Researchers from the US Department of Energy’s (DOE) Argonne National Laboratory announced the development of a new AI-driven defect-detection and prediction method in 3D printed materials, which could revolutionise the additive manufacturing process. One of the main reasons why users do not trust 3D printed parts is structural defects that form during the construction process, but this new method may change that perception as the results improve.
Many industries rely on metal additive manufacturing to create parts and components quickly. Additive manufacturing is used to create rocket engine nozzles, pistons for high-performance cars, and custom orthopaedic implants.
“The APS offered the 100% accurate ground truth that allowed us to achieve perfect prediction of pore generation with our model.”
– Tao Sun, University of Virginia
AI-driven defect-detection in 3D printed materials
A research team led by Argonne and the University of Virginia recently published this new AI-driven defect-detection method in the journal Science (UVA). The researchers used various imaging and machine learning techniques to detect and predict the formation of pores in 3D printed metals in near-real time.
The metal samples used in the study were created using a process known as laser powder bed fusion, which involves heating metal powder with a laser and then melting it into the desired shape. However, this method frequently results in the formation of pores, which can impair the performance of a part.
Many additive manufacturing machines have thermal imaging sensors that monitor the build process, but because they only image the surface of the parts being constructed, they can miss the formation of pores. The only way to detect pores inside dense metal parts is to use intense X-ray beams, such as those produced by Argonne’s Advanced Photon Source (APS), a DOE Office of Science user facility.
“Our X-ray beams are so intense that we can image more than a million frames per second. These images allowed the researchers to see pore generation in real time. By correlating X-ray and thermal images, the scientists discovered that pores formed within a sample cause distinct thermal signatures at the surface that thermal cameras can detect.”
– Samuel Clark, an assistant physicist at Argonne National Laboratory
The researchers then used only thermal images to train a machine learning model to predict the formation of pores within 3D metals. They validated the model using X-ray image data that they knew accurately reflected the formation of pores. The model’s ability to detect thermal signals and predict pore generation in unlabeled samples was then tested.
Tao Sun, an associate professor at UVA said, “The APS offered the 100% accurate ground truth that allowed us to achieve perfect prediction of pore generation with our model.”
Many additive manufacturing machines already have sensors, but they aren’t nearly as accurate as the method discovered by the researchers.
“Our approach can readily be implemented in commercial systems. With only a thermal camera, the machines should be able to detect when and where pores are generated during the printing process and adjust their parameters accordingly.”
– Kamel Fezzaa, a physicist at Argonne National Laboratory
For example, if a machine detects a major defect early in the manufacturing process, it can automatically stop building a part. Even if the manufacturing process is not halted, the new method can provide information on where pore defects may exist within the part, saving users time during inspection.
“If you have a log file that tells you these four locations could have defects, then you’re just going to check out these four locations instead of looking at the entire part,” said Sun.
Sun concluded by saying, “The ultimate goal is to create a system that not only detects defects, but repairs them during the manufacturing process. Moving forward, the researchers will study sensors that can detect other types of defects that occur during the additive manufacturing process. In the end, we want to develop a comprehensive system that can tell you not only where you possibly have defects, but also what exactly the defect is and how it might be fixed.”
