基于改进的Apriori算法的铁路事故风险源关联分析方法

doi:10.3976/j.issn.1002-4026.2023.05.009

Abstract

Abstract:

The causes of railway accidents are difficult to determine as several hazards can lead to accidents. To prevent the occurrence of railway accidents, the hazards responsible for railway accidents should be analyzed, and the occurrence rules of previous railway accidents should be revealed. In this study,data mining analysis on railway accidents and hazards was conducted using the improved Apriori algorithm.Considering the severity of accident casualties, a new calculation method for support and confidence indicators was proposed to weigh and quantify railway accident factors.Furthermore, time constraints were added to explore association rules of hazards with corresponding railway accidents at different times. Using the actual UK railway accident data, the association rules between railway accidents and hazards were discovered, and effective preventive measures were formulated for actual cases. Results show that the improved Apriori algorithm can explore more association rules between railway accidents and hazards, which can play an important role in preventing railway accidents.

Key words: hazards, railway accidents, association rule, Apriori algorithm, data mining analysis

CLC Number:

U298.5

WANG Ning, CHANG Ximing, YANG Xin, WU Jianjun. Association analysis method for railway accident hazards based on the improved Apriori algorithm[J].Shandong Science, 2023, 36(5): 67-74.

Figures/Tables 8

Table 1

Fig.1

Fig.2

Table 2

Table 3

Fig.3

Fig.4

Table 4

References 13

[1]	国家铁路局. “6.4”兰新线K596次旅客列车与作业人员相撞铁路交通事故调查处理情况公告[EB/OL]. [2022-08-10]. http://www.nra.gov.cn/zzjg/jgj/lzgl/gglz/202107/t20210729_337941.shtml
[2]	张萌, 梁正, 祝思清. 基于关联规则的数据挖掘在医疗诊断中的应用[J]. 山东科学, 2008, 21(1): 80-82.
[3]	降惠, 尹振保, 武丽娟, 等. Apriori算法在手足口病与气象因素关系分析中的应用[J]. 智能计算机与应用, 2021, 11(7): 124-128. DOI: 10.3969/j.issn.2095-2163.2021.07.023.
[4]	陈治, 吴娟娟. 基于关联规则的医疗数据挖掘研究[J]. 统计与决策, 2020, 36(6): 174-177. DOI: 10.13546/j.cnki.tjyjc.2020.06.040.
[5]	刘媛, 孙辉, 许苑南, 等. 基于数据挖掘及网络药理学探讨中药治疗消化性溃疡的用药规律及作用机制[J]. 山东科学, 2022, 35(5): 37-45. DOI: 10.3976/j.issn.1002-4026.2022.05.005.
[6]	何林, 刘宇红, 张荣芬. 基于关联规则对工业铀测量数据挖掘分析研究[J]. 计算机技术与发展, 2022, 32(5): 147-152. DOI: 10.3969/j.issn.1673-629X.2022.05.025.
[7]	程岩, 任国兴, 杜立彬. 基于Apriori模型的海洋灾害预警数据挖掘技术[J]. 山东科学, 2009, 22(2): 57-60.
[8]	ÖZAYDIN E, FISKIN R, UĞURLU Ö, et al. A hybrid model for marine accident analysis based on Bayesian Network (BN) and Association Rule Mining (ARM)[J]. Ocean Engineering, 2022, 247:110705. DOI: 10.1016/j.oceaneng.2022.110705.
[9]	LAN H, MA X, MA L, et al. Pattern investigation of total loss maritime accidents based on association rule mining[J]. Reliability Engineering & SystemSafety, 2023, 229:108893. DOI: 10.1016/j.ress.2022.108893.
[10]	刘文雅, 徐永能. 基于改进Apriori算法的地铁故障关联规则挖掘[J]. 兵器装备工程学报, 2021, 42(12):210-215. DOI: 10.11809/bqzbgcxb2021.12.033.
[11]	许未, 何世伟, 刘朝辉, 等. 基于关联规则的铁路事故致因网络构建与分析[J]. 铁道运输与经济, 2020, 42(11): 72-79. DOI: 10.16668/j.cnki.issn.1003-1421.2020.11.13.
[12]	徐红, 矫桂娥, 张文俊, 等. 基于卷积神经网络的结构化非平衡数据分类算法[J]. 计算机工程, 2023, 49(2): 81-89. DOI: 10.19678/j.issn.1000-3428.0063871.
[13]	何文竹, 彭长根, 王毛妮, 等. 面向结构化数据集的敏感属性识别与分级算法[J]. 计算机应用研究, 2020, 37(10): 3077-3082. DOI: 10.19734/j.issn.1001-3695.2019.05.0187.

Metrics

Comments

Recommended 0

Open Access This article is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License (CC BY-NC 4.0), which permits third parties to freely share (i.e., copy and redistribute the material in any medium or format) and adapt (i.e., remix, transform, or build upon the material) the articles published in this journal, provided that appropriate credit is given, a link to the license is provided, and any changes made are indicated. The material may not be used for commercial purposes. For details of the CC BY-NC 4.0 license, please visit: https://creativecommons.org/licenses/by-nc/4.0

伤害程度	权重
1级轻伤/多人2级受伤	0.008
多人1级轻伤/重伤	0.04
1~2级重伤	0.2
多起重大/单一死亡	1
多人死亡	5

风险源编号	风险源描述	风险源类型
H01	列车司机经验或能力不够	人员
H02	列车司机对危险形势的误判	人员
H03	列车司机忽视或误解警告警示	人员
H35	刹车系统问题	设备
H36	制动系统设备、性能问题	设备
H37	公路轨道车辆故障或异常状态	设备
H56	树叶	环境
H57	山体滑坡	环境
H58	天气温度过高	环境
H71	应对洪水、暴雨的准备计划不足	管理
H72	不合适的排班次作业或工作规划	管理
H73	对安全工作制度的监督审查无效	管理

事故编号	事故描述	事故危害后果(FWI/年)
H90	碰撞事故	2.652 0
H91	脱轨事故	0.162 4
H92	失控事故	0.050 4
H93	坠落事故	0.222 4
H94	拖拽事故	0.102 4
H95	电气事故	0.028 8
H96	超速事故	0.004 0
H97	未遂事故	0.000 8

时间	强关联规则
	脱轨⇒碰撞
日间	行人、乘客、骑行者进行的不安全行为⇒碰撞
	行人、乘客、骑行者对危险形势的误判⇒碰撞
夜间	脱轨⇒碰撞
	失控⇒碰撞
	车辆、机械设备等操作员违规操作或操作错误⇒碰撞
	列车司机压力、疲劳或者分心⇒碰撞

Association analysis method for railway accident hazards based on the improved Apriori algorithm

RichHTML

PDF (PC)

Like

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 8

References 13

Related Articles 1

Metrics

Comments

Recommended 0