基于贝叶斯网络的两栖车辆海上航行安全评估研究  

Safety Assessment of Amphibious Vehicle Navigation on Sea Based on Bayesian Network

作　　者：宋超 罗建华 Song Chao;Luo Jianhua(PLA Army Academy of Armored Forces,Beijing 100072,China)

机构地区：[1]中国人民解放军陆军装甲兵学院,北京100072

出　　处：《计算机测量与控制》2020年第10期251-255,共5页Computer Measurement &Control

摘　　要：分析了两栖车辆海上航行相关风险,进行安全风险评估,并对可能发生的风险提出了一种可行的解决方案;基于贝叶斯点估计和贝叶斯学习估计与两栖车辆海上航行有关的交通事故,建立了两栖车辆海上航行交通系统(QRA)分析模型,通过贝叶斯网络来获取其相对风险的QRA;研究结果显示:使用该方法描述了两栖车辆海上航行的风险分布,并在QRA上显示了与各种特征相关结果,对两栖车辆航行构成相对风险综合分析,高风险区域的规模按降序排列如下:(1)航道—引航—国内水道—航行;(2)沿海地区—非引航区—国家水道—航行;该评估模型具有较好的应用价值,可为两栖车辆海上安全航行提供借鉴。This paper analyzes the risks related to amphibious vehicle navigation,evaluates the safety risks,and puts forward a feasible solution to the possible risks.Based on Bayesian point estimation and Bayesian learning estimation of traffic accidents related to amphibious vehicle navigation on the sea,an analysis model of amphibious vehicle navigation on the sea(QRA)is established.The QRA of relative risk is obtained by Bayesian network.The results show that this method is used to describe the risk distribution of amphibious vehicle navigation on the sea,and the results related to various characteristics are displayed on QRA.The relative risk of amphibious vehicle navigation is analyzed comprehensively.The scale of high-risk areas is arranged in descending order as follows:(1)waterway pilotage domestic waterway navigation;(2)coastal area non-pilotage national waterway navigation.The evaluation model has good application value and can provide reference for amphibious vehicles to navigate safely at sea.

关 键 词：两栖车辆 贝叶斯网络 定量风险评价 安全评估 

分 类 号：TP391[自动化与计算机技术—计算机应用技术] U698[自动化与计算机技术—计算机科学与技术]