Key cause chains selection of electric personal accidents based on combinatorial association analysis model

doi:10.16265/j.cnki.issn1003-3033.2022.04.015

Abstract

Abstract:

In order to improve security management ability and production safety of power enterprises, with 208 electric personal accidents in China from 2015 to 2019 as samples, their occurrence path and inherent cause law were explored. Firstly, a screening model of key cause chains based on association rule mining and grey association analysis was proposed considering the two methods' defects, namely the former was difficult to determine thresholds and the latter can not find hidden connection of data. Then, empirical analysis was conducted, strong association rules among accident causes were discovered by using association rules, and pairwise causes which could reflect accident paths were selected by increasing threshold of grey relational degree to identify key cause chains. Finally, the similarity between these key chains and accident samples was verified by Jaccard similarity calculation method. The results show that they are highly similar, which meanwhile demonstrates the effectiveness of the proposed model.

Key words: electric personal accident, combinatorial association analysis model, key cause chain, association rule, grey relational analysis, similarity coefficient

ZHAO Chufan, MI Chuanmin, ZHOU Zhipeng, FANG Jing. Key cause chains selection of electric personal accidents based on combinatorial association analysis model[J]. China Safety Science Journal, 2022, 32(4): 99-106.

Figures/Tables 7

Fig.1

Tab.1

Tab.2

Fig.2

Tab.3

Results of association rules mining

序号	前项	后项	支持度/%	置信度/%	提升度	序号	前项	后项	支持度/%	置信度/%	提升度
1	$R 1$	$R 7$	52.40	79.56	1.14	10	$R 7$	$R 17$	26.92	38.62	1.07
2	$R 14$	$R 18$	49.52	93.64	1.06	11	$R 1$	$R 6$	22.60	34.31	1.19
3	$R 4$	$R 7$	39.90	73.45	1.05	12	$R 7$	$R 15$	21.15	30.35	1.05
4	$R 1$	$R 5$	39.42	59.85	1.14	13	$R 8$	$R 17$	20.19	42.42	1.18
5	$R 7$	$R 14$	37.98	54.48	1.03	14	$R 5$	$R 17$	19.71	37.62	1.04
6	$R 5$	$R 14$	30.77	58.72	1.11	15	$R 4$	$R 6$	18.75	34.51	1.20
7	$R 4$	$R 5$	30.77	56.64	1.08	16	$R 6$	$R 14$	16.35	56.67	1.07
8	$R 4$	$R 8$	29.81	54.87	1.15	17	$R 3$	$R 7$	15.87	75.00	1.08
9	$R 15$	$R 18$	27.40	95.00	1.08	18	$R 8$	$R 15$	15.87	33.33	1.16

Tab.3

Fig.3

Tab.4

Selection results of key cause chains under three sets of association rule thresholds

$α = 8 %$ $β = 25 %$ $δ = 1$
灰色关联度阈值	断裂致因链	Jaccard取值
灰色关联度阈值	断裂致因链	1	0.75	0.5	0.25	0
$γ = 0.80$	$R 2$ → $R 7$ → $R 14$ → $R 18$	6	83	85	27	7
	$R 2$ → $R 7$ → $R 15$ → $R 18$	3	58	94	46	7
	$R 2$ → $R 7$ → $R 17$ → $R 19$	0	21	77	79	31
$γ = 0.85$	$R 3$ → $R 8$ → $R 15$ → $R 18$	7	45	84	55	17
$γ = 0.85$	$R 4$ → $R 8$ → $R 15$ → $R 18$	18	68	68	43	11
$γ = 0.88$	$R 1$ → $R 6$ → $R 14$ → $R 18$	27	71	69	31	10
	$R 4$ → $R 6$ → $R 14$ → $R 18$	24	58	78	40	8
	$R 3$ → $R 8$ → $R 17$ → $R 19$	4	18	52	88	46
	$R 4$ → $R 8$ → $R 17$ → $R 19$	7	31	67	76	27
$γ = 0.89$	$R 1$ → $R 6$ → $R 15$ → $R 18$	16	59	77	45	11
	$R 1$ → $R 6$ → $R 17$ → $R 19$	4	33	61	79	31
	$R 4$ → $R 6$ → $R 17$ → $R 19$	5	21	65	79	38
$γ = 0.90$	$R 4$ → $R 6$ → $R 15$ → $R 18$	15	46	82	54	11
	$R 1$ → $R 5$ → $R 17$ → $R 19$	8	38	80	59	23
	$R 1$ → $R 7$ → $R 17$ → $R 19$	10	51	80	48	19
	$R 3$ → $R 5$ → $R 17$ → $R 19$	5	15	60	87	41
	$R 3$ → $R 7$ → $R 17$ → $R 19$	4	26	63	88	27
	$R 4$ → $R 5$ → $R 17$ → $R 19$	6	31	77	70	24
$α = 8 %$ $β = 25 %$ $δ = 1$
灰色关联度阈值	断裂致因链	Jaccard取值
灰色关联度阈值	断裂致因链	1	0.75	0.5	0.25	0
	$R 4$ → $R 7$ → $R 17$ → $R 19$	9	34	93	53	19
	$R 1$ → $R 7$ → $R 15$ → $R 18$	31	92	49	27	9
	$R 3$ → $R 7$ → $R 15$ → $R 18$	11	55	91	41	10
	$R 4$ → $R 7$ → $R 15$ → $R 18$	24	80	69	27	8
$γ = 0.92$	$R 3$ → $R 5$ → $R 14$ → $R 18$	14	66	74	44	10
$γ = 0.93$	$R 3$ → $R 7$ → $R 14$ → $R 18$	16	81	72	31	8
$γ = 0.94$	$R 1$ → $R 7$ → $R 14$ → $R 18$	55	86	39	19	9
$γ = 0.94$	$R 4$ → $R 7$ → $R 14$ → $R 18$	44	80	57	21	6
$γ = 0.95$	$R 4$ → $R 5$ → $R 14$ → $R 18$	38	65	70	28	7
$γ = 0.95$	$R 1$ → $R 5$ → $R 14$ → $R 18$	45	75	56	22	10
$α = 15 %$ $β = 25 %$ $δ = 1$
灰色关联度阈值	断裂致因链	Jaccard取值
灰色关联度阈值	断裂致因链	1	0.75	0.5	0.25	0
$γ = 0.86$	$R 4$ → $R 8$ → $R 15$ → $R 18$	18	68	68	43	11
	$R 1$ → $R 6$ → $R 14$ → $R 18$	27	71	69	31	10
	$R 4$ → $R 6$ → $R 14$ → $R 18$	24	58	78	40	8
$γ = 0.90$	$R 1$ → $R 7$ → $R 15$ → $R 18$	31	92	49	27	9
	$R 3$ → $R 7$ → $R 15$ → $R 18$	11	55	91	41	10
	$R 4$ → $R 7$ → $R 15$ → $R 18$	24	80	69	27	8
$γ = 0.93$	$R 3$ → $R 7$ → $R 14$ → $R 18$	16	81	72	31	8
$γ = 0.94$	$R 1$ → $R 7$ → $R 14$ → $R 18$	55	86	39	19	9
$γ = 0.94$	$R 4$ → $R 7$ → $R 14$ → $R 18$	44	80	57	21	6
$γ = 0.95$	$R 4$ → $R 5$ → $R 14$ → $R 18$	38	65	70	28	7
$γ = 0.95$	$R 1$ → $R 5$ → $R 14$ → $R 18$	45	75	56	22	10
$α = 15 %$ $β = 55 %$ $δ = 1$
灰色关联度阈值	断裂致因链	Jaccard取值
灰色关联度阈值	断裂致因链	1	0.75	0.5	0.25	0
$γ = 0.95$	$R 4$ → $R 5$ → $R 14$ → $R 18$	38	65	70	28	7
$γ = 0.95$	$R 1$ → $R 5$ → $R 14$ → $R 18$	45	75	56	22	10

Tab.4

References 21

[1]	魏秀宁, 柳亦钢, 黄玉龙, 等. 供电作业人身事故危害多元线性回归预测[J]. 中国安全生产科学技术, 2015, 11(7):178-184.
	WEI Xiuning, LIU Yigang, HUANG Yulong, et al. Prediction on human casualty hazard in power-supplying operation based on multiple linear regression[J]. Journal of Safety Science and Technology, 2015, 11(7):178-184.
[2]	吴声声, 宋守信. 人本管理、工作压力与安全绩效的关系:基于电力企业的实证研究[J]. 中国安全科学学报, 2012, 22(10):133-138.
	WU Shengsheng, SONG Shouxin. Relationship between human oriedted management, work stress, and safety performance:an empirical research based on electricity enterprises[J]. China Safety Science Journal, 2012, 22(10):133-138.
[3]	李彦斌, 金宁, 洪梦琳. 基于HFACS和灰色关联法电网企业人为事故隐性危险源的辨识与评价[J]. 中国安全生产科学技术, 2013, 9(2):157-161.
	LI Yanbin, JIN Ning, HONG Menglin. Human accident hidden hazard identification and evaluation of power grid enterprise based on HFACS and grey correlation analysis method[J]. Journal of Safety Science and Technology, 2013, 9(2):157-161.
[4]	LAUREL C Austin, DANIEL C Kovacs, SARAH Thorne, et al. Using grounded theory and mental modeling to understand influences on electricians' safety decisions: toward an integrated theory of why electricians work energized[J]. Safety Science, 2020, 130: DOI: 10.1016/j.ssci.2020.104826. doi: 10.1016/j.ssci.2020.104826
[5]	王颖, 施欣. 全球海事事故的时空与类别特征研究[J]. 安全与环境学报, 2018, 18(3):1224-1230.
	WANG Ying, SHI Xin. On the temporal-spatial distribution and the type characteristics of the global maritime accident[J]. Journal of Safety and Environment, 2018, 18(3): 1224-1230.
[6]	CHEN Dejun, PEI Yilou, XIA Qian. Research on human factors cause chain of ship accidents based on multidimensional association rules[J]. Ocean Engineering, 2020, 218(11): DOI: 10.1016/j.oceaneng.2020.107717. doi: 10.1016/j.oceaneng.2020.107717
[7]	薛锋, 何传磊, 黄倩. 成都地铁网络的关键节点识别方法及性能分析[J]. 中国安全科学学报, 2019, 29(1):93-99. doi: 10.16265/j.cnki.issn1003-3033.2019.01.016
	XUE Feng, HE Chuanlei, HUANG Qian. Identification of key nodes in Chengdu metro network and analysis of network performance[J]. China Safety Science Journal, 2019, 29(1):93-99. doi: 10.16265/j.cnki.issn1003-3033.2019.01.016
[8]	AI Xinbo, HU Yanzhu, CHEN Guohong. A systematic approach to identify the hierarchical structure of accident factors with grey relations[J]. Safety Science, 2014, 63(3):83-93. doi: 10.1016/j.ssci.2013.11.001
[9]	刘思峰, 党耀国, 方志耕, 等. 灰色系统理论及其应用(第8版)[M]. 北京: 科学出版社, 2021. 8:55-57.
[10]	江山, 宋柯, 谢维成, 等. 基于灰色关联与Apriori算法的道路交通事故数据分析[J]. 公路工程, 2019, 44(4):67-73.
	JIANG Shan, SONG Ke, XIE Weicheng, et al. Analysis of road traffic accident data based on grey relational analysis and Apriori algorithm[J]. High Engineering, 2019, 44(4):67-73.
[11]	WIEGMANN D A, SHAPPELL S A. Human error analysis of commercial aviation accidents: application of the human factors analysis and classification system(HFACS)[J]. Aviation, Space, and Environmental Medicine, 2001, 72(11):1006-1016.
[12]	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):70-75. doi: 10.16265/j.cnki.issn1003-3033.2019.07.012
	XU Surui. Analysis of human factors of elevator accidents based on HFACS[J]. China Safety Science Journal, 2019, 29(7):70-75. doi: 10.16265/j.cnki.issn1003-3033.2019.07.012
[13]	叶贵, 陈梦莉, 汪红霞. 建筑安全事故人为因素分类研究[J]. 中国安全生产科学技术, 2016, 12(4):131-137.
	YE Gui, CHEN Mengli, WANG Hongxia. Study on classification of human factors in construction safety accidents[J]. Journal of Safety Science and Technology, 2016, 12(4): 131-137.
[14]	张建伟. 基于HFACS的电力事故人因失误研究[D]. 苏州: 苏州大学, 2016.
	ZHANG Jianwei. Research on human error of power accidents based on HFACS[D]. Suzhou: Soochow University, 2016.
[15]	刘雅. 基于HFACS的电力生产人因事故研究及信息管理系统开发[D]. 衡阳: 南华大学, 2017.
	LIU Ya. Research on human accident in electricity production based on HFACS model and the development of information management system[D]. Hengyang: University of South China, 2017.
[16]	AGRAWAL R, IMIELINSKI T, SWAMI A. Mining association rules between sets of items in large databases[C]. Acm Sigmod International Conference on Management of Data, 1993, 22(2):207-216.
[17]	国家能源局电力安全监管司. 全国电力事故和电力安全事件汇编(2015年)[M]. 北京: 中国电力传媒集团, 2016:4-78.
[18]	国家能源局电力安全监管司. 全国电力事故和电力安全事件汇编(2016年)[M]. 北京: 中国电力传媒集团, 2017:4-97.
[19]	国家能源局电力安全监管司. 全国电力事故和电力安全事件汇编(2017年)[M]. 北京: 中国电力传媒集团, 2018:4-96.
[20]	国家能源局电力安全监管司. 全国电力事故和电力安全事件汇编(2018年)[M]. 北京: 中国电力传媒集团, 2019:4-88.
[21]	国家能源局电力安全监管司. 全国电力事故和电力安全事件汇编(2019年)[M]. 北京: 中国电力传媒集团, 2020:4-81.

事故	事故致因
事故	R₁	R₂	…	R₁₉
X₁	a₁₁	a₁₂	…	a_1×19
X₂	a₂₁	a₂₂	…	a_2×19
︙	︙	︙	︙	︙
X_n	a_n₁	a_n₂	…	a_n_×19

事故致因	年份
事故致因	Y₁	Y₂	…	Y_m
R₁	b₁₁	b₁₂	…	b₁_m
R₂	b₂₁	b₂₂	…	b₂_m
︙	︙	︙	︙	︙
R₁₉	b_19×1	b_19×2	…	b_19×_m