Defect detection in additive manufacturing using image processing techniques

Additive manufacturing (AM) allows to produce parts layer by layer from an STL file. It is then possible through this technology to obtain customized geometries and complex shapes at a lower cost. However, these shapes pose problems of defect control, microstructure, residual stresses, and deformations in parts. This study aims to develop an efficient method allowing defect detection while printing pieces using Fused Deposition Modelling (FDM). The monitoring system contains a camera acquisition system for automatic image capture of filament layers deposited on the print bed. Various monitoring techniques have been simulated to achieve an optimal defect correction solution. Material excess and deficiency are detectable in the layer of actual printed parts. Defects are controlled and compared to original part obtained from Computer Aided Design (CAD). An app-designer application was created in this regard. It displays the image reference generated from the G-code, the layer image captured by the camera, and returns the error percentage in the printed layers. The developed method of surface calculation has shown its efficiency in detecting the lack and excess of material, which has an accuracy of 1.07%. This method allows users to stop and monitor printing to save cost, material, and time.