In the past years, the increasing availability of health-monitoring data for aircraft systems has stimulated the development of advanced algorithms for Remaining-Useful-Life (RUL) prognostics. Most such RUL prognostics are developed using a model-based or a machine-learning approach. Few studies, however, integrate these RUL prognostics into maintenance planning. This session aims to present recent progress on the integration of RUL prognostics of aircraft systems into maintenance planning.
Chair: Mihaela Mitici (TU Delft) - M.A.Mitici@tudelft.nl
All systems, materials, and structures eventually degrade or get damaged during their lifecycle. The sources of these defects can be varied from environmental conditions to operational usage. There is an assortment of sensor packages and technologies for engineers to choose that can be applied to monitor the influence of these degradation factors. Crucially, the techniques employed to exploit the data collected from the sensor systems have a significant impact on the effectiveness of damage detection and monitoring. The combination of the right sensors with the appropriate prognostic/diagnostic algorithm provides valuable information to the engineer to make the best decision for maintenance action. The goal of this session is to share the state-of-the-art research in these health monitoring techniques and learn from the challenges encountered through real-life applications.
Technical Session Organizer: NLR - Royal Netherlands Aerospace
Centre Main coordinator: Vis Dhanisetty (email@example.com)
Co-organizers: Marcel Bos (firstname.lastname@example.org), Frank Grooteman (email@example.com), and Jason Hwang (firstname.lastname@example.org)