不确定条件下任务风险分析的贝叶斯网络方法

Bayesian network method for mission risk analysis under uncertain conditions

针对作战任务系统复杂多样、任务数据难以获取、专家评估主观性强等问题,基于模糊理论和置信度提出模糊置信贝叶斯网络模型并开展任务风险分析。首先,结合模糊理论和置信度理论度量节点的先验概率及条件概率;然后,基于贝叶斯网络和模糊理论的运算规则反向推理根节点的后验概率,通过灵敏度分析确定根节点的重要程度;最后,进行方法的对比分析。通过对某次重装空投任务进行风险分析,验证所提方法的有效性和先进性。

In order to solve the problems such as the complexity and diversity of the combat mission system,the difficulty of obtaining mission data and the strong subjectivity of expert evaluation,this paper proposes a fuzzy confidence Bayesian network model based on fuzzy theory and confidence degree to carry out mission risk analysis.Firstly,the prior probability and conditional probability of nodes are measured by combining fuzzy theory and confidence theory.Then,the posterior probability of the root node is calculated based on the reverse reasoning of Bayesian network and fuzzy theory,and the importance of the root node is determined through sensitivity analysis.Finally,the comparative analysis of the methods is carried out.The effectiveness and advance of the proposed method are verified by a case of a heavy equipment airdrop mission.