• electron beam melting
• defects detection
• quality control
• medical devices
• artificial intelligence

Quality control is a key aspect in medical devices manufacturing. In the case of metal orthopedic implants fabricated using Additive Manufacturing technologies, the presence of defects could affect the final part quality in term of structural integrity and mechanical properties. In this context, the aim of the thesis is to design and implement an Artificial Intelligence (AI) based system capable of automated detection of defects that could occur in prosthetic components, such as tibial trays, printed through Electron Beam Melting (EBM) in CoCr alloy. An algorithm was developed ad hoc to analyze images of the manufacturing process taken from a camera embedded in the printer (Arcam Q10plus). Images can be used to identify defects, performing a non-destructive evaluation which supports the process of part qualification. The developed algorithm automates and improves the visual inspection task conducted by human experts, including quantitative assessment on the size and location of the defects and reporting the presence of high defects density areas. The defects detection is performed with a sensitivity of 91% and a precision of 76%. Furthermore, during the thesis a comparison with another non-destructive evaluation technique, namely the computed tomography (CT) evaluation, was performed to validate the algorithm (percent agreement of 97%). The developed assessment allows to quickly evaluate an entire printing volume with several components representing a reliable and fast tool for defects detection and quality control of EBM-printed prosthetic components.