Journal of System Simulation
Abstract
Abstract: To achieve advance prediction of enemy target intention, a three-layer air combat intention prediction method based on multi-feature continuous time series and BiLSTM+Attention, including trajectory prediction, threat assessment, and intention prediction was proposed. To prevent the onesidedness of intention prediction results caused by state information at a single moment, prediction was carried out from multiple state features and trajectory information in a continuous time series. An LSTM neural network was used to predict the trajectory of the target aircraft, and the threat assessment of the target aircraft before and after the prediction was conducted. The BiLSTM + Attention model was used for intention prediction. Experimental results show that in 2v2 air combat, the intention prediction accuracy of the proposed method reaches 96.56%. Compared with contrast algorithms, the proposed method has better performance in terms of accuracy, precision, recall, and F1 score, and the prediction effect is good.
Recommended Citation
Li, Qiuni; Wang, Dong; Wang, Chaozhe; and Liu, Zongcheng
(2026)
"A BiLSTM+Attention Method for Predicting the Intentions of Air Combat Targets Based on Multi-feature Continuous Time Series,"
Journal of System Simulation: Vol. 38:
Iss.
4, Article 8.
DOI: 10.16182/j.issn1004731x.joss.25-0251
Available at:
https://dc-china-simulation.researchcommons.org/journal/vol38/iss4/8
First Page
948
Last Page
958
CLC
TP183
Recommended Citation
Li Qiuni, Wang Dong, Wang Chaozhe, et al. A BiLSTM+Attention Method for Predicting the Intentions of Air Combat Targets Based on Multi-feature Continuous Time Series[J]. Journal of System Simulation, 2026, 38(4): 948-958.
DOI
10.16182/j.issn1004731x.joss.25-0251
Included in
Artificial Intelligence and Robotics Commons, Computer Engineering Commons, Numerical Analysis and Scientific Computing Commons, Operations Research, Systems Engineering and Industrial Engineering Commons, Systems Science Commons