An improved aircraft hard landing prediction model based on panel data clustering

Abstract

This paper proposes a hard landing prediction method based on panel data clustering with flight data. The hard landing is a hazard that is critical to flight during the landing phase. It may cause damage to the aircraft structure, resulting in direct or indirect economic losses, damaging to human comfort and other adverse consequences. Firstly, based on the panel data in economics, the flight panel data is established; secondly, extracts the characteristic information of several key flight variables that affect the hard landing in each landing. The feature information includes mean, standard deviation, median, maximum, kurtosis, skewness and trend, and constitutes the eigenvectors describing the landings; then the k-means method is used to cluster the feature information. Finally, the empirical study is carried out on the 22 landing data of fixed wing unmanned aerial vehicles (UAVs). The results show that the clustering of flight panel data can be applied to hard landing prediction, and the prediction effect is obvious.