An early warning model of unsafe behaviors of construction workers based on BP neural network

doi:10.16265/j.cnki.issn1003-3033.2022.01.004

Abstract

Abstract:

In order to reduce unsafe behaviors of construction workers and improve safety management of corporations, methods of statistical analysis, literature analysis and qualitative interview were adopted to obtain influencing factors of unsafe behaviors. Then, an early warning index system was established from four aspects, namely organization, individual, environment and equipment. Based on BP neural network principle, with these indicators as network input, and four unsafe states were output, a warning questionnaire was designed, and the questionnaire data were repeatedly trained and learned. Finally, a three-layer BP neural network warning model of "23-9-4" was constructed, trained and tested. The results show that this model accurately predicts unsafe behavior states of workers, thereby enabling them to take prevention and control measures in advance.

Key words: back propagation (BP) neural network, construction workers, unsafe behavior, pre-warning model, index system

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.

Figures/Tables 7

Fig.1

Tab.1

Warning index system of unsafe behaviors of construction workers

一级指标	二级指标	指标说明
组织A₁	安全制度B₁	企业安排安全管理工作、制定安全规章制度等的情况
	安全文化B₂	员工所处环境中的安全氛围状况,员工和企业对安全的重视程度
	安全领导力B₃	管理者或“头领”引导、影响员工减少不安全行为的能力
	奖惩措施B₄	企业对不安全行为奖励和惩罚的管理情况
	工友影响B₅	员工间彼此交流,互相影响,从而对不安全行为产生影响的状况
	群体关系B₆	员工个体在群体中互相联系、互相影响的程度
	安全监察B₇	监督、检查、管理员工不安全行为的情况
个人A₂	心理状态B₈	员工的心理品质、性格特点、情绪管理能力、心理适应能力等心理状态
	机能状态B₉	员工在工作中表现出的身体状况,诸如力量、耐力、灵敏和速度等
	安全意识B₁₀	员工在作业时对可能发生的危险的警惕心理状态
	安全态度B₁₁	员工对安全作业过程中的施工操作、环境和工具等的态度
	技能水平B₁₂	员工掌握工作所需技术和能力的程度
	工作经验B₁₃	员工的工作经历、工作感悟和经验总结等
	安全知识B₁₄	员工为避免安全事故、提升防范意识而掌握的安全知识
	安全感知B₁₅	员工预判、感受施工过程中风险的能力
外在环境A₃	作业环境B₁₆	施工作业现场污染、噪声、空气、温度等环境状况
	法律法规B₁₇	政府等有关部门制定和实施的有关安全施工的规章制度法律法规情况
	生活事件B₁₈	员工在日常生活中遇到各种事情对不安全行为的影响情况
	媒体宣传B₁₉	媒体通过多种渠道报道和宣传安全生产的情况
设备A₄	摆放规范B₂₀	操作工具、防护设备、配件等摆放情况
	人机协同B₂₁	员工与机器智能结合,根据作业场景合理配置资源
	设备可靠性B₂₂	设备避免故障、保持稳定和有效的程度
	设备灵活性B₂₃	设备易于操作、功能性强、使用便利的程度

Tab.1

Fig.2

Tab.2

Tab.3

Fig.3

Tab.4

References 31

[1]	叶银树. 建筑施工安全管理研究[J]. 财经问题研究, 2016(增2): 153-156.
[2]	BOHM J, HARRIS D. Risk perception and risk-taking behavior of construction site dumper drivers[J]. International Journal of Occupational Safety and Ergonomics, 2010, 16(1):55-67. doi: 10.1080/10803548.2010.11076829
[3]	成家磊, 祁神军, 张云波. 组织氛围对建筑工人不安全行为的影响机理及实证研究[J]. 中国安全生产科学技术, 2017, 13(11): 11-16.
	CHENG Jialei, QI Shenjun, ZHANG Yunbo. Influence mechanism and empirical study of organizational climate on unsafe behavior of construction workers[J]. Journal of Safety Science and Technology, 2017, 13(11): 11-16.
[4]	祁凯, 彭程. 基于OCS-EGM模型的网络集群行为监测及预警体系研究[J]. 情报杂志, 2019, 38(9): 134-141,149.
	QI Kai, PENG Cheng. Research on network cluster behavior monitoring and public opinion alert system based on OCS-EGM model[J]. Journal of Intelligence, 2019, 38(9): 134-141,149.
[5]	许阳光, 陈雪波, 孙秋柏. 企业员工不安全行为预警体系构建[J]. 自动化仪表, 2017, 38(6): 56-58.
	XU Yangguang, CHEN Xuebo, SUN Qiubai. Construction of the early warning system of employee unsafe behavior[J]. Process Automation Instrumentation, 2017, 38(6): 56-58.
[6]	郭红领, 刘文平, 张伟胜. 集成BIM和PT的工人不安全行为预警系统研究[J]. 中国安全科学学报, 2014, 24(4): 104-109.
	GUO Hongling, LIU Wenping, ZHANG Weisheng. A BIM-PT-integrated warning system for on-site workers' unsafe behavior[J]. China Safety Science Journal, 2014, 24(4): 104-109.
[7]	BAKHTIARI R, TOMCZAK M V, LANGOR S, et al. Application of tablet-based cognitive tasks to predict unsafe drivers in older adults[J]. Transportation Research Interdisciplinary Perspectives, 2020,4: DOI:10.1016/j. trip.2020.100105.
[8]	LEE E J, KO B C, NAM J Y. Recognizing pedestrian's unsafe behaviors in far-infrared imagery at night[J]. Infrared Physics & Technology, 2016, 76:261-270.
[9]	陈冲, 白硕, 黄丽达, 等. 基于视频分析的人群密集场所客流监控预警研究[J]. 中国安全生产科学技术, 2020, 16(4):143-148.
	CHEN Chong, BAI Shuo, HUANG Lida, et al. Research on monitoring and early-warning of passenger flow in crowded places based on video analysis[J]. Journal of Safety Science and Technology, 2020, 16(4): 143-148.
[10]	郁润, 张知田, 郭红领. 数据驱动的施工现场工人不安全行为管理方法[J]. 中国安全科学学报, 2019, 29(8): 130-135. doi: 10.16265/j.cnki.issn1003-3033.2019.08.021
	YU Run, ZHANG Zhitian, GUO Hongling. A data-driven management approach of construction workers' unsafe behaviors[J]. China Safety Science Journal, 2019, 29(8): 130-135. doi: 10.16265/j.cnki.issn1003-3033.2019.08.021
[11]	黄芹芹, 祁神军, 张云波, 等. 建筑工人习惯性不安全行为干预策略的SD模型[J]. 中国安全科学学报, 2018, 28(7): 25-31. doi: 10.16265/j.cnki.issn1003-3033.2018.07.005
	HUANG Qinqin, QI Shenjun, ZHANG Yunbo, et al. SD model of intervention strategies for habitual unsafe behavior of construction workers[J]. China Safety Science Journal, 2018, 28(7): 25-31. doi: 10.16265/j.cnki.issn1003-3033.2018.07.005
[12]	张孟春, 方东平. 建筑工人不安全行为产生的认知原因和管理措施[J]. 土木工程学报, 2012, 45(增2): 297-305.
	ZHANG Mengchun, FANG Dongping. Cognitive causes of construction worker's unsafe behaviors and management measures[J]. China Civil Engineering Journal, 2012, 45(S2): 297-305.
[13]	仇国芳, 鱼馨水. 基于粗糙集的建筑工人安全认知提升策略研究[J]. 工业工程与管理, 2019, 24(4): 120-127.
	QIU Guofang, YU Xinshui. Safety cognition enhancement strategy of construction workers based on rough sets[J]. Industrial Engineering and Management, 2019, 24(4): 120-127.
[14]	KIWANGO G, FRANCIS F, HASSELBERG M, et al. Perception of unsafe driving behaviour and reported driving behaviour among commercial motorcyclists in Dar es Salaam, Tanzania[J]. Transportation Research Part F: Traffic Psychology and Behaviour, 2020, 74:30-39. doi: 10.1016/j.trf.2020.08.011
[15]	尹斌, 申霞, 揣小明. 山西煤矿企业的行为安全评价研究[J]. 煤矿安全, 2020, 51(6): 255-259.
	YIN Bin, SHEN Xia, CHUAI Xiaoming. Study on assessment of safe behaviors in Shanxi coal enterprises[J]. Safety in Coal Mines, 2020, 51(6): 255-259.
[16]	冷旭, 何静, 张俊忠, 等. 基于BP神经网络的海军飞行员人为差错安全影响评估[J]. 安全与环境学报, 2014, 14(4):120-123.
	LENG Xu, HE Jing, ZHANG Junzhong, et al. Evaluation of human errors on flight safety for naval pilots based on BP neural network[J]. Journal of Safety and Environment, 2014, 14(4): 120-123.
[17]	ONOJAKPOR O, KOCK H L D. Development and pilot testing of a questionnaire to assess sensory quality control (SQC) knowledge, attitudes and practices (KAP) of food company employees[J]. Food Quality and Preference, 2020, 86:103996. doi: 10.1016/j.foodqual.2020.103996
[18]	ZHANG Jingyu, WU Changxu. The influence of dispositional mindfulness on safety behaviors: a dual process perspective[J]. Accident Analysis & Prevention, 2014, 70:24-32. doi: 10.1016/j.aap.2014.03.006
[19]	GHIC G, BENTOIU C G, MORARU A. Developing questionnaires and interview techniques on the standard of living and quality of life-teaching and practical approaches[J]. Procedia, Social and Behavioral Sciences, 2014, 116: 5140-5142. doi: 10.1016/j.sbspro.2014.01.1088
[20]	HON C K H, CHAN A P C, YAM M C H. Relationships between safety climate and safety performance of building repair, maintenance, minor alteration and addition (RMAA) works[J]. Safety Science, 2014, 65:10-19. doi: 10.1016/j.ssci.2013.12.012
[21]	JIANG Wei, FU Gui, LIANG Chunyang, et al. Study on quantitative measurement result of safety culture[J]. Safety Science, 2020, 128:104751. doi: 10.1016/j.ssci.2020.104751
[22]	LI Jingru, LIU Han, ZUO Jian, et al. Are construction enterprises ready for industrialized residential building policy? a case study in Shenzhen[J]. Sustainable Cities and Society, 2018, 41:899-906. doi: 10.1016/j.scs.2018.06.033
[23]	张江石, 赵群, 张文越. 安全管理实践与行为关系研究[J]. 安全与环境学报, 2018, 18(6): 2279-2284.
	ZHANG Jiangshi, ZHAO Qun, ZHANG Wenyue. On the proper relation between the safety management practice and the workers'corresponding behaviors[J]. Journal of Safety and Environment, 2018, 18(6): 2279-2284.
[24]	蔡秋晨, 董建军, 孙剑. 隧道工人安全感知对安全行为的影响机理[J]. 土木工程与管理学报, 2019, 36(1): 181-187.
	CAI Qiuchen, DONG Jianjun, SUN Jian. Influence mechanism of safety perception of tunnel workers on safety behavior[J]. Journal of Civil Engineering and Management, 2019, 36(1): 181-187.
[25]	李红霞, 李思琦. 煤矿工人安全认知与不安全行为关系研究[J]. 煤矿安全, 2017, 48(11): 233-236.
	LI Hongxia, LI Siqi. Research on relationship between safety cognition and unsafe behavior of coal miners[J]. Safety in Coal Mines, 2017, 48(11): 233-236.
[26]	陈海涛, 魏永. 网络舆情、群体心理及群体行为关系研究[J]. 中国矿业大学学报:社会科学版, 2020, 22(6): 81-93.
	CHEN Haitao, WEI Yong. Research on the relationship among network publication,group psychology and group behavior[J]. Journal of China University of Mining and Technology:Social Sciences, 2020, 22(6): 81-93.
[27]	曹璐璐, 刘艳. 有限空间作业人员不安全心理及行为量表研究[J]. 中国安全科学学报, 2020, 30(11): 37-42. doi: 10.16265/j.cnki.issn 1003-3033.2020.11.006
	CAO Lulu, LIU Yan. Research on unsafe mentality and behavior scales of workers in confined space[J]. China Safety Science Journal, 2020, 30(11): 37-42. doi: 10.16265/j.cnki.issn 1003-3033.2020.11.006
[28]	吴开兴, 张亚静, 张明. 行为安全管理在煤矿安全管理与评价系统中的应用[J]. 煤矿安全, 2017, 48(1): 218-220.
	WU Kaixing, ZHANG Yajing, ZHANG Ming. Application of behavior-based safety in coal mine safety management and assessment system[J]. Safety in Coal Mines, 2017, 48(1): 218-220.
[29]	中国政府网生产安全事故报告和调查处理条例[EB/OL].(2020-12-27).
[30]	中华人民共和国住房和城乡建设部住房城乡建设部关于印发《房屋市政工程生产安全事故报告和查处工作规程》的通知[EB/OL].(2013-01-14).
[31]	中华人民共和国住房和城乡建设部住房和城乡建设部关于印发《规范住房和城乡建设部工程建设行政处罚裁量权实施办法》和《住房和城乡建设部工程建设行政处罚裁量基准》的通知[EB/OL].(2019-09-23).

指标	题项数	主要题项举例	指标	题项数	主要题项举例
安全制度B₁	3	我遵守安全规章,规范自身安全操作	工作经验B₁₃	3	我熟悉我工作的岗位及相应的操作
安全文化B₂	3	企业的安全氛围和传统良好	安全知识B₁₄	3	我熟悉防护急救等危险处理方法
安全领导力B₃	3	我尊重和跟随领导的安全指令	安全感知B₁₅	3	我对容易导致事故的危险操作较敏感
奖惩措施B₄	3	公平的安全奖惩规定有利于我安全操作	作业环境B₁₆	3	在不适的环境中可能导致我违规操作
工友影响B₅	3	我会不自觉地模仿工友的安全操作行为	法律法规B₁₇	3	相关安全规定保障我安全操作
群体关系B₆	3	我和周围人联系较紧密,时常交流心得	生活事件B₁₈	3	生活中遇到烦心事可能影响我的操作
安全监察B₇	3	不定期的安全检查督促我坚持安全作业	媒体宣传B₁₉	3	安全宣传片等让我重视安全施工行为
心理状态B₈	3	我面对突发事件能够沉着应对	规范摆放B₂₀	3	我按照规定正确摆放工具和配件等
机能状态B₉	3	我工作时精力充沛,干活有劲	人机协同B₂₁	3	使用机器使我作业更安全
安全意识B₁₀	3	我有较高的安全作业觉悟和习惯	设备可靠性B₂₂	3	机器性能不稳定容易导致我不按规定作业
安全态度B₁₁	3	我愿意按照规定安全操作	设备灵活性B₂₃	3	不方便使用的工具可能会使我违规作业
技能水平B₁₂	3	掌握较高的技能水平有利于我安全作业	不安全行为	6	我有可能为了赶工期不按照安全规章作业

不安全行为等级	不安全行为状态	不安全行为得分区间	相应的期望输出
Ⅰ	无警	[6,13]	1 0 0 0
Ⅱ	轻警	[14,18]	0 1 0 0
Ⅲ	中警	[19,25]	0 0 1 0
Ⅳ	重警	[26,30]	0 0 0 1

编号	期望输出	实际输出				行为状态
1	0 100	0.001	0.994	0.004	0.031	轻警
2	0 100	0.008	0.997	0.015	0.002	轻警
3	0 001	0.012	0.003	0.006	0.989	重警
4	0 010	0.033	0.005	0.998	0.019	中警
5	1 000	0.993	0.002	0.001	0.003	无警
6	0 010	0.000	0.010	0.985	0.001	中警
7	0 100	0.004	0.999	0.002	0.031	轻警
8	0 001	0.031	0.002	0.007	0.993	重警
9	1 000	0.994	0.011	0.004	0.005	无警
10	0 010	0.006	0.011	0.997	0.009	中警