中距协同空战决策过程二次聚类重构与评估

doi:10.3969/j.issn.1001-506X.2020.01.15

摘要/Abstract

摘要：

未来空战将以中距空战为主，找出导致中距空战结果的原因是开展贴近实际的中距空战智能决策需解决的重要问题。针对空战训练过程中记录数据分布的复杂特点，建立了中距协同空战训练评估模型，提出了基于高阶导数聚类和相对模糊熵聚类的二次聚类方法，计算编队协同决策集，实现编队中距协同空战决策过程重构。以编队协同搜索和协同机动决策的角度，寻找编队协同决策与中距空战结果的相关性，并通过实例评估验证了聚类算法的合理性。

关键词: 空战决策, 中距协同空战, 二次聚类

Abstract:

In the future, the mid-range air combat will become the main air combat style, and the primary problem of intelligent decision-making for the medium-range cooperation air combat is to find the real reason of the air combat result. According to the data distribution of the aircraft record data in the air combat training, an assessment model of medium-range cooperation air combat training is built, a new method is proposed to compute the air combat decision set to reconstruct the medium-range air combat decision-making process based on high-order unite gradient and relative fuzzy entropy. From the perspective of cooperation search and cooperation maneuvering decision-making of the formation, the correlation between the medium-range cooperation air combat decision-making and the final result has been found, then the empirical study proves the rationality of the clustering algorithm proposed.

Key words: air combat decision-making, mid-range air combat cooperation, two phase clustering

中图分类号:

E917

左家亮, 张滢, 杨任农, 张振兴. 中距协同空战决策过程二次聚类重构与评估[J]. 系统工程与电子技术, 2020, 42(1): 108-117.

Jialiang ZUO, Ying ZHANG, Rennong YANG, Zhenxing ZHANG. Reconstruction and evaluation of medium-range cooperation air combat decision-making process with two phase clustering[J]. Systems Engineering and Electronics, 2020, 42(1): 108-117.

图/表 18

图1

图2

图3

图4

图5

图6

图7

图8

图9

图10

图11

图12

表1

表2

表3

图13

图14

图15

参考文献 30

1	MOORE J, TURNER R, PEKALA M. Finite state machines for creating, evaluating, and refining air-to-air combat tactics, ADA490111[R]. USA: Johns Hopkins Univ Laurel MD Applied Physics Laboratory, 2008.
2	左家亮, 杨任农, 张滢, 等. 基于模糊聚类的近距空战决策过程重构与评估[J]. 航空学报, 2015, 36 (5): 1650- 1660.
	ZUO J L , YANG R N , ZHANG Y , et al. Reconstruction and evaluation of close air combat decision-making process based on fuzzy clustering[J]. Acta Aeronautica et Astronautica Sinica, 2015, 36 (5): 1650- 1660.
3	QIAN P, DEYUN Z, JICHAN H, et al. Maneuver decision for cooperative close-range air combat based on state predicted influence diagram[C]//Proc.of the IEEE International Conference on Information and Automation, 2017: 726-731.
4	CHAO F, PENG Y. On close-range air combat based on hidden Markov model[C]//Proc.of the IEEE Chinese Guidance, Navigation and Control Conference, 2016: 687-694.
5	NELSON R L , RAFAL Z . Effectiveness of autonomous decision making for unmanned combat aerial vehicles in dogfight engagements[J]. Journal of Guidance, Control and Dynamics, 2018, 41 (2): 1015- 1021.
6	BURGIN G H, OWENS A J. An adaptive maneuvering logic computer program for the simulation of one-on-one air-to-air combat.volume 2: program desciption[R]. USA: NASA CR-2583, 1975.
7	SMITH R E , DIKE B A , MEHRA R K , et al. Classifier systems in combat:two-sided learning of maneuvers for advanced fight aircraft[J]. Computer Methods in Applied Mechanics and Engineering, 2000, 186 (2/4): 421- 437.
8	冯超, 景小宁, 李秋妮, 等. 基于隐马尔可夫模型的空战决策点理论研究[J]. 北京航空航天大学学报, 2017, 43 (5): 615- 626.
	FENG C , JING X N , LI Q N , et al. Theoretical research of decision-making point in air combat based on hidden Markov model[J]. Journal of Beijing University of Aeronautics and Astronautics, 2017, 43 (5): 615- 626.
9	DING W P , WANG J D . Cooperative extended rough attribute reduction algorithm based on improved PSO[J]. Journal of Systems Engineering and Electronics, 2011, 22 (1): 160- 166.
10	MA Y F , MA X L , SONG X . A case study on air combat decision using approximated dynamic programing[J]. Mathematical Problems in Engineering, 2014, 2014 (4): 183401- 183410.
11	JENS A, ULRIKA O.Intelligent fighter pilot support for distributed unmanned and manned decision making[M]//Intelligent Applications for Heterogeneous System Modeling and Design IGI Global, 2015.
12	HYUNJU P , BYUNG Y L , MIN J T . Differential game based air combat Maneuver generation using scoring function matrix[J]. Journal of Aeronautical and Space Sciences, 2016, 17 (2): 204- 213.
13	左家亮, 杨任农, 张滢, 等. 基于启发式强化学习的空战机动智能决策[J]. 航空学报, 2017, 38 (10): 212- 225.
	ZUO J L , YANG R N , ZHANG Y , et al. Intelligent decision-making in air combat maneuvering based on heuristic reinforcement learning[J]. Acta Aeronautica et Astronautica Sinica, 2017, 38 (10): 212- 225.
14	宋遐淦, 江驹, 徐海燕. 改进模拟退火遗传算法在协同空战中的应用[J]. 哈尔滨工程大学学报, 2017, 38 (11): 1762- 1768.
	SONG X J , JIANG J , XU H Y . Application of improved simulated annealing genetic algorithm in cooperative air combat[J]. Journal of Harbin Engineering University, 2017, 38 (11): 1762- 1768.
15	WANG Y , HUANG C , TANG C . Research of unmanned combat aerial vehicle robust maneuvering decision under incomplete target information[J]. Advances in Mechanical Engineering, 2016, 8 (10): 1- 12.
16	VAHDANI B , TAVAKKOLI M R , MEYSAM M S , et al. Soft computing based on new interval-valued fuzzy modified multi-criteria decision-making method[J]. Applied Soft Computing, 2013, 13 (1): 165- 172.
17	PETROVIČ I , KANKARAŠ M . Dematel-AHP multi-criteria decision making model for the selection and evaluation of criteria for selecting an aircraft for the protection of air traffic[J]. Decision Making:Applications in Management and Engineering, 2018, 1 (2): 93- 110.
18	CORDON O . A historical review of evolutionary learning methods for Mamdani-type fuzzy rule-based systems:designing interpretable genetic fuzzy systems[J]. International Journal of Approximate Reasoning, 2011, 52, 894- 913. doi: 10.1016/j.ijar.2011.03.004
19	JOSHI B P , KUMAR S . Intuitionistic fuzzy sets based method for multi-criteria decision-making[M]. Pennsylvania: IGI Global, 2015: 15- 35.
20	张源原, 吴文海, 汪节. 区间值直觉模糊Petri网及其在空战决策的应用[J]. 系统工程与电子技术, 2017, 39 (5): 1051- 1057.
	ZHANG Y Y , WU W H , WANG J . Interval valued intuitionistic fuzzy Petri net and its application in air combat decision-making[J]. Systems Engineering and Electronics, 2017, 39 (5): 1051- 1057.
21	SHAW R L. Fighter combat: the art and science of air-to-air warfare[M]. 2nd ed.Wellingborough: Patrick Stephens, 1988: 62-182.
22	CARLO K. The Russian philosophy of beyond visual range air combat[R]. Russian: Technical Report APA-TR-2008-0301. http://www.ausairpower.net/APA-Rus-BVR-AAM.html.
23	MIRMOEINI F, KRISHNAMURTHY V. Reconfigurable Bayesian networks for adaptive situation assessment in battle space[C]//Proc.of the IEEE International Conference on networking Sensing and Control, 2005: 810-815.
24	ZHANG K, LIU P, LI K, et al. Multi-target threat assessment in air combat based on entropy and VIKOR[C]//Proc.of the 9th International Conference on Advanced Computational Intelligence, 2017: 175-179.
25	ZHAO K, HUANG C. Air combat situation assessment for UAV based on improved decision tree[C]//Proc.of the Chinese Control and Decision Conference, 2018: 1772-1776.
26	孙庆鹏, 李战武, 常一哲. 基于威力势场的多机种威胁评估方法[J]. 系统工程与电子技术, 2018, 40 (9): 1993- 1999.
	SUN Q P , LI Z W , CHANG Y Z . Multi-types airplane threat assessment based on combat power field[J]. Systems Engineering and Electronics, 2018, 40 (9): 1993- 1999.
27	GAO J , TONG M . Extracting decision rules for cooperative team air combat based on rough set theory[J]. Chinese Journal of Aeronautics, 2003, 16 (4): 223- 228. doi: 10.1016/S1000-9361(11)60188-X
28	KAELBLING L P , LITTMAN M L , MOORE A W . Reinforcement learning:a survey[J]. Journal of Artificial Intelligence Research, 1996, 4 (1): 237- 285.
29	VEERASAMY N. A high-level mapping of cyberterrorism to the OODA loop[C]//Proc.of the 5th European Conference on Information Management and Evaluation, 2011: 352-360.
30	张震, 汪斌强, 伊鹏, 等. 一种分层组合的半监督近邻传播聚类算法[J]. 电子与信息学报, 2013, 35 (3): 645- 651.
	ZHANG Z , WANG B Q , YI P , et al. Semi-supervised affinity propagation clustering algorithm based on stratified combination[J]. Journal of Electronics&Information Technology, 2013, 35 (3): 645- 651.

L_{R_Radar}	A_{v_R}	P(x_{R_i})	Q(x_{R_i})	H(A_{v_R}-x_{R_i})
1	x_{v_north_R}(K+17’)	0.74	0.17	0.210 3
1	x_{v_east_R}(K+19’)	0.62	0.36	0.208 3
1	x_{v_up_R}(K+28’)	0.87	0.11	0.212 7
1	x_{v_up_R}(K+31’)	0.84	0.13	0.212
1	x_{v_north_R}(K+32’)	0.89	0.09	0.213 3
1	x_{v_up_R}(K+33’)	0.85	0.11	0.212 3
1	x_{v_up_R}(K+35’)	0.88	0.08	0.213 3
1	x_{v_up_R}(K+37’)	0.71	0.27	0.209 3
1	x_{v_north_R}(K+38’)	0.67	0.23	0.209 3
1	x_{v_east_R}(K+40’)	0.83	0.12	0.212
1	x_{v_up_R}(K+47’)	0.89	0.1	0.213
1	x_{v_up_R}(K+48’)	0.72	0.25	0.209 7
1	x_{v_north_R}(K+51’)	0.83	0.13	0.212
1	x_{v_up_R}(K+56’)	0.81	0.13	0.211 7
1	x_{v_east_R}(K+57’)	0.75	0.23	0.21
1	x_{v_up_R}(K+61’)	0.71	0.28	0.212 3
1	x_{v_north_R}(K+65’)	0.91	0.03	0.34
1	x_{v_north_R}(K+66’)	0.76	0.23	0.21
1	x_{v_up_R}(K+72’)	0.87	0.11	0.335 8
1	x_{v_up_R}(K+76’)	0.82	0.15	0.211 7
1	x_{v_up_R}(K+78’)	0.61	0.38	0.208 3
1	x_{v_north_R}(K+83’)	0.87	0.11	0.212 7
1	x_{v_east_R}(K+84’)	0.53	0.43	0.208
1	x_{v_up_R}(K+87’)	0.73	0.26	0.209 7
1	x_{v_east_R}(K+87’)	0.63	0.33	0.208 3
1	x_{v_north_R}(K+88’)	0.73	0.21	0.21
2	x_{v_north_R}(K+96’)	0.88	0.1	0.213
2	x_{v_up_R}(K+97’)	0.63	0.21	0.209
2	x_{v_up_R}(K+110’)	0.78	0.16	0.211
2	x_{v_up_R}(K+115’)	0.73	0.21	0.21
2	x_{v_north_R}(K+116’)	0.65	0.33	0.208 7

L_{B_Radar}	A_{v_B}	P(x_{B_i})	Q(x_{B_i})	H(A_{v_B}-x_{B_i})
1	x_{v_up_B}(K+24’)	0.68	0.32	0.190 5
1	x_{v_north_B}(K+28’)	0.81	0.12	0.195 3
1	x_{v_east_B}(K+30’)	0.77	0.21	0.192 6
1	x_{v_north_B}(K+35’)	0.83	0.11	0.195 8
1	x_{v_east_B}(K+43’)	0.83	0.16	0.193 7
2	x_{v_up_B}(K+48’)	0.81	0.17	0.194 2
2	x_{v_up_B}(K+50’)	0.88	0.11	0.196 8
2	x_{v_north_B}(K+52’)	0.91	0.07	0.198 4
2	x_{v_east_B}(K+56’)	0.53	0.45	0.188 9
2	x_{v_north_B}(K+57’)	0.74	0.21	0.192 1
2	x_{v_up_B}(K+57’)	0.89	0.09	0.197 4
2	x_{v_up_B}(K+66’)	0.91	0.05	0.199 4
2	x_{v_north_B}(K+70’)	0.83	0.12	0.195 3
2	x_{v_up_B}(K+75’)	0.87	0.1	0.196 8
2	x_{v_up_B}(K+82’)	0.78	0.21	0.192 6
3	x_{v_north_B}(K+98’)	0.87	0.09	0.196 8
3	x_{v_up_B}(K+99’)	0.87	0.1	0.196 8
3	x_{v_up_B}(K+102’)	0.81	0.15	0.194 7
4	x_{v_north_B}(K+107’)	0.67	0.31	0.190 5
4	x_{v_north_B}(K+109’)	0.64	0.32	0.19

L_{B_Radar}	A_{v_B}约简后	蓝方编队协同机动决策集A_{v_B}
1	x_{v_B1}(K+24’)	x_{v_up_B}(K+24’)
1	x_{v_B2}(K+28’)	x_{v_north_B}(K+28’)
1	x_{v_B3}(K+30’)	x_{v_east_B}(K+30’)
1	x_{v_B4}(K+35’)	x_{v_north_B}(K+35’)
1	x_{v_B5}(K+43’)	x_{v_east_B}(K+43’)
2	x_{v_B6}(K+48’)	x_{v_up_B}(K+48’), x_{v_up_B}(K+50’), x_{v_north_B}(K+52’)
2	x_{v_B7}(K+56’)	x_{v_east_B}(K+56’)
2	x_{v_B8}(K+57’)	x_{v_up_B}(K+57’), x_{v_up_B}(K+66’), x_{v_north_B}(K+70’), x_{v_up_B}(K+75’)
2	x_{v_B9}(K+82’)	x_{v_up_B}(K+82’)
3	x_{v_B10}(K+98’)	x_{v_north_B}(K+98’), x_{v_up_B}(K+99’), x_{v_up_B}(K+102’)
4	x_{v_B11}(K+107’)	x_{v_north_B}(K+107’)
4	x_{v_B12}(K+109’)	x_{v_north_B}(K+109’)

[1]	马文, 李辉, 王壮, 黄志勇, 吴昭欣, 陈希亮. 基于深度随机博弈的近距空战机动决策[J]. 系统工程与电子技术, 2021, 43(2): 443-451.
[2]	徐安，寇英信，于雷，李战武. 基于RBF神经网络的Q学习飞行器[J]. Journal of Systems Engineering and Electronics, 2012, 34(1): 97-101.
[3]	徐安，于雷，寇英信，徐保伟，李战武. 基于MDP框架的飞行器隐蔽接敌策略[J]. Journal of Systems Engineering and Electronics, 2011, 33(5): 1063-.