The MRO market currently spans around 9.5% of the total operating cost of an airline. Of this, 70% is covered by heavy-maintenance. Reduction of these costs and improving efficiency could, therefore, be significant for an airline. A possible solution is the optimization of the long-term schedule of heavy-maintenance checks. Current approaches are found to be reliant on manual input and operator experience. Next to that, revisions to the initial schedule are made continuously due to the inherently stochastic nature of aircraft maintenance through non-routine maintenance. Taking this uncertainty into account could offer more robust schedules, saving cost and improve quality of service.

This study proposes a genetic algorithm that can generate robust and efficient C-check schedules for a fleet of heterogeneous aircraft. Uncertainty in check duration and utilization are taken into account by assessing multiple scenarios through min-max optimization. This study is the first to address the long-term scheduling of heavy-maintenance checks while taking uncertainty into account. The proposed genetic algorithm finds robust and efficient C-check schedules for a case study of a European airline for a fleet of over 40 aircraft in under 30 minutes. The total number of C-checks is reduced by 7% while increasing utilization by 4.4%. This could lead to a reduction of direct annual maintenance costs of $122.5K - $612.5K and an additional $1.8M - $7.1M in annual revenue due to the increased availability of aircraft. Monte Carlo simulations show that with a probability of 41% no adjustments to the schedule are necessary over the planning horizon.

This research concerns the problem of scheduling aircraft maintenance tasks, that must be carried in multiple maintenance checks to keep the aircraft airworthy. During this research the allocation of maintenance tasks to their maintenance opportunities is referred to as the task allocation problem. It is a complex combinatorial problem that is solved daily by aircraft operators.We propose a novel two-stage framework capable of solving the task allocation problem, for an entire fleet. A Mixed-Integer Linear Programming (MILP) formulation was developed for both stages of the framework. In the first stage an exact method is used to pre-determine the workforce to allocate per day to each aircraft under maintenance. In the second stage, the task allocation problem is solved in- dependently for each aircraft, allocating task at the work shift level and per workforce skill. Moreover, an approximation algorithm is proposed, using bin packaging problem solution techniques, for both stages of the framework.Both stages were tested and validated using data of 45 aircraft from a European airline. The compu- tational performance of the approximation algorithm is benchmarked using a MILP formulation, solved with a commercial solver. Results indicate that the solution quality of the proposed algorithm remains excellent and runs up to 26 times faster than the exact method.This research is the first to present an optimization model to solve the maintenance task allocation problem, being solved at the work shift level. Furthermore, it presents a bin-packaging approximation algorithm that can be solved within minutes for the 45 aircraft fleet and a planning horizon of 4 years. The framework was validated in practice and the results give insights on the potential benefit of using such framework to solve this daily recurrent problem.