Oak Ridge National Laboratory (ORNL) scientists have built a new software to assess the quality of parts being developed by powder bed 3D printers in real-time.
Called ‘Peregrine’, the new AI software has been designed to support ORNL’s advanced manufacturing ‘digital thread’ that collects and analyzes data through every step of the manufacturing process – from design to feedstock selection to the print build to material testing.
This is to ensure that every part rolling off a 3D printer is ready to install in essential applications like cars, airplanes, and energy facilities.
According to the project’s team lead Vincent Paquit, standard cameras were used in the research, ranging in most cases from 4 to 20 megapixels and installed so they produce images of the print bed at each layer.
The new software has been tested successfully on seven powder bed printers at ORNL so far, including electron beam melting, laser powder bed, and binder jetting.
Some of these are part of the Transformational Challenge Reactor (TCR) Demonstration Program that is pursuing the world’s first 3D printed nuclear reactor.
Powder bed printers distribute a fine layer of powder over a build plate, with the material then melted and fused using a laser or electron beam.
Binder jetting systems on the other hand rely on a liquid binding agent rather than heat to fuse powdered materials.
The systems print layer by layer, guided by the CAD blueprint, and are popular for the production of metal parts.
Nevertheless, they all face problems such as uneven distribution of the powder or binding agent, spatters, insufficient heat, and some porosities that can result in defects at the surface of each layer.
Some of these issues can happen in such a very short time-frame and they go undetected by conventional techniques, opines ORNL’s principal investigator for Peregrine, Luke Scime.
This is why Peregine is important. It uses a custom algorithm that processes pixel values of images, taking into account the composition of edges, lines, corners and textures.
If the software detects an anomaly that may affect the quality of the part, it automatically alerts operators so adjustments can be made.
Image and content: Luke Scime/ORNL