基于文本挖掘的城镇燃气事故致因及关联分析

doi:10.16265/j.cnki.issn1003-3033.2023.07.1644

摘要/Abstract

摘要：

为有效预防城镇燃气事故发生,采用文本挖掘与复杂网络理论相结合的方法,系统分析影响城镇燃气安全的事故致因及其关联性。首先运用文本挖掘技术,从2017—2021年间的 1 256份燃气事故案例中提取城镇燃气事故致因因素,采用Apriori算法挖掘城镇燃气事故致因的关联规则,共得到49条强关联规则;然后基于共现矩阵构建事故致因网络图,通过度中心性、紧密中心性、介数中心性分析,明确燃气事故的关键致因项和事故致因集合。研究结果表明:管道破损,阀门未关,设备老化,操作、使用不当和软管破损、脱落是城镇燃气事故关键致因因素,气体泄漏是燃气事故常见的事故类型,主要与管道破损、阀门未关等具有强关联性。

关键词: 城镇燃气, 事故致因, 文本挖掘, 关联规则, Apriori算法

Abstract:

In order to effectively prevent the occurrence of urban gas accidents, the causes of accidents affecting urban gas safety and their relevance were systematically analyzed by using the research method of text mining and complex network theory. Firstly, text mining technology was used to extract the causative factors of urban gas accidents from 1 256 gas accident cases from 2017 to 2021, and the Apriori algorithm was used to mine the association rules of urban gas accident causes, and 49 strong association rules were obtained. Then the accident cause network diagram was constructed based on the co-occurrence matrix, and the key causes and accident cause sets of gas accidents were identified through the analysis of degree centrality, compact centrality and intermediary centrality. The research results show that pipeline damage, valve opening, equipment aging, improper operation and use, hose damage and shedding are the key causes of urban gas accidents, and gas leakage is a common type of gas accident. It is mainly related to pipeline damage, valve failure and so on.

Key words: urban gas, accident cause, text mining, association rule, Apriori algorithm

郑彬彬, 冯婷婷, 王佳贺, 肖远, 孙文浩. 基于文本挖掘的城镇燃气事故致因及关联分析[J]. 中国安全科学学报, 2023, 33(7): 190-195.

ZHENG Binbin, FENG Tingting, WANG Jiahe, XIAO Yuan, SUN Wenhao. Causes and correlation analysis of urban gas accidents based on text mining[J]. China Safety Science Journal, 2023, 33(7): 190-195.

图/表 9

图1

图2

表1

表2

表3

图3

表4

图4

图5

参考文献 23

[1]	彭开和. 基于十堰市“6·13”重大燃气爆炸事故的城市天然气管道事故原因分析及对策研究[J]. 工业安全与环保, 2022, 48(5):20-22.
	PENG Kaihe. Study on the causes and countermeasures of urban natural gas pipeline accidents based on the "June 13" gas explosion accident in Shiyan[J]. Industrial Safety and Environmental Protection, 2022, 48(5):20-22.
[2]	赵孟孟, 亢永, 吴壮. 城市燃气爆炸事故及其防治措施[J]. 北京石油化工学院学报, 2021, 29(2):61-66.
	ZHAO Mengmeng, KANG Yong, WU Zhuang. City gas explosion accident and its prevention measures[J]. Journal of Beijing Institute of Petrochemical Technology, 2021, 29(2):61-66.
[3]	许仁辞, 岳永魁, 胡鑫杰. 城市燃气爆炸事故统计分析与对策[J]. 煤气与热力, 2020, 40(7):33-36.
	XU Renci, YUE Yongkui, HU Xinjie. Statistical analysis and countermeasure of urban gas explosion accidents[J]. Gas & Heat, 2020, 40(7):33-36.
[4]	刘爱华, 黄检, 吴卓儒, 等. 城市燃气管道状况及燃气事故统计分析[J]. 煤气与热力, 2017, 37(10):27-33.
	LIU Aihua, HUANG Jian, WU Zhuoru, et al. Statistics analysis of urban gas pipeline situation and gas accidents[J]. Gas & Heat, 2017, 37(10):27-33.
[5]	QIAN Xinming, ZHANG Ruoheng, ZHANG Qi, et al. Cause analysis of the large-scale LPG explosion accident based on key investigation technology: a case study[J]. ACS Omega, 2021, 6(31):20644-20 656. doi: 10.1021/acsomega.1c02837 pmid: 34396010
[6]	孙逸林, 王冶, 刘险峰, 等. 基于24Model的燃气管道维抢事故致因定量分析方法[J]. 油气储运, 2022, 41(7):795-801.
	SUN Yilin, WANG Ye, LIU Xianfeng, et al. Quantitative analysis method for causal factors of gas pipeline repair and rescue accidents based on 24Model[J]. Oil & Gas Storage and Transportation, 2022, 41(7):795-801.
[7]	谌志群, 张国煊. 文本挖掘与中文文本挖掘模型研究[J]. 情报科学, 2007, 25(7):1046-1051.
	CHEN Zhiqun, ZHANG Guoxuan. Study on the text mining and Chinese text mining framework[J]. Information Science, 2007, 25(7):1046-1051.
[8]	BROWN D E. Text mining the contributors to rail accidents[J]. IEEE Transactions on Intelligent Transportation Systems, 2016, 17(2):346-355. doi: 10.1109/TITS.2015.2472580
[9]	NAYAK R, PIYATRAPOOMI N, WELIGAMAGE J. Application of text mining in analysing road crashes for road asset management[C]. Proceedings of the 4^th World Congress on Engineering Asset Management, 2010: 49-58.
[10]	韩天园, 田顺, 吕凯光, 等. 基于文本挖掘的重特大交通事故成因网络分析[J]. 中国安全科学学报, 2021, 31(9):150-156. doi: 10.16265/j.cnki.issn1003-3033.2021.09.021
	HAN Tianyuan, TIAN Shun, LYU Kaiguang, et al. Network analysis on causes for serious traffic accidents based on text mining[J]. China Safety Science Journal, 2021, 31(9):150-156. doi: 10.16265/j.cnki.issn1003-3033.2021.09.021
[11]	许娜, 王文顺, 王建平, 等. 城市轨道交通建设项目安全事故致因挖掘与重要度评估[J]. 科技进步与对策, 2018, 35(24):134-138.
	XU Na, WANG Wenshun, WANG Jianping, et al. Using text mining to extract safety accident causes and to assess importance on urban rail transit construction project[J]. Science & Technology Progress and Policy, 2018, 35(24):134-138.
[12]	QIU Zunxiang, LIU Quanlong, LI Xinchun, et al. Construction and analysis of a coal mine accident causation network based on text mining[J]. Process Safety and Environmental Protection, 2021, 153:320-328. doi: 10.1016/j.psep.2021.07.032
[13]	陈聪聪, 赵怡晴, 姜琳婧, 等. 基于文本挖掘的尾矿库隐患因素关联分析[J]. 矿业研究与开发, 2021, 41(11):26-33.
	CHEN Congcong, ZHAO Yiqing, JIANG Linjing, et al. Correlation analysis on the hidden risk factors of tailings pond based on text mining[J]. Mining Research and Development, 2021, 41(11):26-33.
[14]	TOBBACK E, NAUDTS H, DAELEMANS W, et al. Belgian economic policy uncertainty index: Improvement through text mining[J]. International Journal of Forecasting, 2018, 34(2):355-365. doi: 10.1016/j.ijforecast.2016.08.006
[15]	LI Hanguang, NI Yu. Intrusion detection technology research based on Apriori algorithm[J]. Physics Procedia, 2012, 24:1615-1620. doi: 10.1016/j.phpro.2012.02.238
[16]	李晶, 罗泰晔. 基于文本挖掘的5G技术研究热点分析[J]. 科技管理研究, 2020, 40(19):153-158.
	LI Jing, LUO Taiye. Hot research topics analysis of 5G technology based on text mining[J]. Science and Technology Management Research, 2020, 40(19):153-158.
[17]	王亚坤. 基于文本挖掘的铁路事故致因分类识别及关联规则辨识方法研究[D]. 北京: 北京交通大学, 2021.
	WANG Yakun. Research on classification and recognition of railway accident causes and association rules recognition based on text mining[D]. Beijing: Beijing Jiaotong University, 2021.
[18]	陈述, 习俊博, 王建平, 等. 水电工程施工安全隐患关联规则挖掘[J]. 中国安全科学学报, 2021, 31(8):75-82. doi: 10.16265/j.cnki.issn1003-3033.2021.08.011
	CHEN Shu, XI Junbo, WANG Jianping, et al. Mining association rules of near-misses of hydropower projects construction[J]. China Safety Science Journal, 2021, 31(8):75-82. doi: 10.16265/j.cnki.issn1003-3033.2021.08.011
[19]	王兵, 黄丹, 李文璟. 基于支持度矩阵Apriori算法的钻井隐患关联挖掘[J]. 西南石油大学学报:自然科学版, 2022, 44(2):113-122.
	WANG Bing, HUANG Dan, LI Wenjing. Correlation mining of hidden hazards in drilling based on support matrix Apriori algorithm[J]. Journal of Southwest Petroleum University:Science & Technology Edition, 2022, 44(2):113-122.
[20]	LIU Guanyang, BOYD M, YU Mengxi, et al. Identifying causality and contributory factors of pipeline incidents by employing natural language processing and text mining techniques[J]. Process Safety and Environmental Protection, 2021, 152:37-46. doi: 10.1016/j.psep.2021.05.036
[21]	李浩然, 王子恒, 杨起帆, 等. 复杂网络下地铁灾害链演化模型与风险分析[J]. 中国安全科学学报, 2021, 31(11):141-147. doi: 10.16265/j.cnki.issn 1003-3033.2021.11.020
	LI Haoran, WANG Ziheng, YANG Qifan, et al. Evolutionary model and risk analysis of metro disaster chain under complex network[J]. China Safety Science Journal, 2021, 31(11):141-147. doi: 10.16265/j.cnki.issn 1003-3033.2021.11.020
[22]	江滔. 基于社交网络的源定位算法研究与系统实现[D]. 扬州: 扬州大学, 2022.
	JIANG Tao. Research and system implementation of source location algorithm based on social network[D]. Yangzhou: Yangzhou University, 2022.
[23]	李解, 王建平, 许娜, 等. 基于文本挖掘的地铁施工安全风险事故致险因素分析[J]. 隧道建设, 2017, 37(2):160-166.
	LI Jie, WANG Jianping, XU Na, et al. Analysis of safety risk factors for metro construction based on text mining method[J]. Tunnel Construction, 2017, 37(2):160-166.

致因分类	关键词
人为因素	操作、使用不当,自杀,维修调试……
设备因素	管道破损,设备老化,产品不合格,……
环境因素	明火,空间密闭,老鼠……
管理因素	长时间未检修,违规操作,违规存放……

序号	关联规则	支持度	置信度	提升度
1	设备老化⇒气体泄漏	0.019 904	0.862 069	1.459 243
2	设备老化⇒爆炸	0.011 943	0.517 241	1.143 759
3	用电用火⇒气体泄漏	0.040 605	0.772 727	1.308 013
︙	︙	︙	︙	︙
17	第三方施工⇒破损	0.064 490	0.852 632	7.816 827
18	管道破损⇒气体泄漏	0.080 414	0.737 226	1.247 919
︙	︙	︙	︙	︙
48	气体泄漏/第三方施工⇒管道破损	0.046 178	0.840 580	7.706 337
49	第三方施工⇒管道破损/气体泄漏	0.046 178	0.610 526	7.592 288

事故致因	软管破损、脱落	气体泄漏	产品不合格	操作、使用不当
软管破损、脱落	0	61	3	7
气体泄漏	61	0	7	42
产品不合格	3	7	0	1
操作、使用不当	7	42	1	0

致因编号	事故致因	D_i	C_i	B_i	致因编号	事故致因	D_i	C_i	B_i
F₁	气体泄漏	48	0.85	531.74	F₁₆	安装不当	12	0.53	3.35
F₂	爆炸	43	0.78	335.82	F₁₇	家庭纠纷	11	0.53	0.67
F₃	火灾	33	0.69	199.98	F₁₈	车祸	11	0.53	12.85
F₄	操作、使用不当	26	0.63	51.9	F₁₉	第三方施工	11	0.53	0.94
F₅	爆燃	26	0.62	67.87	F₂₀	产品过期	10	0.53	0.56
F₆	明火	25	0.61	37.07	F₂₁	空间密闭	10	0.52	1.98
F₇	管道破损	22	0.6	66.09	F₂₂	老鼠	10	0.53	0.22
F₈	软管破损、脱落	21	0.59	19.2	F₂₃	违规改造	10	0.53	8.32
F₉	阀门未关	21	0.59	11.7	F₂₄	违规操作	10	0.53	6.79
F₁₀	用电用火	20	0.59	17.78	F₂₅	违规存放	10	0.54	69.07
F₁₁	中毒	17	0.55	11.93	F₂₆	更换煤气	9	0.52	0.14
F₁₂	设备老化	16	0.57	17.38	F₂₇	违规作业	9	0.52	0.63
F₁₃	产品不合格	13	0.53	10.87	F₂₈	罐体着火	9	0.53	9.23
F₁₄	自杀	13	0.54	2.72	F₂₉	阀门损坏、脱落	9	0.53	3.5
F₁₅	人为破坏	12	0.54	6.26	F₃₀	维修调试	8	0.51	1.67