Ambuj Kumar Agarwal, D. Angeline Ranjithamani , Pavithra M, A.Velayudham, Anandaraj Shunmugam and Mohammed Ismail B
Additive manufacturing, or 3D printing, is a vital innovation in the field production processes. Furthermore, the decision to change the filling without influencing the outside creates a different vulnerability for 3D printer technologies. This research includes a clause to identify fraudulent filling problems in the printed object: 1) look into malevolent faults in the 3D printing process, 2) remove outliers from modeled 3d printer method photos, and 3) perform an object detection test with one sample of the non-infill test set and another cluster of fault reinforced test set from the 3D printing process. Layer by layer, the photos are gathered from the isometric perspective of the program model display. The data extracted is provided to the developed algorithms, Naive Bayes method, and J48 Decision Trees. Among them, the Naive Bayes method shows a higher accuracy rate of 86%, and J48 Decision Trees show an accuracy of 96%.
English 
Spanish 
Chinese 
Russian 
German 
French 
Japanese 
Portuguese 
Hindi