Prediction of civil aircraft hard landing risk based on GBDT-GS method

Hard landing may cause symptom events such as structural damage to the aircraft, or even cause fatal flight accidents. In view of the lack of physical analysis in the current hard landing risk assessment, in order to effectively implement the hard landing risk identification and grade judgment criteria, so as to improve the quality of pilots' landing operations, a hard landing risk prediction model was constructed based on the gradient boosting decision tree algorithm (GBDT) and grid search (GS) combined with flight state analysis. Firstly, the five flight state parameters closely related to the hard landing were determined by analyzing the aircraft force and constructing the landing flight kinematic equation; then, the flight state data was extracted from the data recorded by the onboard Quick Access Recorder (QAR) to construct a data set, and according to the QAR parameter characteristics, the hard landing risk prediction model was constructed by the GBDT algorithm, and the model parameters were optimized by GS; finally, taking the "Chengdu-Shenyang" route of an airline as an example, 530 QAR data were selected to train and test the model, and the results were compared with those of random forest, logistic multivariate regression, recurrent neural network (RNN) and other algorithms. The results show that the performance of GBDT-GS algorithm in predicting hard landing risk is better than other algorithms, and the prediction accuracy reaches , which 92%，verifies the objective effectiveness of the model.