Prediction Model of Train Fault Probability on Urban Rail Transit Main Line
CSTR:
Author:
Affiliation:

1.Key Laboratory of Road and Traffic Engineering of the Ministry of Education, Tongji University, Shanghai 201804, China;2.Shanghai Key Laboratory of Rail Infrastructure Durability and System Safety, Tongji University, Shanghai 201804, China;3.Technology Center of Shanghai Shentong Metro Group Co., Ltd., Shanghai 201103, China

Clc Number:

U239.5

  • Article
  • |
  • Figures
  • |
  • Metrics
  • |
  • Reference [17]
  • |
  • Related
  • |
  • Cited by
  • | |
  • Comments
    Abstract:

    A qualitative analysis was made to investigate the major influencing factors in predicting the probability of the train fault happening on urban rail main line. Then, a discrete dataset was collected about a single train’s fault in running for 120 000 km . Three alternative models were established on the basis of the data characteristics, Poisson distribution and zero-inflated Poisson distribution as well as the potential fault forms. According to the comparative study results,a Poisson distribution-based prediction model of train fault probability is finally proposed. Study results show that the train fault probability tends to increase with the increasing of train formation. It decreases first and then increases with the cumulative running kilometers,and the minimum train fault probability occurs in the fourth 120 000 km period, but the initial value is exceeded in the seventh 120 000 km period.

    Table 2
    Table 4
    Fig.1 Statistics of train fault cause
    Fig.2 Data generation of fault occurrence number for single train in each cumulative running kilometer period
    Fig.3 Trend of train fault frequency with cumulative running kilometer period
    Fig.4 Observation frequencies for different train fault occurrence numbers
    Fig.5 ROC curves for each alternative model
    Table 1
    Table 3
    Reference
    [1] DING Xiaobing, YANG Xuechen, HU Hua, et al. The safety management of urban rail transit based on operation fault log[J]. Safety Science, 2017, 94: 10.
    [2] 徐田坤. 城市轨道交通网络运营安全风险评估理论与方法研究[D]. 北京: 北京交通大学, 2012.
    [3] 中华人民共和国住房和城乡建设部. 地铁设计规范:GB 50157-2013[S]. 北京: 中国建筑工业出版社, 2014.
    [4] LORD D, WASHINGTON S P, IVAN J N. Poisson, Poisson-gamma and zero-inflated regression models of motor vehicle crashes: balancing statistical fit and theory[J]. Accident Analysis & Prevention, 2005, 37: 35.
    [5] 黄合来, 许鹏鹏, 翟晓琪. 不同区划方案对宏观交通事故建模的影响[J]. 同济大学学报(自然科学版), 2016, 44(3): 377.
    [6] NAZNIN F, CURRIE G, LOGAN D, et al. Application of a random effects negative binomial model to examine tram-involved crash frequency on route sections in Melbourne, Australia[J]. Accident Analysis & Prevention, 2016, 92: 15.
    [7] DONG C J, RICHARDS S H, CLARKE D B, et al. Examining signalized intersection crash frequency using multivariate zero-inflated Poisson regression[J]. Safety Science, 2014, 70: 63.
    [8] 陈颖雪, 石志峰, 刘志钢. 基于零膨胀回归模型的城市轨道交通触网故障频次研究[J]. 数学的实践与认识, 2019, 49(9): 172.
    [9] 孟祥海, 覃薇, 霍晓艳. 基于统计与假设检验的高速公路交通事故数据分布特性[J]. 交通运输工程学报, 2018, 18(1): 139.
    [10] 邵伟中, 宋博, 刘纯洁. 城市轨道交通车辆运行与维修[M]. 北京: 中国建筑工业出版社, 2019.
    [11] 程祖国, 王居宽, 陈鞍龙, 等. 城市轨道交通车辆部件故障与均衡修修程周期[J]. 城市轨道交通研究, 2006, 9(1): 46.
    [12] 许帅帅. 地铁车辆故障信息统计分析及检修策略优化[D]. 成都: 西南交通大学, 2013.
    [13] 陆万忠. 城市轨道交通车辆检修制度研究[D] . 北京: 北京交通大学, 2007.
    [14] 皇甫小燕, 程祖国, 王建兵. 上海轨道交通列车车门故障时域特征分析[J]. 城市轨道交通研究, 2012, 15(7): 30.
    [15] 顾保南, 叶霞飞. 城市轨道交通工程[M]. 武汉: 华中科技大学出版社, 2007.
    [16] 蒋源. 基于时空关联分析的交通拥堵判别及预测[D] . 北京: 北方工业大学, 2019.
    [17] 解锋昌, 韦博成, 林金官. 零过多数据的统计分析及其应用[M]. 北京: 科学出版社, 2013.
    Related
    Cited by
Get Citation

WANG Zhenbo, YE Xiafei, SHEN Jian, SHI Dongyan. Prediction Model of Train Fault Probability on Urban Rail Transit Main Line[J].同济大学学报(自然科学版),2020,48(12):1751~1757

Copy
Share
Article Metrics
  • Abstract:
  • PDF:
  • HTML:
  • Cited by:
History
  • Received:February 18,2020
  • Online: December 31,2020
Article QR Code