基于贝叶斯网络云模型的目标毁伤评估方法  

Battle Damage Assessment Method Based on BN-Cloud Model

作　　者：曲婉嘉 徐忠林[1] 张柏林 刘颖[1] 

机构地区：[1]空军航空大学 [2]94810部队

出　　处：《兵工学报》2016年第11期2075-2084,共10页Acta Armamentarii

基　　金：武器装备军内科研项目(KJ2013122)

摘　　要：针对复杂的现代战场环境和较多不确定性因素影响下目标毁伤评估问题,提出一种新的基于贝叶斯网络云模型的毁伤评估方法。分析目标特性,建立分级式评估指标体系,构建贝叶斯网络结构;将蒙特卡洛法引入参数学习之中,仿真得到各网络节点的条件概率表,利用网络推理得到目标属于各毁伤等级的概率;利用云模型将得到的目标毁伤概率转化为确定的毁伤值,从而实现由不确定性到确定性的转化。在贝叶斯网络模型中,将目标的物理毁伤程度作为功能毁伤程度的子节点之一,通过条件概率表将物理毁伤程度与功能毁伤程度联系起来,实现了一种新的物理毁伤到功能毁伤的转换方法。以雷达目标为例进行仿真实验,结果表明,该方法能够有效解决目标毁伤评估问题,且与传统贝叶斯网络模型评估结果相比,在精确度和可靠性上都有明显提高。A new damage assessment method based on BN-Cloud model is put forward for the impact of complex and uncertain factors in modern battlefield environment. The characteristics of targets are analyzed,and a hierarchical evaluation index system is established,which is used to build a Bayesian network（ BN） structure. Monte Carlo method is introduced into parameter learning,a condition probability table（ CPT） of each network node is obtained through simulation,and the probability of each damage level is obtained by using the network inference. Finally,cloud model is used to transform target damage probability into real damage value so as to realize the transformation from uncertainty to certainty. The target physical damage degree is used as one of sub-nodes of functional damage degree in BN,in which CPT is used as a link. As a result,a new method to transform physical damage into function damage is realized. A radar target is taken as an example for simulation. The simulated result shows that the proposed method can be effectively used for target damage assessment,and achieves a significant improvement in accuracy and reliability compared with the existing algorithms.

关 键 词：兵器科学与技术 毁伤评估 贝叶斯网络 云模型 雷达 蒙特卡洛算法 

分 类 号：E919[军事]