Analysis of Machine Learning Techniques for Fault Detection in 3D Printing

In recent years, 3-D printing has gained sizable interest in the production enterprise due to its capacity to supply complex designs and prototypes. but the high degree of automation and complexity concerned with the manner also pose demanding situations in detecting and resolving ability faults. To cope with this issue, researchers have turned to device-getting-to-know techniques to broaden automated fault detection systems for 3-D printing. This paper evaluates the numerous gadget mastering procedures in fault detection for 3D printing, including supervised, unsupervised, and semi-supervised mastering methods. The effectiveness and limitations of every process are mentioned at the side of their applications in one-of-a-kind tiers of the 3-D printing method. The analysis shows promising consequences for using gadgets to gain knowledge of fault detection, highlighting the potential for enhancing the general first-class performance of 3-D printing. However, similarly studies and developments are had to deal with demanding situations along with restricted data availability and information heterogeneity.