Aircraft running off the runway during landing is a high risk of accident. Due to the difficulty of circumvention and the frequency of accidents, a neural network-based online prediction method is proposed to predict the landing distance of the aircraft in advance. Specifically, the wind field conditions can be adapted by the method to realize dynamic prediction. The B737-800 reference object was selected as the desktop simulation platform for the aircraft landing process. Multiple wind field conditions and flight trajectory data are simulated and collected, and key feature data are preprocessed, and a long and short-term memory (LSTM) neural network is selected to build the prediction model. The results indicate that the prediction error for longitudinal landing distance is 188.4 m and for lateral landing deviation distance is 43.5 m. For runways that are at least 2000 m long and 40 m wide, the prediction errors can provide the accuracy required for pilots to make go-around decisions in the air.
A Neural Network-Based Method for Online Prediction of Aircraft Landing Distance
Lect. Notes Electrical Eng.
International Conference on Guidance, Navigation and Control ; 2024 ; Changsha, China August 09, 2024 - August 11, 2024
2025-03-04
11 pages
Article/Chapter (Book)
Electronic Resource
English
Airborne Landing Distance: A Neural Network Approach
AIAA | 2016
|Boeing 737NG Aircraft Landing Distance Assessment
IEEE | 2021
|