Flight path prediction method

Abstract

The invention discloses a flight path prediction method. The method comprises the steps: considering the meteorological environment of a flight, extracting meteorological features through a convolutional neural network, modeling flight path features through a recurrent neural network, and finally outputting a series of future flight paths, specifically including the steps of flight path data preprocessing, meteorological feature extraction, time sequence model definition, model compiling and training, and flight path prediction. Through the technical scheme of the invention, the long-term flight trajectory can be accurately predicted in an actual environment.

Description

Technical field [0001] The invention belongs to the technical field of civil aviation, and particularly relates to a flight track prediction method. Background technique [0002] The high-quality growth of the national economy has promoted the vigorous development of the air transport industry. According to the Statistical Bulletin on the Development of the Civil Aviation Industry in 2018, there will be new downward pressure on the economy in 2018, and the development of the civil aviation industry has maintained a steady and progressing momentum. . It can be seen from statistical data that the air traffic flow in my country is increasing, the air route coverage is wider and the airport distribution is denser. However, airspace resources are limited, coupled with severe weather disturbances, congestion in large-scale airspace, and large-scale flight delays have become increasingly prominent. Therefore, in order to ensure the safety of airspace operations and improve operational...

AI Technical Summary

Problems solved by technology

Deterministic methods include optimal estimation and dynamics or kinematics modeling, the limitation of which is that it does not consider any uncertainties, such as convective weather effects, etc., and the prediction accuracy is low

The probabilistic method is mainly the machine learning model. Although the traditional machine learning model has achieved good performance in data mining and prediction, there are still the following deficiencies in track prediction: First, the existing methods lack consideration of dynamic meteorological impacts. Second, it is difficult for existing methods to predict medium and long-term flight paths; Third, due to the numerous characteristics of flight trajectories and strong time series correlation, it shows complex nonlinear characteristics, and it is difficult for traditional machine learning methods to predict them. accurate characterization

In summary, the existing methods are not effective in actual long-term trajectory prediction

Images