Aircraft trajectory prediction method based on social long short-term memory network

Abstract

The invention discloses an aircraft trajectory prediction method based on a social long and short term memory network. The method comprises the following steps: modeling long-time sequence data of a plurality of aircrafts, capturing sequences and implicit relationships among the sequences, learning interaction behaviors among trajectories, and synchronously obtaining time-space characteristics and operation rules of all trajectories. The real-time sharing of dynamically updated implicit information is realized by establishing a long-short-term memory deep network for each aircraft and establishing pooling layer connection correlative networks between the networks, historical four-dimensional flight paths, speeds and angle information of a plurality of aircrafts in a certain airspace are taken as model input samples, model training is repeatedly performed, and model parameters are continuously updated, so that the prediction effect meets user expectation.

Description

technical field [0001] The invention relates to an aircraft track prediction method based on a social long-term and short-term memory network, which belongs to the technical field of civil aviation. Background technique [0002] In recent years, with the rapid growth of air traffic flow, limited airspace resources have been unable to meet the growing demand for air traffic, which puts the air transport system under enormous pressure, resulting in intensified aircraft flight conflicts, heavy workload of controllers, Problems such as airspace congestion and flight delays arise. To this end, the safe and efficient use of airspace resources and the management of flight traffic through an effective air traffic management system have become the key to solving the problem, and it is also the main problem facing the development of in-person air traffic. [0003] The core of the air traffic management system is the decision support system. Its development depends on accurate traject...

AI Technical Summary

Problems solved by technology

[0005] The existing technology currently has the following problems: (1) The prediction effect is unstable and lacks universality

Due to the strong randomness of aircraft trajectories, only using kinematic models or dynamics methods to predict aircraft with different motion characteristics has a large difference in prediction accuracy, and the universality is insufficient; (2) Lack of learning ability

The characteristics of the predicted trajectory obtained by parameter-free estimation are limited to the characteristics of the existing trajectory, and the prediction accuracy of other trajectory features is poor, and the ability to learn and improve is lacking; (3) The interaction between multiple aircraft in the airspace is ignored function, unable to achieve simultaneous prediction of multiple aircraft trajectories

Data-driven models usually need to learn a large amount of historical aircraft trajectory data, which directly includes basic information such as three-dimensional position, angle, and speed, and indirectly reflects potential uncertain factors such as flight intention, control behavior, and unstable weather conditions. , but ignores the interaction between multiple aircraft, which will affect the effect of track prediction to a certain extent

Images