Abstract: For the existing path planning models, it is difficult to solve the problem of optimal path planning under different aircraft types and transportation time conditions with a single cost planning. This paper combines aircraft type configuration, transportation time and system cost, and establishes an optimization model of hub-and-spoke airline network through the location of hub cities, the flow distribution from non-hub city nodes to hub city nodes, the flight time of the fleet and the fleet size. The entropy method is used to establish the chromosome selection mechanism, and the adaptive crossover rate is introduced to improve the genetic algorithm. The improved algorithm (IGA) is used to optimize the location distribution of the best route and hub nodes. Our method is compared with the traditional genetic algorithm, bee colony algorithm and grey Wolf algorithm. The research indicates that combining different aircraft type configurations and transportation times is superior to single-cost path planning. By optimizing and solving the hub-and-spoke airline network model with the improved algorithm, the total system cost is reduced by 3.41×1010, providing a reference for the reasonable allocation of fleet resources.

Key words: improved genetic algorithm, multi-objective optimization, route network, path planning