As reported by 3D Printing Industry, a team of researchers at Kansas State University have recently released an article in the scientific journal Procedia Manufacturing, in which they detail their development of an AI system for the purposes of monitoring 3D printing processes.
These researchers, from the school’s Department of Industrial and Manufacturing Systems Engineering (IMSE), have developed this system using “integrated supervised machine learning, a camera, and image processing software.” This system is now able to “assess 3D printed parts in real-time.”
As the researchers’ article explains: “Conventionally, the quality of 3D printed parts is being checked after the printing is done. Detecting defects during the printing process not only helps to eliminate waste of material and time but also prevent the need to reprint the whole part.”
Indeed, the researchers’ system “demonstrates that with the use of step-by-step quality checks, production-scale 3D printing operations can be improved with cost and time efficiency.” The researchers used a LulzBot Mini 3D printer during their study.
As for the process itself, “the researchers proposed a three-step quality monitoring system to identify and assess the stages of the 3D printing process. Firstly, the researchers established checkpoints for a 3D printed part according to its geometry. Secondly, with the help of a mounted camera, images were taken of the semi-finished parts at each checkpoint. Finally, part quality was automatically assessed through image processing and a supervised machine learning algorithm called a support vector machine (SVM).”
This system can detect both completion failure defects or geometrical defects.
Image and Quotes Courtesy of 3D Printing Industry