一种基于贝叶斯网络的作战重心评估模型

作战重心（Center of Gravity）是指战役体系中敌我双方的关键环节。作战重心评估是一个经验性、模糊性的过程。贝叶斯网络作为一种不确定知识表示模型,具有概率论及图论基础,对于解决复杂系统决策问题具有较强的优势,适合用于作战重心评估。文中提出并实现了一种基于贝叶斯网络推理的作战重心评估模型。通过该模型,可以定量地评估各个环节对于证据的重要程度,从而确定该作战过程中的作战重心。文中使用联合树（Clique Tree）算法进行贝叶斯网络精确推理,并详细阐述了推理过程中联合树建立,消息传递的过程。最后通过实例验证,基于贝叶斯网络推理的模型能够有效地对作战重心进行定量的评估。

An Evaluation Model of Center of Gravity Based on Bayesian Network

Center Of Gravity （COG） is the key to a campaign. Center of gravity evaluation is an empirical and fuzzy process. Bayesian Networks （BN）, as a representation model for uncertain knowledge, is based on probability theory and graph theory, with strong advantages for solving the complex system decision problem, which is suitable for COG evaluation. Propose and implement a COG evaluation model based on Bayesian network inference. Through this model, can evaluate the importance of each step for evidence quantitatively, determining the COG in the combat process. Use clique tree algorithm to perform Bayesian network inference and elaborate the ways to build the clique tree and to process message delivering in detail. An experiment is used to verify the proposed model. Results show that the proposed method can perform COG evaluation effectively and quantitatively.