A Method of Aircraft Trajectory Prediction Based on Dual Channel Bidirectional Neural Network

Abstract

The invention discloses an aircraft trajectory prediction method based on a dual-channel bidirectional neural network, which is applied to a hypersonic aircraft, comprising: constructing a pre-training data set of a flight trajectory; constructing a dual-channel bidirectional neural network; using the pre-training data set to The neural network parameters of the dual-channel bidirectional neural network are pre-trained; the neural network parameters are retrained through real-time trajectory data; and trajectory prediction is performed on segments without observation data through the trained dual-channel bidirectional neural network. The invention can reduce the dependence on relevant parameters of the aircraft in trajectory prediction, realize intelligent, fast and accurate prediction of the trajectory of the aircraft, and meet the actual application requirements.

Description

technical field [0001] The present invention relates to the technical field of aircraft, in particular to an aircraft trajectory prediction method, system, computer-readable storage medium and terminal equipment based on a dual-channel bidirectional neural network. Background technique [0002] Hypersonic aircraft refers to aircraft, missiles, artillery shells and other winged or wingless aircraft that fly faster than 5 times the speed of sound. The trajectory prediction of a hypersonic vehicle refers to the extrapolation and prediction of the trajectory of the vehicle at subsequent moments based on the current state information of the vehicle. [0003] Trajectory prediction of traditional hypersonic vehicles is mainly achieved by modeling the kinematics and dynamics models of the target vehicle, and then performing integral solutions to the models to achieve trajectory prediction. However, this method has high prediction accuracy under the condition that the target aircraf...

AI Technical Summary

Problems solved by technology

However, this method has high prediction accuracy under the condition that the target aircraft model is established accurately, but it is difficult to model the target aircraft, the amount of calculation is large, and the real-time performance is not good. Poor trajectory prediction and other problems, so it is difficult to carry out universal promotion and use

Images