利用贝叶斯网络提高港口国检查效率  

Improving the Efficiency of Port State Control Using Bayesian Network

作　　者：范丽先[1] 张紫梦 尹静波[2] FAN Li-xian;ZHANG Zi-meng;YIN Jing-bo(Shanghai University,Shanghai 200444,China;Shanghai Jiaotong University,Shanghai 200240,China)

机构地区：[1]上海大学管理学院,上海200444 [2]上海交通大学船舶海洋与建筑工程学院,上海200240

出　　处：《运筹与管理》2019年第8期107-115,共9页Operations Research and Management Science

基　　金：国家自然科学资助基金(71673181));国家社科基金资助项目(17BGL259)

摘　　要：提高港口国监控(PSC)的检查效率,本文研究了船舶固有属性(船舶年龄、船旗、船级社、船舶尺度)、港口国检查缺陷项与船舶事故间的影响关系。本文所使用的数据主要来自于英国劳氏船级社(LR)、国际海事组织(IMO)和东京谅解备忘录(Tokyo MOU)三个数据库,共5478条干散货船数据。利用贝叶斯网络(BN)构建模型,并分别采用Bayesian Network (BN)和Greedy thick thinning(GTT)算法构建网络模型。同时利用K-折交叉验证、对数似然函数(LL)、赤池信息量准则(AIC)和贝叶斯信息准则(BIC)对模型进行评估。结果表明船舶的固有属性和关键检查缺陷项对船舶事故均有较高的直接影响,而大多数的港口国监控检查缺陷之间具有相互影响,并且通过关键检查缺陷项对船舶事故产生间接影响。因此可以利用关键检查缺陷项优化港口国检验制度,提高检验效率。To improve the efficiency of port state control(PSC), this study investigates the impact of various factors on ship accident along with the port state’s detected deficiency items. Very importantly, it manages to identify the structural connections between the checked deficiency items. The data used in this study are mainly from Lloyd’s register of shipping(LR), International Maritime Organization(IMO)and Tokyo Memorandum of Understanding(Tokyo MOU), with a total of 5478 observations obtained for the bulker vessels. The Bayesian Network(BN)model is employed and the Greedy thick thinning(GTT)algorithm and Bayesian search(BS)algorithms are used to learn the structural networks. It then employs K-fold, Loglikelihood, AIC and BIC validation methods to choose the optimal model for structure explanation. In addition to the impacts of the deficiency items and the ship inherent attributes on ship accident, this study identifies some key deficiency items for port states. It also analyzes the intense connections between the key deficiency items with others. This helps simplify the port state’s inspection procedure and improve operational efficiency.

关 键 词：船舶事故 贝叶斯网络 港口国检查缺陷项 船舶固有属性 

分 类 号：U698[交通运输工程—港口、海岸及近海工程]