基于模糊灰色认知图的复杂战场智能态势感知建模方法

doi:10.12382/bgxb.2021.0259

摘要/Abstract

摘要： 针对复杂战场环境的动态、不确定性特征，提出一种基于模糊灰色认知图（FGCM）的智能态势感知（SA）建模方法。基于SA理论，采用自上而下任务驱动的态势觉察方式实现态势元素的提取；以目标威胁评估为态势理解的建模对象，利用FGCM在不确定数据表达和推理的模型特性，同时引入外部环境控制节点建立威胁评估动态FGCM模型。以目标意图预测为态势预测的建模对象，在基于专家知识建立的FGCM模型结构基础上，采用粒子群优化算法提高了意图预测模型对历史数据样本的参数学习能力。仿真验证分析结果表明，基于FGCM的智能SA建模方法能够较好地应对动态、不确定的战场环境，发挥知识和数据在建模中的综合作用。

关键词: 态势感知, 威胁评估, 意图预测, 模糊灰色认知图, 粒子群优化算法

Abstract: An intelligent situation awareness modeling method based on fuzzy grey cognitive map (FGCM) is proposed the dynamic and uncertain characteristics of complex battlefield environment. Based on situation awareness theory，the situation elements are extracted by top-down task driven situation awareness method. The target threat assessment is taken as the modeling object of situation understanding， and the dynamic FGCM model of threat assessment is established by using the model characteristics of FGCM in uncertain data expression and reasoning，in which the external environment control node is introduced. The target intention prediction is taken as the modeling object of situation prediction on the basis of FGCM model structure established based on expert knowledge， and the particle swarm optimization is used to improve the parameter learning ability of intention prediction model for historical data samples. The simulated results show that the intelligent situation awareness modeling method based on FGCM can deal with the dynamic and uncertain battlefield environment better，and play a comprehensive role of knowledge and data in modeling.

Key words: situationawareness, threatassessment, intentionprediction, fuzzygreycognitivemap, particleswarmoptimization

中图分类号:

TP181
V279

陈军，张岳，陈晓威，佟龑. 基于模糊灰色认知图的复杂战场智能态势感知建模方法[J]. 兵工学报, 2022, 43(5): 1093-1106.

CHEN Jun， ZHANG Yue， CHEN Xiaowei， TONG Yan. FGCM-based Modeling Method of Intelligent Situation Awareness in Complex Battlefield[J]. Acta Armamentarii, 2022, 43(5): 1093-1106.

参考文献

［1］ ENDSLEY M R.Toward a theory of situation awareness in dynamic systems［J］.Human Factors，1995，37(1):32-64.
［2］ ENDSLEY M R.Design and evaluation for situation awareness enhancement［C］∥Proceedings of the Human Factors Society Annual Meeting. Santa Monica,CA, US: SAGE, 1988, 32(2): 97-101.
［3］ SALOMON P M，WALKER G H，STANTON N A. Pilot error versus sociotechnical systems failure: a distributed situation awareness analysis of Air France 447［J］. Theoretical Issues in Ergonomics Science，2016，17(1):64-79.
［4］ NGUYEN T，LIM C P，NGUYEN N D，et al. A review of situation awareness assessment approaches in aviation environments［J］.IEEE Systems Journal，2019，13(3):3590-3603.
［5］马鹏杰，吴松涛.基于模糊TOPSIS的陆军合成营战场态势感知效能评估［J］.火力与指挥控制，2020，45(7):132-135，142.
MA P J，WU S T. Battlefield situation awareness effectiveness evaluation of army synthetic battalion based on fuzzy TOPSIS［J］.Firepower and Command and Control，2020，45(7):132-135，142.(in Chinese)
［6］ KOSKO B. Fuzzy cognitive maps［J］.International Journal of Man-Machine Studies，1986，24(1):65-75.
［7］ ADAMAS J A.Unmanned vehicle situation awareness: a path forward［C］∥Proceedings of Human Systems Integration Symposium. Nashville，TN，US: Vanderbilt University，2007.
［8］ JONES R E T，CONNORS E S，MOSSEY M E，et al.Using fuzzy cognitive mapping techniques to model situation awareness for army infantry platoon leaders［J］.Computational and Mathematical Organization Theory，2011，17(3): 272-295.
［9］ JIANG G H，TIAN Z Q，JIANG T.Using fuzzy cognitive maps to analyze the information processing model of situation awareness［C］∥ Proceedings of the 2014 6th International Conference on Intelligent Human-Machine Systems and Cybernetics.Hangzhou，China:IEEE，2014: 245-248.
［10］陈军，张新伟，高晓光，等.有人/无人机混合编队有限干预式协同决策［J］.航空学报，2015，36(11):3652-3665.
CHEN J，ZHANG X W，GAO X G，et al.Limited intervention cooperative decision making for manned/UAV hybrid formation［J］.Acta Aeronautica Sinica，2015，36(11):3652-3665.(in Chinese)
［11］ ZHAO Z，NIU Y F.Situation-driven fuzzy cognitive maps applied in air-to-ground target attack［C］∥Proceedings of the 2017 29th Chinese Control and Decision Conference.Chongqing，China:IEEE，2017:6384-6389.
［12］陈军，徐嘉，高晓光.基于ABFCM模型框架的UCAV自主攻击决策［J］.系统工程与电子技术，2017，39(3)：549-556.
CHEN J，XU J，GAO X G.UCAV autonomous attack decision based on ABFCM model framework［J］.Systems Engineering and Electronic Technology，2017，39(3)：549-556.(in Chinese)
［13］ ZHAO Z，NIU Y F，SHEN L C.Adaptive level of autonomy for human-UAVs collaborative surveillance using situated fuzzy cognitive maps［J］. Chinese Journal of Aeronauticsm, 2020，33(11): 2835-2850.
［14］ DONG J，WU G W，YANG T T，et al.Battlefield situation awareness and networking based on agent distributed computing［J］.Physical Communication，2019，33:178-186.
［15］许凯，曾云秀，武万森，等.面向计算机生成兵力的意图识别行为建模框架［J］.系统仿真学报，2021，33(10):2344-2355.
XU K，ZENG Y X，WU W S，et al. Research on CGF-oriented intention recognition behavioral modeling framework［J］.Journal of System Simulation，2021，33(10):2344-2355.(in Chinese)
［16］杨爱武，李战武，徐安，等.基于加权动态云贝叶斯网络空战目标威胁评估［J］.飞行力学，2020，38(4):87-94.
YANG A W，LI Z W，XU A，et al.Target threat assessment based on weighted dynamic cloud Bayes network［J］.Flight Mechanics，2020，38(4):87-94.(in Chinese)
［17］林傲，金庭，王志锐.基于DBN的预警机战场威胁评估模型研究［J］.空军预警学院学报，2019，33(5):358-361.
LIN A，JIN T，WANG Z R.Research on battlefield threat assessment model of early warning aircraft based on DBN ［J］.Journal of Air Force Early Warning Academy，2019，33(5):358-361. (in Chinese)
［18］张银燕，李弼程，崔家玮.基于云贝叶斯网络的目标威胁评估方法［J］.计算机科学，2013，40(10):127-131.
ZHANG Y Y，LI B C，CUI J W. Method of target threat assessment based oncloudy Bayesian network［J］.Computer Science，2013，40(10):127-131.(in Chinese)
［19］杨远志，王红卫，索中英，等.基于粗糙集-逼近理想解排序的辐射源威胁排序方法［J］.兵工学报，2016，37(5):945-952.
YANG Y Z，WANG H W，SUO Z Y，et al.Emitter threat ranking method based on rough set and approximate ideal solution［J］.Acta Armamentarii，2016，37(5):945-952.(in Chinese)
［20］奚之飞，徐安，寇英信，等.基于前景理论的空战目标威胁评估［J］.兵工学报，2020，41(6):1236-1248.
XI Z F，XU A，KOU Y X，et al.Air combat target threat assessment based on prospect theory［J］.Acta Armamentarii，2020，41(6): 1236-1248.(in Chinese)
［21］胡涛，王栋，孙曜，等.基于改进CRITIC-LRA和灰色逼近理想解排序法的空战威胁评估［J］.兵工学报，2020，41(12):2561-2569.
HU T，WANG D，SUN Y，et al.Air combat threat assessment of improved CRITIC-LRA and grey TOPSIS［J］.Acta Armamentarii，2020，41(12): 2561-2569.(in Chinese)
［22］马鹏杰，吴松涛.基于模糊TOPSIS的陆军合成营战场态势感知效能评估［J］.火力与指挥控制，2020，45(7):132-135，142.
MA P J，WU S T.Battlefield situation awareness effectiveness evaluation of army synthetic battalion based on fuzzy TOPSIS［J］.Fire Control and Command Control，2020，45(7):132-135,142.(in Chinese)
［23］郭圣明，贺筱媛，吴琳，等.基于强制稀疏自编码神经网络的作战态势评估方法研究［J］.系统仿真学报，2018，30(3):772- 784,800.
GUO S M，HE X Y，WU L，et al.Research on operational situation assessment method based on forced sparse self coding neural network［J］.Journal of System Simulation，2018，30(3):772-784,800.(in Chinese)
［24］ ZHAO J，GUO Q，TENG L，et al. Application of deep neural Network in air target threat assessment［C］∥Proceedings of the 2019 IEEE 3rd Information Technology，Networking，Electronic and Automation Control Conference.Chengdu，China: IEEE，2019:1633-1637.
［25］徐公国，段修生.基于改进Elman神经网络的目标威胁度预测评估［J］.探测与控制学报，2017，39(3):101-106.
XU G G，DUAN X S.Target threat prediction and evaluation based on improved Elman neural network［J］.Journal of Detection and Control，2017，39(3):101-106.(in Chinese)
［26］王海旺，史红权，李晓丹.基于直觉模糊集和贝叶斯推理的意图识别方法［J］.舰船电子工程，2019，39(6):42-45.
WANG H W，SHI H Q，LI X D.Intention recognition method based on intuitionistic fuzzy sets and Bayesian reasoning［J］.Naval Electronic Engineering，2019，39(6):42-45.(in Chinese)
［27］葛顺，夏学知.用于战术意图识别的动态序列贝叶斯网络［J］.系统工程与电子技术，2014，36(1):76-83.
GE S，XIA X Z.Dynamic sequential Bayesian network for tactical intention recognition［J］.Systems Engineering and Electronic Technology，2014，36(1):76-83.(in Chinese)
［28］周旺旺，姚佩阳，张杰勇，等.基于深度神经网络的空中目标作战意图识别［J］.航空学报，2018，39(11):200-208.
ZHOU W W，YAO P Y，ZHANG J Y，et al.Air target combat intention recognition based on deep neural network ［J］.Acta Aeronautica Sinica，2018，39(11):200-208.(in Chinese)
［29］滕飞，刘曙，宋亚飞.BiLSTM-Attention：一种空中目标战术意图识别模型［J］.航空兵器，2021，28(5):24-32.
TENG F，LIU S，SONG Y F.BiLSTM-Attention: an air target tactical intention recognition model［J］.Aviation Weaponry，2021，28(5):24-32.(in Chinese)
［30］徐建平，张立凡，韩德强.基于模糊推理的空中目标意图识别［J］.指挥信息系统与技术，2020，11(3):44-48.
XU J P，ZHANG L F，HAN D Q.Air target intention recognition based on fuzzy inference［J］.Command Information System and Technology，2020，11(3):44-48.(in Chinese)
［31］常天庆，孔德鹏，戴文君，等.基于目标作战意图信息融合的威胁评估方法［J］.控制与决策，2019，34(3):591-601.
CHANG T Q，KONG D P，DAI W J，et al.Threat assessment method based on target operational intention information fusion［J］.Control and Decision，2019，34(3):591-601.(in Chinese)
［32］ JOSE L,SALMERON. Modelling grey uncertainty with fuzzy grey cognitive maps［J］.Expert Systems with Applications，2010，37(12): 7581-7588.
［33］朱道元. 2015年全国研究生数学建模竞赛A题［J］.数学的实践与认识，2016(14):4-6.
ZHU D Y. 2015 National Graduate mathematical modeling contest，question A［J］.Practice and Understanding of Mathematics， 2016(14): 4-6.(in Chinese)
［34］赵福均，周志杰，胡昌华，等.基于置信规则库和证据推理的空中目标意图识别方法［J］.电光与控制，2017，24(8):15-19，50.
ZHAO F J，ZHOU Z J，HU C H，et al.Air target intention recognition method based on belief rule base and evidential reasoning［J］.Electronics Optics & Control，2017，24(8):15-19，50. (in Chinese)

[1]	李欢欢, 刘辉, 盖江涛, 李训明. 基于粒子群优化算法PID参数优化的双电机耦合驱动履带车辆转向控制[J]. 兵工学报, 2024, 45(3): 916-924.
[2]	王磊, 徐超, 李淼, 赵慧武. 多飞行器协同任务分配的改进粒子群优化算法[J]. 兵工学报, 2023, 44(8): 2224-2232.
[3]	范博洋, 赵高鹏, 薄煜明, 吴祥. 多目标空地异构无人系统协同任务分配方法[J]. 兵工学报, 2023, 44(6): 1564-1575.
[4]	陈美杉, 刘赢, 曾维贵, 钱坤. 空射诱饵弹干扰资源动态分配策略[J]. 兵工学报, 2023, 44(5): 1443-1455.
[5]	卢佳兴, 刘海鸥, 关海杰, 李德润, 陈慧岩, 刘龙龙. 基于双参数自适应优化的无人履带车辆轨迹跟踪控制[J]. 兵工学报, 2023, 44(4): 960-971.
[6]	周孝添, 任宏斌, 苏波, 齐志权, 汪洋. 基于微分平坦的分层轨迹规划算法[J]. 兵工学报, 2023, 44(2): 394-405.
[7]	张渊博, 项昌乐, 王伟达, 陈泳丹. 基于粒子群优化-蚁群融合算法的分布式电驱动车辆模型预测转矩协调控制策略[J]. 兵工学报, 2023, 44(11): 3253-3258.
[8]	周铖, 罗杨, 魏江, 曹宏瑞, 兰海, 张万昊. 履带车辆制动器扭振信号瞬时频率特征提取方法研究[J]. 兵工学报, 2023, 44(1): 316-324.
[9]	唐泽月, 刘海鸥, 薛明轩, 陈慧岩, 龚小杰, 陶俊峰. 基于MPC-MFAC的双侧独立电驱动无人履带车辆轨迹跟踪控制[J]. 兵工学报, 2023, 44(1): 129-139.
[10]	孙海文，于邵祯，江源，周末，唐嘉钰，李丹. 海上无人机蜂群目标威胁评估方法[J]. 兵工学报, 2022, 43(S2): 32-39.
[11]	郭志明，王迪，庞婷，李娟，赵丹，杨建新. 面向装备体系联合检验的指数分布定时截尾方案优化研究[J]. 兵工学报, 2022, 43(S1): 203-207.
[12]	许晓东，唐圣金，谢建，于传强，王凤飞，韩洋洋. 随机退化应力作用下设备剩余寿命预测方法[J]. 兵工学报, 2022, 43(3): 712-719.
[13]	田恒，许荣滨，姜艳红，张文虎，邓四二. 基于离散粒子群优化算法的多值属性系统故障诊断策略[J]. 兵工学报, 2022, 43(12): 3240-3246.
[14]	李晓雄，张淑宁，赵惠昌，陈思. 基于1DC-CGAN和小波能量特征的引信小样本地形目标识别[J]. 兵工学报, 2022, 43(10): 2545-2553.
[15]	奚之飞，徐安，寇英信，李战武，杨爱武. 基于前景理论的空战目标威胁评估[J]. 兵工学报, 2020, 41(6): 1236-1248.