Aircraft flight path prediction method based on LSTM network

Abstract

The invention discloses an aircraft flight path prediction method based on an LSTM network, and the method comprises the following steps: (1), reading aircraft flight path data, and carrying out the normalization of the data; (2) establishing an LSTM deep neural network model, and setting the input and output of a neural network, the step number, the LSTM layer number and the number of neurons ofeach layer; (3) setting evaluation indexes to be RMSE and MAE; (4) training a network model, and debugging related parameters to minimize the values of RMSE and MAE, i.e., the network effect is optimal; and (5) outputting the predicted flight path of the aircraft through the trained optimal network. According to the method, the flight path of the aircraft in a period of time in the future can be quickly and effectively predicted, the LSTM network is applied to the flight path prediction problem, the LSTM flight path prediction model is trained through a large amount of data, and the robustnessand accuracy of flight path prediction are effectively improved.

Description

technical field [0001] The invention belongs to the technical field of algorithm design software, in particular to an LSTM network-based aircraft track prediction method. Background technique [0002] Track prediction is an important technology in airspace traffic management. Accurately predicting the trajectory of aircraft is a necessary condition for realizing intelligent airspace traffic management. Accurate trajectory prediction can improve the efficiency of airspace traffic management, while inaccurate trajectory prediction will cause confusion in airspace traffic management and increase the flight risk factor of aircraft. Therefore, the trajectory prediction of aircraft has important research value. [0003] The traditional track prediction model based on BP neural network realizes multi-dimensional aircraft track feature prediction. Usually, the BP neural network is selected as 3 layers. Increasing the number of BP network layers will increase its training time and ...

AI Technical Summary

Problems solved by technology

Using the deep learning method to improve the accuracy of aircraft track prediction, solve the problem that the traditional BP method tends to make the training result of the loss function fall into the local optimum and the problem of over-fitting, and can make full use of the track sequence Useful distant information in the data

Images