基于事故致因的标准化煤矿建筑规范库构建

doi:10.16265/j.cnki.issn1003-3033.2023.05.1865

摘要/Abstract

摘要：

为有效检查煤矿建筑设计的合规性,从事故致因角度出发,利用词相似度计算(Word2Vec)模型和数据库技术,整理数量庞大、排列冗杂的规范数据,使其标准化表达。首先,运用Word2Vec模型对2009—2021年225起由煤矿建筑设计不合规引起的事故分析报告进行词向量训练,发掘出与各类事故发生最为相关的煤矿建筑设计风险要素;其次,从已获取的建筑设计风险要素出发,收集与筛选相关现行的煤矿建设规范,通过分析具体规范条款,构建规范标准化表达框架;最后,将其整理到结构化查询语言(SQL)数据库中,构建标准化规范数据库。结果表明:利用Word2Vec模型,可根据词深层次特征发掘出事故分析报告中与事故发生的建筑风险要素,将其作为检索中心词初步检索和过滤规范信息,构建基于事故致因的标准化煤矿建筑规范库,打破规范标准间的壁垒。

关键词: 事故致因, 煤矿建筑, 规范库, 设计规范, 词相似度计算(Word2Vec)模型

Abstract:

In order to effectively check the compliance of coal mine building design, this paper used word similarity calculation (Word2Vec) model and database technology to organize and standardize a large number of regulations data from the perspective of accident causation. Firstly, the Word2Vec model was used to train word vectors on 225 accident reports from 2009 to 2021 caused by non-compliance of coal mine building design, so as to find out the risk elements of coal mine building design which were most associated with the occurrence of various accidents. Then, the relevant existing coal mine construction regulations were collected and screened from the acquired building design risk factors, a standardized expression framework was constructed for the regulations by analyzing specific regulations provisions. Finally, the regulations were organized into a structured query language (SQL) database to build a standardized regulation database. Using the Word2Vec model, the construction risk elements associated with the occurrence of accidents in accident analysis reports can be uncovered based on the deep-level characteristics of words. The construction risk elements can be used as the central word for the initial search and filtering of specification information, thus building the standardized library of coal mine construction regulations, which breaks the barriers between regulations and standards.

Key words: accident causation, coal mine building, regulation database, building regulation, Word2Vec model

刘全龙, 张晓霖, 张悦倩, 邱尊相. 基于事故致因的标准化煤矿建筑规范库构建[J]. 中国安全科学学报, 2023, 33(5): 128-133.

LIU Quanlong, ZHANG Xiaolin, ZHANG Yueqian, QIU Zunxiang. Construction of a database of standardized coal mine building regulation based on accident causation[J]. China Safety Science Journal, 2023, 33(5): 128-133.

图/表 3

表1

表2

表3

参考文献 23

[1]	孙宝东, 张军, 韩一杰, 等. “双碳”目标下统筹能源安全与低碳转型的我国能源系统演化趋势与路径研究[J]. 中国煤炭, 2022, 48(10):1-15.
	SUN Baodong, ZHANG Jun, HAN Yijie, et al. Research on the evolution trend and path of China's energy system in coordinating energy security and low-carbon transformation based on the carbon neutrality goals[J]. China Coal, 2022, 48(10):1-15.
[2]	王国法, 杜毅博, 任怀伟, 等. 智能化煤矿顶层设计研究与实践[J]. 煤炭学报, 2020, 45(6):1909-1924.
	WANG Guofa, DU Yibo, REN Huaiwei, et al. Research and practice on top-level design of intelligent coal mines[J]. Journal of Coal Society, 2020, 45(6):1909-1924.
[3]	FA Ziwei, LI Xinchun, QIU Zunxinag, et al. From correlation to causality: path analysis of accident-causing factors in coal mines from the perspective of human, machinery, environment and management[J]. Resources Policy, 2021, 73(6): DOI:10.1016/j.resourpol.2021.102157. doi: 10.1016/j.resourpol.2021.102157
[4]	张经阳, 王松江. 煤矿建设项目安全生产系统集成模型研究[J]. 生产力研究, 2011(11):89-92.
	ZHANG Jingyang, WANG Songjiang. Research on integration model of safety production system in coal mine construction project[J]. Productivity Research, 2011, (11):89-92.
[5]	刘力源, 纪洪广, 王涛, 等. 高渗透压和不对称围压作用下深竖井围岩损伤破裂机理[J]. 工程科学学报, 2020, 42(6):715-722.
	LIU Liyuan, JI Hongguang, WANG Tao, et al. Mechanism of country rock damage and failure in deep shaft excavation under high pore pressure and asymmetric geostress[J]. Chinese Journal of Engineering, 2020, 42(6): 715-722.
[6]	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
[7]	肖时瑞. 建筑信息模型技术在土木工程中的运用[J]. 建筑科学, 2021, 37(1):148.
[8]	FENVES S J. Tabular decision logic for structural design[J]. American Society of Civil Engineers, 1966, 92(6): 473-490.
[9]	GARRETT J H, FENVES S J. A knowledge-based standards processor for structural component design[J]. Engineering with Computers, 1987, 2(4): 219-238. doi: 10.1007/BF01276414
[10]	CRONEMBOLD J R, LAW K H. Automated processing of design standards[J]. Journal of Computing in Civil Engineering, 1988, 2(3): 255-273. doi: 10.1061/(ASCE)0887-3801(1988)2:3(255)
[11]	HAN C S, KUNZ J C, LAW K H. Client server framework for on-line building code checking[J]. Journal of Computing in Civil Engineering, 1998, 12(4): 181-194. doi: 10.1061/(ASCE)0887-3801(1998)12:4(181)
[12]	PAUWELS P, VAN D D, VERSTRAETEN R, et al. A semantic regulation checking environment for building performance checking[J]. Automation in Construction, 2011, 20: 506-518. doi: 10.1016/j.autcon.2010.11.017
[13]	YU Mengxi, QUDDUS N, PERES S C, et al. Development of a safety management system (SMS) for drilling and servicing operations within OSHA jurisdiction area of Texas[J]. Journal of Loss Prevention in the Process Industries, 2017, 50: 266-274. doi: 10.1016/j.jlp.2017.10.005
[14]	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
[15]	BROWN D E. Text mining the contributors to rail accidents[J]. IEEE Transactions on Intelligent Transportation Systems, 2015, 17(2): 346-355. doi: 10.1109/TITS.2015.2472580
[16]	SINGLE J I, SCHMIDT J, DENECKE J. Knowledge acquisition from chemical accident databases using an ontology-based method and natural language processing[J]. Safety Science, 2020, 129: DOI:10.1016/j.ssci.2020.104747. doi: 10.1016/j.ssci.2020.104747
[17]	SINGH K, MAITI J, DHALMAHAPATRA K. Chain of events model for safety management: data analytics approach[J]. Safety Science, 2019, 118: 568-582. doi: 10.1016/j.ssci.2019.05.044
[18]	谭章禄, 陈孝慈. 基于文本挖掘的煤矿安全隐患管理研究[J]. 中国安全生产科学技术, 2020, 16(2): 43-48.
	TAN Zhanglu, CHEN Xiaoci. Research on management of hidden danger in coal mine based on text mining[J]. Journal of Safety Science and Technology, 2020, 16(2):43-48.
[19]	KAMKARHAGHIGHI M, MAKREHCHI M. Content tree word embedding for document representation[J]. Expert Systems with Applications, 2017, 90: 241-249. doi: 10.1016/j.eswa.2017.08.021
[20]	JING Sifeng, LIU Xiwei, GONG Xiaoyan, et al. Correlation analysis and text classification of chemical accident cases based on word embedding[J]. Process Safety and Environmental Protection, 2022, 158: 698-710. doi: 10.1016/j.psep.2021.12.038
[21]	陈丹华, 王艳娜, 周子力, 等. 基于Word2Vec的WordNet词语相似度计算研究[J]. 计算机工程与应用, 2022, 58(3):222-229. doi: 10.3778/j.issn.1002-8331.2009-0090
	CHEN Danhua, WANG Yanna, ZHOU Zili, et al. Research on WordNet word similarity calculation based on Word2Vec[J]. Computer Engineering and Applications, 2022, 58(3):222-229. doi: 10.3778/j.issn.1002-8331.2009-0090
[22]	SOLIHIN W, EASTAM C. Classification of regulations for automated BIM regulation checking development[J]. Automation in Construction, 2015, 53:69-82. doi: 10.1016/j.autcon.2015.03.003
[23]	陈远, 张雨, 康虹. 基于知识管理的BIM模型建筑设计合规性自动检查系统研究[J]. 图学学报, 2020, 41(3):490-499.
	CHEN Yuan, ZHANG Yu, KANG Hong. Research on knowledge-based BIM for automated compliance checking system in architectural design[J]. Journal of Graphics, 2020, 41(3): 490-499.

检索事故	重点煤矿建筑要素及相似度
顶板事故	工作面(0.978 8)	收作面(0.977 8)	煤岩柱(0.977 1)	回风巷(0.968 0)	巷修巷(0.945 0)
透水事故	煤岩柱(0.985 9)	探水点(0.974 4)	排水系统(0.969 9)	内水仓(0.946 5)	涌水量(0.937 2)
瓦斯事故	回风巷(0.972 3)	通风系统(0.970 9)	煤岩柱(0.969 0)	工作面(0.965 5)	收作面(0.948 0)
运输事故	输送机(0.977 8)	缓冲器(0.977 3)	供电系统(0.975 4)	钢绞线(0.965 9)	临点柱(0.963 1)
机电事故	供电系统(0.972 8)	过滤器(0.970 1)	输送机(0.968 3)	传感器(0.962 4)	通风机(0.959 8)
其他事故	架空线(0.578 2)	通风机(0.569 5)	带式输送机(0.568 8)	进风巷(0.565 6)	钢绞线(0.565 2)

序号	类型名称	示例
1	无前提条件构件属性一对一约束	检查孔取心率不宜小于75%
2	有前提条件构件属性一对一约束	现浇混凝土支护,混凝土塌落度不应小于150 mm
3	无前提条件构件属性一对多约束	工作面预注浆的段高宜为30~50 m
4	有前提条件构件属性一对多约束	Ⅱ类岩层中锚喷临时支护的段高宜为50~80 m
5	无前提条件由多种构件进行的单一属性约束	检查孔终深宜大于井筒设计深度10 m
6	有前提条件由多种构件进行的单一属性约束	灌筑混凝土下料导管,下料导管距离槽孔端面宜为1.5 m
7	无前提条件由多种构件进行的多属性约束	轨枕埋入道渣的深度,应为轨枕厚度的1/2~2/3
8	有前提条件由多种构件进行的多属性约束	光面爆破时,周边眼的眼距应控制在0.4~0.6 m

规范来源	前提条件	构件名称	相关构件	构建属性	程度词	比较词	属性值	具体描述
GB50511—2010	空	检查孔	空	取心率	不宜	<	75%	检查孔取心率不宜小于75%
	现浇混凝土支护	混凝土	空	塌落度	不应	<	150 mm	现浇混凝土支护,混凝土塌落度不应小于150 mm
	空	预注浆	空	段高	宜	≥	30 m	工作面预注浆的段高宜为30~50 m
	空	预注浆	空	段高	宜	≤	50 m	工作面预注浆的段高宜为30~50 m
	Ⅱ类岩层中	锚喷临时支护	空	段高	宜	≥	50 m	Ⅱ类岩层中锚喷临时支护的段高宜为50~80 m
	Ⅱ类岩层中	锚喷临时支护	空	段高	宜	≤	80 m	Ⅱ类岩层中锚喷临时支护的段高宜为50~80 m
	空	检查孔终深	井筒设计深度	距离	宜	>	10 m	检查孔终深宜大于井筒设计深度10 m
	空	轨枕	为轨枕厚度	埋入深度	应	>	1/2	轨枕埋入道渣的深度,应为轨枕厚度的1/2~2/3
	空	轨枕	轨枕厚度	埋入深度	应	≤	2/3	轨枕埋入道渣的深度,应为轨枕厚度的1/2~2/3
GB50215—2015	光面爆破时	周边眼	其他周边眼	距离	宜	≥	0.4 m	光面爆破时,周边眼的眼距应控制在0.4~0.6 m
GB50215—2015	光面爆破时	周边眼	其他周边眼	距离	宜	≥	0.6 m	光面爆破时,周边眼的眼距应控制在0.4~0.6 m