Causal analysis of construction safety accidents in hydropower projects based on unsupervised LDA

doi:10.16265/j.cnki.issn1003-3033.2023.10.1924

Abstract

Abstract:

To achieve the intelligent mining of causative factors in hydropower construction safety accident reports, 1 206 accident analysis reports were processed by using Jieba segmentation. Also, the TF-IDF (Term Frequency-Inverse Document Frequency) keyword processing algorithm for accident analysis text was proposed, which was used to determine word frequency weight and construct word vector of accident text. Furthermore, based on the TF-IDF features, the unsupervised LDA topic model was trained to extract accident topics and topic words. Finally, social network analysis was performed on the topic words to reveal the potential relationships among accidents elements and intelligently output the causes of hydropower engineering construction safety accidents. The results show that the LDA theme model can quickly dig out multiple accident data information effectively, and calculate five accident themes such as safety awareness, accident hazards and violation behaviors. Besides, the results of automatic cause analysis indicate that the most important causes of construction safety accidents in hydropower projects are violation of rules and regulations, failure to master safe operation techniques, material and equipment problems, violation of construction procedures and poor working environment. The behavior supervision of construction personnel should be strengthened, to improve the prevention ability of the main causes of accidents, which can effectively improve the safety control level of hydropower project construction.

Key words: ydropower engineering, construction safety accident, unsupervised latent Dirichlet allocation (LDA) topic model, accident causation, social network analysis, factor analysis

CHEN Shu, SUN Mengwen, CHEN Yun, NIE Benwu, LI Zhi, LIU Wenzhuo. Causal analysis of construction safety accidents in hydropower projects based on unsupervised LDA[J]. China Safety Science Journal, 2023, 33(10): 79-85.

Figures/Tables 9

Fig.1

Tab.1

Tab.2

Tab.3

Fig.2

Tab.4

Fig.3

Tab.5

Tab.6

References 17

[1]	樊启祥, 陆佑楣, 李果, 等. 金沙江下游大型水电工程智能建造管理创新与实践[J]. 管理世界, 2021, 37(11):206-226.
	FAN Qixiang, LU Youmei, LI Guo, et al. Innovation and practice of intelligent construction management of large-scale hydropower projects on the lower Jinsha River[J]. Journal of Management World, 2021, 37(11):206-226.
[2]	CHEN Shu, XI Junbo, CHEN Yun, et al. Association mining of near misses in hydropower engineering construction based on convolutional neural network text classification[J]. Computational Intelligence and Neuroscience, 2022, 2022:1-16.
[3]	陈述, 朱丽萍, 陈云, 等. 基于复杂网络的水电工程施工安全隐患时序特性[J]. 中国安全科学学报, 2022, 32(8):61-66. doi: 10.16265/j.cnki.issn1003-3033.2022.08.2315
	CHEN Shu, ZHU Liping, CHEN Yun, et al. Sequential characteristics of safety hazards in hydropower project construction based on complex networks[J]. China Safety Science Journal, 2022, 32(8):61-66. doi: 10.16265/j.cnki.issn1003-3033.2022.08.2315
[4]	REASON J. The contribution of latent human failures to the breakdown of complex systems[J]. Philosophical Transactions of the Royal Society of London. Series B, Biological Sciences, 1990, 327(1241):475-484.
[5]	傅贵, 索晓, 贾清淞, 等. 10种事故致因模型的对比研究[J]. 中国安全生产科学技术, 2018, 14(2):58-63.
	FU Gui, SUO Xiao, JIA Qingsong, et al. Comparative study on ten accident causation models[J]. Journal of Safety Science and Technology, 2018, 14(2):58-63.
[6]	郑霞忠, 周佳丽, 邵波, 等. 基于D-I的塔机作业物体打击事故致因分析[J]. 中国安全科学学报, 2021, 31(6):83-89. doi: 10.16265/j.cnki.issn 1003-3033.2021.06.011
	ZHENG Xiazhong, ZHOU Jiali, SHAO Bo, et al. Causal analysis of strike accident of tower crane operating object based on D-I[J]. China Safety Science Journal, 2021, 31(6):83-89. doi: 10.16265/j.cnki.issn 1003-3033.2021.06.011
[7]	张伟, 朱双娜, 张潇, 等. 建筑施工安全事故致因系统模型与实证分析[J]. 中国安全科学学报, 2019, 29(6):56-62. doi: 10.16265/j.cnki.issn1003-3033.2019.06.010
	ZHANG Wei, ZHU Shuangna, ZHANG Xiao, et al. Systematic model of construction accident causation and its empirical analysis[J]. China Safety Science Journal, 2019, 29(6):56-62. doi: 10.16265/j.cnki.issn1003-3033.2019.06.010
[8]	张建荣, 张伟, 薛楠楠, 等. 基于随机森林算法的塔式起重机安全事故预测及致因分析[J]. 安全与环境工程, 2021, 28(5):36-42.
	ZHANG Jianrong, ZHANG Wei, XUE Nannan, et al. Prediction and cause analysis of tower-crane safety accidents by using random forest algorithm[J]. Safety and Environmental Engineering, 2021, 28(5):36-42.
[9]	SHAO Bo, HU Zhigen, LIU Quan, et al. Fatal accident patterns of building construction activities in China[J]. Safety Science, 2019, 111(1):253-263. doi: 10.1016/j.ssci.2018.07.019
[10]	邓晓衡, 曾德天. 基于AHP和混合Apriori-Genetic算法的交通事故成因分析模型[J]. 计算机应用研究, 2019, 36(6):1633-1637.
	DENG Xiaoheng, ZENG Detian. Traffic accident causation analysis model based on AHP and hybrid Apriori-Genetic algorithm[J]. Application Research of Computers, 2019, 36(6):1633-1637.
[11]	ETEIFA S O, El-ADAWAY I H. Using social network analysis to model the interaction between root causes of fatalities in the construction industry[J]. Journal of Management in Engineering, 2018, 34(1):1-15.
[12]	刘婷, 张社荣, 王超, 等. 水利施工事故文本智能分析的BERT-BiLSTM混合模型[J]. 水力发电学报, 2022, 41(7):1-12.
	LIU Ting, ZHANG Sherong, WANG Chao, et al. Text intelligent analysis for hydraulic construction accidents based on BERT-BiLSTM hybrid model[J]. Journal of Hydroelectric Engineering, 2022, 41(7):1-12.
[13]	张东成, 强茂山, 江汉臣, 等. 大型工程安全隐患管理协作特征挖掘[J]. 清华大学学报:自然科学版, 2022, 62(2):208-214.
	ZHANG Dongcheng, QIANG Maoshan, JIANG Hanchen, et al. Mining safety hazard management collaboration features from large construction projects[J]. Journal of Tsinghua University: Science and Technology, 2022, 62(2):208-214.
[14]	牛毅, 樊运晓, 高远. 基于数据挖掘的化工生产事故致因主题抽取[J]. 中国安全生产科学技术, 2019, 15(10):165-170.
	NIU Yi, FAN Yunxiao, GAO Yuan. Topic extraction on causes of chemical production accidents based on data mining[J]. Journal of Safety Science and Technology, 2019, 15(10):165-170.
[15]	BIGGERS L R, BOCOVICH C, CAPSHAW R. Configuring latent dirichlet allocation based feature location[J]. Empirical Software Engineering, 2014, 19(3):465-500. doi: 10.1007/s10664-012-9224-x
[16]	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
[17]	曾小清, 林海香, 王奕曾, 等. 基于事故数据的轨道交通运行安全风险辨识方法[J]. 同济大学学报:自然科学版, 2022, 50(3): 418-424.
	ZENG Xiaoqing, LIN Haixiang, WANG Yizeng, et al. Safety risk identification of rail transit signaling system based on accident data[J]. Journal of Tongji University: Natural Science, 2022, 50(3):418-424.

序号	事故分析报告文本
1	操作控制设备有缺陷,24缆机为西德进口设备,采用无线遥控操作,运行中突然发生故障,信号中断,致使小车突然停车;缆机工李某某违章乘小车,高处检修未系安全绳(带)
2	梁某某缺乏起重的安全基本知识,自我保护意识淡薄,在无任何防护措施的情况下,将头部伸进吊物下方违章冒险作业
︙	︙
1 206	杨某某违章指挥缆机起吊,所站位置在距栈桥约40 m的船闸尾部,无法准确判断吊物周围情况

关键词	权重值	关键词	权重值
违章	0.136	坠落	0.045
作业	0.106	钢丝绳	0.044
施工	0.055	指挥	0.039
违反	0.052	起吊	0.038
操作规程	0.049

主题类型	主题词
安全意识	安全意识、坠落、车辆、过程、发生、洞内、司机、检修、拆除、水泥、措施不当、程序、自我保护意识、身体、高压
事故隐患	钢丝绳、钢筋、事故隐患、固定、排架、平台、人员、安全带、位置、安全绳、失稳、撤离、盲目、地面、脚手架
操作规程	施工、操作规程、模板、操作、起吊、违反、技术、装载机、人员、倒车、不慎、边墙、临危、淡薄、起重
违章行为	违章、指挥、工作、驾驶员、部位、断裂、信号、车速、制动、支撑、地质、开关、倾倒、工作面、机械
冒险作业	作业、行走、高处、冒险、避炮、措施、防护、驾驶、擅自、条件、电工、现场、倒塌、照明、吊车

事故因素	事故特征
操作人员、驾驶员、电工等	安全意识、技术、冒险、起吊、驾驶、防护措施、操作规程、违章、身体、施工程序、车速过快等
安全带、钢丝绳、吊车、脚手架,防护、模板等	检修运行、信号、失稳、质量、断裂、制动检查坠落、倒塌等
地质、高处、工作面、照明等	事故隐患、车速、倒车、坠落、打滑等

成分	死亡人数	重伤人数	轻伤人数	事故数量
1	0.299	0.723	-0.426	0.236
2	0.135	-0.455	0.889	0.214