Advancing Machine-to-Machine Learning for a Network of 3D Printers in Industrial Cyber-Physical Systems

This paper explores the integration of machine-to-machine calibration within a cyber-physical system. As Industry 4.0 revolutionizes manufacturing processes, the focus shifts to interconnected machines for enhanced efficiency. This study addresses the critical role of cyber-physical systems in managing 3D printers for additive manufacturing and exploring automatic pressure advance calibration using machine vision. An instrumented 3D printer was used to calibrate an un-instrumented 3D printer, showing a systematic calibration process. Test beads were printed on the instrumented system and the optimal pressure advance time constant value was automatically found. The optimal pressure advance time constant value was then applied to a non-instrumented system to print a test part. A case study on ball valve production illustrates the effectiveness of our approach in mitigating defects and optimizing print quality. The results of the case study demonstrate the effectiveness of our automated calibration system.