Additive Manufacturing plays a key role in enabling circular and sustainable production through repair and remanufacturing. However, guaranteeing consistent quality in AM-based remanufacturing remains a critical challenge. The process involves complex, nonlinear, and partially observable dynamics, while the condition of returned parts introduces additional uncertainty. Current quality control practices are often fragmented, reactive, and not sufficiently adaptive to real-time process variations.
The main research issue is how to design an integrated and intelligent quality control framework capable of handling uncertainty and supporting reliable decision-making throughout the remanufacturing process. This project investigates the development of a hybrid AI-based approach that combines data-driven learning techniques with model-based methods. The goal is to enable accurate assessment of returned parts, real-time monitoring of in-process performance, and adaptive optimization of remanufacturing actions. Ultimately, the research aims to enhance process robustness, ensure consistent product quality, and support continuous improvement in AM-based remanufacturing systems within a circular economy context.
