Propagation of trained flight performance and observed anomalies to air traffic models

An integrated monitoring framework is developed in this work to detect in-flight performance anomalies in aircraft and investigate the propagation of observed anomalies. A robust detection algorithm is developed and trained using a historical flight dataset recorded from commercial aircrafts to detect flight performance anomalies in real-time, which significantly deviates from normal behavior. Additionally, an air traffic simulator is utilized to integrate aircraft level flight information to airspace. The detected performance anomalies are then introduced in air traffic interface and the impact of aircraft level anomalies on large-scale air traffic system is investigated.