Taxiing Time Prediction Based on the Feature Selection of BP Neural Network Algorithm
In order to accurately predict the taxiing time of departing flights,the influence of multiple fac-tors such as the number of aircraft taxiing on the surface and the average taxiing time at the same time on the taxiing time of departing aircraft was analyzed based on data statistics.In order to make taxiing time prediction better,the Pearson correlation coefficient and random forest algorithm are combined to reduce redundant feature variables.Then combined with the actual flight data,a BP neural network prediction model was established,and the model passed the cross-validation.The prediction results show that the prediction accuracy of the model after feature selection is high,the proportion of error values within 5 min increases from 88.23％to 92.26％,and the prediction effect is relatively stable.The model can accurate-ly predict the taxiing time of departing flights and provide decision-making basis for airport operations.
taxiing time predictionBP neural networkfeature screeningpearson correlation coefficientrandom forest
万方数据
维普
