This work addresses the cockpit crew training scheduling problem. The objective is to produce a robust cockpit crew training schedule, including the assignment of trainees, instructors and simulators. To attain this objective, we propose a scheduling framework composed of four modules: a Training Scheduling & Assignment Model (TS&AM), a Disruption Generator (DG), a Rule-Based Recovery (RBR) algorithm, and a Neural Network (NN). The TS&AM is an integer programming model that integrates the scheduling of courses and the assignment of resources. The output roster serves as input for a data-driven DG based on Monte-Carlo Simulation. The disruptions are then solved using the RBR algorithm. Finally, The NN feedback algorithm learns the recovery costs experienced in the disruption impact simulator and updates these costs in the TS&AM to generate more robust rosters. The proposed modelling framework was calibrated, tested, and demonstrated in a simulation environment developed using four years of historical crew training data from a major European airline. The experiment showed that our approach outperformed the roster produced by the airline. The approach proposed produces rosters that reduce recovery costs by 21 percent, while still decreasing total training costs by 3 percent.

In airline crew rostering, pilots’ requests to operate specific flights need to be evaluated efficiently to avoid inefficient schedules. Despite the relevance of correctly assessing and granting crew requests, this topic has received very little attention in the literature. In this paper, we address the case this process is a dynamic problem, in which flight requests are submitted while others have already been granted and pre-assigned. This is the first work to dynamically model flight requests during the crew rostering process. We propose a simulation-trained neural-network algorithm to evaluate flight requests, providing a systematic way of assessing flight requests and supporting the definition of a cost-efficient request granting policy. To train and test this algorithm, we developed an innovative rolling rostering framework that captures the dynamic process in practice. The framework relies on an integer linear programming crew rostering model solved with the help of a column-generation algorithm. The neural-network algorithm is trained and tested in a case study with a major European airline. The results show that the algorithm is more effective than the current practice at the airline, granting 22% more requests while using the same workforce to operate the flight schedule.