Aircraft maintenance planning under uncertainty
I. Tseremoglou (TU Delft - Aerospace Engineering)
D. Zarouchas – Promotor (TU Delft - Aerospace Engineering)
I.I. de Pater – Copromotor (TU Delft - Aerospace Engineering)
B.F. Santos – Copromotor (KLM Royal Dutch Airlines)
More Info
expand_more
Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.
Abstract
Nowadays, aircraft maintenance is performed following either the preventive or the corrective approach. However, with the increased number of sensors installed in modern aircraft and the recent advancements in the field of machine learning and predictive data analytics, airlines are gradually shifting to Condition-Based Maintenance (CBM). CBM is based on the use of Remaining Useful Life (RUL) prognostics to anticipate failures and leverages these predictions to optimize the scheduling of maintenance tasks. Currently, most airlines (in the best case) use linear programming tools for scheduling maintenance tasks. However, when adjustments to the maintenance schedule are necessary, they often resort to manual scheduling methods. This approach leads to sub-optimal planning.
This dissertation aims to develop automated data-driven optimization approaches, to increase the efficiency of maintenance operations of an aircraft fleet in a CBM environment. Since the traditional maintenance strategies will remain necessary for an effective transition to CBM, the focus is placed in a ’hybrid’ CBM context, where each aircraft is having multiple components that are maintained through the preventive, corrective or the CBM approach, resulting to a mixture of preventive, corrective and CBM tasks....