A prediction and early warning model of miners' unsafe behavior based on random forest

doi:10.16265/j.cnki.issn1003-3033.2022.12.2752

Abstract

Abstract:

In order to reduce the unsafe behaviors of coal miners and make scientific judgement of current status and future trend, this study constructed a database of accidents of coal mines and an attribute table of unsafe behaviors of miners with accident statistics and literatures. On this basis, association rules between unsafe factors and behaviors were explored by adopting Apriori algorithm. An original model was established to fit training, which was formed by taking strong correlation rule as input indicators to the random forest prediction model and the frequency of unsafe behaviors as output indicators. Early warning threshold based on correlation analysis and expert recommendations was also set to refine the early warning model of miners' unsafe behaviors. The results show that safety culture, on-site monitoring, ineffective correction, technical environment, and personnel status constitute strong correlation rules with miners' unsafe behaviors. For the prediction of miners' unsafe behavior, the predicted value has less deviations from the actual, and the early warning model has relatively high accuracy. Among them, technical environment, work environment, organizational management, and identification of hazards play the key role in predicting outcomes.

Key words: random forest, miner, unsafe behavior, prediction and early warning model, association rule mining

LI Hongxia, XU Haoran, TIAN Shuicheng. A prediction and early warning model of miners' unsafe behavior based on random forest[J]. China Safety Science Journal, 2022, 32(12): 10-18.

Figures/Tables 11

Fig.1

Tab.1

Tab.2

Tab.3

Fig.2

Fig.3

Tab.4

Fig.4

Tab.5

Fig.5

Fig.6

References 18

[1]	ALIABADI, MOSTAFA M, AGHAEI H, et al. Effects of human and organizational deficiencies on workers' safety behavior at a mining site in Iran[J]. Epidemiology and Health, 2018, 40(5):1-9.
[2]	张兴凯. 我国“十二五”期间生产安全死亡事故直接经济损失估算[J]. 中国安全生产科学技术, 2016, 12(6):5-8.
	ZHANG Xingkai. Estimation of the direct economic loss of production safety fatal accidents during the "Twelfth Five-Year Plan" period in China[J]. Journal of Safety Science and Technology, 2016, 12(6):5-8.
[3]	CHEN Hong, QI Hui, FENG Qun. Characteristics of direct causes and human factors in major gas explosion accidents in Chinese coal mines: case study spanning the years 1980—2010[J]. Journal of Loss Prevention in the Process Industries, 2013, 26(1):38-44. doi: 10.1016/j.jlp.2012.09.001
[4]	石娟, 常丁懿, 郑鹏. 基于BP神经网络的建筑工人不安全行为预警模型[J]. 中国安全科学学报, 2022, 32(1):27-33. doi: 10.16265/j.cnki.issn1003-3033.2022.01.004
	SHI Juan, CHANG Dingyi, ZHENG Peng. An early warning model of unsafe behaviors of construction workers based on BP neural network[J]. China Safety Science Journal, 2022, 32(1):27-33. doi: 10.16265/j.cnki.issn1003-3033.2022.01.004
[5]	XU Ruihua, LUO Fan. Risk prediction and early warning for air traffic controllers' unsafe acts using association rule mining and random forest[J]. Safety Science, 2021, 135(1):1-10.
[6]	PATELA D A, JHA K N. Evaluation of construction projects based on the safe work behavior of co-employees through a neural network model[J]. Safety Science, 2016, 89(1):240-248. doi: 10.1016/j.ssci.2016.06.020
[7]	王道元, 王俊, 孟志斌, 等. 煤矿安全风险智能分级管控与信息预警系统[J]. 煤炭科学技术, 2021, 49(10):136-144.
	WANG Daoyuan, WANG Jun, MENG Zhibin, et al. Intelligent hierarchical management&control and information pre-warning system of coal mine safety risk[J]. Coal Science and Technology, 2021, 49(10):136-144.
[8]	刘聪美. 基于图像处理的矿用电机车行人监测预警系统设计[J]. 煤炭工程, 2021, 48(5):17-19.
	LIU Congmei. Pedestrian monitoring and early warning system for mine electric locomotive based on image processing[J]. Coal Engineering, 2021, 48(5):17-19.
[9]	温廷新, 王贵通, 孔祥博, 等. 基于迁移学习与残差网络的矿工不安全行为识[J]. 中国安全科学学报, 2020, 30(3):41-46. doi: 10.16265/j.cnki.issn1003-3033.2020.03.007
	WEN Tingxin, WANG Guitong, KONG Xiangbo, et al. Identification of miners' unsafe behaviors based on transfer learning and residual network[J]. China Safety Science Journal, 2020, 30(3):41-46. doi: 10.16265/j.cnki.issn1003-3033.2020.03.007
[10]	赵江平, 王垚. 基于图像识别技术的不安全行为识别[J]. 安全与环境工程, 2020, 27(1):158-165.
	ZHAO Jiangping, WANG Yao. Unsafe behavior recognition based on image recognition technology[J]. Safety and Environmental Engineering, 2020, 27(1):158-165.
[11]	AGRAWAL R. Mining association rules between sets of items in large databases[C]. Proceedings Acm Sigmod Conference on Management of Data, 1993:207-216.
[12]	BREIMAN L. Random forest[J]. Machine Learning, 2001, 45(1):5-32. doi: 10.1023/A:1010933404324
[13]	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):37-42.
	ZHANG Jianrong, ZHANG Wei, XUE Nannan, et al. Forecast and cause analysis of tower crane safety accidents based on random forest algorithm[J]. Safety and Environmental Engineering, 2021, 28(5):37-42.
[14]	YOU Mengjie, LI Shuang, LI Dingwei, et al. Applications of artificial intelligence for coal mine gas risk assessment[J]. Safety Science, 2021, 143(1):1-15.
[15]	王军武, 王梦雨, 刘登辉, 等. 基于HFACS-BN的地铁车站施工高处坠落可能性评价[J]. 中国安全科学学报, 2021, 31(6):91-98.
	WANG Junwu, WANG Mengyu, LIU Denghui, et al. Evaluation of the possibility of falling from a height during subway station construction based on HFACS-BN[J]. China Safety Science Journal, 2021, 31(6):91-98.
[16]	许素睿. 基于HFACS的电梯事故人因分析[J]. 中国安全科学学报, 2019, 29(7):71-75.
	XU Surui. Human cause analysis of elevator accidents based on HFACS[J]. China Safety Science Journal, 2019, 29(7):71-75.
[17]	李红霞, 樊恒子, 陈磊, 等. 智慧矿山工人不安全行为影响因素模糊评价[J]. 矿业研究与开发, 2021, 41(1):40-43.
	LI Hongxia, FAN Hengzi, CHEN Lei, et al. Fuzzy evaluation of influencing factors of unsafe behaviors of smart mine workers[J]. Mining Research and Development, 2021, 41(1):40-43.
[18]	白彦龙, 李海立, 陈昱, 等. 基于HFACS的煤矿一般事故人因分析[J]. 煤矿安全, 2021, 52(5):250-255.
	BAI Yanlong, LI Haili, CHEN Yu, et al. Human cause analysis of coal mine general accidents based on HFACS[J]. Safety in Coal Mines, 2021, 52(5):250-255.

类别		属性	内容	类别		属性	内容
A_i	组织影响	A₁组织生产	无视监管、违法组织生产活动	C_i	环境因素	C₁设备隐患	安全设施、作业设备存在隐患
		A₂安全文化	安全教育薄弱、组织安全氛围差			C₂工作环境	工作面环境恶劣、地质隐患较多
		A₃组织管理	违规外包、以包带管、擅自复产			C₃技术环境	技术管理缺陷、未编制技术规程
		A₄资源管理	安全投入不足、人力物力不协调			C₄制度环境	安全生产制度未编制、或存在缺陷
B_i	不安全监督	B₁监督不足	企业未按要求执行监督、擅自替岗	D_i	人员状态	D₁隐患识别	现场人员未识别出隐患
		B₂现场监护	现场监管缺失			D₂安全意识	人员安全意识淡薄、安全知识不足
		B₃无效纠正	故意忽视、未及时阻止违规行为			D₃个人能力	人员专业技术、安全技能不足
		B₄作业计划	人员配备、工作计划不合理			D₄班组准备	班组协调沟通能力、互保能力不足
不安全行为		E₁违规行为	无证上岗、违规侵入、未穿防护装置	不安全行为		E₂错误操作	未支护作业、采用淘汰工艺、判断失误

数据类型	样本数据	内容	编码
无序分类变量	各不安全因素的发生情况	未发生	0
	各不安全因素的发生情况	发生	1
	违规行为发生频次E₁	未发生	0
		发生1次	1
		发生2次	2
		︙	︙
		发生m次	m
	错误操作发生频次E₂	未发生	0
		发生1次	1
		发生2次	2
		︙	︙
		发生m次	m
	不安全行为发生频次E'	发生1次	1
		发生2次	2
		︙	︙
		发生m次	m
	不安全行为发生情况E	E'<1	0
	不安全行为发生情况E	E'≥1	1

后项	前项	支持度	置信度	提升度
E	D₃	13.07	100	1.205
E	D₁, B₂	23.708	100	1.205
E	B₃, D₄	10.942	100	1.205
E	B₂, C₃, D₂	15.502	100	1.205
E	B₂, C₃, A₂	17.629	100	1.205
E	B₂, A₂	42.249	98.561	1.188
E	B₂, D₂	40.122	98.485	1.187
E	B_2, C₄, A₂	19.757	98.462	1.187
E	B₃	19.149	98.413	1.186
E	B₂, D₂, A₂	38.298	98.413	1.186
E	B₂, B₄, A₂	18.845	98.387	1.186
E	B₂, C₄, D₂	17.629	98.276	1.184
E	B₃, A₂	17.325	98.246	1.184
E	B₂, B₄, D₂	17.021	98.214	1.184
E	B₂, C_4, D₂, A₂	17.021	98.214	1.184
E	B₂, B₄, D₂, A₂	16.109	98.113	1.182
︙	︙	︙	︙	︙
E	A₁, B₁, C₃, B₄, C₄	10.03	81.818	0.986

参数	名称	数值
n_estimators	分类器个数	100
random_state	随机种子	0
min_samples_split	最小分裂样本数	10
min_samples_leaf	最小叶子结点样本数	5
max_features	特征子集中的特征个数	None
min_impurity_decrease	最小分裂不纯度	0.01

变量名称	检验参数	不安全行为频次	事故等级
不安全行为频次	皮尔逊相关性	1	0.460^**
	显著性(双尾)	—	0.000
	个案数	329	329
事故等级	皮尔逊相关性	0.460^**	1
	显著性(双尾)	0.000	—
	个案数	329	329