While the safety of civil air transportation is enviable, there is still room for improvement. Loss of control is still a leading cause of air transportation accidents. In this paper, we develop a methodology for real-time classification of flight trajectories in order to be able to distinguish between an undamaged aircraft and five different damage scenarios. We use a principal components analysis; this allows a lower-dimensional representation of three-dimensional trajectories in time. Classification trees provide a computationally efficient approach with sufficient accuracy to be able to detect and classify the different scenarios in real-time. We demonstrate our approach by classifying realizations of a 45 degree bank angle generated from NASA Langley's Generic Transport Model flight simulator.
展开▼
