Accident injuries model of ship repair and building enterprises based on binary Logistic regression

doi:10.16265/j.cnki.issn1003-3033.2024.12.0350

Abstract

Abstract:

In order to explore the factors influencing accident injuries in SRBE, a binary LR model was constructed based on data from 1 411 accidents from a Chinese shipbuilding group. OR were used to quantify the impact of factors such as enterprise, time, location, personnel, environment, and accident types to accident injuries. The result identifies 11 significant factors influencing accident injuries. Non-contract workers face significantly higher risks of injury compared to contract workers. Non-approved hazardous operations pose 3.246 times the risk of accident injuries compared to approved hazardous operations. Male perpetrators present a significantly higher risk of causing accident injuries than female perpetrators. The education level of the workers is predominantly at junior high school, and higher education levels are associated with a lower risk of causing accident injuries compared to those with junior high school education. Accident injuries exhibit seasonal characteristics, with accidents occurring frequently in the second quarter, while relatively fewer and less risky in the first quarter. Peak working hours and workdays significantly increase injury risks compared to off-peak hours and non-working days. Object strikes are the primary type of accidents, and mechanical injuries significantly increase the risk of accident injuries. Ships and workshops are the most likely locations for accident injuries within the shipyards. Longer years of service reduce the risk of accident injuries, while higher temperatures increase it.

Key words: Logistic regression (LR), ship repair and building enterprises (SRBE), accident injuries, influencing factor, odds ratio (OR)

CLC Number:

X928.4机械伤害事故

LI Xian, JIAO Yu, SHI Danda, WU Jianjun, KANG Yutao. Accident injuries model of ship repair and building enterprises based on binary Logistic regression[J]. China Safety Science Journal, 2024, 34(12): 120-128.

Figures/Tables 7

Table 1

Table 2

Descriptive statistics and encoding results for categorical variables

变量维度	变量名称	编码=类别(频数,占比/%)	变量维度	变量名称	编码=类别(频数,占比/%)
事故伤害	人员伤害	1=人员伤害(1 078, 76.40) 0=无人员伤害(333, 23.60)	时间	星期	1=星期三(233, 16.51) 2=星期五(217, 15.38) 3=星期六(217, 15.38) 4=星期四(205, 14.53) 5=星期二(200, 14.17) 6=星期一(182, 12.90) 7=星期日(157, 11.13)
企业	用工形式	1=非合同制(1 206, 85.47) 2=合同制(205, 14.53)		星期
	人员规模	1=[1 000, +∞)(862, 61.09) 2=[0, 1 000)(549, 38.91)		季节	1=第二季度(412, 29.20) 2=第三季度(370, 26.22) 3=第一季度(327, 23.18) 4=第四季度(302, 21.40)
	人员规模	1=[1 000, +∞)(862, 61.09) 2=[0, 1 000)(549, 38.91)		是否工作日	1=是(1 007, 71.37) 0=否(404, 28.63)
	危险作业审批项	1=否(1 130, 80.09) 0=是(281, 19.91)		高峰事故时刻	1=[8, 12) & [14,18)(1 024, 72.57) 0=其他(387, 27.43)
人员	性别	1=男(1 331, 94.33) 0=女(80, 5.67)	环境	天气	1=晴(876, 62.08) 2=雨雪雾霾(283, 20.06) 3=阴(252, 17.86)
	婚姻状态	1=已婚(1 219, 86.39) 0=未婚(192, 13.61)		风向	1=东南风(377, 26.72) 2=西北风(197, 13.96) 3=南风(192, 13.61) 4=北风(173, 12.26) 5=东北风(172, 12.19) 6=东风(152, 10.77) 7=西南风(90, 6.38) 8=西风(58, 4.11)
	受教育水平	1=初中(966, 68.46) 2=高中(287, 20.34) 3=专科(69, 4.89) 4=小学(53, 3.76) 5=本科及以上(36, 2.55)		风向
	新工人	1=否(1 148, 81.36) 0=是(263, 18.64)		风力	1=3级(466, 33.03) 2=5级(290, 20.55) 3=4级(278, 19.70) 4=2级(229, 16.23) 5=6级+(91, 6.45) 6=1级(57, 4.04)
事故	事故性质	1=责任事故(1 029, 72.93) 0=非责任事故(382, 27.07)	空间	事故地点	1=内场(468, 33.17) 2=船舶(406, 28.77) 3=码头或坞(390, 27.64) 4=车间(132, 9.36) 5=厂区外(15, 1.06)
事故	事故类型	1=物体打击(462, 32.74) 2=其他伤害(374, 26.51) 3=机械伤害(162, 11.48) 4=高处坠落(144, 10.21) 5=起重伤害(102, 7.23) 6=合并类别(167, 11.83)	空间	事故地点

Table 2

Table 3

Table 4

Table 5

Table 6

Results for binning of continuous variables

变量名称	分箱方式	编码=类别(频数,占比/%)
$A 1$	自定义	1=熟练工(1 240, 87.88) 0=新手(171, 12.12)
$A 2$	等距	1=0~10(909, 64.42) 2=10~20(313, 22.18) 3=20~30(157, 11.13) 4=30~40(33, 2.27)
$B 1$	自定义	1=非高温(1 353, 95.89) 0=高温(58, 4.11)
$B 2$	等距	1=20~30(603, 42.74) 2=10~20(379, 26.86) 3=0~10(252, 17.86) 4=30~40(125, 8.86) 5=小于0(52, 3.69)

Table 6

Table 7

Results of the comparison between binned variable combination models

编号	模型	H-L检验p值	-2LL	AUC
1	$A - B -$	0.407	1 102.038	0.852
2	$A 1 B -$	0.273	1 108.014	0.850
3	$A 2 B -$	0.273	1 108.014	0.850
4	$A - B 1$	0.252	1 116.673	0.847
5	$A 1 B 1$	0.082	1 121.395	0.845
6	$A 2 B 1$	0.082	1 121.395	0.845
7	$A - B 2$	0.079	1 107.755	0.850
8	$A 1 B 2$	0.559	1 111.497	0.848
9	$A 2 B 2$	0.559	1 111.497	0.848

Table 7

References 18

[1]	王颖丽, 夏昭林, 庄惠民. 某造船企业1994—2005年职业伤害流行病学调查[J]. 环境与职业医学, 2008, 25(1): 49-50.
	WANG Yingli, XIA Zhaolin, ZHUANG Huimin. Epidemiological study of occupational injuries in a shipyard during the period of 1994-2005[J]. Journal of Environmental & Occupational Medicine, 2008, 25(1): 49-50.
[2]	丁永明, 朱靳良, 傅华. 造船企业工伤事故调查[J]. 中国工业医学杂志, 2000, 13(5): 284-285.
	DING Yongming, ZHU Jinliang, FU Hua. A survey on occupational injuries in a shipyard[J]. Chinese Journal of Industrial Medicine, 2000, 13(5): 284-285.
[3]	YONG J B. Prevalence of occupational accidents and factors associated with deaths and disabilities in the shipbuilding industry: comparisons of novice and skilled workers[J]. WORK-A Journal of Prevention Assessment & Rehabilitation, 2021, 69(3): 997-1005.
[4]	YOU W S, JEONG B Y, LEE D K. Comparison of occupational accidents and illnesses in shipbuilding industry[J]. Journal of the Ergonomics Society of Korea, 2019, 38(5):385-392.
[5]	LEE K T. The characteristics of industrial accidents in shipbuilding industry[J]. Journal of the Ergonomics Society of Korea, 2012, 31(1): 137-142.
[6]	BARLAS B, IZCI F B. Individual and workplace factors related to fatal occupational accidents among shipyard workers in Turkey[J]. Safety Science, 2018, 101: 173-179.
[7]	IZCI F B, GOKYAY O, BARLAS B. Investigation of non-fatal occupational accidents and their causes in Turkish shipyards[J]. International Journal of Occupational Safety and Ergonomics, 2024, 30(1): 33-40.
[8]	蔡玉良, 于淳, 孙旭, 等. 我国沿海船舶事故特征及影响因素分析[J]. 中国航海, 2021, 44(2): 45-52.
	CAI Yuliang, YU Chun, SUN Xu, et al. Characteristics of ship accidents in coastal waters of China and analysis on influencing factors[J]. Navigation of China, 2021, 44(2): 45-52.
[9]	王磊, 吕璞, 林永杰. 高速公路交通事故影响因素分析及伤害估计[J]. 中国安全科学学报, 2016, 26(3): 86-90.
	WANG Lei, LYU Pu, LIN Yongjie. Traffic accidents on freeways: influencing factors analysis and injury severity evaluation[J]. China Safety Science Journal, 2016, 26(3): 86-90.
[10]	于洪霞, 季建华, 李兴. 一种基于Logistic回归的全损飞行事故分析与预测[J]. 中国安全科学学报, 2010, 20(3): 34-38.
	YU Hongxia, JI Jianhua, LI Xing. An analysis and forecast model of total loss flight accidents based on logistic regression method[J]. China Safety Science Journal, 2010, 20(3): 34-38.
[11]	GB/T 6441—1986, 企业职工伤亡事故分类标准[S].
	GB/T 6441-1986, Classification for casualty accidents of enterprise staff and workers[S].
[12]	焦宇, 李显, 刘琦, 等. 2005—2019年我国重特大安全生产事故特征分析[J]. 安全与环境学报, 2021, 21(6): 2875-2882.
	JIAO Yu, LI Xian, LIU Qi, et al. Analysis of the characteristics of major accidents and particularly serious accidents from 2005 to 2019 in China[J]. Journal of Safety and Environment, 2021, 21(6): 2875-2882.
[13]	李显, 焦宇, 陈文涛, 等. 船舶修造企业火灾事故特征挖掘与致因分析[J]. 中国安全科学学报, 2024, 34(3): 29-38. doi: 10.16265/j.cnki.issn1003-3033.2024.03.0368
	LI Xian, JIAO Yu, CHEN Wentao, et al. Feature mining and causative analysis of fire accidents in ship repair and building enterprises[J]. China Safety Science Journal, 2024, 34(3): 29-38. doi: 10.16265/j.cnki.issn1003-3033.2024.03.0368
[14]	LEE S Y, KIM E, PARK K. Subcontracting workers outside of Korean social safety net: a case study of subcontracting workers in Ulsan shipbuilding industry[J]. Social Welfare Policy, 2017, 44(2):111-144.
[15]	王卫杰, 沈轩霆, 王贵彬, 等. 电动自行车骑行者事故伤害程度影响因素分析[J]. 中国安全科学学报, 2019, 29(2): 20-25.
	WANG Weijie, SHEN Xuanting, WANG Guibin, et al. Analysis of factors affecting injury to electric bicycle rider in crash[J]. China Safety Science Journal, 2019, 29(2):20-25.
[16]	戢晓峰, 李德林, 杨文臣. 山区二级公路交通事故致因的时间演化机制[J]. 中国安全科学学报, 2019, 29(4): 31-36. doi: 10.16265/j.cnki.issn1003-3033.2019.04.006
	JI Xiaofeng, LI Delin, YANG Wenchen. Temporal evolution analysis on causes of traffic accidents occurring on secondary highways in mountain areas[J]. China Safety Science Journal, 2019, 29(4): 31-36. doi: 10.16265/j.cnki.issn1003-3033.2019.04.006
[17]	李海萍, 龙志航, 杨滋恒, 等. 基于Logistic模型的四川凉山州森林火灾风险分析[J]. 安全与环境学报, 2021, 21(2): 498-505.
	LI Haiping, LONG Zhihang, YANG Ziheng, et al. Analysis of forest fire risk in Sichuan Liangshan based on Logistic model[J]. Journal of Safety and Environment, 2021, 21(2): 498-505.
[18]	QX/T 280—2015, 极端高温监测指标[S].
	QX/T 280-2015, Monitoring indices of high temperature extremes[S].

变量维度	变量名称	平均值	标准差	最小值	中位数	最大值
人员	年龄/岁	38.04	9.16	19	38	60
	工龄/a	10.22	8.48	1	8	40
	本工种工龄/a	6.83	5.74	1	5	38
环境	最低温度/℃	13.66	9.46	-17	15	36
	最高温度/℃	20.90	9.61	-13	23	40
	正弦温度/℃	18.64	9.66	-14.5	20.5	39.8

变量名称	卡方值	自由度	显著性	VIF
年龄	—	—	0.140	1.757
工龄	—	—	0.025^*	2.089
本工种工龄	—	—	0.047^*	1.598
正弦温度	—	—	0.030^*	1.415
危险作业审批项	63.308	1	0.000^*	1.047
用工形式	7.722	1	0.005^*	1.015
人员规模	0.685	1	0.408	1.197
事故地点	31.121	4	0.000^*	1.045
事故性质	1.019	1	0.313	1.168
事故类型	59.263	5	0.000^*	1.018
性别	9.087	1	0.003^*	1.057
婚姻状态	0.944	1	0.331	1.401
新老工人	2.132	1	0.144	1.071
教育水平	16.520	4	0.002^*	1.042
季节	13.882	3	0.003^*	1.330
工作日与休息日	6.694	1	0.010^*	1.073
星期	14.870	6	0.021^*	1.069
高峰事故时刻	4.788	1	0.029^*	1.014
风级	15.231	5	0.009^*	1.030
风向	23.545	7	0.001^*	1.086
天气	3.542	2	0.170	1.042

变量维度	变量名称	变量类别	回归系数	标准误差	df	Sig.	OR	OR的 95%
企业	用工形式		0.355	0.181	1	0.047	1.427	1.000	2.036
企业	危险作业审批项		1.177	0.160	1	0.000	3.246	2.373	4.441
人员	性别		0.956	0.264	1	0.000	2.602	1.550	4.368
	工龄		-0.030	0.013	1	0.026	0.970	0.945	0.996
	受教育程度	初中^a			4	0.001
		高中	-0.478	0.170	1	0.005	0.620	0.444	0.866
		专科	-0.907	0.289	1	0.002	0.404	0.229	0.710
		大学	-0.965	0.432	1	0.025	0.381	0.163	0.888
时间	季节	第二季度^a			3	0.001
	季节	第一季度	-0.499	0.184	1	0.007	0.607	0.424	0.871
	高峰事故时刻		0.376	0.166	1	0.023	1.457	1.053	2.017
	是否工作日		0.356	0.145	1	0.015	1.462	1.073	1.898
事故	事故类型	物体打击^a			5	0.000
		其他伤害	-0.825	0.176	1	0.000	0.438	0.310	0.619
		合并类别	-0.477	0.227	1	0.035	0.621	0.398	0.968
		机械伤害	0.616	0.303	1	0.042	1.851	1.022	3.352
空间	事故地点	内场^a			4	0.000
		船舶	0.383	0.185	1	0.039	1.467	1.020	2.108
		码头或坞	-0.353	0.169	1	0.036	0.702	0.504	0.978
		车间	0.852	0.297	1	0.004	2.345	1.310	4.198
		厂区外	-1.611	0.733	1	0.028	0.200	0.047	0.840
环境	正弦温度		0.058	0.009	1	0.000	1.060	1.041	1.079
常数项			-0.293	0.450	1	0.515	0.746