高速铁路故障分类及其影响列车数模型*

doi:10.16265/j.cnki.issn1003-3033.2018.S2.009

中国安全科学学报 ›› 2018, Vol. 28 ›› Issue (S2): 46-53.doi: 10.16265/j.cnki.issn1003-3033.2018.S2.009

高速铁路故障分类及其影响列车数模型^*

黄平^1,2,3, 彭其渊^1,2 教授, 文超^**1,2,3 副教授, 李忠灿^1,2

1 西南交通大学综合交通运输国家地方联合工程实验室, 四川成都 610031;
2 西南交通大学综合交通大数据应用技术国家工程实验室, 四川成都 610031;
3 滑铁卢大学铁路研究中心, 加拿大滑铁卢 N2L3G1

收稿日期:2018-08-29 修回日期:2018-11-10 出版日期:2018-12-30 发布日期:2020-11-11
通讯作者: **文超(1984—),男,江西宜春人,博士,副教授,主要从事铁路运输组织优化、交通大数据应用等方面研究。E-mail: wenchao@swjtu.cn。
作者简介:黄平 (1990—),男,四川宜宾人,博士研究生,研究方向为铁路运输组织优化、交通数据分析建模、机器学习。E-mail:huangping129@my.swjtu.edu.cn。
基金资助:
国家自然科学基金资助(71871188); 国家重点研发计划(2017YFB1200701); 四川省科技厅应用基础研究项目(2018JY0567); 西南交通大学博士研究生创新基金资助(D-CX201827)。

Study on high-speed railway disruption classification and model of its influence on train number

HUANG Ping^1,2,3, PENG Qiyuan^1,2, WEN Chao^1,2,3, LI Zhongcan^1,2

1 National United Engineering Laboratory of Integrated and Intelligent Transportation, Southwest Jiaotong University,Chengdu Sichuan 610031, China;
2 National Engineering Laboratory of Integrated Transportation Big Data Application Technology, Southwest Jiaotong University, Chengdu Sichuan 610031, China;
3 Railway Research Centre, University of Waterloo, Waterloo N2L3G1, Canada

Received:2018-08-29 Revised:2018-11-10 Online:2018-12-30 Published:2020-11-11

摘要/Abstract

摘要： 准确衡量高速铁路 (HSR)系统故障的影响,对于提高高速铁路行车调度指挥水平和运营管理质量具有重要意义。基于武汉—广州高速铁路列车运行实际数据,提取故障影响晚点列车运行序列;运用K-Means聚类算法根据故障自身及运行图特征将其聚为4个不同类别,利用5类常见分布模型对训练集影响列车数分布进行拟合;以柯尔莫可洛夫-斯米洛夫(K-S)检验结果为模型拟合优度的比选依据,建立高速铁路故障影响列车数分布模型。测试集数据对拟合模型校验结果表明:测试数据集分布与拟合的最优模型分布一致,所建模型可以用于高速铁路实时调度指挥过程中故障影响列车数的估计。

关键词: 高速铁路 (HSR), 故障, 影响列车数, K-Means算法, 分布模型

Abstract: It is of great significance for the influence of high-speed railway disruption to be accurately measured forimproving the real-time dispatching and management abilities of HSR. First, based on the historical train operation records of Wuhan-Guangzhou HSR, delayed train groups caused by disruptions were extracted and a K-Means clustering algorithm was used to classify them into four categories, according to disruption and timetable characteristics. Then, five distribution models were investigated to fit the distributions of the affected train number in different clustered categories. Next, optimal distribution models for the number of affected trains were selected according to Kolmogorov-Smirnov (K-S) test. Finally, verification results show that distributions of the affected train numberin the test dataset were consistent with the fitted optimal distribution models. The fitted models can be used to estimate the number of trains affected by disruptions in real-time dispatching process of HSR.

Key words: high-speed railway (HSR), disruption, affected trains number, K-Means algorithm, distribution model

中图分类号:

X951

黄平, 彭其渊, 文超, 李忠灿. 高速铁路故障分类及其影响列车数模型^*[J]. 中国安全科学学报, 2018, 28(S2): 46-53.

HUANG Ping, PENG Qiyuan, WEN Chao, LI Zhongcan. Study on high-speed railway disruption classification and model of its influence on train number[J]. China Safety Science Journal, 2018, 28(S2): 46-53.

参考文献

[1] 彭其渊, 李建光, 杨宇翔, 等. 高速铁路建设对我国铁路运输的影响 [J]. 西南交通大学学报, 2016, 51(3): 525-533.
PENG Qiyuan, LI Jianguang, YANG Yuxiang, et al. Influences of high-speed railway construction on railway transportation of China[J]. Journal of Southwest Jiaotong University, 2016,51(3): 525-533.
[2] 文超, 彭其渊, 陈芋宏. 高速铁路列车运行冲突判定及其实现 [J]. 西南交通大学学报, 2012, 47(5): 867-873.
WEN Chao, PENG Qiyuan, CHEN Yuhong. Judgment of train operation conflict and its implementation for high-speed railway [J]. Journal of Southwest Jiaotong University, 2012, 47(5): 867-873.
[3] 刘健, 孟学雷, 王金霞. 突发事件下的列车运行图稳定性分析 [J]. 铁路计算机应用, 2015, 24(9): 1-5.
LIU Jian, MENG Xuelei, WANG Jinxia. Stability analysis of train diagram in emergency[J]. Railway Computer Application, 2015, 24(9): 1-5.
[4] 黄平, 彭其渊, 文超, 等. 武广高速铁路列车晚点恢复时间预测的随机森林模型 [J]. 铁道学报, 2018, 40(7): 1-9.
HUANG Ping, PENG Qiyuan, WEN Chao, et al. Random forest prediction model for Wuhan-Guangzhou HSR primary train delays recovery [J]. Journal of the China Railway Society, 2018, 40(7): 1-9.
[5] HUISMAN T, BOUCHERIE R J. Running times on railway sections with heterogeneous train traffic [J]. Transportation Research Part B: Methodological, 2001, 35(3): 271-292.
[6] CORMAN F, D'ARIANO A, HANSEN I A. Evaluating disturbance robustness of railway schedules [J]. Journal of Intelligent Transportation Systems, 2014, 18(1): 106-120.
[7] WENG J, ZHENG Y, QU X, et al. Development of a maximum likelihood regression tree-based model for predicting subway incident delay [J]. Transportation Research Part C: Emerging Technologies, 2015, 57: 30-41.
[8] ZILKO A A, KUROWICKA D, GOVERDE R M. Modeling railway disruption lengths with Copula Bayesian networks [J]. Transportation Research Part C: Emerging Technologies, 2016, 68: 350-368.
[9] 范正日. 我国铁路重特大事故发生规律与特征研究 [J]. 中国安全科学学报, 2018, 28(增1): 135-140.
FAN Zhengri. Cycle analysis and characteristics for the occurrence of major railway accidents in China [J]. China Safety Science Journal, 2018, 28(S1): 135-140.
[10] YUAN J. Stochastic modelling of train delays and delay propagation in stations [D]. Delfe: Delft University of Technology, 2006.
[11] BRIGGS K, BECK C. Modelling train delays with q-exponential functions [J]. Physica A: Statistical Mechanics and its Applications, 2007, 378(2): 498-504.
[12] XU P, CORMAN F, PENG Q. Analyzing railway disruptions and their impact on delayed traffic in Chinese high-speed railway [J]. IFAC-Papers On Line, 2016, 49(3): 84-89.
[13] WEN C, LI Z, LESSAN J, et al. Statistical investigation on train primary delay based on real records: evidence from Wuhan-Guangzhou HSR [J]. International Journal of Rail Transportation, 2017, 5(3): 170-189.
[14] 中国铁路总公司. 非正常情况下高速铁路调度指挥应急处置案例 [M]. 北京:中国铁道出版社, 2013:1-66.
[15] HARTIGAN J A, WONG M A. Algorithm AS 136: a k-means clustering algorithm [J]. Journal of the Royal Statistical Society Series C :Applied Statistics:, 1979, 28(1): 100-108.
[16] ROSS S M. Introduction to probability models 11^th edition [M]. New York: Academic Press, 2014: 21-33
[17] MASSEY JR F J. The Kolmogorov-Smirnov test for goodness of fit [J]. Journal of the American Statistical Association, 1951, 46(253): 68-78.

高速铁路故障分类及其影响列车数模型^*

Study on high-speed railway disruption classification and model of its influence on train number

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	邢玉龙, 王剑, 上官伟, 彭聪, 朱林富. 面向海量不平衡数据的轨道电路故障诊断方法[J]. 中国安全科学学报, 2022, 32(5): 112-118.
[2]	崔铁军, 李莎莎. 系统故障演化过程最终事件状态及发生概率研究^*[J]. 中国安全科学学报, 2021, 31(8): 1-7.
[3]	崔铁军, 李莎莎. 基于特征函数和联系数的系统故障模式识别[J]. 中国安全科学学报, 2021, 31(6): 1-6.
[4]	古莹奎, 刘平, 林忠海, 邱光琦. 基于Kurtogram与DSCN的滚动轴承故障诊断方法[J]. 中国安全科学学报, 2021, 31(6): 99-105.
[5]	马润, 仇维斌 , 秦云, 欧红香. 模糊区间TOPSIS动车组塞拉门故障风险评估[J]. 中国安全科学学报, 2021, 31(4): 177-183.
[6]	高涵, 多依丽, 孙铁, 王志荣, 郭品坤. 基于DBT-DBN模型的气化炉超温动态风险分析[J]. 中国安全科学学报, 2021, 31(3): 73-81.
[7]	吴耀男, 林雷, 任新温, 王龙庭, 刘志慧, 刘增凯. 一种基于逻辑结构数的改进型FMEA方法^*[J]. 中国安全科学学报, 2021, 31(10): 97-104.
[8]	任乐峰, 孟祥坤, 陈国明. 滩海油气管道泄漏风险演化与评估[J]. 中国安全科学学报, 2021, 31(1): 159-164.
[9]	陈志煌, 刘国恒, 王莹莹, 朱春丽, 单荐, 翟小东. 基于动态贝叶斯网络的水下连接器故障诊断[J]. 中国安全科学学报, 2020, 30(5): 81-87.
[10]	余敬芝, 燕飞, 牛儒. 基于Petri网的形式化安全分析方法^*[J]. 中国安全科学学报, 2019, 29(S2): 138-143.
[11]	李天册, 孙继星, 吴命利, 杨少兵, 宋可荐, 李瑾. 高次谐波下动车组车顶避雷器故障机制研究^*[J]. 中国安全科学学报, 2019, 29(S1): 88-93.
[12]	王睿, 朱江洪, 李延来. 基于共识模型与IN-TODIM的FMEA风险评估方法[J]. 中国安全科学学报, 2019, 29(9): 125-131.
[13]	宋志红, 耿秀丽. 基于HFACS的民机总装过程人为失误风险分析[J]. 中国安全科学学报, 2019, 29(6): 146-151.
[14]	王文和, 董传富, 刘林精, 李伟, 米红甫, 沈溃领. 基于FTA-BN模型的页岩气井口装置失效概率分析[J]. 中国安全科学学报, 2019, 29(4): 89-95.
[15]	黄平, 李忠灿, 文超, 彭其渊. 高速铁路故障时空分布及持续时长分布特征研究^*[J]. 中国安全科学学报, 2018, 28(S2): 99-104.