Predictive 3D Printing with IoT

Abstract

Industry 4.0 marks a new industrial revolution centered around technologies that connect digital and physical realms, revamping how information is used to manage work. Two core enablers are the Internet of Things (IoT) and 3D printing. The former monitors the real-time status of a complex system, and the latter responds to that information with agile manufacturing. Nevertheless, how exactly this can be done remains unclear. To gain insights, we consider the context of a 3D printer supplying a critical part installed in multiple machines embedded with sensors and interconnected via IoT. While it is tempting to perceive that the marriage of 3D printing and IoT would make on-demand printing a reality, our results indicate that this is not necessarily so. The true benefit of the marriage is enabling predictive printing. In particular, it is optimal for the 3D printer to print-to-stock predictively in advance of demand, triggered by a system-lifetime-status dependent threshold. Whether it is optimal to print-on-advance-demand to achieve minimum inventory depends crucially on the printing speed. We further quantify the impact of IoT on system cost and inventory by separately assessing the impact of advance demand information from embedded sensors and that of IoT’s real-time information fusion from sensor interconnections. We demonstrate that information fusion intensifies the inventory reduction through advance demand information, and IoT’s impact hinges upon the effectiveness of embedded sensors. Our framework can be leveraged to aid IoT investment decisions and to help develop operating policies for predictive 3D printing.