Optimisation of Aircraft Maintenance Schedules

TL;DR

This paper tackles the aircraft maintenance scheduling problem, where 24 work packages across 20 aircraft must be assigned to technicians with heterogeneous qualifications within fixed turnaround windows. It introduces AERO-EA, a steady-state evolutionary algorithm, with a hierarchical chromosome representation that preserves intra‑WP WO order while allowing flexible WP reordering and staff allocations. The approach uses custom operators and a penalty-based fitness to enforce scheduling feasibility, validated on 60 synthetic instances across relaxed and tight workload scenarios. Results show the best runs achieve zero penalties in all instances, demonstrating the method’s feasibility and robustness, with discussion on practical deployment and future enhancements such as real-world data, soft constraints, and multi‑objective extensions.

Abstract

We present an aircraft maintenance scheduling problem, which requires suitably qualified staff to be assigned to maintenance tasks on each aircraft. The tasks on each aircraft must be completed within a given turn around window so that the aircraft may resume revenue earning service. This paper presents an initial study based on the application of an Evolutionary Algorithm to the problem. Evolutionary Algorithms evolve a solution to a problem by evaluating many possible solutions, focusing the search on those solutions that are of a higher quality, as defined by a fitness function. In this paper, we benchmark the algorithm on 60 generated problem instances to demonstrate the underlying representation and associated genetic operators.