A Machine Learning-Based Extraction of Cruise Phase from Trajectory Data

초록

When analyzing historical trajectory data, identifying the cruise phase is crucial. However, duetovariousverticalmaneuversalongthecourseoftheflight,itisnotstraightforwardtoextract the cruise phase, and rule-based algorithms tend to be inaccurate when the vertical trajectory becomes complicated. This study presents a machine learning-based technique to extract the cruise phase of a flight from recorded trajectory data. The trajectory data are normalized by maximumtimeandaltitude, and then grouped into clusters using an agglomerative hierarchical clustering technique and a Gaussian Mixture Model algorithm. Finally, a rule-based selection Downloaded by Hak-tae Lee on August 2, 2024 | http://arc.aiaa.org | DOI: 10.2514/6.2024-4552 criterion is applied to each cluster centroid to identify search regions for top-of-climb (TOC) and top-of-descent (TOD). The TOC and TOD are extracted for the individual trajectory that belongs to the cluster. The study classified a total of 38,051 trajectories into 41 clusters. The cruise phase was extracted for 36,712 flights, accounting for 96.5% of the total trajectories. The proposed method is particularly useful when the cruise phase needs to be extracted for a large data only with the trajectory data without the flight management system information.