Research on spatial and temporal distribution characteristics of safety nazards in hydropower projects

doi:10.16265/j.cnki.issn1003-3033.2022.11.2227

Abstract

Abstract:

In order to reveal the temporal and spatial distribution characteristics of safety hazards, the data of 32 060 safety hazards during the construction of a large-scale hydropower project were mined. The phrase extraction technology based on the TF-CRF algorithm was used to establish a word cloud map of the types and parts of hazards, reflecting the word frequency distribution feature of key information about safety hazards. The Sankey diagram was produced to represent the information flow features among characteristics, locations and types of safety hazards. The sequential network of near-misses was constructed to analyze the time characteristics and dynamic relationships of different types of safety hazards. The results show that safety hazards such as the construction of the bent frame, steel formwork trolley, and bent frame erection frequently occur in underground caverns, caves, platforms and other parts, which are the focus of safety management. From the Sankey diagram, the information flow related to the steel formwork trolley and the bent frame is the densest, and the safety hazards related to them are the most. From the network diagram, Electric shock safety hazards occur most frequently in November and December, and the number of occurrences is the least in January and February. Integrating three types of safety hazards into the same network for verification shows that this method is feasible and also finds the highest number of safety hazards related to civilized construction. These should be attached with great importance by the managers.

Key words: hydroelectric engineering construction, safety hazards, spatial and temporal distribution, Sankey diagram, sequential network, term frequency-category relevance factors(TF-CRF)algorithm

CHEN Shu, LIU Wenzhuo, SHAO Bo, XI Junbo, WANG Jianping. Research on spatial and temporal distribution characteristics of safety nazards in hydropower projects[J]. China Safety Science Journal, 2022, 32(11): 90-96.

Figures/Tables 8

Tab.1

Tab.2

Fig.1

Tab.3

Fig.2

Fig.3

Fig.4

Fig.5

References 15

[1]	陈述, 申浩播, 郑霞忠, 等. 大坝浇筑立体交叉作业空间竞争程度研究[J]. 水力发电学报, 2018, 37(7):106-112.
	CHEN Shu, SHEN Haobo, ZHENG Xiazhong, et al. Competition of spatial conflict strength during cross operation of dam construction[J]. Journal of Hydroelectric Engineering, 2018, 37(7):106-112.
[2]	CHEN Shu, TIAN Ya, JIN Lianghai, et al. Estimating the frequency of exposure to uncertain hazards:impact of wind conditions on concrete dam construction[J]. Journal of Construction Engineering and Management, 2021, 147(2):1-13.
[3]	李红霞, 田辰宁. 基于Cite Space Ⅴ的煤矿安全管理可视化分析[J]. 中国安全科学学报, 2018, 28(9):148-153. doi: 10.16265/j.cnki.issn1003-3033.2018.09.025
	LI Hongxia, TIAN Chenning. Analysis of coal mine safety management based on Cite Space V[J]. China Safety Science Journal, 2018, 28(9):148-153. doi: 10.16265/j.cnki.issn1003-3033.2018.09.025
[4]	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
[5]	谭章禄, 王泽, 陈晓. 基于LDA的煤矿安全隐患主题发现研究[J]. 中国安全科学学报, 2016, 26(6):123-128.
	TAN Zhanglu, WANG Ze, CHEN Xiao. Research on topic extraction for coal mine hidden danger based on LDA[J]. China Safety Science Journal, 2016, 26(6):123-128.
[6]	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.
[7]	李擎, 张秋艳, 白磊. 一种基于文本挖掘的铁路基础设施设备风险隐患识别模型[J]. 铁路计算机应用, 2018, 27(2):1-4.
	LI Qing, ZHANG Qiuyan, BAI Lei. Text mining based identification model for railway infrastructure risk[J]. Railway Computer Application, 2018, 27(2):1-4.
[8]	GOH Y M, UBEYNARAYANA C U. Construction accident narrative classification:an evaluation of text mining techniques[J]. Accident Analysis and Prevention, 2017, 108:122-130. doi: 10.1016/j.aap.2017.08.026
[9]	PENG Hanchuan, LONG Fuhui, DING Chen. Feature selection based on mutual information:criteria of max-dependency, max-relevance, and min-redundancy[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(8):1226-1238. pmid: 16119262
[10]	郭理, 张恒旭, 王嘉岐, 等. 基于Trie树的词语左右熵和互信息新词发现算法[J]. 现代电子技术, 2020, 43(6):65-69.
	GUO Li, ZHANG Hengxu, WANG Jiaqi, et al. Trie tree based new word discovery algorithm using left-right entropy and mutual information[J]. Modern Electronics Technique, 2020, 43(6):65-69.
[11]	李璐, 何利力. 融合信息熵与多权TF-IDF的营销评论关键词提取算法[J]. 智能计算机与应用, 2020, 10(9):69-72, 76.
	LI Lu, HE Lili. Keyword extraction algorithm integrating information entropy and multi-weight TF-IDF[J]. Intelligent Computer and Applications, 2020, 10(9):69-72, 76.
[12]	路永和, 李焰锋. 改进TF-IDF算法的文本特征项权值计算方法[J]. 图书情报工作, 2013, 57(3):90-95.
	LU Yonghe, LI Yanfeng. Improvement of text feature weighting method based on TF-IDF algorithm[J]. Library and Information Service, 2013, 57(3):90-95.
[13]	FANG Yong, ZHAO Cuirong, HUANG Cheng, et al. SankeyVis:visualizing active relationship from emails based on multiple dimensions and topic classification methods[J]. Forensic Science International:Digital Investigation, 2020,35:DOI:10.1016/j.fsidi.2020.300981. doi: 10.1016/j.fsidi.2020.300981
[14]	周诚, 张涵涛. 基于复杂网络的盾构施工参数时间序列研究[J]. 铁道工程学报, 2017, 34(3):80-86.
	ZHOU Cheng, ZHANG Hantao. Analysis of metro shield construction parameters time series based on complex networks in metro construction[J]. Journal of Railway Engineering Society, 2017, 34(3):80-86.
[15]	杜斐, 黄宏伟, 张东明, 等. 上海轨道交通网络的复杂网络特性及鲁棒性研究[J]. 武汉大学学报:工学版, 2016, 49(5):701-707.
	DU Fei, HUANG Hongwei, ZHANG Dongming, et al. Analysis of characteristics of complex network and robustness in Shanghai metro network[J]. Engineering Journal of Wuhan University, 2016, 49(5):701-707.

编号	隐患问题	隐患部位	隐患类型
20160912012740	坝肩槽安明队施工完后遗留的废旧材料未及时清理	坝肩槽	文明施工
20161028015838	卷扬控制电缆破损	尾水出口边坡	触电
︙
20170509030330	钻爆台车杆件变形	左岸泵房交通洞	坍塌

关键词短语	改进前权值	改进后权值
施工排架	28.324 521 38	23.85
钢模台车	26.876 541 26	22.58
排架搭设	24.675 886 31	21.17
漏电伤人	22.213 345 79	20.37

安全隐患	TF	I	E_L	E_R	权值
施工排架	76	17.440 476 69	3.055 227 269	3.353 238 290	23.85
下游排架	36	16.693 262 28	2.909 249 429	3.191 418 518	22.78
钢模台车	31	16.543 730 55	2.798 832 474	3.255 110 513	22.58
排架搭设	24	16.287 797 18	2.217 434 873	2.672 351 698	21.17
漏电伤人	18	16.000 115 10	1.783 073 469	2.736 339 051	20.51
伤人隐患	18	16.000 115 10	1.671 530 802	2.707 269 710	20.37
踢脚板缺失	14	15.748 800 68	2.304 619 385	1.965 237 049	20.01
排架平台	10	15.412 328 44	2.163 955 657	2.025 326 221	19.60
排架施工	12	15.594 650 00	2.253 857 590	1.352 209 399	19.20