Multi-step Prediction of Aircraft Trajectory based on CNN-LSTM Neural Network

Lu Yang ； Yinfeng Li ； Chang Ruan ； Ranran Shang ； Shumin Xiao ； Xiujie Wei

《International Core Journal of Engineering》 8卷8期 (2022/08) Pp. 429-438

https://doi.org/10.6919/ICJE.202208_8(8).0055

摘要

In order to predict the risk of aircraft conflict and enable controllers to make corresponding decisions accurately and quickly, an aircraft trajectory prediction model based on CNN-LSTM combined neural network is established in this paper. The longitude, latitude, height and heading characteristics of the track point in the future period are predicted, and compared with GRU, RNN and LSTM algorithms. The experimental results show that the CNN-LSTM combined neural network prediction model is better than other models, and the prediction error is the smallest. It can be used for controllers to find possible future anomalies of aircraft and carry out real-time warning.

關鍵字

Aircraft Trajectory ； Prediction ； CNN ； LSTM

參考文獻

Yu Liang, Hao Zhang. Ship Track Prediction Based on AIS Data and PSO Optimized LSTM Network[J]. International Core Journal of Engineering,2020,6(5).

Zhengyi Wang, Man Liang, Daniel Delahaye. A hybrid machine learning model for short-term estimated time of arrival prediction in terminal manoeuvring area[J]. Transportation Research Part C,2018,95.

Zhi-Jun Wu, Shan Tian ,Lan Ma. A 4D Trajectory Prediction Model Based on the BP Neural Network[J]. Journal of Intelligent Systems,2019,29(1).

HaiZhou,12, YaojieChen,12, SuminZhang. Ship Trajectory Prediction Based on BP Neural Network[J]. Journal on Artificial Intelligence,2019,1(1).

Ping Han, Jucai Yue,Cheng Fang, et al. Short-term 4D trajectory prediction based on LSTM neural network[P]. Target Recognition and Artificial Intelligence Summit Forum,2020.