Target intention prediction of air combat based on Mog-GRU-D network under incomplete information

doi:10.23919/JSEE.2025.000104

Journal of Systems Engineering and Electronics ›› 2025, Vol. 36 ›› Issue (4): 972-984.doi: 10.23919/JSEE.2025.000104

• SYSTEMS ENGINEERING • Previous Articles

Target intention prediction of air combat based on Mog-GRU-D network under incomplete information

Jun CHEN(), Xiang SUN(), Zhe XUE(), Xinyu ZHANG()

School of Electronics and Information, Northwestern Polytechnical University, Xi’an 710072, China

Received:2023-10-16 Online:2025-08-18 Published:2025-09-04
Contact: Xinyu ZHANG E-mail:junchen@nwpu.edu.cn;sun_xiang@mail.nwpu.edu.cn;zhexue@mail.nwpu.edu.cn;xinyu.zhang@nwpu.edu.cn
About author:
CHEN Jun was born in 1979. He received his B.S., M.S., and Ph.D. degrees in system engineering from Northwestern Polytechnical University, China, in 2001, 2005, and 2009, respectively. Currently he is an associate professor at the School of Electronics and Information, Northwestern Polytechnical University, China. His research interests include encompass modeling and applications based on machine learning, intelligent decision-making for complex autonomous systems, and human-machine interactions. E-mail: junchen@nwpu.edu.cn

SUN Xiang was born in 1997. He received his B.S. degree in automation from Northwestern Polytechnical University, China, in 2019. He is currently pursuing his M.S. degree in Northwestern Polytechnical University, China. His research interests include complex system modeling, fuzzy cognitive maps, and machine learning. E-mail: sun_xiang@mail.nwpu.edu.cn

XUE Zhe was born in 2000. She received her B.S. degree in detection guidance and control technology from Northwestern Polytechnical University, China, in 2022. She is currently pursuing her M.S. degree in Northwestern Polytechnical University, China. Her research interests include complex system modeling, data mining, and machine learning. E-mail: zhexue@mail.nwpu.edu.cn

ZHANG Xinyu was born in 1996. She received her Ph.D. degree from the Department of Data Science and Artificial Intelligence, Faculty of Information Technology, Monash University, Australia, in 2023. Her research interests include exploring potential applications of computerized methodologies in the realms of digital health, education, and brain intelligence. E-mail: xinyu.zhang@nwpu.edu.cn
Supported by:
This work was supported by the Aeronautical Science Foundation of China (2020Z023053002).

Abstract

Abstract:

High complexity and uncertainty of air combat pose significant challenges to target intention prediction. Current interpolation methods for data pre-processing and wrangling have limitations in capturing interrelationships among intricate variable patterns. Accordingly, this study proposes a Mogrifier gate recurrent unit-D (Mog-GRU-D) model to address the combat target intention prediction issue under the incomplete information condition. The proposed model directly processes missing data while reducing the independence between inputs and output states. A total of 1200 samples from twelve continuous moments are captured through the combat simulation system, each of which consists of seven dimensional features. To benchmark the experiment, a missing valued dataset has been generated by randomly removing 20% of the original data. Extensive experiments demonstrate that the proposed model obtains the state-of-the-art performance with an accuracy of 73.25% when dealing with incomplete information. This study provides possible interpretations for the principle of target interactive mechanism, highlighting the model’s effectiveness in potential air warfare implementation.

Key words: intention prediction, incomplete information, gate recurrent unit (GRU), Mogrifier interaction mechanism

Jun CHEN, Xiang SUN, Zhe XUE, Xinyu ZHANG. Target intention prediction of air combat based on Mog-GRU-D network under incomplete information[J]. Journal of Systems Engineering and Electronics, 2025, 36(4): 972-984.

Figures/Tables 15

Fig 1

Table 1

Fig 2

Fig 3

Fig 4

Fig 5

Table 2

Table 3

Fig 6

Fig 7

Table 4

Fig 8

Table 5

Table 6

Table 7

References 45

1	WANG D L, WU X F, LENG H P Some problem for intention assessment to foe in battlefield. Ship Electronic Engineering, 2004, 24 (6): 4- 9.
2	ZHOU T L, CHEN M, CHEN S D, et al Intention prediction of aerial target under incomplete information. Innovative Computing, Information and Control (ICIC) Express Letters, 2017, 8 (3): 623- 631.
3	PU Z Q, YI J Q, LIU Z, et al Knowledge-based and data-driven integrating methodologies for collective intelligence decision making: a survey. Acta Automatica Sinica, 2022, 48 (3): 627- 643.
4	CHUNG J Y, GULCEHRE C, CHO K, et al. Empirical evaluation of gated recurrent neural networks on sequence modeling. Proc. of the Neural Information Processing Systems (NIPS) Deep Learning and Representation Learning Workshop, 2014. DOI: 10.48550/arXiv.1412.3555.
5	CHE Z, PURUSHOTHAM S, CHO K, et al Recurrent neural networks for multivariate time series with missing values. Scientific Reports, 2018, 8, 6085. doi: 10.1038/s41598-018-24271-9
6	KIRILLOV V P Constructive stochastic temporal reasoning in situation assessment. IEEE Trans. on System, Man and Cybernetics, 1994, 21 (7): 1099- 1113.
7	XIA X. The study of target intent assessment method based on the template-matching. Changsha: National University of Defense Technology, 2006. (in Chinese)
8	CHEN L, LI F F, ZOU C H Intension recognition of air-defense target based on dynamic Bayesian network and template matching. Modern Defense Technology, 2023, 51 (2): 62- 70.
9	XU J P, ZHANG L F, HAN D Q Air target intention recognition based on fuzzy inference. Command Information System and Technology, 2020, 11 (3): 44- 48.
10	YIN X, ZHANG M, CHENG M Q Combat intention recognition of the target in the air based on discriminant analysis. Journal of Projectiles, Rockets, Missiles and Guidance, 2018, 38 (3): 46- 50.
11	LEI Z, DONG Z M, WU D Y. Target tactical intention recognition based on fuzzy dynamic Bayesian network. Proc. of the International Conference on Modeling, Analysis, Simulation Technologies and Applications, 2019. DOI: 10.2991/masta-19.2019.41.
12	MENG H D, SUN C, FENG Y C, et al. One-to-one close air combat maneuver decision method based on target maneuver intention prediction. Proc. of the IEEE International Conference on Unmanned Systems, 2022: 1454−1465.
13	JIN Q, GOU X T, JIN W D, et al. Intention recognition of aerial targets based on Bayesian optimization algorithm. Proc. of the 2nd IEEE International Conference on Intelligent Transportation Engineering, 2017: 356−359.
14	ZHANG Y, DENG X Y, LI M D, et al Air target intention recognition based on evidence-network causal analysis. Acta Aeronautica et Astronautica Sinica, 2022, 43 (S1): 726896.
15	WU G Y, SHI H Q, QIU C C Intention recognition method of air target based on SSA-SVM. Ship Electronic Engineering, 2022, 42 (3): 29- 34.
16	DUAN X B, FAN Q C, BI W H, et al Belief exponential divergence for D-S evidence theory and its application in multi-source information fusion. Journal of Systems Engineering and Electronics, 2024, 35 (6): 1454- 1468. doi: 10.23919/JSEE.2024.000101
17	MENG G L, ZHAO R N, WANG B, et al Target tactical intention recognition in multiaircraft cooperative air combat. International Journal of Aerospace Engineering, 2021, 2021 (1): 9558838.
18	XI Z F, LYU Y, KU Y X, et al An online ensemble semi-supervised classification framework for air combat target maneuver recognition. Chinese Journal of Aeronautics, 2023, 36 (6): 340- 360. doi: 10.1016/j.cja.2023.04.020
19	LIU Q H, CHONG Y Tactical intention recognition based on operation knowledge neural network. Modern Defence Technology, 2021, 49 (3): 73- 79.
20	YU G, WANG X X, JI L N, et al Air targets intention estimation based on improved grey neural network. Journal of Detection and Control, 2021, 43 (5): 106- 112.
21	WANG T, ZHU T, ZHOU X, et al A function-based behavioral modeling method for air combat simulation. Journal of Systems Engineering and Electronics, 2024, 35 (4): 945- 954. doi: 10.23919/JSEE.2024.000068
22	XUE J J, ZHU J, XIAO J Y, et al Panoramic convolutional long short-term memory networks for combat intension recognition of aerial targets. IEEE Access, 2020, 8, 183312- 183323. doi: 10.1109/ACCESS.2020.3025926
23	ZHANG Z, WANG H F, GENG J, et al An information fusion method based on deep learning and fuzzy discount-weighting for target intention recognition. Engineering Applications of Artificial Intelligence, 2022, 109, 104610. doi: 10.1016/j.engappai.2021.104610
24	LI Y C, YANG Z, LV X F, et al. Online recognition method for target maneuver in UAV autonomous air combat. Proc. of the 22nd International Conference on Control, Automation and Systems , 2022: 32−39.
25	QIU C C, XIONG Z X, WU G Y, et al An air target intention prediction method based on sparrow search algorithm. Fire Control & Command Control, 2023, 48 (4): 65- 71.
26	TENG F, LIU S, SONG Y F BiLSTM-attention: an air target tactical intention recognition model. Aero Weaponry, 2021, 28 (5): 24- 32.
27	HASHEMI S M, BOTEZ R M, GRIGORIE T L New reliability studies of data-driven aircraft trajectory prediction. Aerospace, 2020, 7 (10): 145. doi: 10.3390/aerospace7100145
28	ZHOU W W, YAO P Y, ZHANG J Y, et al Combat intention recognition for aerial targets based on deep neural network. Acta Aeronautica et Astronautica Sinica, 2018, 39 (11): 322468.
29	WEI Z L, TANG S Q, WANG X F, et al. A tactical maneuver trajectory prediction method using gate recurrent unit based on triangle search optimization with AdaBoost. Proc. of the 33rd Chinese Control and Decision Conference , 2021: 2325−2330.
30	WANG S Y, WANG G, FU Q, et al STABC-IR: an air target intention recognition method based on bidirectional gated recurrent unit and conditional random field with space-time attention mechanism. Chinese Journal of Aeronautics, 2023, 36 (3): 316- 334. doi: 10.1016/j.cja.2022.11.018
31	ZHANG J D, YU Y F, ZHENG L H, et al Situational continuity-based air combat autonomous maneuvering decision-making. Defence Technology, 2022, 29, 66- 79.
32	TENG F, GUO X P, SONG Y F, et al An air target tactical intention recognition model based on bidirectional GRU with attention mechanism. IEEE Access, 2021, 9, 169122- 169134. doi: 10.1109/ACCESS.2021.3135495
33	FU L, XU Y, WANG J H, et al Analysis of radar stealth cross section characteristics of a stealth aircraft. Journal of Microwaves, 2020, 36 (2): 85- 89.
34	XIONG Z M, GUO H Y, WU Y X Review of missing data processing methods. Computer Engineering and Application, 2021, 57 (14): 27- 38.
35	THERESE D P A review of methods for missing data. Educational Research and Evaluation, 2001, 7 (4): 353- 383. doi: 10.1076/edre.7.4.353.8937
36	PINROLINVIC M, ANGREINE K, BRAMMY W. Missing data solution of electricity consumption based on Lagrange interpolation case study: IntelligEnSia data monitoring. Proc. of the International Conference on Electrical Engineering and Informatics , 2015: 511−516.
37	KOREDIANTO U, MOHAMMAD R. Comparison of classical interpolation methods and compressive sensing for missing data reconstruction. Proc. of the IEEE International Conference on Signals and Systems , 2019: 29−33.
38	CHEN X Y, LIU Y N, SHEN Y, et al. A data interpolation method for missing irradiance data of photovoltaic power station. Proc. of the Chinese Automation Congress, 2020: 4735−4740.
39	WANG Y, ZHANG X M, ZHOU P, et al Empirical correlation weighting (ECW) spatial interpolation method for satellite aerosol optical depth products by MODIS AOD over northern China in 2016. Remote Sensing, 2023, 15 (8): 4462.
40	LI Z, LU T D, YU K G, et al Interpolation of GNSS position time series using GBDT, XGBoost, and RF machine learning algorithms and models error analysis. Remote Sensing, 2023, 15 (8): 4374.
41	RUAN X Y, FU S Y, CURTIS B S, et al Real-time risk prediction of colorectal surgery-related post-surgical complications using GRU-D model. Journal of Biomedical Informatics, 2022, 135, 104202. doi: 10.1016/j.jbi.2022.104202
42	GUO C Y, GONG M H, SHEN Q C, et al. Development and validation of dynamic prediction models using vital signs time series data for fatal massive hemorrhage in trauma. Medical Journal of Chinese People’s Liberation Army, 2024, 49(6): 629−635. (in Chinese)
43	LI Q T. Research on classification method of time series with massive missing data. Shenzhen: South China University of Technology, 2020. (in Chinese)
44	CHEN Z Z. Human posture prediction based on gated recurrent neural network. Shenyang: Shenyang University of Technology, 2020. (in Chinese)
45	GABOR M, TOMAS K, PHIL B. Mogrifier LSTM. Proc. of the International Conference on Learning Representations, 2020. DOI: 10.48550/arXiv.1909.01792.

Maneuver type	Most possible combat intention	Sub-possible combat intention
High dive	Penetration	Attack
Low leap	Attack	Transport
S-Type	Electronic jamming	−
8-Type	Reconnaissance	Electronic jamming
0-Type	Aerial refuelling	Reconnaissance

Intention	Number of samples	Proportion of sample/%
Penetration	200	16.67
Attack	212	17.67
Electronic jamming	198	16.50
Shield	196	16.33
Surveillance	199	16.58
Reconnaissance	195	16.25

Value	Test accuracy/%	Macro-average			Weighted-average
Value	Test accuracy/%	Precision	Recall	F1-score	Precision	Recall	F1-score
0	67.42	0.6778	0.6766	0.6772	0.6782	0.6742	0.6716
1	68.33	0.7055	0.6837	0.6944	0.7038	0.6833	0.6934
2	69.75	0.6923	0.6997	0.6960	0.6916	0.6974	0.6945
3	70.17	0.7041	0.7044	0.7043	0.7044	0.7017	0.7031
4	40.83	0.4263	0.4037	0.4147	0.4255	0.4083	0.4167
5	23.50	0.2594	0.2321	0.2450	0.2589	0.2350	0.2464

Network	Test accuracy/%	Macro-average			Weighted-average
Network	Test accuracy/%	Precision	Recall	F1-score	Precision	Recall	F1-score
GRU	71.67	0.7319	0.7191	0.7255	0.7312	0.7167	0.7238
GRU-D	72.17	0.7291	0.7235	0.7263	0.7297	0.7217	0.7256
Mog-GRU	72.42	0.7392	0.7265	0.7328	0.7371	0.7242	0.7306
Mog-GRU-D	73.25	0.7410	0.7343	0.7376	0.7390	0.7325	0.7358

Model	Accuracy
Model	Penetration	Attack	Electronic jamming	Shield	Surveillance	Reconnaissance
GRU	94.50	50.47	91.91	60.20	49.25	85.13
GRU-D	94.00	54.72	87.37	59.69	55.78	82.56
Mog-GRU	93.50	52.83	87.37	65.31	51.26	85.64
Mog-GRU-D	93.00	58.02	88.38	64.80	52.26	84.10

Target intention prediction of air combat based on Mog-GRU-D network under incomplete information

RichHTML

PDF (PC)

Knowledge

Abstract

Cite this article

Share this article

Figures/Tables 15

References 45

Related Articles 4

Recommended Articles

Metrics

Comments

Model	Difference	Accuracy/%
BP	No	38.20
LSTM+PSO	No	84.21
Mog-GRU-D	No	98.55
Mog-GRU-D	Yes	73.25

[1]	Shouyi LI, Mou CHEN, Qingxian WU, Yuhui WANG. Threat sequencing of multiple UCAVs with incomplete information based on game theory [J]. Journal of Systems Engineering and Electronics, 2022, 33(4): 986-996.
[2]	Shengbao Yao and Wan’an Cui. Method for multi-attribute group decision-making based on the compromise weights [J]. Journal of Systems Engineering and Electronics, 2010, 21(4): 591-597.
[3]	Jianqiang Wang, Hongyu Zhang, and Zhong Zhang. Fuzzy multi-criteria decision-making approach with incomplete information based on evidential reasoning [J]. Journal of Systems Engineering and Electronics, 2010, 21(4): 604-608.
[4]	Luo Kaiping & Li Yijun. Target-tracked prioritization to surveille ballistic missiles? [J]. Journal of Systems Engineering and Electronics, 2009, 20(6): 1198-1206.