US team explores machine learning for detecting 3D printing defects

In a paper published by Advanced Materials Technologies, the group explained how it has developed so-called convolutional neural networks (CNNs), a popular type of algorithm primarily used to process images and videos, to predict whether a part will be good by looking at as little as 10 milliseconds of video.

"This is a revolutionary way to look at the data that you can label video by video, or better yet, frame by frame," said principal investigator and LLNL researcher Brian Giera. "The advantage is that you can collect video while you're printing something and ultimately make conclusions as you're printing it.”

Giera said that the approach has considerable advantages over the use post-build sensor analysis, which is expensive. With parts that take days to weeks to print, CNNs could prove valuable for understanding the print process, learning the quality of the part sooner and correcting or adjusting the build in real time if necessary.