Designing an Automatic Load Planning Tool for Military Transport Aircraft
I.P. van Alkemade (TU Delft - Aerospace Engineering)
P.C. Roling – Mentor (TU Delft - Aerospace Engineering)
M.J. Ribeiro – Graduation committee member (TU Delft - Aerospace Engineering)
A. Bombelli – Graduation committee member (TU Delft - Aerospace Engineering)
Daan Wiltenburg – Mentor (Royal Netherlands Aerospace Centre)
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
This paper proposes two complementary optimisation approaches to support the the load planning problem (LPP) for military transport aircraft. A mixed-integer linear programming (MILP) model is designed as a baseline method to find exact, high-quality solutions. The model includes operational procedures derived from semi-structured interviews with loadmasters and mission planners. To address scalability limitations from the traditional MILP formulation, a hybrid TS-MILP approach is designed. It combines tabu search (TS) in a first layer for fast global assignment of items over a fleet, and MILP refinement in a second layer for constraint-accurate positioning optimisation within each aircraft. MILP and TS-MILP are evaluated across three realistic scenarios on the C-130 Hercules military transport aircraft, where the fleet size is increased from 1 to 16 aircraft, and the input size and composition varies for troops and cargo. MILP shows best results for the LPP with palletised cargo only, where up to a fleet of 6 aircraft, a feasibility success rate of 45.5 to 100$\%$ is achieved within a time limit of 600 seconds. For more complex item compositions, TS-MILP proves scalability and a better success rate and runtime than MILP while maintaining solution quality. The study demonstrates that by leveraging the strengths of both exact and heuristic methods, load planning can be effectively automated and be used as a decision-making tool for military operations.