Aircraft Damage Classification by using Machine Learning Methods

Abstract

Safety is the most significant factor that affected incidents (non-fatal) and accidents (fatal) in civil aviation history related to scheduled flights. In the history of scheduled flights, the total incident and accident number until 2022 is 1988. In this study, 677 of them are taken into consideration since 11 September 2001. The purpose of this study is to reveal the factors that can classify type of aircraft damages such as none, minor and substantial in all-time incidents and accidents. ML algorithms with different configurations are applied for the classification process. The RFE and PCA are used to find the most important factors that are effective on the classification. Four components are found with PCA as zone, weather, time, and history. The results of multinomial logistic regression and ANNs showed that the most important 5 features are latitude, wind speed, wind direction, year, and longitude to classify aircraft damage. Then, temperature, total number of injury passenger, and month factors comes with more than 50% importance. The managerial implication of the study shows that as time passes the number of substantial accidents has decreased due to increasing level of safety precautions in civil aviation.