AI-based monitoring of 3D printing

The monitoring particularly addresses the areas of service and production in the value chain. SWMS Systemtechnik Ingenieurgesellschaft mbH is a technology company for digital industry solutions and not a direct provider of 3D printing services, so the AI process initially has little impact on resource efficiency in its own company (in the context of testing and developing the pilot). However, the integration of a defect detection component into the control software for additive manufacturing has a multiplier effect, as the software can be used by many different companies.

As the printed objects are continuously monitored for defects during the printing process instead of being controlled after the printing process is complete, the AI solution will have a significant impact on the consumption of printing material, known as filament.
It is estimated that this can save about a third of the material used for desktop 3D printing. In addition, resources are saved for operating and controlling the robot arm, heating the filament and, if necessary, actively cooling the printing material.

The costs for the specific application of the AI solution are relatively low, since these only require the trained AI model to evaluate the visual data from the cameras, which can be carried out with standard hardware. Higher costs arise when training the AI models, since the training cycles usually require more powerful hardware or access to computing clusters. In addition, costs arise from the manual labelling of the data and the use of sensors, the computer for storing the data, the license fees for the system software and the construction material for the setup. How quickly the investments pay off depends on several parameters, such as the print volume, the amount of filament used as well as the tolerance range for deviations in printing.