Research on early warning for prefabricated building workers' unsafe behaviors of working at height based on RF-SFLA-SVM

doi:10.16265/j.cnki.issn1003-3033.2024.03.1288

Abstract

Abstract:

In order to effectively provide early warning of the occurrence trend or state of prefabricated building workers' unsafe behaviors (PBWUBs) of working at height, and to enhance the control of PBWUBs, RF-SFLA-SVM model was proposed to conduct an early warning study on workers' unsafe behaviors. Firstly, the SHEL (Software-Hardware-Environment-Liveware) model was used to analyze the factors influencing the unsafe behaviors of prefabricated building workers in danger of working at height. RF was used to determine the key warning indicators. Then SFLA was used to find the best parameters for SVM. Finally, the RF-SFLA-SVM model was used to predict and warn about the unsafe behavioral state of the prefabricated building workers working at height, and its performance was compared with other warning models. The results show that the RF-SFLA-SVM-based warning accuracy of PBWUBs of working at height was the highest, 91.67%, which was a maximum improvement of 14% compared with the warning performance of other models. The research results can give a reference for the control and prevention of PBWUBs working at height.

Key words: random forest (RF), shuffled frog leaping algorithm (SFLA), support vector machine (SVM), prefabricated buildings, working at height, unsafe behaviors

CLC Number:

X948

WANG Junwu, HE Juanjuan, SONG Yinghui, LIU Yipeng, CHEN Zhao, GUO Jingyi. Research on early warning for prefabricated building workers' unsafe behaviors of working at height based on RF-SFLA-SVM[J]. China Safety Science Journal, 2024, 34(3): 1-8.

Figures/Tables 11

Tab.1

Fig.1

Tab.2

Tab.3

Fig.2

Tab.4

Fig.3

Fig.4

Fig.5

Fig.6

Tab.5

References 18

[1]	住房和城乡建设部和国家发展改革委关于印发城乡建设领域碳达峰实施方案的通知[EB/OL].(2022-06-30). https://www.gov.cn/zhengce/zhengceku/2022-07/13/content_5700752.htm.
[2]	FANG Qi, LI Heng, LUO Xiaochun, et al. Computer vision aided inspection on falling prevention measures for steeplejacks in an aerial environment[J]. Automation in Construction, 2018, 93:148-164. doi: 10.1016/j.autcon.2018.05.022
[3]	MARTIN J E, RIVAS T, MATIAS J M, et al. A Bayesian network analysis of workplace accidents caused by falls from a height[J]. Safety Science, 2009, 47(2): 206-214. doi: 10.1016/j.ssci.2008.03.004
[4]	王军武, 潘子瑶, 王靖, 等. 基于STPA和模糊BN的装配式建筑吊装施工安全风险分析[J]. 中国安全生产科学技术, 2022, 18(4):12-19.
	WANG Junwu, PAN Ziyao, WANG Jing, et al. Safety risk analysis on hoisting construction of prefabricated building based on STPA and fuzzy BN[J]. Journal of Safety Science and Technology, 2022, 18(4):12-19.
[5]	周建亮, 胡飞翔, 邢艳冬, 等. 工作压力、职业倦怠对建筑工人不安全行为的影响[J]. 中国安全科学学报, 2022, 32(11):14-22. doi: 10.16265/j.cnki.issn1003-3033.2022.11.2539
	ZHOU Jianliang, HU Feixiang, XING Yandong, et al. Influence of job stress and burnout on unsafe behaviors of construction workers[J]. China Safety Science Journal, 2022, 32(11):14-22. doi: 10.16265/j.cnki.issn1003-3033.2022.11.2539
[6]	林新奇, 栾宇翔, 赵国龙. 领导风格与员工安全行为关系的元分析[J]. 中国安全生产科学技术, 2021, 17(10):5-10.
	LIN Xinqi, LUAN Yuxiang, ZHAO Guolong. Meta-analysis on relationship between leadership style and employee safety behavior[J]. Journal of Safety Science and Technology, 2021, 17(10):5-10.
[7]	LIU Rulin, CHENG Weimin, YU Yanbin, et al. An impacting factors analysis of miners' unsafe acts based on HFACS-CM and SEM[J]. Process Safety and Environmental Protection, 2018, 122:221-231. doi: 10.1016/j.psep.2018.12.007
[8]	SHAKERIAN M, JAHANGIRI M, ALIMOHAMMADLOU M, et al. Individual cognitive factors affecting unsafe acts among Iranian industrial workers: An integrative meta-synthesis interpretive structural modeling (ISM) approach[J]. Safety Science, 2019, 120:89-98. doi: 10.1016/j.ssci.2019.06.041
[9]	谢逸, 张竞文, 李韬, 等. 基于视频监控的地铁施工不安全行为检测预警[J]. 华中科技大学学报:自然科学版, 2019, 47(10):46-51.
	XIE Yi, ZHANG Jingwen, LI Tao, et al. Research on detection and early warning of unsafe behavior in metro construction based on video monitoring[J]. Journal of Huazhong University of Science and Technology:Natural Science Edition, 2019, 47(10):46-51.
[10]	GAO Yifan, GONZALEZ V A, YIU T W, et al. Predicting construction workers' intentions to engage in unsafe behaviours using machine learning algorithms and taxonomy of personality[J]. Buildings, 2022, 12(6):841-869. doi: 10.3390/buildings12060841
[11]	LI Feng, WANG Wenhe, XU Jiang, et al. Comparative study on vulnerability assessment for urban buried gas pipeline network based on SVM and ANN methods[J]. Process Safety and Environmental Protection, 2019, 122:23-32. doi: 10.1016/j.psep.2018.11.014
[12]	叶贵, 李学征, 杨丽萍, 等. 建筑工人不安全行为量化分类研究[J]. 安全与环境学报, 2021, 21(6):2617-2627.
	YE Gui, LI Xuezheng, YANG Liping, et al. Study on the quantitative classification of construction workers' unsafe behaviors[J]. Journal of Safety and Environment, 2021, 21(6): 2617-2627.
[13]	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
[14]	EUSUFF M M, LANSEY K E. Optimization of water distribution network design using the shuffled frog leaping algorithm[J]. Journal of Water Resources Planning and Management, 2003, 129(3):210-225. doi: 10.1061/(ASCE)0733-9496(2003)129:3(210)
[15]	田水承, 徐磊, 陈婷. 基于Reason模型的煤矿事故致因分析[J]. 矿业安全与环保, 2009, 36(3):81-83.
[16]	赵金先, 范轲, 孙境韩, 等. 基于SHEL和三角模糊数理论的地铁钻爆法施工安全评价方法研究[J]. 隧道建设, 2017, 37(3):291-297.
	ZHAO Jinxian, FAN Ke, SUN Jinghan, et al. Study of safety evaluation of metro construction by drilling and blasting method based on SHEL and triangular fuzzy number[J]. Tunnel Construction, 2017, 37(3):291-297.
[17]	姜立春, 任晓会. 基于W-R-SHEL的露天矿山运输系统风险因素研究[J]. 中国安全科学学报, 2011, 21(6):104-110.
	JIANG Lichun, REN Xiaohui. Research on transport system risk factors of open-pit mine based on W-R-SHEL[J]. China Safety Science Journal, 2011, 21(6):104-110.
[18]	TIXIER A J P, HALLOWELL M R, RAJAGOPALAN B, et al. Application of machine learning to construction injury prediction[J]. Automation in Construction, 2016, 69: 102-114. doi: 10.1016/j.autcon.2016.05.016

级别	描述	区间划分		数字表示		预警颜色
安全	工人施工作业状况正常,处于安全状态	[0,0.2)		1		绿色
轻警	工人正常作业,处于一般安全状态	[0.2,0.5)		2		黄色
中警	工人作业时作出不安全行为,安全状态较为严重	[0.5,0.7)		3		橙色
级别	描述	区间划分	数字表示		预警颜色
重警	工人发生多项不安全行为举动,安全状态严重	[0.7,1]	4		红色

类别	影响因素
L因素子系统	风险感知L₁,工作经验L₂,安全态度L₃,心理状况L₄,安全知识L₅,工作技能L₆
L-L因素子系统	工友影响LL₁,领导风格LL₂,沟通交流LL₃
L-S因素子系统	安全规章制度LS₁,安全投入LS₂,事故预防及应急准备LS₃,安全生产教育培训LS₄,安全监管LS₅,施工组织设计LS₆
L-H因素子系统	安全应急装置LH₁,预制构件LH₂,设备检查与维修LH₃,施工作业设备LH₄,临边、高处及登高安全防护设施LH₅,支撑体系LH₆,人机协同LH₇
L-E因素子系统	光线照明LE₁,施工高度LE₂,现场清洁状况LE₃,天气及气候状况LE₄,工地噪音LE₅

指标	题目数量	示例类型	问题设置举例
安全态度	4	正	我认为是运气不好才会在施工过程中受伤
工友影响	2	正	我会跟从同事工作时不良的施工行为
事故预防及应急准备	2	反	我具备安全应急知识,能够在危险来临时正确应对
人机协同	3	反	我熟悉机器的操作步骤或工作流程
工地噪音	2	正	施工作业时设备发出的巨大噪音会影响我工作的专注度
不安全行为	8	正	我施工作业时会站、坐、攀在不太安全的地方

类别	影响因素
L	风险感知X₁₁,工作经验X₁₂,安全态度X₁₃,心理状况X₁₄,安全知识X₁₅,工作技能X₁₆
L-L	工友影响X₂₁,领导风格X₂₂,沟通交流X₂₃
L-S	安全规章制度X₃₁,安全投入X₃₂,事故预防及应急准备X₃₃,安全生产教育培训X₃₄,安全监管X₃₅
L-H	预制构件X₄₁,设备检查与维修X₄₂,施工作业设备X₄₃,临边、高处及登高安全防护设施X₄₄,支撑体系X₄₅,人机协同X₄₆
L-E	光线照明X₅₁,现场清洁状况X₅₂,天气及气候状况X₅₃

分类算法模型	准确率/%	精确率/%	召回率/%	F₁/%	参数C	参数g
RF-SFLA-SVM	91.67	92.08	91.33	91.45	3.701 1	0.769 7
RF-PSO-SVM	86.11	89.02	86.38	86.11	327.176 7	0.001 0
RF-GA-SVM	83.33	85.60	83.13	83.10	2.446 2	1.996 0
RF-SVM	77.78	80.18	74.92	79.21	241.000 0	3.000 0
SFLA-SVM	84.72	84.34	84.29	84.21	1.231 9	0.600 6