一类驼峰调车事故的贝叶斯网络模型研究  

Research on bayesian networks model of a class of shunting accident on hump

作　　者：张春民[1] 李引珍[1] 何瑞春[1] 

机构地区：[1]兰州交通大学交通运输学院,甘肃兰州730070

出　　处：《铁道科学与工程学报》2012年第5期103-107,共5页Journal of Railway Science and Engineering

基　　金：国家自然科学基金资助项目(61064012;61164003)

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。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.

关 键 词：跟钩撞车 侧面冲突 事故树 贝叶斯网络 

分 类 号：X951[环境科学与工程—安全科学]