Mining association rules of near-misses of hydropower projects construction

doi:10.16265/j.cnki.issn1003-3033.2021.08.011

Abstract

Abstract: To efficiently mine the large amount of text data accumulated in the near-misses investigation of hydropower projects, phrase extraction technology based on mutual information and left-right information entropy was adopted to extract structured key phrases from unstructured near-misses data. Sankey diagram was used to describe information flow among characteristics, locations and types of potential hazards. Combined with phrase extraction technology, Apriori association algorithm was optimized, association rules of hidden danger locations and types were mined, association rules network diagram was drawn, and rules were analyzed with Sankey diagram. 13 820 hidden danger data cases of a hydropower station was verified. The results show that near-misses data switch box guardrails is key of hidden perils, such as easy for shelving electric welding machine switch box cable clutter object at gate, such as electric shock stick slope, falling of correlation degree is higher, study provides hidden perils in hydropower engineering and management.

Key words: hydroelectric engineering construction, near-misses, association rules, text mining, Sankey diagram, Apriori algorithm

CLC Number:

X948

CHEN Shu, XI Junbo, WANG Jianping, CHEN Yun. Mining association rules of near-misses of hydropower projects construction[J]. China Safety Science Journal, 2021, 31(8): 75-82.

References

[1] 陈述, 袁越, 田亚, 等.大坝浇筑立体交叉作业空间冲突强度仿真研究[J].中国安全科学学报,2019,29(6):63-69.
CHEN Shu, YUAN Yue, TIAN Ya, et al. Simulation of spatial conflict during cross operation in dam construction [J]. China Safety Science Journal, 2019,29(6):63-69.
[2] 樊启祥, 林鹏, 魏鹏程, 等. 水电工程安全事故发生机制与管理对策[J]. 中国安全科学学报, 2019,29(1):144-149.
FAN Qixiang, LIN Peng, WEI Pengcheng, et al. Occurrence mechanism and management countermeasures of safety accidents in hydropower projects [J]. China Safety Science Journal, 2019,29(1):144-149.
[3] 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):1 046-1 051.
CHEN Zhiqun, ZHANG Guoxuan. Research on text mining and Chinese text mining model [J]. Information Science, 2007, 25(7):1 046-1 051.
[4] 樊启祥, 杨宗立, 汪志林, 等. 大型水电工程建设全过程数字化动态管控[J]. 水力发电学报, 2019,38(1):1-11.
FAN Qixiang, YANG Zongli, WANG Zhilin, et al. Digital dynamic control and control throughout the construction of large hydropower projects[J]. Journal of Hydroelectric Engineering,2019,38(1):1-11.
[5] 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.
LI Hongxia, TIAN Chenning. Based on the Cite Space Ⅴ visualization analysis of coal mine safety management[J]. China Safety Science Journal, 2018,28(9):148-153.
[6] 邵冠宇, 王慧芳, 吴向宏, 等. 基于依存句法分析的电力设备缺陷文本信息精确辨识方法[J]. 电力系统自动化, 2020,44(12):178-189.
SHAO Guanyu, WANG Huifang, WU Xianghong, et al. Precise information identification method of power equipment defect text based on dependency parsing [J]. Automation of Electric Power Systems,2020,44(12):178-189.
[7] 张长鲁. 煤矿事故隐患大数据处理与知识发现分析方法研究[J]. 中国安全生产科学技术, 2016,12(9):176-181.
ZHANG Changlu. Study on big data processing and knowledge discovery analysis method for safety hazard in coal mine[J]. Journal of Safety Science and Technology,2016,12(9):176-181.
[8] 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.
[9] 王新浩, 秦绪华, 罗云. 基于垂直数据格式的企业隐患预警方法研究[J]. 中国安全科学学报, 2017,27(2):157-162.
WANG Xinhao, QIN Xuhua, LUO Yun. Research on vertical data format-based method for enterprise hidden trouble early warning [J]. China Safety Science Journal,2017,27(2):157-162.
[10] 张明媛, 朱密, 赵雪峰. 任务驱动下的建筑施工现场危险源关联规则挖掘[J]. 安全与环境学报, 2019,19(1):14-20.
ZHANG Mingyuan, ZHU Mi, ZHAO Xuefeng. Task-driven mining of hazard association rules in construction site[J]. Journal of Safety and Environment, 2019,19(1):14-20.
[11] 李明超, 田丹, 沈扬, 等. 融入Attention机制改进Word2vec技术的水利水电工程专业词智能提取与分析方法[J]. 水利学报, 2020,51(7):816-826.
LI Mingchao, TIAN Dan, SHEN Yang, et al. An intelligent word extraction and analysis method for water conservancy and hydropower engineering by integrating the Attention mechanism and improving Word2vec technology [J].Journal of Hydraulic Engineering,2020,51(7):816-826.
[12] 刘晨晖, 张德生, 胡钢. 基于Kert的中文主题关键短语提取算法[J]. 计算机应用, 2019,39(增1):245-249.
LIU Chenhui, ZHANG Desheng, HU Gang. Chinese topic key phrase extraction algorithm based on Kert[J]. Journal of Computer Applications,2019,39(S1):245-249.
[13] 胡瑾秋, 张曦月,吴志强.结合TF-IDF的企业生产隐患关联预警及可视化研究[J].中国安全科学学报,2019,29(7):170-176.
HU Jinqiu, ZHANG Xiyue, WU Zhiqiang. Research on associated early-warning and visualization of hidden danger in enterprise production based on TF-IDF [J]. China Safety Science Journal, 2019,29(7):170-176.
[14] 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.
[15] 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 Techniqu,2020,43(6):65-69.
[16] 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): 1 226-1 238.
[17] SUN Yanlindsay, WEI Yu, ZHU Han, et al. Information theoretic framework of trust modeling and evaluation for ad hoc networks[J]. IEEE Journal on Selected Areas in Communications, 2006,24(2):305-317.
[18] PANINSKI L. Estimation of entropy and mutual information[J]. Neural Computation, 2003,15(6): 1 191-1 253.
[19] 周炜翔, 张仰森, 张良. 面向微博热点事件的话题检测及表述方法研究[J]. 计算机应用研究, 2019,36(12):3 565-3 569.
ZHOU Weixiang, ZHANG Yangsen, ZHANG Liang. Research on topic detection and expression method for Weibo hot events[J]. Application Research of Computers,2019,36(12):3 565-3 569.
[20] AGRAWAL R, SRIKANT R. Fast algorithm for mining association rules[C]. Proc the 20^th International Conference on Very Large Data Bases,1994:21-30.
[21] 圣文顺, 张林慧. Apriori算法在数据挖掘中的应用[J]. 电子世界, 2018, 67(19):122-123,126.
[22] KHALILI A, SAMI A. SysDetect: a systematic approach to critical state determination for industrial intrusion detection Systems using Apriori algorithm[J]. Journal of Process Control, 2015,32: 154-160.
[23] CHAKRABORTY K, BHATIA S, BHATTACHARYYA S, et al. Sentiment analysis of COVID-19 tweets by deep learning classifiers—a study to show how popularity is affecting accuracy in social media[J]. Applied Soft Computing, 2020,97: DOI:10.1016/j.asoc.2020.106754.
[24] DING Yuxin, WU Rui, ZHANG Xiao. Ontology-based knowledge representation for malware individuals and families[J]. Computers & Security, 2019,87:DOI:10.1016/j.cose.2019.101574.
[25] GB6441—1986,企业职工伤亡事故分类[S].
GB6441-1986, Classification standard for casualty accidents of enterprise workers[S].
[26] MATSUO Y, ISHIZUKA M. Keyword extraction from a single document using word co-occurrence statistical information[J].International Journal on Artificial Intelligence Tools, 2004, 13(1):157-169.