您目前所在的位置:首页 - 期刊简介 - 详细页面

铁道科学与工程学报

JOURNAL OF RAILWAY SCIENCE AND ENGINEERING

第9卷    第5期    总第49期    2012年10月

[PDF全文下载]    [Flash在线阅读]

    

文章编号:1672-7029( 2012) 05-0103-05
一类驼峰调车事故的贝叶斯网络模型研究
张春民,李引珍,何瑞春

(兰州交通大学交通运输学院,甘肃兰州730070)

摘 要: 驼峰跟钩撞车及侧面冲突调车事故会给驼峰调车作业带来较大安全隐患,影响驼峰解体作业的效率和能力。从技术条件角度考虑,对线路、车辆以及调车设备3 个方面因素进行分析。鉴于驼峰系统是复杂的大系统,具有不确定性的特点,考虑贝叶斯网络能较好解决不确定性问题,建立跟钩撞车及侧面冲突调车事故的贝叶斯网络模型。利用Matlab 中的BN推理工具软件包BNT 计算顶上事件的发生概率以及基本事件的后验概率。结果表明: 影响此类调车事故的主要因素为线路和车辆两方面。

 

关键字: 跟钩撞车; 侧面冲突; 事故树; 贝叶斯网络

Research on bayesian networks model of a class of shunting accident on hump
ZHANG Chun-min ,LI Yin-zhen,HE Rui-chun

Traffic & Transportation School,Lanzhou Jiaotong University,Lanzhou 730070,China

Abstract:The rear-end and side collision accident on hump would bring great hidden danger,which affects the efficiency and breaking-up capacity.Three main factors,i.e.,track,rolling stock and speed control equipments were analyzed from technical condition point of view.In view of the complexity and uncertainty of hump system and the characteristics of Bayesian network which is good at solving uncertainty problem,a Bayesian network model of the rear-end and side collision accident was established.The BNT of Matlab was used to calculate the top event’s probability and basic events’posterior probability.The results show that the main factors affecting the type shunting accident are track and rolling stock.

 

Key words: rear-end collision; side collision; fault tree; Bayesian network

ISSN 1672-7029
CN 43-1423/U

主管:中华人民共和国教育部 主办:中南大学 中国铁道学会 承办:中南大学
湘ICP备09001153号 版权所有:《铁道科学与工程学报》编辑部
------------------------------------------------------------------------------------------
地 址:湖南省长沙市韶山南路22号 邮编:410075
电 话:0731-82655133,82656174   传真:0731-82655133   电子邮箱:jrse@mail.csu.edu.cn