from the research institution. According to a recent press release, the ORNL has publicly released 3D printing datasets to help users to verify the quality of additively manufactured parts without restoring to post-production analysis.
Quality control is one of the biggest stumbling blocks slowing down the wider of adoption of additive manufacturing. Although 3D printed parts have been proven to be of the same quality or even superior to components made using more traditional methods, the fact that the industry is so new compared to other processes means that quality control research is nowhere near as extensive. But this announcement will allow users to take a lot of the guesswork out of the equation.
The 3D printing datasets from the ORNL are available publically and can be used for quality control (photo credits: ORNL)
Vincent Paquid, head of the ORNL Secure and Digital Manufacturing section, confirms, “We are providing trustworthy datasets for industry to use toward certification of products. 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.”
3D Printing Datasets From the ORNL
To be more specific, this announcement has been made for what is the fourth and apparently most extensive in a series of additive manufacturing datasets from the ORNL. The data for these have been captured over a decade at DOE’s Manufacturing Demonstration Facility, or MDF, at ORNL as researchers have extensively analyzed and tested resulting components made with different 3D printers. This includes data related to pushing the boundaries of 3D printing with new technologies, materials and even controls.
The result is a 230-gigabyte dataset which covers the design, printing and testing of five sets of parts with different geometric shapes, all made using laser powder bed fusion. This means that anyone using the data will get access to machine health sensor data, laser scan paths, 30,000 powder bed images and 6,300 tests of the material’s tensile strength. The datasets can also be searched for specific information related to rare failure mechanisms, tools to develop online analysis software and even model material properties. Furthermore, this latest 3D printing dataset builds upon previous ones that were dedicated to electron beam melting and binder jetting.
Considering the fact that any evaluation techniques for monitoring the quality of parts include damaging the objects, for example destructive mechanical testing, or are limiting, as non-destructive x-ray computed tomography will not worth on large-scale parts, the ORNL hopes the 3D printing datasets will be the answer to better, more reliable quality control in 3D printing. The institution further notes that due to the comprehensive nature of the datasets, they could be used to train machine learning models to improve quality assessment for any type of component.
In the datasets, ORNL researchers were able to track common powder bed fusion errors and how they came about, including the ones shown above (photo credits: ORNL)
Moreover, testing by ORNL researchers has shown not just how to apply the datasets by training a machine learning algorithm on using measurements taken during the 3D printing process, but also have shown their reliability. It seems that when paired with high-performance computing methods, an algorithm trained this way can reliably predict whether a mechanic test will be successful and also made 61% fewer errors in predicting the ultimate tensile strength of a part. The hope is that this will help improve confidence in whether additional test of the part are needed.
Piquet concludes, “This is a key enabler to additive manufacturing at industry scale, because they can’t afford to characterize every piece. Using this data can help them capture the link between intent, manufacturing and outcomes.” The free 3D printing datasets from the ORNL are available for public use HERE.
What do you think of these publicly released 3D printed datasets from the ORNL? Do you think they will help in the continued industrialization and adoption of additive manufacturing? Let us know in a comment below or on our LinkedIn, Facebook, and Twitter pages! Don’t forget to sign up for our free weekly newsletter here for the latest 3D printing news straight to your inbox! You can also find all our videos on our YouTube channel.