Journal of Jilin University(Engineering and Technology Edition) ›› 2024, Vol. 54 ›› Issue (2): 427-435.doi: 10.13229/j.cnki.jdxbgxb.20220352

Previous Articles    

Urban rail transit emergency risk level identification method

Bo-song FAN1,2(),Chun-fu SHAO2,3()   

  1. 1.School of Traffic Management，People's Public Security University of China，Beijing 100038，China
    2.Key Laboratory of Transport Industry of Big Data Application Technologies for Comprehensive Transport，Beijing Jiaotong University，Beijing 100044，China
    3.School of Transportation Engineering，Xinjiang University，Urumqi 830046，China
  • Received:2022-03-31 Online:2024-02-01 Published:2024-03-29
  • Contact: Chun-fu SHAO E-mail:fanbosong@bjtu.edu.cn;cfshao@bjtu.edu.cn

RICH HTML

 0   

PDF (PC)

144

Abstract:

In order to promote the accuracy of risk level identification， to solve the real-time risk control and emergency treatment problems of urban rail transit system， an improved feature selection algorithm （Im-F-score+XGB） on filtering features of the risk factors for emergencies was proposed. Through the analysis of the basic data of urban rail transit emergency， the feature importance degree of each risk feature was calculated， the influence degree of different features on the risk of emergencies was excavated， and the important features for determining the risk level of emergencies was obtained. Besides， the cyclic multi-time window scanning method and the weighted cascade residual forest model were used to obtain the mapping relationship between the emergency risk grade and the feature of risk features， and an improved emergency risk level identification model （Im-F-GCF） was established. Compared with RF， HGBDT， GCF and LightGBM models， the validity of the proposed model is verified.

Key words: transportation planning and management, urban rail transit, emergency, risk level, feature selection, weighted cascade residual forest

CLC Number: 

  • U121

Fig.1

Im-F-GCF model framework"

Table 1

30 risk features and their descriptions"

变量名称变量描述
日路网客运量/万人次每日轨道交通路网客运量
实际开行列数/列每日路网实际开行列车数
列车兑现率/%每日路网实际与计划开行列车比值
延误时长/min每起突发事件延误时间长度
2分晚点列车数/列每日路网晚点超过2 min的列车数
正点率/%每日路网实际开行列车正点到达比率
加开临客列车/列每日路网加开临时列车数量
工作日工作日、非工作日取值：0、1
天气恶劣天气、非恶劣天气取值：0、1
线路突发事件所发生的线路
专业类别突发事件所属的类别（信号故障、车辆故障等）
1号线断面满载率/%每日高峰时段各条线路断面满载率平均值
2号线断面满载率/%
5号线断面满载率/%
6号线断面满载率/%
7号线断面满载率/%
8号线断面满载率/%
9号线断面满载率/%
10号线断面满载率/%
13号线断面满载率/%
15号线断面满载率/%
昌平线断面满载率/%
房山线断面满载率/%
亦庄线断面满载率/%
八通线断面满载率/%
机场线断面满载率/%
4-大兴线断面满载率/%
14号线（西段）断面满载率/%
14号线（东段）断面满载率/%
16号线断面满载率/%

Table 2

Number of train adjustments to the network and each line on a given day"

运营企业及线路列车调整
停运通过清人掉线中折
路网81846
北京地铁1号线
2号线
5号线12
6号线7166
7号线
8号线
9号线
10号线22
13号线
15号线
昌平线
房山线
亦庄线
八通线
机场线
S1线
小计81846
京港地铁4-大兴线
14号线（西段）
14号线（东段）
16号线（北段）
小计

Fig.2

Importance and cumulative contribution of emergency features （Im-F-score model）"

Table 3

Important risk features"

变量名称变量描述
日路网客运量每日轨道交通路网客运量
实际开行列数每日轨道交通运营管理部门实际开行列车数
列车兑现率每日路网实际开行列车数与计划开行列车数比值
延误时长突发事件从产生影响到影响结束的持续时间
机场线断面满载率每日高峰时段各条线路断面满载率平均值
4-大兴线断面满载率
16号线断面满载率

Table 4

Classification matrix of prediction results of each risk level"

实际情况判别结果
正类负类
正类TPFN
负类FPTN

Table 5

Experimental results"

模型

Acc/

%

Pre/

%

Rec/

%

Spe/

%

F1/

%

Kap/

%

Im-F-GCF训练90.8694.7693.1383.7093.9487.78
测试89.7093.7792.5081.0793.1386.24
RF84.5089.7688.7173.4789.2379.59
HGBDT86.2590.7790.7373.3090.7581.76
GCF88.2492.5991.6977.7692.1484.40
Light GBM88.6593.5891.0581.5292.3084.88

Fig.3

ROC curves of each model"

1 Wang J, Yan W, Xu H, et al. Investigation of the probability of a safe evacuation to succeed in subway fire emergencies based on Bayesian theory[J]. KSCE Journal of Civil Engineering, 2018, 22(3): 877-886.
2 Yan H, Gao C, Elzarka H, et al. Risk assessment for construction of urban rail transit projects[J]. Safety Science, 2019, 118: 583-594.
3 Singh R, Hörcher D, Graham D J, et al. Decomposing journey times on urban metro systems via semiparametric mixed methods[J]. Transportation Research Part C: Emerging Technologies, 2020, 114: 140-163.
4 汪益敏, 罗跃, 于恒, 等. 人员密集型地铁车站安全风险评价方法[J]. 交通运输工程学报, 2020, 20(5): 198-207.
Wang Yi-min, Luo Yue, Yu Heng, et al. Evaluation method of security risk on crowded metro station[J]. Journal of Traffic and Transportation Engineering, 2020, 20(5): 198-207.
5 李炜, 周丙相, 蒋栋年, 等. 基于多状态时间序列预测学习的电源车故障预测方法[J]. 吉林大学学报:工学版, 2020, 50(4): 1532-1544.
Li Wei, Zhou Bing-xiang, Jiang Dong-nian, et al. Fault prediction of power supply vehicle based on multi-state time series prediction learning[J]. Journal of Jilin University (Engineering and Technology Edition), 2020, 50(4): 1532-1544.
6 郑宣传, 魏运, 秦勇, 等. 一种改进K-means模型的城市轨道交通突发事件分级方法[J]. 交通运输系统工程与信息, 2019, 19(3): 134-140.
Zheng Xuan-chuan, Wei Yun, Qin Yong, et al. Classification method of urban rail transit emergencies based on improved K-means algorithm[J]. Journal of Transportation Systems Engineering and Information Technology, 2019, 19(3): 134-140.
7 Mohanty S, Pozdnukhov A, Cassidy M. Region-wide congestion prediction and control using deep learning[J]. Transportation Research Part C: Emerging Technologies, 2020, 116: 1-21.
8 Yu B, Lee Y, Sohn K. Forecasting road traffic speeds by considering area-wide spatio-temporal dependencies based on a graph convolutional neural network (GCN)[J]. Transportation Research Part C: Emerging Technologies, 2020, 114: 189-204.
9 He D, Zou Z, Chen Y, et al. Obstacle detection of rail transit based on deep learning[J]. Measurement, 2021, 176: 109241.
10 Paltrinieri N, Comfort L, Reniers G. Learning about risk: machine learning for risk assessment[J]. Safety Science, 2019, 118: 475-486.
11 Zhou Z H, Feng J. Deep forest: towards an alternative to deep neural networks[C]∥IJCAI, Melbourne, Australia, 2017: 3553-3559.
12 Liu X, Tian Y, Lei X, et al. Deep forest based intelligent fault diagnosis of hydraulic turbine[J]. Journal of Mechanical Science and Technology, 2019, 33(5): 2049-2058.
13 Zhang Y, Xu T, Chen C, et al. A hierarchical method based on improved deep forest and case-based reasoning for railway turnout fault diagnosis[J]. Engineering Failure Analysis, 2021, 127: 105446.
14 姜万录, 李满, 张培尧, 等. 基于全矢增强深度森林的旋转设备智能故障诊断方法[J]. 中国机械工程, 2022, 33(11): 1324-1335.
Jiang Wan-lu, Li Man, Zhang Pei-yao, et al. Intelligent fault diagnosis method for rotating equipment derived from full vector enhanced deep forest[J]. China Mechanical Engineering, 2022, 33(11): 1324-1335.
15 邵怡韦, 陈嘉宇, 林翠颖, 等. 小训练样本下齿轮箱故障诊断:一种基于改进深度森林的方法[J]. 航空学报, 2021, 42(): 25-29.
Shao Yi-wei, Chen Jia-yu, Lin Cui-ying, et al. Gearbox fault diagnosis under small training samples: An improved deep forest based method[J]. Acta Aeronautica et Astronautica Sinica, 2021, 42(Sup.1): 25-29.
16 李志慧, 孙雅倩, 陶鹏飞, 等. 交通事故后的交通运行风险状态等级预测方法[J]. 吉林大学学报:工学版, 2022, 52(1): 127-135.
Li Zhi-hui, Sun Ya-qian, Tao Peng-fei, et al. Prediction method of traffic operation risk level after traffic accident[J]. Journal of Jilin University (Engineering and Technology Edition), 2022,52(1): 127-135.
[1] Chang-jiang ZHENG,Huan HU,Mu-qing DU. Design of multimodal express delivery network structure considering hub failure [J]. Journal of Jilin University(Engineering and Technology Edition), 2023, 53(8): 2304-2311.
[2] Dian-hai WANG,You-wei HU,Zheng-yi CAI,Jia-qi ZENG,Wen-bin YAO. Dynamic road resistance model of intermittent flow on urban roads based on BPR function [J]. Journal of Jilin University(Engineering and Technology Edition), 2023, 53(7): 1951-1961.
[3] Zi-yu LIU,Shi-tong CHEN,Mo-mo ZHI,Xiao-ming HUANG,Zhe-xin CHEN. Ultimate bearing capacity of temporary⁃permanent conversion rush⁃repair steel pier for emergency use [J]. Journal of Jilin University(Engineering and Technology Edition), 2023, 53(6): 1601-1611.
[4] Yan-bo LI,Bai-song LIU,Bo-bin YAO,Jun-shuo CHEN,Kai-fa QU,Qi-sheng WU,Jie-ning CAO. Location of electrical changing station of expressway considering stochastic characteristics of road network [J]. Journal of Jilin University(Engineering and Technology Edition), 2023, 53(5): 1364-1371.
[5] Ying HU,Chun-fu SHAO,Shu-ling WANG,Xi JIANG,Hai-rui SUN. Identification of road riding quality based on shared bike trajectory data [J]. Journal of Jilin University(Engineering and Technology Edition), 2023, 53(4): 1040-1046.
[6] Hai-bo LONG,Jia-qi YANG,Liang YIN,Xue-yu ZHAO,Zi-quan XIANG. Multi-objective decision-making on emergency material distribution under uncertain demand based on robust optimization [J]. Journal of Jilin University(Engineering and Technology Edition), 2023, 53(4): 1078-1084.
[7] Jing WANG,Feng WAN,Chun-jiao DONG,Chun-fu SHAO. Modelling on catchment area and attraction intensity of urban rail transit stations [J]. Journal of Jilin University(Engineering and Technology Edition), 2023, 53(2): 439-447.
[8] Zhan-zhong WANG,Ting JIANG,Jing-hai ZHANG. Evaluation of road transportation efficiency based on fuzzy double frontiers network model [J]. Journal of Jilin University(Engineering and Technology Edition), 2023, 53(2): 385-395.
[9] Qing-yong WANG,Wei-qiang QU. Optimization algorithm of urban rail transit operation scheduling based on linear programming [J]. Journal of Jilin University(Engineering and Technology Edition), 2023, 53(12): 3446-3451.
[10] Feng-feng ZHOU,Zhen-wei YAN. A model for identifying neuropeptides by feature selection based on hybrid features [J]. Journal of Jilin University(Engineering and Technology Edition), 2023, 53(11): 3238-3245.
[11] Hui GUO,Jie-di FU,Zhen-dong LI,Yan YAN,Xiao LI. SVM parameters and feature selection optimization based on improved whale algorithm [J]. Journal of Jilin University(Engineering and Technology Edition), 2023, 53(10): 2952-2963.
[12] Min YANG,Cong-wei ZHANG,Da-wei LI,Chen-xiang MA. Travel satisfaction model for air-rail integration passengers based on Bayesian network [J]. Journal of Jilin University(Engineering and Technology Edition), 2023, 53(10): 2839-2846.
[13] Yan-yan QIN,Xiao-qing YANG,Hao WANG. Impacts of CO2 emissions and improving method for connected and automated mixed traffic flow [J]. Journal of Jilin University(Engineering and Technology Edition), 2023, 53(1): 150-158.
[14] Qing GAO,Hao-dong WANG,Yu-bin LIU,Shi JIN,Yu CHEN. Experimental analysis on spray mode of power battery emergency cooling [J]. Journal of Jilin University(Engineering and Technology Edition), 2022, 52(8): 1733-1740.
[15] Pei-ze LI,Shi-shun ZHAO,Xiao-hui WENG,Xin-mei JIANG,Hong-bo CUI,Jian-lei QIAO,Zhi-yong CHANG. A new method for rapid detection of pesticide residues based on multi⁃sensor optimization [J]. Journal of Jilin University(Engineering and Technology Edition), 2022, 52(8): 1951-1956.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
Copyright © Journal of Jilin University(Engineering and Technology Edition), All Rights Reserved.
Tel: +86-431-85095297　Fax: +86-431-85094074　E-mail: xbgxb@jlu.edu.cn
Powered by Beijing Magtech Co. Ltd