초록
The go-around procedure plays a crucial role in aviation safety, allowing pilots to abort unsafe landings and attempt a new approach. While existing studies have primarily focused on predicting the onset of go-arounds, relatively little attention has been paid to evaluating aircraft stability and performance after a go-around has been initiated. This study aims to address this gap by systematically assessing the dynamic response and stability of aircraft following a go-around using Quick Access Recorder (QAR) data. The methodology involves classifying go-around events into 'near-ground' and 'at-altitude' categories, and analyzing changes in pitch, descent rate, engine performance, and environmental factors after the initiation of the go-around to evaluate its stability and efficiency. The XGBoost machine learning algorithm is employed to model the aircraft's response post go-around and to predict stability across various go-around scenarios. The findings from this study provide insights that can enhance the safety and efficiency of go-around procedures through systematic analysis of QAR data, contributing to improvements in operational protocols and pilot training programs.