基于模糊专家系统与IDE算法的UCAV逃逸机动决策

doi:10.12305/j.issn.1001-506X.2022.06.26

摘要/Abstract

摘要：

针对现有研究中无人作战飞机(unmanned combat air vehicle, UCAV)近距逃逸机动的自适应性不足和战术性匮乏问题, 提出一种将模糊专家系统与双策略竞争的可选外部存档差分进化算法(external archiving differential evolution algorithm with dual strategy competition, DSC-JADE)相结合的逃逸机动决策算法。通过对战术知识的学习, 建立模糊专家系统, 将逃逸决策过程通过滚动时域划分为离散片段, 根据模糊专家系统决策得到机动动作, 在其控制量对应的可行域内, 采用改进差分进化算法(improved differential evolution, IDE)进行寻优得到最优控制量, 完成逃逸机动决策。在UCAV处于劣势的初始条件下进行仿真验证, 证明DSC-JADE算法相较原始差分进化以及其他传统群智能算法搜索能力更强，采用专家系统相较不采用专家系统逃逸决策能力更优。

关键词: 逃逸机动决策, 模糊专家系统, 改进差分进化算法, 滚动时域控制

Abstract:

Aiming at the problems of insufficient adaptability and lack of tactical capabilities of unmanned combat air vehicle (UCAV) in short-range escape maneuvers in existing research, an escape maneuvering decision algorithm combining fuzzy expert system and external archiving differential evolution algorithm with dual strategy competition (DSC-JADE) is proposed. Through the learning of tactical knowledge, a fuzzy expert system is established, and the escape decision process is divided into discrete segments through the receding horizon. According to the decision of the fuzzy expert system, the maneuver is obtained. In the feasible region corresponding to its control quantity, an improved differential evolution (IDE) algorithm is used to search the optimal control quantity, and the escape maneuver decision is completed. Under the initial conditions of inferior (UCAV) for simulation and verification, the DSC-JADE algorithm has a stronger search ability than the differential evolution algorithm and other traditional group intelligence algorithms; the use of expert systems has better escape decision-making capabilities than the use of expert systems.

Key words: escape maneuvering decision, fuzzy expert system, improved differential evolution algorithm, receding horizon control

中图分类号:

V279

谭目来, 丁达理, 谢磊, 丁维, 吕丞辉. 基于模糊专家系统与IDE算法的UCAV逃逸机动决策[J]. 系统工程与电子技术, 2022, 44(6): 1984-1993.

Mulai TAN, Dali DING, Lei XIE, Wei DING, Chenghui LYU. UCAV escape maneuvering decision based on fuzzy expert system and IDE algorithm[J]. Systems Engineering and Electronics, 2022, 44(6): 1984-1993.

图/表 20

图1

图2

图3

图4

表1

图5

表2

图6

表3

图7

图8

图9

图10

图11

图12

图13

图14

图15

图16

表4

参考文献 30

1	AUSTIN F, CARBONE G, FALCO M, et al. Automated maneuvering decisions for air-to-air combat[C]//Proc. of the Gui-dance, Navigation and Control Conference, 1987: 2393.
2	PARK H , LEE B Y , TAHK M J , et al. Differential game based air combat maneuver generation using scoring function matrix[J]. International Journal of Aeronautical and Space Sciences, 2016, 17 (2): 204- 213. doi: 10.5139/IJASS.2016.17.2.204
3	MCGREW J S , HOW J P , WILLIAMS B , et al. Air-combat strategy using approximate dynamic programming[J]. Journal of Guidance, Control, and Dynamics, 2010, 33 (5): 1641- 1654. doi: 10.2514/1.46815
4	YANG Z , ZHOU D Y , PIAO H Y , et al. Evasive maneuver strategy for UCAV in beyond-visual-range air combat based on hierarchical multi-objective evolutionary algorithm[J]. IEEE Access, 2020, 8, 46605- 46623. doi: 10.1109/ACCESS.2020.2978883
5	POROPUDAS J , VIRTANEN K . Game-theoretic validation and analysis of air combat simulation models[J]. IEEE Trans.on Systems, Man, and Cybernetics Part A: Systems and Humans, 2010, 40 (5): 1057- 1070. doi: 10.1109/TSMCA.2010.2044997
6	TENG T H, TAN A H, TAN Y S, et al. Self-organizing neural networks for learning air combat maneuvers[C]//Proc. of the IEEE International Joint Conference on Neural Networks, 2012.
7	LI B , LIANG S Y , CHEN D Q , et al. A decision-making method for air combat maneuver based on hybrid deep learning network[J]. Chinese Journal of Electronics, 2022, 31 (1): 107- 115.
8	KONG W R , ZHOU D Y , YANG Z , et al. Maneuver strategy generation of UCAV for within visual range air combat based on multi-agent reinforcement learning and target position prediction[J]. Applied Sciences, 2020, 10 (15): 5198. doi: 10.3390/app10155198
9	YANG Q M , ZHANG J D , SHI G Q , et al. Maneuver decision of UAV in short-range air combat based on deep reinforcement learning[J]. IEEE Access, 2019, 8, 363- 378.
10	傅莉, 谢福怀, 孟光磊, 等. 基于滚动时域的无人机空战决策专家系统[J]. 北京航空航天大学学报, 2015, 41 (11): 1994- 1999.
	FU L , XIE F H , MENG G L , et al. An UAV air-combat decision expert system based on receding horizon control[J]. Journal of Beijing University of Aeronautics and Astronautics, 2015, 41 (11): 1994- 1999.
11	FU Z W , LI Z W , QIANG X M , et al. Tactical decision-making method based on receding horizon control for air combat[J]. Electronics Optics & Control, 2013, 20 (3): 20- 29.
12	WILLIAMS P . Three-dimensional aircraft terrain-following via real-time optimal control[J]. Journal of Guidance, Control, and Dynamics, 2007, 30 (4): 1201- 1206. doi: 10.2514/1.29145
13	GRAUER J A, MORELLI E A. A generic nonlinear aerodynamic model for aircraft[C]//Proc. of the AIAA Atmospheric Flight Mechanics Conference, 2014.
14	邓可, 彭宣淇, 周德云. 基于矩阵对策与遗传算法的无人机空战决策[J]. 火力与指挥控制, 2019, 44 (12): 61- 66. 61-66, 71 doi: 10.3969/j.issn.1002-0640.2019.12.013
	DENG K , PENG X Q , ZHOU D Y . Study on air combat decision method of UAV based on matrix game and genetic algorithm[J]. Fire Control & Command Control, 2019, 44 (12): 61- 66. 61-66, 71 doi: 10.3969/j.issn.1002-0640.2019.12.013
15	张堃, 周德云. 空战目标机规避仿真设计研究[J]. 计算机仿真, 2008, 11, 98- 100. 98-100, 123
	ZHANG K , ZHOU D Y . Design of the intelligent target of air combat[J]. Computer Simulation, 2008, 11, 98- 100. 98-100, 123
16	王杰, 丁达理, 许明, 等. 基于目标逃逸机动预估的空空导弹可发射区[J]. 北京航空航天大学学报, 2019, 45 (4): 722- 734.
	WANG J , DING D L , XU M , et al. Air-to-air missile launchable area based on target escape maneuver estimation[J]. Journal of Beijing University of Aeronautics and Astronautics, 2019, 45 (4): 722- 734.
17	HUANG C Q , DONG K S , HUANG H Q , et al. Autonomous air combat maneuver decision using Bayesian inference and moving horizon optimization[J]. Journal of Systems Engineering and Electronics, 2018, 29 (1): 86- 97. doi: 10.21629/JSEE.2018.01.09
18	高申玉. 多机空战战术机动专家系统与决策支持系统研究[J]. 系统工程理论与实践, 1999, 19 (8): 77- 80. 77-80, 127
	GAO S Y . Research on expert system and decision support system for multiple air combat tactical maneuvering[J]. Systems Engineering Theory&Practice, 1999, 19 (8): 77- 80. 77-80, 127
19	FU L, XIE F H, WANG D Z, et al. The overview for UAV air-combat decision method[C]//Proc. of the 26th Chinese Control and Decision Conference, 2014: 3380-3384.
20	董肖杰, 余敏建, 宋帅. 空战机动动作库及控制算法设计研究[C]//第五届中国指挥控制大会论文集, 2017: 188-193.
	DONG X J, YU M J, SONG S. Research on the design of air combat maneuver library and control arithmetic of movements[C]//Proc. of the 5th China Command and Control Conference, 2017: 188-193.
21	AHMAD I S , ABUBAKAR S , GAMBO F L , et al. A rule-based expert system for automobile fault diagnosis[J]. International Journal on Perceptive and Cognitive Computing, 2021, 7 (1): 20- 25.
22	王炫, 王维嘉, 宋科璞, 等. 基于进化式专家系统树的无人机空战决策技术[J]. 兵工自动化, 2019, 38 (1): 42- 47.
	WANG X , WANG W J , SONG K P , et al. UAV air combat decision based on evolutionary expert system tree[J]. Ordnance Industry Automation, 2019, 38 (1): 42- 47.
23	SMITH R E, DIKE B A, RAVICHANDEAN B, et al. The fighter aircraft LCS: a case of different LCS goals and techniques[C]//Proc. of the International Workshop on Learning Classifier Systems, 1999: 283-300.
24	SMITH R E , DIKE B A , MEHRA R K , et al. Classifier systems in combat: two-sided learning of maneuvers for advanced fighter aircraft[J]. Computer Methods in Applied Mechanics and Engineering, 2000, 186 (2/4): 421- 437.
25	SHAW R L . Fighter combat tactics and maneuvering[M]. 5th ed Maryland: Maryland Naval Institute Press, 1987.
26	POLAKOVA R. L-SHADE with competing strategies applied to constrained optimization[C]//Proc. of the IEEE Congress on Evolutionary Computation, 2017: 1683-1689.
27	ZHANG J , SANDERSON A C . JADE: adaptive differential evolution with optional external archive[J]. IEEE Trans.on Evolutionary Computation, 2009, 13 (5): 945- 958. doi: 10.1109/TEVC.2009.2014613
28	KAELO P , ALI M M . A numerical study of some modified differential evolution algorithms[J]. European Journal of Operational Research, 2006, 169 (3): 1176- 1184. doi: 10.1016/j.ejor.2004.08.047
29	TVRDIK J, POLAKOVA R. Competitive differential evolution applied to CEC 2013 problems[C]//Proc. of the IEEE Congress on Evolutionary Computation, 2013: 1651-1657.
30	王杰, 丁达理, 陈诚, 等. 导弹攻击状态评估下的UCAV试探机动决策[J]. 哈尔滨工业大学学报, 2021, 53 (6): 118- 127.
	WANG J , DING D L , CHEN C , et al. UCAV trial maneuvering decision under missile attack state assessment[J]. Journal of Harbin Institute of Technology, 2021, 53 (6): 118- 127.

序号	高度差	视线角－ψ_t	模糊输出
1	\|h_u－h_t\|≤50	视线角－ψ_t≥15π/180	左前方
2	\|h_u－h_t\|≤50	\|视线角－ψ_t\|≤15π/180	正前方
3	\|h_u－h_t\|≤50	视线角－ψ_t < －15π/180	右前方
4	h_u－h_t > 50	视线角－ψ_t≥15π/180	左上方
5	h_u－h_t > 50	\|视线角－ψ_t\|≤15π/180	正上方
6	h_u－h_t > 50	视线角－ψ_t < －15π/180	右上方
7	h_u－h_t < －50	视线角－ψ_t≥15π/180	左下方
8	h_u－h_t < －50	\|视线角－ψ_t\|≤15π/180	正下方
9	h_u－h_t < －50	视线角－ψ_t < －15π/180	右下方

IF	THEN
(LR is S)and(Lv is L)and(Lγ is M)and(Lh is M)and(LW is 1)	(DZ is 11)
(LR is S)and(Lv is L)and(Lγ is L)and(Lh is M)and(LW is 4)	(DZ is 7)
(LR is S)and(Lv is M)and(Lγ is L)and(Lh is L)and(LW is 4)	(DZ is 6)

算法名称	参数设置
DE	F₀=0.8, CR₀=0.6
ACO	α=0.3, β=0.2, μ=0.9
PSO	C₁=1.5, C₂=1.5, ω=0.8
GA	P_c=0.6, P_m=0.05

[1]	赵雨, 张斌, 徐安, 李洪钶. 双机协同战术对策及近似最优解[J]. 系统工程与电子技术, 2015, 37(3): 589-593.
[2]	黄长强，刘鹤鸣，黄汉桥，程华，陈少华. 不确定条件下无人作战飞机在线攻击轨迹决策[J]. 系统工程与电子技术, 2014, 36(8): 1558-1565.
[3]	吴旭忠，唐胜景，郭杰，熊俊辉. 基于滚动时域控制的再入轨迹跟踪制导律[J]. 系统工程与电子技术, 2014, 36(8): 1602-1608.
[4]	陈孚, 赵光宙. 基于收缩序列集的约束PWA系统鲁棒预测控制[J]. Journal of Systems Engineering and Electronics, 2009, 31(5): 1176-1179.
[5]	包子阳, 陈客松, 何子述, 韩春林. 基于改进差分进化算法的圆阵稀布方法[J]. Journal of Systems Engineering and Electronics, 2009, 31(3): 497-499.