Article(id=1148106721299521658, tenantId=1146029695717560320, journalId=1146031787341344770, issueId=1148106708670477182, articleNumber=1003-3033(2025)03-0052-08, orderNo=null, doi=10.16265/j.cnki.issn1003-3033.2025.03.0471, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1729008000000, receivedDateStr=2024-10-16, revisedDate=1734883200000, revisedDateStr=2024-12-23, acceptedDate=null, acceptedDateStr=null, onlineDate=1751659573148, onlineDateStr=2025-07-05, pubDate=1743091200000, pubDateStr=2025-03-28, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1751659573148, onlineIssueDateStr=2025-07-05, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1751659573148, creator=13701087609, updateTime=1751659573148, updator=13701087609, issue=Issue{id=1148106708670477182, tenantId=1146029695717560320, journalId=1146031787341344770, year='2025', volume='35', issue='3', pageStart='1', pageEnd='268', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=0, createTime=1751659570138, creator=13701087609, updateTime=1757401518130, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1172190184155238915, tenantId=1146029695717560320, journalId=1146031787341344770, issueId=1148106708670477182, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1172190184155238916, tenantId=1146029695717560320, journalId=1146031787341344770, issueId=1148106708670477182, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=52, endPage=59, ext={EN=ArticleExt(id=1149767558850593292, articleId=1148106721299521658, tenantId=1146029695717560320, journalId=1146031787341344770, language=EN, title=Enterprise safety risk management model of machinery manufacturing industry based on improved YOLOv5, columnId=1149733271128420907, journalTitle=China Safety Science Journal, columnName=Safety social science and safety management, runingTitle=null, highlight=null, articleAbstract=

In order to improve the efficiency and accuracy of safety risk management in machinery manufacturing enterprises,the Bayesian network and machine vision technology were combined. Based on improved YOLOv5,Intersection over Union(IoU) values of safety hazard events occurring at the operation site were calculated. By leveraging the audit risk assessment in conjunction with AHP to derive the danger weights,the prior probabilities of the root nodes of Bayesian network were determined. Bayesian network model and design management system were established to realize closed-loop control. A safety risk management model of machinery manufacturing enterprises was constructed and verified by examples. The results show that the model has a more accurate identification and evaluation ability,and can find some potential safety hazards,so as to optimize the current management process. At the same time,the model also successfully realizes the effective combination of qualitative and quantitative analysis,integrates the expert experience and data quantification results,and confirms each other,so that the risk assessment results have a certain improvement in scientificity and reliability,which can provide a practical new idea for safety risk management.

, correspAuthors=Aierken HAIMUDULA, authorNote=null, correspAuthorsNote=null, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=null, magXml=null, pdfUrl=null, pdf=null, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=null, mapNumber=null, authorCompany=null, fund=null, authors=null, authorsList=Hao ZHANG, Aierken HAIMUDULA), CN=ArticleExt(id=1148106724944372204, articleId=1148106721299521658, tenantId=1146029695717560320, journalId=1146031787341344770, language=CN, title=基于改进YOLOv5的机械制造业企业安全风险管理模型, columnId=1149733271296193071, journalTitle=中国安全科学学报, columnName=安全社会科学与安全管理, runingTitle=null, highlight=null, articleAbstract=

为提升机械制造业企业安全风险管理的效率与精确性,融合贝叶斯网络与机器视觉技术,基于改进的 YOLOv5计算作业现场安全隐患事件交并比(IoU)值,利用审计风险评估结合层次分析法(AHP)得出危险权重确定贝叶斯网络根节点的先验概率,建立贝叶斯网络模型与设计管理体系,实现闭环控制,构建一种机械制造业企业安全风险管理模型,并经实例验证。结果表明:该模型有着较为准确的识别与评估能力,能够发现一些潜在的安全隐患,据此可对现行的管理流程作适当优化。同时,该模型还能够实现定性与定量分析的有效结合,把专家经验和数据量化成果相互融合、彼此印证,使得风险评估结果在科学性与可靠性方面有一定提升,可为安全风险管理工作提供一个实用的新思路。

, correspAuthors=艾尔肯·亥木都拉, authorNote=null, correspAuthorsNote=
** 艾尔肯·亥木都拉(1974—),男,新疆乌鲁木齐人,维吾尔族,硕士,副教授,主要从事同微电子、计算机、信息、网络等新兴技术领域交叉等方面的研究。E-mail:
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=N5ssq6DcjOWsY6BSpQgnLQ==, magXml=8sr9rCasVGuiliuZMgWqiQ==, pdfUrl=null, pdf=eVOX0mXWaTC0AF7E0b2LQw==, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=rI3ORkopFirIXwP+lEOvIQ==, mapNumber=null, authorCompany=null, fund=null, authors=

张 浩 (2000—),男,安徽合肥人,硕士研究生,主要研究方向为机械制造业企业生产安全风险管理。E-mail:

, authorsList=张浩, 艾尔肯·亥木都拉)}, authors=[Author(id=1165678263268553470, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106721299521658, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=1010729604@qq.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1165678263314690816, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106721299521658, authorId=1165678263268553470, language=EN, stringName=Hao ZHANG, firstName=Hao, middleName=null, lastName=ZHANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 Business School,Xinjiang University,Urumqi Xinjiang 830046,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1165678263356633857, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106721299521658, authorId=1165678263268553470, language=CN, stringName=张浩, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 新疆大学 商学院,新疆 乌鲁木齐 830046, bio={"img":"ODTmttxPJ+f8BogT9KMCHQ==","content":"

张 浩 (2000—),男,安徽合肥人,硕士研究生,主要研究方向为机械制造业企业生产安全风险管理。E-mail:

"}, bioImg=ODTmttxPJ+f8BogT9KMCHQ==, bioContent=

张 浩 (2000—),男,安徽合肥人,硕士研究生,主要研究方向为机械制造业企业生产安全风险管理。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1165678263109169910, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106721299521658, xref=1, ext=[AuthorCompanyExt(id=1165678263117558519, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106721299521658, companyId=1165678263109169910, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 Business School,Xinjiang University,Urumqi Xinjiang 830046,China), AuthorCompanyExt(id=1165678263121752824, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106721299521658, companyId=1165678263109169910, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 新疆大学 商学院,新疆 乌鲁木齐 830046)])]), Author(id=1165678263402771203, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106721299521658, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=arkin@xju.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1165678263453102853, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106721299521658, authorId=1165678263402771203, language=EN, stringName=Aierken HAIMUDULA, firstName=Aierken, middleName=null, lastName=HAIMUDULA, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, **, address=2 School of Intelligent Manufacturing Modern Industry,Xinjiang University,Urumqi Xinjiang 830046,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1165678263499240198, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106721299521658, authorId=1165678263402771203, language=CN, stringName=艾尔肯·亥木都拉, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, **, address=2 新疆大学 智能制造现代产业学院,新疆 乌鲁木齐 830046, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1165678263176278777, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106721299521658, xref=2, ext=[AuthorCompanyExt(id=1165678263184667386, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106721299521658, companyId=1165678263176278777, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 School of Intelligent Manufacturing Modern Industry,Xinjiang University,Urumqi Xinjiang 830046,China), AuthorCompanyExt(id=1165678263188861691, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106721299521658, companyId=1165678263176278777, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 新疆大学 智能制造现代产业学院,新疆 乌鲁木齐 830046)])])], keywords=[Keyword(id=1165678263604097799, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106721299521658, language=EN, orderNo=1, keyword=machinery manufacturing industry), Keyword(id=1165678263650235144, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106721299521658, language=EN, orderNo=2, keyword=safety risk management), Keyword(id=1165678263704761097, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106721299521658, language=EN, orderNo=3, keyword=Bayesian network), Keyword(id=1165678263755092746, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106721299521658, language=EN, orderNo=4, keyword=machine vision), Keyword(id=1165678263805424395, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106721299521658, language=EN, orderNo=5, keyword=improved YOLOv5), Keyword(id=1165678263872533260, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106721299521658, language=EN, orderNo=6, keyword=analytic hierarchy process (AHP)), Keyword(id=1165678263918670605, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106721299521658, language=EN, orderNo=7, keyword=prior probability), Keyword(id=1165678263973196558, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106721299521658, language=CN, orderNo=1, keyword=机械制造业企业), Keyword(id=1165678264036111119, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106721299521658, language=CN, orderNo=2, keyword=安全风险管理), Keyword(id=1165678264115802896, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106721299521658, language=CN, orderNo=3, keyword=贝叶斯网络), Keyword(id=1165678264166134545, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106721299521658, language=CN, orderNo=4, keyword=机器视觉), Keyword(id=1165678264220660498, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106721299521658, language=CN, orderNo=5, keyword=改进YOLOv5), Keyword(id=1165678264270992147, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106721299521658, language=CN, orderNo=6, keyword=层次分析法(AHP)), Keyword(id=1165678264321323796, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106721299521658, language=CN, orderNo=7, keyword=先验概率)], refs=[Reference(id=1165678266443641653, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106721299521658, doi=null, pmid=null, pmcid=null, year=2018, volume=null, issue=null, pageStart=108, pageEnd=117, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=AMIN T, KHAN F, IMTIAZ S, journalName=Reliability Engineering and System Safety, refType=null, unstructuredReference=AMIN T, KHAN F, IMTIAZ S. Dynamic availability assessment of safety critical systems using a dynamic bayesian network[J]. Reliability Engineering and System Safety, 2018,178: 108-117., articleTitle=Dynamic availability assessment of safety critical systems using a dynamic bayesian network, refAbstract=null), Reference(id=1165678266493973302, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106721299521658, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[2], rfOrder=1, authorNames=高萦莹, journalName=基于计算机视觉数据驱动的新型施工安全风险评估研究, refType=null, unstructuredReference=高萦莹. 基于计算机视觉数据驱动的新型施工安全风险评估研究[D]. 大连: 东北财经大学, 2023., articleTitle=null, refAbstract=null), Reference(id=1165678266540110647, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106721299521658, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[2], rfOrder=2, authorNames=GAO Yingying, journalName=Research on newvonstruction safety risk assessment driven by computer vision data, refType=null, unstructuredReference=GAO Yingying. Research on newvonstruction safety risk assessment driven by computer vision data[D]. Dalian: Dongbei University of Finance and Economics, 2023., articleTitle=null, refAbstract=null), Reference(id=1165678266611413816, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106721299521658, doi=null, pmid=null, pmcid=null, year=2023, volume=44, issue=1, pageStart=21, pageEnd=29, url=null, language=null, rfNumber=[3], rfOrder=3, authorNames=杜敏维, 于德湖, 邵志国, journalName=青岛:青岛理工大学学报, refType=null, unstructuredReference=杜敏维, 于德湖, 邵志国. 基于T-S模糊故障树和贝叶斯网络的建筑施工风险评估模型建立及应用[J]. 青岛:青岛理工大学学报, 2023, 44(1):21-29., articleTitle=基于T-S模糊故障树和贝叶斯网络的建筑施工风险评估模型建立及应用, refAbstract=null), Reference(id=1165678266670134073, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106721299521658, doi=null, pmid=null, pmcid=null, year=2023, volume=44, issue=1, pageStart=21, pageEnd=29, url=null, language=null, rfNumber=[3], rfOrder=4, authorNames=DU Minwei, YU Dehu, SHAO Zhiguo, journalName=Journal of Qingdao University of Technology, refType=null, unstructuredReference=DU Minwei, YU Dehu, SHAO Zhiguo. Establishment and application of construction risk assessment model based on T-S fuzzy fault tree and bayesian network[J]. Journal of Qingdao University of Technology, 2023, 44(1):21-29., articleTitle=Establishment and application of construction risk assessment model based on T-S fuzzy fault tree and bayesian network, refAbstract=null), Reference(id=1165678266716271418, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106721299521658, doi=null, pmid=null, pmcid=null, year=2024, volume=39, issue=3, pageStart=132, pageEnd=138, url=null, language=null, rfNumber=[4], rfOrder=5, authorNames=吕艳, journalName=灾害学, refType=null, unstructuredReference=吕艳, 古丽赛乃穆·阿布都热合曼,高程. 网红景点安全风险管理初探[J]. 灾害学, 2024, 39(3):132-138., articleTitle=网红景点安全风险管理初探, refAbstract=null), Reference(id=1165678266762408763, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106721299521658, doi=null, pmid=null, pmcid=null, year=2024, volume=39, issue=3, pageStart=132, pageEnd=138, url=null, language=null, rfNumber=[4], rfOrder=6, authorNames=LYU Yan, journalName=Journal of Catastrophology, refType=null, unstructuredReference=LYU Yan, ABUDUREHEMAN Gulisainaimu, GAO Cheng. A preliminary study on safety risk management of Internet-famous tourist attractions[J]. Journal of Catastrophology, 2024, 39 (3): 132-138., articleTitle=A preliminary study on safety risk management of Internet-famous tourist attractions, refAbstract=null), Reference(id=1165678266821129020, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106721299521658, doi=null, pmid=null, pmcid=null, year=2023, volume=33, issue=10, pageStart=16, pageEnd=22, url=null, language=null, rfNumber=[5], rfOrder=7, authorNames=王金江, 关鹏婷, 陈卓, journalName=中国安全科学学报, refType=null, unstructuredReference=王金江, 关鹏婷, 陈卓, 等. 基于深度学习的检修作业过程风险智能预警[J]. 中国安全科学学报, 2023, 33(10): 16-22., articleTitle=基于深度学习的检修作业过程风险智能预警, refAbstract=null), Reference(id=1165678266892432189, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106721299521658, doi=null, pmid=null, pmcid=null, year=2023, volume=33, issue=10, pageStart=16, pageEnd=22, url=null, language=null, rfNumber=[5], rfOrder=8, authorNames=WANG Jinjiang, GUAN Pengting, CHEN Zhuo, journalName=China Safety Science Journal, refType=null, unstructuredReference=WANG Jinjiang, GUAN Pengting, CHEN Zhuo, et al. Intelligent early warning of risks in the maintenance operation process based on deep learning[J]. China Safety Science Journal, 2023, 33 (10): 16-22., articleTitle=Intelligent early warning of risks in the maintenance operation process based on deep learning, refAbstract=null), Reference(id=1165678266942763838, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106721299521658, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=8, pageStart=48, pageEnd=51, url=null, language=null, rfNumber=[6], rfOrder=9, authorNames=唐哲, 刘艺超, 方汀, journalName=科学技术创新, refType=null, unstructuredReference=唐哲, 刘艺超, 方汀, 等. 基于YOLOv5和特征提取机制的作业穿戴装备检测方法研究[J]. 科学技术创新, 2023(8): 48-51., articleTitle=基于YOLOv5和特征提取机制的作业穿戴装备检测方法研究, refAbstract=null), Reference(id=1165678266988901183, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106721299521658, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=8, pageStart=48, pageEnd=51, url=null, language=null, rfNumber=[6], rfOrder=10, authorNames=TANG Zhe, LIU Yichao, FANG Ting, journalName=Scientific and Technological Innovation, refType=null, unstructuredReference=TANG Zhe, LIU Yichao, FANG Ting, et al. Research on the detection method of work wearing equipment based on YOLOv5 and feature extraction mechanism[J]. Scientific and Technological Innovation, 2023 (8): 48-51., articleTitle=Research on the detection method of work wearing equipment based on YOLOv5 and feature extraction mechanism, refAbstract=null), Reference(id=1165678267039232832, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106721299521658, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[7], rfOrder=11, authorNames=魏斌庆, journalName=基于文本和图像信息的建筑施工现场险兆事件管理研究, refType=null, unstructuredReference=魏斌庆. 基于文本和图像信息的建筑施工现场险兆事件管理研究[D]. 徐州: 中国矿业大学, 2023., articleTitle=null, refAbstract=null), Reference(id=1165678267081175873, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106721299521658, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[7], rfOrder=12, authorNames=WEI Binqing, journalName=Research on the management of near-miss events in construction sites based on text and image information, refType=null, unstructuredReference=WEI Binqing. Research on the management of near-miss events in construction sites based on text and image information[D]. Xuzhou: China University of Mining and Technology, 2023., articleTitle=null, refAbstract=null), Reference(id=1165678267135701826, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106721299521658, doi=null, pmid=null, pmcid=null, year=2024, volume=35, issue=6, pageStart=641, pageEnd=649, url=null, language=null, rfNumber=[8], rfOrder=13, authorNames=魏峰, 周建平, 谭翔, journalName=光电子·激光, refType=null, unstructuredReference=魏峰, 周建平, 谭翔, 等. 针对低空微小型无人机的轻量型YOLOv5检测算法[J]. 光电子·激光, 2024, 35(6): 641-649., articleTitle=针对低空微小型无人机的轻量型YOLOv5检测算法, refAbstract=null), Reference(id=1165678267181839171, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106721299521658, doi=null, pmid=null, pmcid=null, year=2024, volume=35, issue=6, pageStart=641, pageEnd=649, url=null, language=null, rfNumber=[8], rfOrder=14, authorNames=WEI Feng, ZHOU Jianping, TAN Xiang, journalName=Journal of Optoelectronics·Laser, refType=null, unstructuredReference=WEI Feng, ZHOU Jianping, TAN Xiang, et al. Lightweight YOLOv5 detection algorithm for low-altitude micro and small unmanned aerial vehicles[J]. Journal of Optoelectronics·Laser, 2024, 35 (6): 641-649., articleTitle=Lightweight YOLOv5 detection algorithm for low-altitude micro and small unmanned aerial vehicles, refAbstract=null), Reference(id=1165678267240559428, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106721299521658, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[9], rfOrder=15, authorNames=崔雅欣, journalName=基于故障树和贝叶斯网络的建筑施工高处坠落事故致因分析, refType=null, unstructuredReference=崔雅欣. 基于故障树和贝叶斯网络的建筑施工高处坠落事故致因分析[D]. 西安: 西安理工大学, 2023., articleTitle=null, refAbstract=null), Reference(id=1165678267282502469, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106721299521658, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[9], rfOrder=16, authorNames=CUI Yaxin, journalName=Cause analysis of construction falls accidents based on fault Tree and bayesian network, refType=null, unstructuredReference=CUI Yaxin. Cause analysis of construction falls accidents based on fault Tree and bayesian network[D]. Xi'an: Xi'an University of Technology, 2023., articleTitle=null, refAbstract=null), Reference(id=1165678267328639814, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106721299521658, doi=null, pmid=null, pmcid=null, year=2023, volume=33, issue=2, pageStart=202, pageEnd=208, url=null, language=null, rfNumber=[10], rfOrder=17, authorNames=马港, 徐晓楠, 郭小芳, journalName=中国安全科学学报, refType=null, unstructuredReference=马港, 徐晓楠, 郭小芳, 等. 基于贝叶斯网络的电镀企业火灾事故情景推演[J]. 中国安全科学学报, 2023, 33(2): 202-208., articleTitle=基于贝叶斯网络的电镀企业火灾事故情景推演, refAbstract=null), Reference(id=1165678267378971463, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106721299521658, doi=null, pmid=null, pmcid=null, year=2023, volume=33, issue=2, pageStart=202, pageEnd=208, url=null, language=null, rfNumber=[10], rfOrder=18, authorNames=MA Gang, XU Xiaonan, GUO Xiaofang, journalName=China Safety Science Journal, refType=null, unstructuredReference=MA Gang, XU Xiaonan, GUO Xiaofang, et al. Scenario deduction of fire accidents in electroplating enterprises based on Bayesian network[J]. China Safety Science Journal, 2023, 33 (2): 202-208., articleTitle=Scenario deduction of fire accidents in electroplating enterprises based on Bayesian network, refAbstract=null), Reference(id=1165678267433497416, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106721299521658, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[11], rfOrder=19, authorNames=李博宇, journalName=铁路技术站生产作业智能化安全管理及评价技术研究, refType=null, unstructuredReference=李博宇. 铁路技术站生产作业智能化安全管理及评价技术研究[D]. 北京: 中国铁道科学研究院, 2023., articleTitle=null, refAbstract=null), Reference(id=1165678267479634761, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106721299521658, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[11], rfOrder=20, authorNames=LI Boyu, journalName=Research on intelligent safety management and evaluation technology for production operations at railway technical stations, refType=null, unstructuredReference=LI Boyu. Research on intelligent safety management and evaluation technology for production operations at railway technical stations[D]. Beijing: China Academy of Railway Sciences, 2023., articleTitle=null, refAbstract=null)], funds=null, companyList=[AuthorCompany(id=1165678263109169910, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106721299521658, xref=1, ext=[AuthorCompanyExt(id=1165678263117558519, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106721299521658, companyId=1165678263109169910, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 Business School,Xinjiang University,Urumqi Xinjiang 830046,China), AuthorCompanyExt(id=1165678263121752824, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106721299521658, companyId=1165678263109169910, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 新疆大学 商学院,新疆 乌鲁木齐 830046)]), AuthorCompany(id=1165678263176278777, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106721299521658, xref=2, ext=[AuthorCompanyExt(id=1165678263184667386, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106721299521658, companyId=1165678263176278777, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 School of Intelligent Manufacturing Modern Industry,Xinjiang University,Urumqi Xinjiang 830046,China), AuthorCompanyExt(id=1165678263188861691, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106721299521658, companyId=1165678263176278777, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 新疆大学 智能制造现代产业学院,新疆 乌鲁木齐 830046)])], figs=[ArticleFig(id=1165678264472318741, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106721299521658, language=EN, label=Fig.1, caption=Safety risk management model process, figureFileSmall=Zrhv/UCfsrbKFG1ETrTRZQ==, figureFileBig=928d+ZGyZ1ZsyfarYg8eKQ==, tableContent=null), ArticleFig(id=1165678264535233302, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106721299521658, language=CN, label=图1, caption=安全风险管理模型流程, figureFileSmall=Zrhv/UCfsrbKFG1ETrTRZQ==, figureFileBig=928d+ZGyZ1ZsyfarYg8eKQ==, tableContent=null), ArticleFig(id=1165678264581370647, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106721299521658, language=EN, label=Fig.2, caption=Process of target detection for potential safety hazard events in the production site, figureFileSmall=QJANZNnK1HesYyz/xWbIbQ==, figureFileBig=SwA7uiodDQT4+F+3dRFvgA==, tableContent=null), ArticleFig(id=1165678264703005464, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106721299521658, language=CN, label=图2, caption=生产现场隐患事件的目标检测流程, figureFileSmall=QJANZNnK1HesYyz/xWbIbQ==, figureFileBig=SwA7uiodDQT4+F+3dRFvgA==, tableContent=null), ArticleFig(id=1165678264795280153, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106721299521658, language=EN, label=Fig.3, caption=Improved network structure of YOLOv5, figureFileSmall=JK509SayJ5qCNjpY02Dkvw==, figureFileBig=waFCjshCPRR0W2aFTeeKfA==, tableContent=null), ArticleFig(id=1165678264916914970, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106721299521658, language=CN, label=图3, caption=改进YOLOv5网络结构

注:跨阶段局部网络(Cross-Stage Partial Network,CSP);残差单元(Residual Unit,Resunit);空间金字塔池化(Spatial Pyramid Pooling,SPP);切片操作(Slicing Operation,Focus);连接(Concatenation,CONCAT);特征金字塔网络(Feature Pyramid Network,FNP);批量归一化(Batch Normalization,BN);路径聚合网络(Path Aggregation Network,PAN);卷积(Convolution,CONV);上采样(Up-sampling,UP-S);深度神经网络(Deep Neural Network,DNN)。

, figureFileSmall=JK509SayJ5qCNjpY02Dkvw==, figureFileBig=waFCjshCPRR0W2aFTeeKfA==, tableContent=null), ArticleFig(id=1165678264984023835, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106721299521658, language=EN, label=Fig.4, caption=Bayesian network model of work safety risk in a machinery manufacturing enterprise, figureFileSmall=BRptlWG60wiWheUSzhPPUA==, figureFileBig=C8K+8YlKTyRnSioNJ1/Z4g==, tableContent=null), ArticleFig(id=1165678265034355484, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106721299521658, language=CN, label=图4, caption=某机械制造业企业生产安全风险贝叶斯网络模型, figureFileSmall=BRptlWG60wiWheUSzhPPUA==, figureFileBig=C8K+8YlKTyRnSioNJ1/Z4g==, tableContent=null), ArticleFig(id=1165678265080492829, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106721299521658, language=EN, label=Fig.5, caption=Posterior probability of vehicle injury root node event, figureFileSmall=kl7uhDRuqSztJMXlw2ZObg==, figureFileBig=hsoUuk6qk+Gk/dzefnn56w==, tableContent=null), ArticleFig(id=1165678265126630174, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106721299521658, language=CN, label=图5, caption=车辆伤害根节点事件后验概率, figureFileSmall=kl7uhDRuqSztJMXlw2ZObg==, figureFileBig=hsoUuk6qk+Gk/dzefnn56w==, tableContent=null), ArticleFig(id=1165678265172767519, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106721299521658, language=EN, label=Table 1, caption=

Ablation test results

, figureFileSmall=null, figureFileBig=null, tableContent=
模型 F1 mAP@0.5
YOLOv5-/NL(原模型) 0.87 0.919
YOLOv5-/NS 0.96 0.967
YOLOv5-/SS 0.85 0.917
YOLOv5-/SL 0.97 0.966
YOLOv5-SSL 0.96 0.964
YOLOv5-SNL 0.97 0.972
YOLOv5-SNS 0.97 0.980
YOLOv5-SSS 0.97 0.983
), ArticleFig(id=1165678265231487776, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106721299521658, language=CN, label=表1, caption=

消融试验结果

, figureFileSmall=null, figureFileBig=null, tableContent=
模型 F1 mAP@0.5
YOLOv5-/NL(原模型) 0.87 0.919
YOLOv5-/NS 0.96 0.967
YOLOv5-/SS 0.85 0.917
YOLOv5-/SL 0.97 0.966
YOLOv5-SSL 0.96 0.964
YOLOv5-SNL 0.97 0.972
YOLOv5-SNS 0.97 0.980
YOLOv5-SSS 0.97 0.983
), ArticleFig(id=1165678265281819425, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106721299521658, language=EN, label=Table 2, caption=

1-9 scaling method

, figureFileSmall=null, figureFileBig=null, tableContent=
标度 具体含义
1 2指标相比同等重要
3 2指标相比,前者比后者稍微重要
5 2指标相比,前者比后者明显重要
7 2指标相比,前者比后者强烈重要
9 2指标相比,前者比后者极端重要
2、4、6、8 2指标相比,前者比后者重要的
程度在上述之间
1/3、1/5、1/7、1/9 2指标相比,后者比前者重要的
上述相应程度
1/2、1/4、1/6、1/8 2指标相比,后者比前者重要的
程度在上述之间
), ArticleFig(id=1165678265336345378, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106721299521658, language=CN, label=表2, caption=

1~9标度法

, figureFileSmall=null, figureFileBig=null, tableContent=
标度 具体含义
1 2指标相比同等重要
3 2指标相比,前者比后者稍微重要
5 2指标相比,前者比后者明显重要
7 2指标相比,前者比后者强烈重要
9 2指标相比,前者比后者极端重要
2、4、6、8 2指标相比,前者比后者重要的
程度在上述之间
1/3、1/5、1/7、1/9 2指标相比,后者比前者重要的
上述相应程度
1/2、1/4、1/6、1/8 2指标相比,后者比前者重要的
程度在上述之间
), ArticleFig(id=1165678265374094115, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106721299521658, language=EN, label=Table 3, caption=

Average random index (RI) of consistency

, figureFileSmall=null, figureFileBig=null, tableContent=
1 2 3 4 5 6 7 8 9
0.00 0.00 0.58 0.90 1.12 1.24 1.32 1.14 1.45
), ArticleFig(id=1165678265420231460, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106721299521658, language=CN, label=表3, caption=

平均随机一致性指标 RI

, figureFileSmall=null, figureFileBig=null, tableContent=
1 2 3 4 5 6 7 8 9
0.00 0.00 0.58 0.90 1.12 1.24 1.32 1.14 1.45
), ArticleFig(id=1165678265483146021, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106721299521658, language=EN, label=Table 4, caption=

Criteria layer judgment matrix

, figureFileSmall=null, figureFileBig=null, tableContent=
隐患事件 环境复
杂程度
事故后
果严
重性
历史事
故发生
次数
人员密
集度
应急响
应有
效性
环境复
杂程度
1 1/7 1/5 1/4 1/6
事故后果
严重性
7 1 5 6 3
历史事故发
生次数
5 1/5 1 3 2
人员密集
程度
4 1/6 1/3 1 1/4
应急响应的
有效性
6 1/3 1/2 4 1
), ArticleFig(id=1165678265537671974, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106721299521658, language=CN, label=表4, caption=

准则层判断矩阵

, figureFileSmall=null, figureFileBig=null, tableContent=
隐患事件 环境复
杂程度
事故后
果严
重性
历史事
故发生
次数
人员密
集度
应急响
应有
效性
环境复
杂程度
1 1/7 1/5 1/4 1/6
事故后果
严重性
7 1 5 6 3
历史事故发
生次数
5 1/5 1 3 2
人员密集
程度
4 1/6 1/3 1 1/4
应急响应的
有效性
6 1/3 1/2 4 1
), ArticleFig(id=1165678265596392231, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106721299521658, language=EN, label=Table 5, caption=

Normalization of criteria level judgment matrix

, figureFileSmall=null, figureFileBig=null, tableContent=
隐患事件 环境复杂度 事故后果
严重性
历史事故
发生次数
人员密集度 应急响应
有效性
O Aw
环境复杂度 0.043 0.078 0.028 0.018 0.026 0.038 6 0.20
事故后果严重性 0.304 0.543 0.711 0.421 0.467 0.489 5 2.83
历史事故发生次数 0.217 0.109 0.142 0.211 0.312 0.198 1 1.12
人员密集度 0.174 0.091 0.047 0.070 0.039 0.084 2 0.43
应急响应有效性 0.261 0.181 0.071 0.281 0.156 0.189 9 1.02
), ArticleFig(id=1165678265650918184, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106721299521658, language=CN, label=表5, caption=

准则层判断矩阵归一化

, figureFileSmall=null, figureFileBig=null, tableContent=
隐患事件 环境复杂度 事故后果
严重性
历史事故
发生次数
人员密集度 应急响应
有效性
O Aw
环境复杂度 0.043 0.078 0.028 0.018 0.026 0.038 6 0.20
事故后果严重性 0.304 0.543 0.711 0.421 0.467 0.489 5 2.83
历史事故发生次数 0.217 0.109 0.142 0.211 0.312 0.198 1 1.12
人员密集度 0.174 0.091 0.047 0.070 0.039 0.084 2 0.43
应急响应有效性 0.261 0.181 0.071 0.281 0.156 0.189 9 1.02
), ArticleFig(id=1165678265709638441, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106721299521658, language=EN, label=Table 6, caption=

Consistency check results of the criteria level judgment matrix

, figureFileSmall=null, figureFileBig=null, tableContent=
检验结果 准则层
λmax 5.432 089 644
CI 0.108 0
RI 1.12
CR 0.096
), ArticleFig(id=1165678265755775786, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106721299521658, language=CN, label=表6, caption=

准则层判断矩阵一致性检验结果

, figureFileSmall=null, figureFileBig=null, tableContent=
检验结果 准则层
λmax 5.432 089 644
CI 0.108 0
RI 1.12
CR 0.096
), ArticleFig(id=1165678265818690347, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106721299521658, language=EN, label=Table 7, caption=

Complexity of the environment - judgment matrix for pairwise comparison of IoU intervals

, figureFileSmall=null, figureFileBig=null, tableContent=
环境复杂度 IoU区间(0~0.15) IoU区间(0.15~0.2) IoU区间(0.2~0.3) IoU区间(>0.3)
IoU区间(0~0.15) 1 3 6 9
IoU区间(0.15~0.2) 1/3 1 4 7
IoU区间(0.2~0.3) 1/6 1/4 1 5
IoU区间(>0.3) 1/9 1/7 1/5 1
), ArticleFig(id=1165678265873216300, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106721299521658, language=CN, label=表7, caption=

环境复杂程度-IoU区间两两比较判断矩阵

, figureFileSmall=null, figureFileBig=null, tableContent=
环境复杂度 IoU区间(0~0.15) IoU区间(0.15~0.2) IoU区间(0.2~0.3) IoU区间(>0.3)
IoU区间(0~0.15) 1 3 6 9
IoU区间(0.15~0.2) 1/3 1 4 7
IoU区间(0.2~0.3) 1/6 1/4 1 5
IoU区间(>0.3) 1/9 1/7 1/5 1
), ArticleFig(id=1165678265927742253, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106721299521658, language=EN, label=Table 8, caption=

Normalization of the judgment matrix for pairwise comparison of IoU intervals regarding the complexity of environment

, figureFileSmall=null, figureFileBig=null, tableContent=
环境复杂度 IoU区间
(0~0.15)
IoU区间
(0.15~0.2)
IoU区间
(0.2~0.3)
IoU区间
(>0.3)
O Aw
IoU区间(0~0.15) 0.621 0.683 0.536 0.409 0.5621 2.4807
IoU区间(0.15~0.2) 0.207 0.228 0.357 0.318 0.2775 1.2302
IoU区间(0.2~0.3) 0.103 0.057 0.089 0.227 0.1192 0.4883
IoU区间(>0.3) 0.069 0.033 0.018 0.045 0.0412 0.1671
), ArticleFig(id=1165678265990656814, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106721299521658, language=CN, label=表8, caption=

环境复杂程度-IoU区间两两比较判断矩阵归一化

, figureFileSmall=null, figureFileBig=null, tableContent=
环境复杂度 IoU区间
(0~0.15)
IoU区间
(0.15~0.2)
IoU区间
(0.2~0.3)
IoU区间
(>0.3)
O Aw
IoU区间(0~0.15) 0.621 0.683 0.536 0.409 0.5621 2.4807
IoU区间(0.15~0.2) 0.207 0.228 0.357 0.318 0.2775 1.2302
IoU区间(0.2~0.3) 0.103 0.057 0.089 0.227 0.1192 0.4883
IoU区间(>0.3) 0.069 0.033 0.018 0.045 0.0412 0.1671
), ArticleFig(id=1165678266045182767, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106721299521658, language=EN, label=Table 9, caption=

Consistency test eesults of the pair - wise comparison judgment matrix between the alternative layer and the criterion layer

, figureFileSmall=null, figureFileBig=null, tableContent=
检验结果 环境复杂度 事故后果严重性 历史事故发生次数 人员密集程度 应急响应有效性
λmax 4.250 4.215 4.152 4.241 4.243
CI 0.083 0.072 0.050 0.080 0.080
RI 0.90 0.90 0.90 0.90 0.90
CR 0.092 0.080 0.056 0.090 0.090
), ArticleFig(id=1165678266103903024, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106721299521658, language=CN, label=表9, caption=

方案层-准则层两两比较判断矩阵一致性检验结果

, figureFileSmall=null, figureFileBig=null, tableContent=
检验结果 环境复杂度 事故后果严重性 历史事故发生次数 人员密集程度 应急响应有效性
λmax 4.250 4.215 4.152 4.241 4.243
CI 0.083 0.072 0.050 0.080 0.080
RI 0.90 0.90 0.90 0.90 0.90
CR 0.092 0.080 0.056 0.090 0.090
), ArticleFig(id=1165678266154234673, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106721299521658, language=EN, label=Table 10, caption=

Comprehensive weight distribution

, figureFileSmall=null, figureFileBig=null, tableContent=
综合权重分配 O IoU区间(0~0.15) IoU区间(0.15~0.2) IoU区间(0.2~0.3) IoU区间(>0.3)
环境复杂程度 0.038 6 0.562 1 0.277 5 0.119 2 0.041 2
事故后果严重性 0.489 5 0.590 2 0.258 3 0.102 3 0.049 2
历史事故发生次数 0.198 1 0.562 4 0.255 9 0.131 1 0.050 5
人员密集程度 0.084 2 0.611 5 0.222 1 0.111 4 0.055 0
应急响应有效性 0.189 9 0.622 7 0.205 4 0.131 0 0.041 0
WD危险权重 0.59 0.25 0.11 0.05
), ArticleFig(id=1165678266221343538, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106721299521658, language=CN, label=表10, caption=

综合权重分配

, figureFileSmall=null, figureFileBig=null, tableContent=
综合权重分配 O IoU区间(0~0.15) IoU区间(0.15~0.2) IoU区间(0.2~0.3) IoU区间(>0.3)
环境复杂程度 0.038 6 0.562 1 0.277 5 0.119 2 0.041 2
事故后果严重性 0.489 5 0.590 2 0.258 3 0.102 3 0.049 2
历史事故发生次数 0.198 1 0.562 4 0.255 9 0.131 1 0.050 5
人员密集程度 0.084 2 0.611 5 0.222 1 0.111 4 0.055 0
应急响应有效性 0.189 9 0.622 7 0.205 4 0.131 0 0.041 0
WD危险权重 0.59 0.25 0.11 0.05
), ArticleFig(id=1165678266275869491, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106721299521658, language=EN, label=Table 11, caption=

Acetylene cylinders do not have fixed facilities hidden danger event IoU indicator system

, figureFileSmall=null, figureFileBig=null, tableContent=
隐患事件IoU
区间
IoU区间出
现次数ni
区间危险
权重WD
先验概
P
0~0.15 16 0.59 0.18
0.15~0.2 20 0.25
0.2~0.3 14 0.11
>0.3 50 0.05
), ArticleFig(id=1165678266330395444, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106721299521658, language=CN, label=表11, caption=

乙炔气瓶没有固定设施隐患事件IoU指标体系

, figureFileSmall=null, figureFileBig=null, tableContent=
隐患事件IoU
区间
IoU区间出
现次数ni
区间危险
权重WD
先验概
P
0~0.15 16 0.59 0.18
0.15~0.2 20 0.25
0.2~0.3 14 0.11
>0.3 50 0.05
)], attaches=null, journal=Journal(id=1123942128916217864, delFlag=0, nameCn=中国安全科学学报, nameEn=China Safety Science Journal, nameHistory1=null, nameHistory2=null, issn=1003-3033, eissn=, cn=11-2865/X, coden=null, periodic=0, language=CN, oaType=0, ccby=null, superviseOffice=null, ownerOffice=null, pubOffice=null, editorOffice=null, officeType=null, aims=null, clcCode=null, officeProv=null, officeCity=null, officeAddr=null, officeZip=null, officeEmail=null, officePhone=null, editDirector=null, officeDirector=null, officeDirectorPhone=null, officeStaffNum=null, officeEmpNum=null, coverPicUrl=fkqsFM6VKlHC4gCtS5XqTw==, journalPrice=null, startedYear=null, abbrevIsoEn=Chin Saf Sci J, journalRemark=null, publicationField=null, createdTime=null, updatedTime=1754269350027, createdBy=null, updatedBy=13701087609, firstLetterCn=C, firstLetterEn=C, subjectCode=Engineering, subjectName=工程, subjectCodeEn=Engineering, subjectNameEn=null, picCn=fkqsFM6VKlHC4gCtS5XqTw==, picEn=SHn9HgqSxtJrOcAxqD++4Q==, jcr=null, cjcr=null, exts=[JournalExt(id=1159052918994595848, language=CN, name=中国安全科学学报, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=null, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=http://www.cssjj.com.cn/, createdTime=1754269350050, updatedTime=1754269350050, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=http://www.cssjj.com.cn/CN/column/item15.shtml, submissionAuthorUrl=https://zgaqkxxbauthor.manuscriptcloud.com/login, submissionEditorUrl=https://zgaqkxxbeditor.manuscriptcloud.com/login, submissionReviewUrl=https://zgaqkxxbauthor.manuscriptcloud.com/login, submissionCeEditorUrl=https://zgaqkxxbeditor.manuscriptcloud.com/login, submissionAeEditorUrl=https://zgaqkxxbeditor.manuscriptcloud.com/login, option={"copyright":""}), JournalExt(id=1159052919040733193, language=EN, name=China Safety Science Journal, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=null, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=http://www.cssjj.com.cn/EN/1003-3033/home.shtml, createdTime=1754269350061, updatedTime=1754269350061, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=https://synbioj.cip.com.cn/EN/column/column3.shtml, submissionAuthorUrl=https://zgaqkxxbauthor.manuscriptcloud.com/login, submissionEditorUrl=https://zgaqkxxbeditor.manuscriptcloud.com/login, submissionReviewUrl=https://zgaqkxxbauthor.manuscriptcloud.com/login, submissionCeEditorUrl=https://zgaqkxxbeditor.manuscriptcloud.com/login, submissionAeEditorUrl=https://zgaqkxxbeditor.manuscriptcloud.com/login, option={"copyright":""})], databaseList=null, tenantJournalId=1146031787341344770, websiteList=[Website(id=1148243202345263519, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146031787341344770, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/zgaqkxxb/CN, language=CN, createTime=1751692112766, createBy=18614031015, updateTime=1753502583634, updateBy=18614031015, name=《中国安全科学学报》中文站点, tplId=1146099689490845704, title=中国安全科学学报, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1148618794941046792, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202345263519, code=articleTextType, value=kx, createTime=1751781661020, updateTime=1751781661020, creator=18614031015, updator=18614031015), WebsiteProps(id=1148618794911686661, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202345263519, code=banner, value=null, createTime=1751781661012, updateTime=1751781661012, creator=18614031015, updator=18614031015), WebsiteProps(id=1148618794894909444, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202345263519, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=tui0IVO9FMwB61HHtX5scg==, createTime=1751781661008, updateTime=1751781661008, creator=18614031015, updator=18614031015), WebsiteProps(id=1148618794932658183, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202345263519, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1751781661017, updateTime=1751781661017, creator=18614031015, updator=18614031015), WebsiteProps(id=1148618794924269574, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202345263519, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1751781661015, updateTime=1751781661015, creator=18614031015, updator=18614031015)]), Website(id=1155836763751993353, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146031787341344770, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/zgaqkxxb/EN, language=EN, createTime=1753502558893, createBy=18614031015, updateTime=1753524450387, updateBy=18614031015, name=《中国安全科学学报》英文站点, tplId=1146101810881728533, title=China Safety Science Journal, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1155895925743669425, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155836763751993353, code=articleTextType, value=kx, createTime=1753516664205, updateTime=1753516664205, creator=18614031015, updator=18614031015), WebsiteProps(id=1155895925722697902, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155836763751993353, code=banner, value=null, createTime=1753516664200, updateTime=1753516664200, creator=18614031015, updator=18614031015), WebsiteProps(id=1155895925714309293, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155836763751993353, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=tui0IVO9FMwB61HHtX5scg==, createTime=1753516664198, updateTime=1753516664198, creator=18614031015, updator=18614031015), WebsiteProps(id=1155895925735280816, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155836763751993353, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1753516664203, updateTime=1753516664203, creator=18614031015, updator=18614031015), WebsiteProps(id=1155895925731086511, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155836763751993353, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1753516664202, updateTime=1753516664202, creator=18614031015, updator=18614031015)])], journalTitle=中国安全科学学报, weixinUrl=null, journalUrl=null, iacademicId=null, status=0, seqNo=null, journalTitleEn=China Safety Science Journal, journalPhotoCn=fkqsFM6VKlHC4gCtS5XqTw==, journalPhotoEn=SHn9HgqSxtJrOcAxqD++4Q==, journalFirstLetter=C, journalRecommend=null, journalNew=null, journalCollection=1, jcrJf=null, cjcrJf=null, jcrJfStr=null, cjcrJfStr=null, submissionFirstDecision=null, sciSubjectClassification=null, casSubjectClassification=null, citeScore=null, totalCitationFrequency=null, icpCode=null, psCode=null, advertisingLicenseCode=null, copyrightInformation=null, country=null, option=null, provinceCode=null, provinceName=null, collectFlag=false), detailUrlCn=https://castjournals.cast.org.cn/joweb/zgaqkxxb/CN/10.16265/j.cnki.issn1003-3033.2025.03.0471, detailUrlEn=https://castjournals.cast.org.cn/joweb/zgaqkxxb/EN/10.16265/j.cnki.issn1003-3033.2025.03.0471, pdfUrlCn=https://castjournals.cast.org.cn/joweb/zgaqkxxb/CN/PDF/10.16265/j.cnki.issn1003-3033.2025.03.0471, pdfUrlEn=https://castjournals.cast.org.cn/joweb/zgaqkxxb/EN/PDF/10.16265/j.cnki.issn1003-3033.2025.03.0471, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于改进YOLOv5的机械制造业企业安全风险管理模型
收藏切换
PDF下载
张浩 1 , 艾尔肯·亥木都拉 2, **
中国安全科学学报 | 安全社会科学与安全管理 2025,35(3): 52-59
收起
收藏切换
中国安全科学学报 | 安全社会科学与安全管理 2025, 35(3): 52-59
基于改进YOLOv5的机械制造业企业安全风险管理模型
全屏
张浩1 , 艾尔肯·亥木都拉2, **
作者信息
  • 1 新疆大学 商学院,新疆 乌鲁木齐 830046
  • 2 新疆大学 智能制造现代产业学院,新疆 乌鲁木齐 830046
  • 张 浩 (2000—),男,安徽合肥人,硕士研究生,主要研究方向为机械制造业企业生产安全风险管理。E-mail:

通讯作者:

** 艾尔肯·亥木都拉(1974—),男,新疆乌鲁木齐人,维吾尔族,硕士,副教授,主要从事同微电子、计算机、信息、网络等新兴技术领域交叉等方面的研究。E-mail:
Enterprise safety risk management model of machinery manufacturing industry based on improved YOLOv5
Hao ZHANG1 , Aierken HAIMUDULA2, **
Affiliations
  • 1 Business School,Xinjiang University,Urumqi Xinjiang 830046,China
  • 2 School of Intelligent Manufacturing Modern Industry,Xinjiang University,Urumqi Xinjiang 830046,China
出版时间: 2025-03-28 doi: 10.16265/j.cnki.issn1003-3033.2025.03.0471
文章导航
收藏切换

为提升机械制造业企业安全风险管理的效率与精确性,融合贝叶斯网络与机器视觉技术,基于改进的 YOLOv5计算作业现场安全隐患事件交并比(IoU)值,利用审计风险评估结合层次分析法(AHP)得出危险权重确定贝叶斯网络根节点的先验概率,建立贝叶斯网络模型与设计管理体系,实现闭环控制,构建一种机械制造业企业安全风险管理模型,并经实例验证。结果表明:该模型有着较为准确的识别与评估能力,能够发现一些潜在的安全隐患,据此可对现行的管理流程作适当优化。同时,该模型还能够实现定性与定量分析的有效结合,把专家经验和数据量化成果相互融合、彼此印证,使得风险评估结果在科学性与可靠性方面有一定提升,可为安全风险管理工作提供一个实用的新思路。

机械制造业企业  /  安全风险管理  /  贝叶斯网络  /  机器视觉  /  改进YOLOv5  /  层次分析法(AHP)  /  先验概率

In order to improve the efficiency and accuracy of safety risk management in machinery manufacturing enterprises,the Bayesian network and machine vision technology were combined. Based on improved YOLOv5,Intersection over Union(IoU) values of safety hazard events occurring at the operation site were calculated. By leveraging the audit risk assessment in conjunction with AHP to derive the danger weights,the prior probabilities of the root nodes of Bayesian network were determined. Bayesian network model and design management system were established to realize closed-loop control. A safety risk management model of machinery manufacturing enterprises was constructed and verified by examples. The results show that the model has a more accurate identification and evaluation ability,and can find some potential safety hazards,so as to optimize the current management process. At the same time,the model also successfully realizes the effective combination of qualitative and quantitative analysis,integrates the expert experience and data quantification results,and confirms each other,so that the risk assessment results have a certain improvement in scientificity and reliability,which can provide a practical new idea for safety risk management.

machinery manufacturing industry  /  safety risk management  /  Bayesian network  /  machine vision  /  improved YOLOv5  /  analytic hierarchy process (AHP)  /  prior probability
张浩, 艾尔肯·亥木都拉. 基于改进YOLOv5的机械制造业企业安全风险管理模型. 中国安全科学学报, 2025 , 35 (3) : 52 -59 . DOI: 10.16265/j.cnki.issn1003-3033.2025.03.0471
Hao ZHANG, Aierken HAIMUDULA. Enterprise safety risk management model of machinery manufacturing industry based on improved YOLOv5[J]. China Safety Science Journal, 2025 , 35 (3) : 52 -59 . DOI: 10.16265/j.cnki.issn1003-3033.2025.03.0471
在机械制造业领域,安全风险管理对于保障企业生产运营的稳定与可持续发展至关重要。随着科技的迅猛进步,贝叶斯网络与机器视觉技术在安全风险管理方面的应用潜力日益凸显。2018年,AMIN等[1] 提出将动态贝叶斯网络的可用性评估技术应用于特定系统并分析失败原因以优化管理;2021年,高萦莹[2] 改进了安全管理,并结合机器视觉与本体技术构建自动化框架;2023年,杜敏维等[3] 引入模糊理论优化贝叶斯网络在安全管理中的应用。然而,这些研究未能有效结合实际生产现场数据,缺乏对现场状况的定量分析,所构建的管理框架难以适应生产环境动态变化,无法及时调整风险评估结果。这导致现有安全风险管理方法在准确性与适应性方面存在缺陷,难以满足机械制造业企业(简称机械制造企业)复杂多变的生产环境需求。
鉴于此,笔者拟提出创新模型,引入基于目标检测的交并比(Intersection over Union,IoU)进行空间位置判断,结合审计风险评估与层次分析法(Analytic Hierarchy Process,AHP)[4]确定贝叶斯网络根节点先验概率,构建贝叶斯网络模型与管理体系,以期完成安全风险管理闭环控制。
安全风险管理模型流程(图1)主要包括生产安全风险的识别、机器视觉的应用、IoU指标体系的构建、贝叶斯网络模型的建立、管理体系的构建。
生产安全风险数据源于某通用设备机械制造企业,其生产流程具普遍性,安全执行依赖人员,管理瑕疵易催生风险与事故[5]。文中基于企业与行业历史事故数据,综合运用事故分析与目标检测方法,对生产安全风险进行识别。事故类型分为火灾、触电、物体打击、高空坠落、机械伤害、车辆伤害6类,隐患事件分为道路地面贴纸破损、叉车不规范行驶、配电箱旁堆积杂物、电线未在规定区域、工作人员未佩戴安全帽、作业现场规定区域无护栏、高处物品无固定措施、设备安全罩丢失、电器电线乱接乱拉导致过载短路、电线绝缘不佳无漏电保护、油品未在安全区、乙炔气瓶没有固定设施、工作人员未穿戴防护手套、设备部件损坏变形、2m以上高处工作人员未穿戴安全带、升降平台违规载人。
YOLOv5 网络结构由输入端、骨干网络、颈部端、预测端构成,分别承担图像数据预处理、特征图提取、特征融合、边框与类别预测工作[6]。模型应用时,目标检测技术除图像分类外,还需确定图像中目标对象概念与空间位置,通过提取目标识别框坐标判断检测对象关系,以识别空间位置[7]。添加Python代码根据坐标数据自动计算IoU值。
I o U = α β α β
式中:αβ 分别为2目标区域;αβ为交集区域;αβ为并集区域;IoU取值为0~1,0代表无重叠,1代表完全重合,值越大2目标框越近。
目标检测数据采集各隐患事件的现场图,划分训练集、验证集与测试集,以labelimg软件标注目标标签,经图像预处理后,代入 YOLOv5 算法训练,按需调整参数,训练完成后运行模型输出结果,流程如图2所示。
机械制造企业作业现场环境复杂,安全隐患有重复性且人员设备常移动,影响目标检测效果。为此,在 YOLOv5 的骨干网络层末尾添加挤压与激励(Squeeze-and-Excitation Network,SE)网络模块,其作用在于增强模型对复杂环境及重复目标的特征提取能力。同时将预测端中的非极大值抑制(Non-Maximum Suppression,NMS)改为软非极大值抑制(Soft Non-Maximum Suppression,SOFT-NMS),有助于提升对动态目标特征的处理及重叠框定位准确性[8]。此外,把损失函数由距离交并比 (Distance Intersection over Union,DIOU)调整为完整交并比(Complete Intersection over Union,CIOU)并将激活函数由带泄露修正线性单元(Leaky Rectified Linear Unit,LEAKY-RELU)改为 S 型加权线性单元(Sigmoid-weighted Linear Unit,SILU),目的是利于 SE 模块提取准确位置特征并进一步提高 SOFT-NMS 对重叠框的定位精度[8]。改进后的网络结构如图 3 所示。
对比消融试验结果见表1。结果表明:使用改进YOLOv5模型时检测指标相较于原模型,精确率和召回率的调和平均数(F1指标)提高10%,均值平均精度(mean Average Precision at 50% Bounding Box Intersection 0.5,mAP@0.5)提高 6.4%,改进效果对比其他模型最优,满足生产安全风险管理的要求。
确定管理模型中贝叶斯网络根节点先验概率依据IoU指标体系建立,将确定先验概率与统计时间段内不同IoU区间出现的次数和专家对于不同IoU区间所分析的危险权重这2点相联系,试验方法是记录每个工作日各隐患事件的不同IoU区间出现次数,当单个事件在不同IoU区间次数发生100次时即为一个试验周期。
P = ( n i × W D ) / N i
式中:P为根节点先验概率;ni为统计时间段内不同IoU区间出现的次数;WD为不同IoU区间的危险权重;Ni为统计的总次数;Σ为所有IoU区间的和。
结合企业安全管理专家组的分析,将各隐患事件不同IoU区间的危险性评估作为目标层,将不同隐患事件的IoU区间作为方案层,为有效连接目标层和方案层,准则层涵盖多个关键评估标准,包括环境复杂程度、事故后果严重性、历史事故发生次数、人员密集程度和应急响应有效性。这些标准旨在综合考虑各类风险因素:控制不同环境因素之间的相互作用,防止潜在后果,优先关注可能导致严重后果的风险因素,针对高频风险点制定相应的风险管理措施,评估人员密集程度对事故伤害人数的影响,提高应急响应的有效性,控制事故蔓延和减少损失[9]
构建判断矩阵和赋值均数采用1~9度评分法确定指标权重,见表2
计算权重向量的方法采用算术平均法,首先对判断矩阵进行按列归一化,再将归一化后的每一行矩阵作为权重向量w的对应元素。
A * i j = A i j i = 1 n A i j
W = 1 n i = 1 n A * i j
式中:Aij为判断矩阵中第i行第j列的元素;A*为经过列归一化处理后得到的归一化矩阵; A i j *为归一化矩阵中第i行第j列的元素;W为不同层次元素之间相对重要性的权重值;n为归一化矩阵A中元素的个数。
计算各判断矩阵的最大特征值λmax
λ m a x = 1 n i = 1 n [ A w ] i O
式中:λmax为判断矩阵的最大特征值;[Aw]i 为判断矩阵 A 与权重向量 w相乘后得到的向量中的第 i 个元素。
在得到λmax后,对得到的每一个判断矩阵的权重进行一致性检验,如果随机性一致性比值 (Consistency Ratio,CR)<0.1,则该判断矩阵通过一致性检验,认为可以接受,否则需要调整判断矩阵。具体见表3
C I = λ m a x - n n - 1
C R = C I R I
式中:CI(Consistency Index)为判断矩阵的一致性指标;RI(Random Index)为对应判断矩阵准则数量的平均随机一致性指标。
不同IoU区间的危险权重WD为方案层相对于目标层的组合权重,即各隐患事件不同IoU区间的危险权重。
W D = j = 1 n ( W 1 ( j ) × W 2 ( j ) )
式中:W1(j)为归一化后准则层判断矩阵第j列元素权重值;W2(j)为归一化后各方案层相对于准则层两两比较判断矩阵的第j列元素权重值。
文中贝叶斯网络模型中的数据展示通过GENIE软件以图形呈现风险因素之间的关系,将各种不确定因素进行建模和分析,通过概率推理和概率分布的更新提供相对准确的风险评估结果,有助于安全管理者更好地理解企业生产中的安全风险,以达成有效管理[10]
P ( E p | E q ) = P ( E q | E p ) P ( E p ) P ( E q )
式中:Ep为事件 pEq为事件qP (Ep)为事件 p 先验概率;P (Eq) 为事件 q先验概率;P (Ep| Eq) 为给定事件q发生时事件p的后验概率;P (Eq| Ep) 为给定事件p发生时事件q的后验概率。
贝叶斯网络根节点先验概率由 IoU 指标体系得出。上层事件的条件概率依故障树 “或门” 方法构建,只要分支事件中有一个发生,上层事件就一定会发生。
根据各隐患事件的试验结果确定每个根节点事件的先验概率,对贝叶斯网络模型逆推理后得得到根节点后验概率值,将其设为每周期新的阈值,当先验概率超过规定阈值应当给予及时提醒与记录,每个周期更新贝叶斯网络模型一次,以达到生产安全管理的实时性与周期性的要求[11]
以乙炔气瓶无固定措施这一隐患事件为例建立该隐患事件的IoU指标体系。首先,确定该事件各IoU区间的危险权重,通过AHP参照1~9标度法建立准则层的判断矩阵,见表4
对准则层的判断矩阵通过算术平均法归一化进行一致性检验,得CR=0.096<0.1,通过一致性检验。归一化过程见表5,一致性检验结果见表6
在已建立好的准则层判断矩阵基础上,继续参照1~9标度法建立方案层中各指标关于准则层各指标的两两比较判断矩阵,环境复杂程度-IoU区间两两比较判断矩阵见表7,算术平均法归一化过程见表8。限于篇幅,其余方案层各指标关于准则层各指标的两两比较判断矩阵的结果不再展示。
方案层各指标关于准则层各指标的两两比较判断矩阵一致性检验结果见表9,CR值皆小于0.1,通过一致性检验。
通过组合权重矩阵可得IoU区间(0~0.15)的危险权重为0.59;IoU区间(0.15~0.2)的危险权重为0.25;IoU区间(0.2~0.3)的危险权重为0.11;IoU区间(>0.3)的危险权重为0.05,见表10
在生产现场收集乙炔气瓶在固定设施中和离固定设施间隔不同距离时800张多角度jpg格式照片作为图像预处理的数据储备,使用labelimg将乙炔气瓶与固定设施分别标注为 gas cylinders和fixed facilities。使用改进YOLOv5算法进行“乙炔气瓶是否有固定措施”的目标检测模型训练。其中,训练轮数为100,每轮训练使用图片数量为640,每次调整超参数后的验证轮数为300。运用训练好的目标检测模型去进行隐患事件的IoU数据收集试验。
试验共记录100次不同的IoU区间出现次数,分析汇总结果见表11,得出该隐患事件的先验概率为0.18。
贝叶斯网络中的其他根节点事件都可以用该方法去判断是否存在潜在的安全风险,在得到各根节点先验概率后,将结果代入GENIE软件计算得出本周期贝叶斯网络模型图,如图4所示。发生火灾概率为53%、发生车辆伤害概率为56%、发生触电伤害概率为60%、发生物体打击伤害概率为68%、发生机械伤害概率为84%、发生高空坠落概率为42%。
企业可依后续管理体系整改各事故根节点事件。以车辆伤害为例,其由安全道路地面贴纸破损和叉车逼近安全路道2个根节点事件组成,二者先验概率分别为 28% 和 26%,车辆伤害概率为 40%。如图5所示。经贝叶斯逆推理,设车辆伤害概率为 100%,更新后安全路道地面贴纸破损后验概率 47%,叉车驾驶不规范后验概率 72%,将后验概率设为阈值作为下周期评价标准,其他事故类型安全风险管理均可依此流程,且每周期更新贝叶斯网络模型。
1) 构建融合贝叶斯网络与机器视觉的机械制造企业安全风险管理模型,该模型可突破传统单一分析模式,将定性、定量分析有机融合。实例中,某企业一个周期内的发生火灾概率为 53%、车辆伤害概率为 56%、触电伤害概率为 60% 物体打击伤害概率为68%,发生机械伤害概率为84%,发生高空坠落概率为42%。模型能够以风险量化的方式预测事故发生概率,通过周期数据的交互构建持续循环的闭环性管理模式,实现对生产安全风险的动态监测和持续优化。
2) 改进后的模型(YOLOv5-SSS)相比于原模型(YOLOv5-/NL),F1 指标从 0.87 提高到 0.97,提升 10%,mAP@0.5 从 0.919 提高到 0.983,提高 6.4%。这说明改进模型在复杂实际作业场景下的目标检测能力有较大增强,能够更精准地识别机械制造现场的各类安全隐患。
3) 试验在受控封闭环境进行,有可能放大风险,后续应在实际生产环境测试应用并优化改进。
4) 文中隐患事件分析多基于目标检测便利,未来需强化人机物料环综合分析,包括员工操作与意识、设备监控预测、物料追踪定位、原料特性等,构建监测体系与智能调控优化模型。
参考文献 引证文献
排序方式:
[1]
AMIN T, KHAN F, IMTIAZ S. Dynamic availability assessment of safety critical systems using a dynamic bayesian network[J]. Reliability Engineering and System Safety, 2018,178: 108-117.
[2]
高萦莹. 基于计算机视觉数据驱动的新型施工安全风险评估研究[D]. 大连: 东北财经大学, 2023.
GAO Yingying. Research on newvonstruction safety risk assessment driven by computer vision data[D]. Dalian: Dongbei University of Finance and Economics, 2023.
[3]
杜敏维, 于德湖, 邵志国. 基于T-S模糊故障树和贝叶斯网络的建筑施工风险评估模型建立及应用[J]. 青岛:青岛理工大学学报, 2023, 44(1):21-29.
DU Minwei, YU Dehu, SHAO Zhiguo. Establishment and application of construction risk assessment model based on T-S fuzzy fault tree and bayesian network[J]. Journal of Qingdao University of Technology, 2023, 44(1):21-29.
[4]
吕艳, 古丽赛乃穆·阿布都热合曼,高程. 网红景点安全风险管理初探[J]. 灾害学, 2024, 39(3):132-138.
LYU Yan, ABUDUREHEMAN Gulisainaimu, GAO Cheng. A preliminary study on safety risk management of Internet-famous tourist attractions[J]. Journal of Catastrophology, 2024, 39 (3): 132-138.
[5]
王金江, 关鹏婷, 陈卓, 等. 基于深度学习的检修作业过程风险智能预警[J]. 中国安全科学学报, 2023, 33(10): 16-22.
WANG Jinjiang, GUAN Pengting, CHEN Zhuo, et al. Intelligent early warning of risks in the maintenance operation process based on deep learning[J]. China Safety Science Journal, 2023, 33 (10): 16-22.
[6]
唐哲, 刘艺超, 方汀, 等. 基于YOLOv5和特征提取机制的作业穿戴装备检测方法研究[J]. 科学技术创新, 2023(8): 48-51.
TANG Zhe, LIU Yichao, FANG Ting, et al. Research on the detection method of work wearing equipment based on YOLOv5 and feature extraction mechanism[J]. Scientific and Technological Innovation, 2023 (8): 48-51.
[7]
魏斌庆. 基于文本和图像信息的建筑施工现场险兆事件管理研究[D]. 徐州: 中国矿业大学, 2023.
WEI Binqing. Research on the management of near-miss events in construction sites based on text and image information[D]. Xuzhou: China University of Mining and Technology, 2023.
[8]
魏峰, 周建平, 谭翔, 等. 针对低空微小型无人机的轻量型YOLOv5检测算法[J]. 光电子·激光, 2024, 35(6): 641-649.
WEI Feng, ZHOU Jianping, TAN Xiang, et al. Lightweight YOLOv5 detection algorithm for low-altitude micro and small unmanned aerial vehicles[J]. Journal of Optoelectronics·Laser, 2024, 35 (6): 641-649.
[9]
崔雅欣. 基于故障树和贝叶斯网络的建筑施工高处坠落事故致因分析[D]. 西安: 西安理工大学, 2023.
CUI Yaxin. Cause analysis of construction falls accidents based on fault Tree and bayesian network[D]. Xi'an: Xi'an University of Technology, 2023.
[10]
马港, 徐晓楠, 郭小芳, 等. 基于贝叶斯网络的电镀企业火灾事故情景推演[J]. 中国安全科学学报, 2023, 33(2): 202-208.
MA Gang, XU Xiaonan, GUO Xiaofang, et al. Scenario deduction of fire accidents in electroplating enterprises based on Bayesian network[J]. China Safety Science Journal, 2023, 33 (2): 202-208.
[11]
李博宇. 铁路技术站生产作业智能化安全管理及评价技术研究[D]. 北京: 中国铁道科学研究院, 2023.
LI Boyu. Research on intelligent safety management and evaluation technology for production operations at railway technical stations[D]. Beijing: China Academy of Railway Sciences, 2023.
2025年第35卷第3期
PDF下载
305
117
引用本文
BibTeX
文章信息
doi: 10.16265/j.cnki.issn1003-3033.2025.03.0471
  • 接收时间:2024-10-16
  • 首发时间:2025-07-05
  • 出版时间:2025-03-28
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2024-10-16
  • 修回日期:2024-12-23
基金
作者信息
    1 新疆大学 商学院,新疆 乌鲁木齐 830046
    2 新疆大学 智能制造现代产业学院,新疆 乌鲁木齐 830046

通讯作者:

** 艾尔肯·亥木都拉(1974—),男,新疆乌鲁木齐人,维吾尔族,硕士,副教授,主要从事同微电子、计算机、信息、网络等新兴技术领域交叉等方面的研究。E-mail:
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/zgaqkxxb/CN/10.16265/j.cnki.issn1003-3033.2025.03.0471
分享至
全文二维码

扫描看全文

引用本文
BibTeX
本文的引用情况
2种不同金属材料的力学参数

Family
属数
Number of
genus
种数
Number of
species
占总种数比例
Percentage of
total species (%)

Genus
种数
Number of
species
占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏