Flight arrival time prediction method and system based on data mining analysis

Abstract

The invention discloses a flight arrival time prediction method and system based on data mining analysis. The flight arrival time prediction method comprises the steps of S1, carrying out flight historical operation data matching fusion and standardization processing; s2, carrying out historical operation data feature screening and correlation analysis; 3, constructing a prediction model; and S4,inputting the characteristic variable data of the predicted flight into the regression prediction model, and performing calculation to obtain a prediction value of the remaining flight time of the flight. According to the invention, flight historical data is collected from an ADS-B system, an ACARS system and other devices; firstly, data is subjected to association and standardization processing;Pearson correlation coefficient calculation is performed according to feature variable screening and feature value calculation, and a regression prediction model based on an XGBoost algorithm is constructed; the parameter optimization model is continuously adjusted to obtain the regression prediction model with the optimal accuracy, the predicted arrival time of the flight can be predicted after the characteristic variable data of the predicted flight is input into the model, and the prediction precision of the arrival time of the flight is improved.

Description

technical field [0001] The invention relates to the field of flight operation management, in particular to a method and system for predicting flight arrival time based on data mining analysis. Background technique [0002] The year-by-year increase in the volume of civil aviation business puts forward higher requirements on the level of flight operations, especially in terms of airline flight punctuality and airport operation efficiency. Accurate estimation of flight arrival time is conducive to improving the operating efficiency and safety level of airports and airlines, and has important and direct significance for improving flight punctuality, improving flight security and operating efficiency, and optimizing resource allocation and task planning. At present, the accuracy of flight arrival time estimation is not ideal. The development of data mining technology provides a new method for flight arrival time estimation. The rich flight operation history database also provide...

AI Technical Summary

Problems solved by technology

At present, the accuracy of flight arrival time estimation is not ideal. The development of data mining technology provides a new method for flight arrival time estimation. The rich flight operation history database also provides sufficient data support for the prediction method based on data mining.

Images