-
摘要:
针对战机飞行员自动化飞行训练评估对于机动动作的在线识别需求,提出了一种改进的基于动态贝叶斯网络的机动动作识别方法。首先,分析了仪表、简单特技和复杂特技飞行科目的机动动作特征。然后,根据战机飞行过程中机动动作与特征参数的因果关系,建立了机动动作识别动态贝叶斯网络模型,克服了传统方法需要滚转角信息,在实际飞行训练中难以通过雷达探测实时获取的缺点。同时,通过设计模型在线调用机制,有效降低了计算复杂度。实验结果表明,所提方法对于战机机动动作识别率高、实时性好,能够满足在线应用需求。
Abstract:An improved online recognition method for fighter maneuver based on dynamic Bayesian network is proposed for automatic flight training evaluation. First, the maneuver characteristics of instrument, simple stunt and complex stunt flight are analyzed. Then, according to the causal relationship between maneuver and characteristic parameters during flight process of fighter, a dynamic Bayesian network model for maneuver recognition is established, which overcomes the shortcomings of traditional methods, such as the need for roll angle information which is difficultly obtained in real time through radar detection in actual flight training. At the same time, the computational complexity is reduced by designing the online invocation mechanism of the model. Experimental results show that this method has high fighter maneuver recognition rate and good real-time performance, and can meet the needs of online application.
-
表 1 典型战机机动动作说明
Table 1. Description of typical fighter maneuvers
动作类别 动作名称 动作说明 仪表 盘旋 水平面内作等速圆周飞行 急跃升 迅速升高高度 俯冲 迅速降低高度、增大速度 水平匀速
直线飞行保持高度、速度不变 水平加速
直线飞行保持高度、速度增大 水平减速
直线飞行保持高度、速度减小 简单特技 半滚倒转 滚转180°后向下俯冲至航向角
突变180°斤斗 以期望法向过载向上拉起至期望
高度后向下俯冲至初始状态半斤斗翻转 以期望法向过载向上拉起至期望
高度后平飞复杂特技 “S”形急转 改变航向、高度保持 战斗转弯 改变飞行方向、高度升高 眼镜蛇机动 飞机达到最大迎角保持高度飞行 表 2 战机机动动作参数特征分析
Table 2. Characteristic analysis of fighter maneuver parameters
机动动作 飞行高度 飞行高度变化率 航向角 航向角变化率 飞行速度 左盘旋 保持 保持 变小 保持 保持 右盘旋 保持 保持 变大 保持 保持 急跃升 升高 先增大后减小 保持 保持 变小 俯冲 降低 先减小后增大 保持 保持 变大 水平匀速
直线飞行保持 保持 保持 保持 保持 水平加速
直线飞行保持 保持 保持 保持 变大 水平减速
直线飞行保持 保持 保持 保持 变小 半滚倒转 降低 先减小后增大 突变 突变 变大 斤斗 先升高
后降低先增大后减小 突变 突变 先减小
后增大半斤斗翻转 先升高
后保持先增大后减小 突变 突变 变小 “S”形急转 保持 保持 先减小后增大/
先增大后减小先减小后增大/
先增大后减小保持 战斗转弯 升高 先增大后减小 变大/变小 先增大后减小/
先减小后增大变小 眼镜蛇机动 先升高
后保持先增大后减小 保持 保持 变小 表 3 节点状态集说明
Table 3. Description of node state set
特征参数 状态集 飞行高度
(ALT)保持(ALT_M)、升高(ALT_U)、降低(ALT_D)、先升高后降低(ALT_UD)、先升高后保持(ALT_UM) 飞行高度
变化率(ALR)保持(ALR_M)、先增大后减小(ALR_UD)、先减小后增大(ALR_DU) 航向角(YAW) 变小(YAW_D)、突变(YAW_V)、先减小后增大(YAW_DU)、先增大后减小(YAW_UD) 航向角
变化率(YAR)保持(YAR_M)、突变(YAR_V)、先减小后增大(YAR_DU)、先增大后减小(YAR_UD) 飞行速度(VK) 保持(VK_M)、变大(VK_U)、变小(VK_D)、先减小后增大(VK_DU) 高度分类结果(MA) 高度保持类机动(MA_M)、高度上升类机动(MA_U)、高度下降类机动(MA_D)、高度先升高后下降类机动(MA_UD)、高度先升高后保持类机动(MA_UM) 航向分类结果(MY) 左盘旋、右盘旋、急跃升、俯冲、半滚倒转、斤斗、半斤斗翻转、“S”形急转、战斗转弯、眼镜蛇机动、水平匀速直线飞行、水平加速直线飞行、水平减速直线飞行 决策节点
(MR)左盘旋、右盘旋、急跃升、俯冲、半滚倒转、斤斗、半斤斗翻转、“S”形急转、战斗转弯、眼镜蛇机动、水平匀速直线飞行、水平加速直线飞行、水平减速直线飞行 表 4 高度分类结果CPT
Table 4. CPT of altitude classification results
MA p(ALT|MA) p(ALR|MA) MA_M (0.26, 0.185, 0.185, 0.185, 0, 185) (0.38, 0.31, 0.31) MA_U (0.185, 0.26, 0.185, 0.185, 0.185) (0.31, 0.38, 0.31) MA_D (0.185, 0.185, 0.26, 0.185, 0.185) (0.31, 0.31, 0.38) MA_UD (0.185, 0.185, 0.185, 0.26, 0.185) (0.31, 0.38, 0.31) MA_UM (0.185, 0.185, 0.185, 0.185, 0.26) (0.31, 0.38, 0.31) 表 5 飞行高度层与机动动作合理性选择
Table 5. Flight level and maneuver reasonable choice
飞行高度层 机动动作名称 高空层(10 000~
20 000 m)左盘旋、右盘旋、俯冲、水平匀速直线飞行、水平加速直线飞行、水平减速直线飞行、半滚倒转、斤斗、半斤斗翻转、“S”形急转、战斗转弯、眼镜蛇机动 中间层(3 000~
10 000 m)左盘旋、右盘旋、急跃升、水平匀速直线飞行、水平加速直线飞行、水平减速直线飞行、“S”形急转、战斗转弯、眼镜蛇机动 低空层(1 000~
3 000 m)左盘旋、右盘旋、急跃升、水平匀速直线飞行、水平加速直线飞行、水平减速直线飞行 -
[1] 倪世宏, 史忠科, 谢川, 等.军用战机机动飞行动作识别知识库的建立[J].计算机仿真, 2005, 22(4):23-26. doi: 10.3969/j.issn.1006-9348.2005.04.007NI S H, SHI Z K, XIE C, et al.Establishment of avion in flight maneuver action recognizing knowledge base[J].Computer Simulation, 2005, 22(4):23-26(in Chinese). doi: 10.3969/j.issn.1006-9348.2005.04.007 [2] 谢川, 倪世宏, 张宗麟, 等.一种基于知识的特技飞行动作快速识别方法[J].计算机工程, 2004, 30(12):116-118. http://d.old.wanfangdata.com.cn/Periodical/jsjgc200412045XIE C, NI S H, ZHANG Z L, et al.A knowledge-based fast recognition method of acrobatic maneuver[J].Computer Engineering, 2004, 30(12):116-118(in Chinese). http://d.old.wanfangdata.com.cn/Periodical/jsjgc200412045 [3] 孟光磊, 陈振, 罗元强.基于动态贝叶斯网络的机动动作识别方法[J].系统仿真学报, 2017, 29(S1):140-145. http://d.old.wanfangdata.com.cn/Periodical/xtfzxb2017z1020MENG G L, CHEN Z, LUO Y Q.Maneuvering action identify method based on dynamic Bayesian network[J].Journal of System Simulation, 2017, 29(S1):140-145(in Chinese). http://d.old.wanfangdata.com.cn/Periodical/xtfzxb2017z1020 [4] 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. http://d.old.wanfangdata.com.cn/Periodical/xtgcydzjs-e201801009 [5] XU X M, YANG R N, FU Y.Situation assessment for air co-mbat based on novel semi-supervised naive Bayes[J].Journal of Systems Engineering and Electronics, 2018, 29(4):768-779. http://www.jseepub.com/EN/abstract/abstract6413.shtml [6] SCHREIER M, WILLERT V, ADAMY J.An integrated approach to maneuver-based trajectory prediction and criticality assessment in arbitrary road environments[J].IEEE Transactions on Intelligent Transportation Systems, 2016, 17(10):2751-2766. doi: 10.1109/TITS.2016.2522507 [7] RODIN E Y, AMIN M.Maneuver prediction in air combat via artificial neural networks[J].Computers & Mathematics with Applications, 1992, 24(3):95-112. https://experts.umn.edu/en/publications/maneuver-prediction-in-air-combat-via-artificial-neural-networks [8] TOLEDO A, TOLEDO-MOREO R.Maneuver prediction for road vehicles based on a novel neuro-fuzzy dynamic architecture[J].Robotics and Autonomous Systems, 2010, 58(12):1316-1320. doi: 10.1016/j.robot.2010.09.002 [9] 杨俊, 谢寿生.基于模糊支持向量机的飞机飞行动作识别[J].航空学报, 2005, 26(6):84-88. http://d.old.wanfangdata.com.cn/Periodical/hkxb200506016YANG J, XIE S S.Fuzzy support vector machines based recognition for aeroplane flight action[J].Acta Aeronautica et Astronautica Sinica, 2005, 26(6):84-88(in Chinese). http://d.old.wanfangdata.com.cn/Periodical/hkxb200506016 [10] LI X H, WANG W S, ZHANG Z, et al. Effects of feature selection on lane-change maneuver recognition:An analysis of naturalistic driving data[J/OL].Journal of Intelligent and Connected Vehicles, 2018:85-98(2018-10-01)[2019-08-15].https://doi.org/10.1108/JICV-09-2018-0010. [11] 曲婉嘉, 徐忠林, 袁昱纬.基于动态贝叶斯网络的对空情报雷达打击效果评估[J].战术导弹技术, 2016(5):93-100.QU W J, XU Z L, YUAN Y W.Air intelligence radar battle damage assessment based on dynamic Bayesian networks[J].Tactical Missile Technology, 2016(5):93-100(in Chinese). [12] 于劲松, 沈琳, 唐荻音, 等.基于贝叶斯网络的故障诊断系统性能评价[J].北京航空航天大学学报, 2016, 42(1):35-40. doi: 10.13700/j.bh.1001-5965.2015.0070YU J S, SHEN L, TANG D Y, et al.Performance evaluation of fault diagnosis system based on Bayesian network[J].Journal of Beijing University of Aeronautics and Astronautics, 2016, 42(1):35-40(in Chinese). doi: 10.13700/j.bh.1001-5965.2015.0070 [13] 何旭, 景小宁, 冯超.基于蒙特卡洛树搜索方法的空战机动决策[J].火力与指挥控制, 2018, 43(3):34-39. http://d.old.wanfangdata.com.cn/Periodical/kjgcdxxb201705007HE X, JING X N, FENG C.Air combat maneuver decision ba-sed on MCTS method[J].Fire and Command Control, 2008, 43(3):34-39(in Chinese). http://d.old.wanfangdata.com.cn/Periodical/kjgcdxxb201705007 [14] QUAN T, FIRL J.Online maneuver recognition and multimodal trajectory prediction for intersection assistance using nonparametric regression[C]//IEEE Intelligent Vehicles Symposium.Piscataway: IEEE Press, 2014: 14452218. [15] 童奇, 李建勋, 童中翔, 等.基于机动识别的空战意图威胁建模与仿真[J].现代防御技术, 2014, 42(4):174-184. doi: 10.3969/j.issn.1009-086x.2014.04.029TONG Q, LI J X, TONG Z X, et al.Air combat intention threat modeling and simulation based on maneuver recognition[J].Modern Defense Technology, 2014, 42(4):174-184(in Chinese). doi: 10.3969/j.issn.1009-086x.2014.04.029 [16] 钟友武, 柳嘉润, 申功璋.自主近距空战中敌机的战术动作识别方法[J].北京航空航天大学学报, 2007, 33(9):1056-1059. doi: 10.3969/j.issn.1001-5965.2007.09.013ZHONG Y W, LIU J R, SHEN G Z.Recognition method for tactical maneuver of target in autonomous close-in air combat[J].Journal of Beijing University of Aeronautics and Astronautics, 2007, 33(9):1056-1059(in Chinese). doi: 10.3969/j.issn.1001-5965.2007.09.013 [17] 高阳阳, 余敏建, 韩其松, 等.基于改进共生生物搜索算法的空战机动决策[J].北京航空航天大学学报, 2019, 45(3):429-436. doi: 10.13700/j.bh.1001-5965.2018.0395GAO Y Y, YU M J, HAN Q S, et al.Air combat maneuver decision-making based on improved symbiotic organisms search algorithm[J].Journal of Beijing University of Aeronautics and Astronautics, 2019, 45(3):429-436(in Chinese). doi: 10.13700/j.bh.1001-5965.2018.0395 [18] ZHONG L, TONG M A, ZHONG W.Sequential maneuvering decisions based on multi-stage influence diagram in air combat[J].Journal of Systems Engineering and Electronics, 2007, 18(3):551-555. http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=xtgcydzjs-e200703019 [19] MA Y, MA X, SONG X.A case study on air combat decision using approximated dynamic programming[J].Mathematical Problems in Engineering, 2014, 2014:1-10. http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=Doaj000003736525