基于动态贝叶斯网络的空袭目标威胁评估  

Threat Assessment of Air Attack Target Based on Dynamic Bayesian Network

作　　者：侯夷 任小平 王长城 王伟 Hou Yi;Ren Xiaoping;Wang Changcheng;Wang Wei(Department of Special Product,Automation Research Institute Co.,Ltd.of China South Industries Group Corporation,Mianyang 621000,China;Norendar International Ltd.,Shijiazhuang 050011,China)

机构地区：[1]中国兵器装备集团自动化研究所有限公司特种产品事业部,四川绵阳621000 [2]北方工程设计研究院有限公司,石家庄050011

出　　处：《兵工自动化》2019年第12期77-81,共5页Ordnance Industry Automation

基　　金：国防基础科研项目(JCKY2018209B010)

摘　　要：针对现有方法在处理不确定性信息推理上的不足,提出一种威胁评估的动态贝叶斯网络模型。基于对动态贝叶斯网络的研究及对空袭目标威胁影响因素的分析,给出网络中节点的状态转移概率表和条件概率表,结合证据观测值推理得到目标威胁的后验概率,对典型航路空袭目标的威胁度进行仿真分析。结果表明:该模型合理有效,能较准确地反映目标的真实威胁度,从而对空袭目标实施有效的末端拦截。In order to solve the shortcomings of the existing methods in dealing with uncertainty information reasoning,a dynamic Bayesian network model for threat assessment is proposed.The state transition probability table and conditional probability table of the nodes in the network are given based on analysis of dynamic Bayesian network and the analysis of the influencing factors of air strike target threat.The posterior probability of the target threat is obtained by reasoning with the evidence observations,and the threat level of the typical airway air attack target is simulated and analyzed.The results show that the model is reasonable and effective,and can accurately reflect the real threat level of the targets,thus effective terminal interception is implemented for air attack targets.

关 键 词：动态贝叶斯网络 威胁评估 概率推理 吉布斯采样 

分 类 号：TP393.02[自动化与计算机技术—计算机应用技术]