Prediction of Tail Strike Incidents in Flight Training Using Ensemble Learning Models

To achieve accurate predictions of tail strike events during the landing phase of flight training, we propose a stacking ensemble learning prediction model that uses Random Forest (RF), Support Vector Regression (SVR), K-Nearest Neighbors (KNN), and Adaptive Boosting (AdaBoost) as base models, with Logistic Regression (LR) serving as the meta-model. This model is built on non-exceedance flight data recorded on airborne SD cards. By evaluating the importance scores of the feature parameters influencing tail strike events, we identified the optimal set of features for model input while using the landing pitch angle as the model output. We then compared the R2 and RMSE of each model. The results indicate that under a prediction horizon of 5 s prior to landing, the ensemble learning model demonstrates high predictive accuracy. This capability provides flight trainees with sufficient reaction time to adjust their flight attitudes, thereby helping to avoid the occurrence of tail strike events during landing.