Trustworthy Artificial Intelligence for Condition Monitoring in Metal Additive Manufacturing to Facilitate a Circular Economy Framework

This paper presents an AI-based condition monitoring service for predictive maintenance of a key component in a cold gas spray metal additive manufacturing system. Following a CRISP-DM methodology, the model leverages operational data collected from a technology demonstrator at TU Dortmund University and is further validated with data from the system manufacturer, Impact Innovations. The approach identifies critical indicators of component degradation to enable proactive maintenance scheduling, achieving promising performance on a holdout test set (Accuracy = 0.99, F1-score = 0.96) as part of a proof-of-concept demonstrator with Technological Readiness Level 5 (TRL 5). By integrating explainability methods and uncertainty quantification, the paper improves the transparency and reliability of predictive maintenance decisions, resulting in an overall more trustworthy operation of the condition monitoring service. While the primary contribution lies in advancing intelligent condition monitoring strategies, this approach is also envisioned as a catalyst for broader sustainable manufacturing frameworks. Future work will explore its integration into circular economy applications, where trustworthy condition monitoring may serve as a driver for circularity.