The imbalance between air traffic capacity and demand, especially in the terminal maneuvering area, constrains the development of the civil aviation industry. To enhance the capacity, providing aircraft with optimal trajectories is the way forward. The key challenge of building a trajectory optimization model lies in embedding air traffic controllers’ operation experience into the optimization process. Previous efforts proposed a data-driven trajectory optimization method to learn operation experience from historical data for trajectory optimization use, which is limited by the issues of insufficient quantity and diversity of trajectory data. To solve those issues, an improved model is proposed to further improve the trajectory optimization performance. Firstly, this paper exploited a connecting-based trajectory generation model to generate massive synthetic trajectories. Then, this paper used a data-mining-based valuable trajectory identification technique to find valuable trajectories that can be used to enrich its operation experience. A case study on Guangzhou Baiyun International Airport was conducted to verify the proposed method. The results show that the proposed model successfully incorporates more operation experience during the optimization process. Compared with the benchmark model, the proposed model can adapt to more complex air traffic and provide optimal trajectories for more incoming aircraft.
Improved Data-Driven Trajectory Optimization Method Utilizing Deep Trajectory Generation
2024-07-19
15 pages
Aufsatz (Zeitschrift)
Elektronische Ressource
Englisch
TRAJECTORY GENERATION DEVICE, TRAJECTORY GENERATION METHOD, AND TRAJECTORY GENERATION PROGRAM
Europäisches Patentamt | 2021
|TRAJECTORY GENERATION DEVICE, TRAJECTORY GENERATION METHOD, AND TRAJECTORY GENERATION PROGRAM
Europäisches Patentamt | 2021
|