Article(id=1149789605853094502, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1149768563956826506, articleNumber=null, orderNo=null, doi=10.12404/j.issn.1671-1815.2406188, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1723996800000, receivedDateStr=2024-08-19, revisedDate=1742227200000, revisedDateStr=2025-03-18, acceptedDate=null, acceptedDateStr=null, onlineDate=1752060804092, onlineDateStr=2025-07-09, pubDate=1749312000000, pubDateStr=2025-06-08, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1752060804092, onlineIssueDateStr=2025-07-09, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1752060804092, creator=13701087609, updateTime=1752060804092, updator=13701087609, issue=Issue{id=1149768563956826506, tenantId=1146029695717560320, journalId=1146123166801305609, year='2025', volume='25', issue='16', pageStart='6587', pageEnd='7021', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=0, createTime=1752055787314, creator=13701087609, updateTime=1768456850262, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1218559607937618069, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1149768563956826506, language=EN, specialIssueTitle=, coverIllustrator=, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1218559607937618070, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1149768563956826506, language=CN, specialIssueTitle=, coverIllustrator=, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=7004, endPage=7012, ext={EN=ArticleExt(id=1149789606033449575, articleId=1149789605853094502, tenantId=1146029695717560320, journalId=1146123166801305609, language=EN, title=YOLOv5s-SimAM-ASFF-based Oil and Gas Drilling and Production Wellsite Safety Hazard Identification and Smart Wearable Device Development, columnId=1156262729993277777, journalTitle=Science Technology and Engineering, columnName=Papers·Environmental and Safe Science, runingTitle=null, highlight=null, articleAbstract=

Oil and gas drilling and production wellsites are complex and have many types of potential safety hazards, in order to improve the accuracy of the identification of potential safety hazards in wellsites, an oil and gas drilling and production wellsite potential safety hazard identification method based on improved YOLOv5 was proposed. Firstly, in order to solve the problem that the background of the picture was complex and the recognition difficulty increased, the SimAM attention mechanism was introduced in the backbone network; secondly, in order to solve the problem that the scales of the types of hidden hazards were different and there were multiple scales in one picture, the original feature fusion was replaced by adaptive spatial fusion of features (ASFF). Lastly, the hidden hazard recognition effect of the improved model was validated by comparing the model with other models. The results show that the improved YOLOv5 model improves the average accuracy value of recognition by 10.4%, and has a better recognition effect on the safety hazards of oil and gas drilling and production well sites. In order to solve the limitation of video monitoring and identification of oil and gas drilling and production wellsite safety hazards, a set of intelligent wearable device was developed, which effectively improved the portability of the identification of wellsite safety hazards.

, correspAuthors=Yang-bai HU, 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=Jin-qiu HU, Lai-bin ZHANG, Yang-bai HU, Sheng-li CHU, Bing-cai SUN, Ze-sen LI), CN=ArticleExt(id=1149789629261504529, articleId=1149789605853094502, tenantId=1146029695717560320, journalId=1146123166801305609, language=CN, title=基于YOLOv5s-SimAM-ASFF的油气钻采井场安全隐患识别及智能穿戴设备研发, columnId=1156262730140078420, journalTitle=科学技术与工程, columnName=论文·环境科学、安全科学, runingTitle=null, highlight=null, articleAbstract=

油气钻采井场情况复杂且安全隐患种类多,为提高井场安全隐患识别的精确性,提出一种基于改进YOLOv5的油气钻采井场安全隐患识别方法。首先,为解决图片背景复杂,识别难度加大的问题,在骨干网络引进SimAM注意力机制;其次,为解决隐患类型的尺度差异较大且一张图片中存在多种尺度的问题,用自适应空间特征融合(ASFF)替换原有特征融合方式;最后,通过与其他模型进行比对来验证改进模型的隐患识别效果。结果表明:改进后的YOLOv5模型识别平均精确值提高了10.4%,对油气钻采井场安全隐患具有较好的识别效果。为解决油气钻采井场安全隐患视频监控识别的限制,研发一套智能穿戴设备,有效提高了井场安全隐患识别的便携性。

, correspAuthors=胡洋柏, authorNote=null, correspAuthorsNote=
* 胡洋柏(2000—),男,汉族,江西上饶人,硕士研究生。研究方向:油气生产安全。E-mail:
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=IYe2gQtZkYONSeQam1OQgw==, magXml=ayeHPfiM9qWi7Du3lxmUOg==, pdfUrl=null, pdf=DRZvENZbBS/u41FUAqLqqA==, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=tjbYqcTnaM0Z1LAk2TxBYA==, mapNumber=null, authorCompany=null, fund=null, authors=

胡瑾秋(1983—),女,汉族,江苏南京人,博士,教授。研究方向:油气生产复杂系统安全预警技术、油气装备监测预警大数据科学与工程。E-mail:

, authorsList=胡瑾秋, 张来斌, 胡洋柏, 储胜利, 孙秉才, 黎泽森)}, authors=[Author(id=1177977365805281975, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=hujq@cup.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1177977365893362362, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, authorId=1177977365805281975, language=EN, stringName=Jin-qiu HU, firstName=Jin-qiu, middleName=null, lastName=HU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1 College of Safety and Ocean Engineering, China University of Petroleum (Beijing), Beijing 102249, China
2 Key Laboratory of Oil and Gas Safety and Emergency Technology, Ministry of Emergency Management, Beijing 102249, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1177977365956276923, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, authorId=1177977365805281975, language=CN, stringName=胡瑾秋, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1 中国石油大学(北京)安全与海洋工程学院, 北京 102249
2 应急管理部油气生产安全与应急技术重点实验室, 北京 102249, bio={"content":"

胡瑾秋(1983—),女,汉族,江苏南京人,博士,教授。研究方向:油气生产复杂系统安全预警技术、油气装备监测预警大数据科学与工程。E-mail:

"}, bioImg=null, bioContent=

胡瑾秋(1983—),女,汉族,江苏南京人,博士,教授。研究方向:油气生产复杂系统安全预警技术、油气装备监测预警大数据科学与工程。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1177977365499097773, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, xref=1, ext=[AuthorCompanyExt(id=1177977365507486382, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, companyId=1177977365499097773, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 College of Safety and Ocean Engineering, China University of Petroleum (Beijing), Beijing 102249, China), AuthorCompanyExt(id=1177977365520069295, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, companyId=1177977365499097773, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 中国石油大学(北京)安全与海洋工程学院, 北京 102249)]), AuthorCompany(id=1177977365599761072, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, xref=2, ext=[AuthorCompanyExt(id=1177977365612343985, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, companyId=1177977365599761072, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 Key Laboratory of Oil and Gas Safety and Emergency Technology, Ministry of Emergency Management, Beijing 102249, China), AuthorCompanyExt(id=1177977365620732594, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, companyId=1177977365599761072, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 应急管理部油气生产安全与应急技术重点实验室, 北京 102249)])]), Author(id=1177977366031774397, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1177977366107271872, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, authorId=1177977366031774397, language=EN, stringName=Lai-bin ZHANG, firstName=Lai-bin, middleName=null, lastName=ZHANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1 College of Safety and Ocean Engineering, China University of Petroleum (Beijing), Beijing 102249, China
2 Key Laboratory of Oil and Gas Safety and Emergency Technology, Ministry of Emergency Management, Beijing 102249, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1177977366178575041, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, authorId=1177977366031774397, language=CN, stringName=张来斌, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1 中国石油大学(北京)安全与海洋工程学院, 北京 102249
2 应急管理部油气生产安全与应急技术重点实验室, 北京 102249, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1177977365499097773, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, xref=1, ext=[AuthorCompanyExt(id=1177977365507486382, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, companyId=1177977365499097773, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 College of Safety and Ocean Engineering, China University of Petroleum (Beijing), Beijing 102249, China), AuthorCompanyExt(id=1177977365520069295, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, companyId=1177977365499097773, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 中国石油大学(北京)安全与海洋工程学院, 北京 102249)]), AuthorCompany(id=1177977365599761072, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, xref=2, ext=[AuthorCompanyExt(id=1177977365612343985, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, companyId=1177977365599761072, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 Key Laboratory of Oil and Gas Safety and Emergency Technology, Ministry of Emergency Management, Beijing 102249, China), AuthorCompanyExt(id=1177977365620732594, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, companyId=1177977365599761072, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 应急管理部油气生产安全与应急技术重点实验室, 北京 102249)])]), Author(id=1177977366237295299, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=hyb819819@163.com, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1177977366308598470, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, authorId=1177977366237295299, language=EN, stringName=Yang-bai HU, firstName=Yang-bai, middleName=null, lastName=HU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, *, address=1 College of Safety and Ocean Engineering, China University of Petroleum (Beijing), Beijing 102249, China
2 Key Laboratory of Oil and Gas Safety and Emergency Technology, Ministry of Emergency Management, Beijing 102249, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1177977366367318727, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, authorId=1177977366237295299, language=CN, stringName=胡洋柏, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, *, address=1 中国石油大学(北京)安全与海洋工程学院, 北京 102249
2 应急管理部油气生产安全与应急技术重点实验室, 北京 102249, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1177977365499097773, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, xref=1, ext=[AuthorCompanyExt(id=1177977365507486382, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, companyId=1177977365499097773, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 College of Safety and Ocean Engineering, China University of Petroleum (Beijing), Beijing 102249, China), AuthorCompanyExt(id=1177977365520069295, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, companyId=1177977365499097773, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 中国石油大学(北京)安全与海洋工程学院, 北京 102249)]), AuthorCompany(id=1177977365599761072, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, xref=2, ext=[AuthorCompanyExt(id=1177977365612343985, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, companyId=1177977365599761072, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 Key Laboratory of Oil and Gas Safety and Emergency Technology, Ministry of Emergency Management, Beijing 102249, China), AuthorCompanyExt(id=1177977365620732594, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, companyId=1177977365599761072, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 应急管理部油气生产安全与应急技术重点实验室, 北京 102249)])]), Author(id=1177977366430233289, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1177977366509925067, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, authorId=1177977366430233289, language=EN, stringName=Sheng-li CHU, firstName=Sheng-li, middleName=null, lastName=CHU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3 CNPC Research Institute of Safety & Environment Technology, Beijing 102206, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1177977366577033932, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, authorId=1177977366430233289, language=CN, stringName=储胜利, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3 中国石油集团安全环保技术研究院有限公司, 北京 102206, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1177977365717201587, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, xref=3, ext=[AuthorCompanyExt(id=1177977365725590196, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, companyId=1177977365717201587, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 CNPC Research Institute of Safety & Environment Technology, Beijing 102206, China), AuthorCompanyExt(id=1177977365733978805, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, companyId=1177977365717201587, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 中国石油集团安全环保技术研究院有限公司, 北京 102206)])]), Author(id=1177977366644142798, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, orderNo=4, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1177977366715445968, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, authorId=1177977366644142798, language=EN, stringName=Bing-cai SUN, firstName=Bing-cai, middleName=null, lastName=SUN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3 CNPC Research Institute of Safety & Environment Technology, Beijing 102206, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1177977366837080785, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, authorId=1177977366644142798, language=CN, stringName=孙秉才, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3 中国石油集团安全环保技术研究院有限公司, 北京 102206, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1177977365717201587, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, xref=3, ext=[AuthorCompanyExt(id=1177977365725590196, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, companyId=1177977365717201587, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 CNPC Research Institute of Safety & Environment Technology, Beijing 102206, China), AuthorCompanyExt(id=1177977365733978805, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, companyId=1177977365717201587, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 中国石油集团安全环保技术研究院有限公司, 北京 102206)])]), Author(id=1177977366908383955, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, orderNo=5, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1177977366992270038, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, authorId=1177977366908383955, language=EN, stringName=Ze-sen LI, firstName=Ze-sen, middleName=null, lastName=LI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1 College of Safety and Ocean Engineering, China University of Petroleum (Beijing), Beijing 102249, China
2 Key Laboratory of Oil and Gas Safety and Emergency Technology, Ministry of Emergency Management, Beijing 102249, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1177977367059378903, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, authorId=1177977366908383955, language=CN, stringName=黎泽森, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1 中国石油大学(北京)安全与海洋工程学院, 北京 102249
2 应急管理部油气生产安全与应急技术重点实验室, 北京 102249, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1177977365499097773, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, xref=1, ext=[AuthorCompanyExt(id=1177977365507486382, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, companyId=1177977365499097773, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 College of Safety and Ocean Engineering, China University of Petroleum (Beijing), Beijing 102249, China), AuthorCompanyExt(id=1177977365520069295, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, companyId=1177977365499097773, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 中国石油大学(北京)安全与海洋工程学院, 北京 102249)]), AuthorCompany(id=1177977365599761072, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, xref=2, ext=[AuthorCompanyExt(id=1177977365612343985, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, companyId=1177977365599761072, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 Key Laboratory of Oil and Gas Safety and Emergency Technology, Ministry of Emergency Management, Beijing 102249, China), AuthorCompanyExt(id=1177977365620732594, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, companyId=1177977365599761072, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 应急管理部油气生产安全与应急技术重点实验室, 北京 102249)])])], keywords=[Keyword(id=1177977367222956760, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, language=EN, orderNo=1, keyword=oil and gas drilling and extraction well sites), Keyword(id=1177977367311037145, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, language=EN, orderNo=2, keyword=safety hazards), Keyword(id=1177977367378146010, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, language=EN, orderNo=3, keyword=image recognition), Keyword(id=1177977367432671963, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, language=EN, orderNo=4, keyword=YOLOv5), Keyword(id=1177977367508169436, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, language=CN, orderNo=1, keyword=油气钻采井场), Keyword(id=1177977367592055517, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, language=CN, orderNo=2, keyword=安全隐患), Keyword(id=1177977367642387166, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, language=CN, orderNo=3, keyword=图像识别), Keyword(id=1177977367696913119, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, language=CN, orderNo=4, keyword=YOLOv5)], refs=[Reference(id=1177977369890534140, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, doi=null, pmid=null, pmcid=null, year=2024, volume=31, issue=4, pageStart=296, pageEnd=298, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=卢宁, journalName=石化技术, refType=null, unstructuredReference=卢宁. 油气储运中的安全隐患及防范策略分析[J]. 石化技术, 2024, 31(4): 296-298., articleTitle=油气储运中的安全隐患及防范策略分析, refAbstract=null), Reference(id=1177977369953448701, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, doi=null, pmid=null, pmcid=null, year=2024, volume=31, issue=4, pageStart=296, pageEnd=298, url=null, language=null, rfNumber=[1], rfOrder=1, authorNames=Lu Ning, journalName=Petrochemical Technology, refType=null, unstructuredReference=Lu Ning. Analysis of safety hazards and prevention strategies in oil and gas storage and transportation[J]. Petrochemical Technology, 2024, 31(4): 296-298., articleTitle=Analysis of safety hazards and prevention strategies in oil and gas storage and transportation, refAbstract=null), Reference(id=1177977370007974654, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, doi=null, pmid=null, pmcid=null, year=2024, volume=null, issue=4, pageStart=115, pageEnd=117, url=null, language=null, rfNumber=[2], rfOrder=2, authorNames=胡庆勇, 杜超, 李宝成, journalName=化工管理, refType=null, unstructuredReference=胡庆勇, 杜超, 李宝成, 等. 钻井作业安全隐患分类量化管理[J]. 化工管理, 2024(4): 115-117., articleTitle=钻井作业安全隐患分类量化管理, refAbstract=null), Reference(id=1177977370066694911, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, doi=null, pmid=null, pmcid=null, year=2024, volume=null, issue=4, pageStart=115, pageEnd=117, url=null, language=null, rfNumber=[2], rfOrder=3, authorNames=Hu Qingyong, Du Chao, Li Baocheng, journalName=Chemical Engineering Management, refType=null, unstructuredReference=Hu Qingyong, Du Chao, Li Baocheng, et al. Classification and quantitative management of drilling operation safety hazards[J]. Chemical Engineering Management, 2024(4): 115-117., articleTitle=Classification and quantitative management of drilling operation safety hazards, refAbstract=null), Reference(id=1177977370129609472, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, doi=null, pmid=null, pmcid=null, year=2024, volume=47, issue=4, pageStart=143, pageEnd=147, url=null, language=null, rfNumber=[3], rfOrder=4, authorNames=唐强, journalName=现代电子技术, refType=null, unstructuredReference=唐强. 基于关键区域特征匹配的生产现场隐患识别方法[J]. 现代电子技术, 2024, 47(4): 143-147., articleTitle=基于关键区域特征匹配的生产现场隐患识别方法, refAbstract=null), Reference(id=1177977370192524033, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, doi=null, pmid=null, pmcid=null, year=2024, volume=47, issue=4, pageStart=143, pageEnd=147, url=null, language=null, rfNumber=[3], rfOrder=5, authorNames=Tang Qiang, journalName=Modern Electronics Technique, refType=null, unstructuredReference=Tang Qiang. Hidden danger identification method of production site based on key region feature matching[J]. Modern Electronics Technique, 2024, 47(4): 143-147., articleTitle=Hidden danger identification method of production site based on key region feature matching, refAbstract=null), Reference(id=1177977370263827202, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[4], rfOrder=6, authorNames=刘慧舟, journalName=基于机器视觉的安全隐患识别方法及其在油气站场的应用研究, refType=null, unstructuredReference=刘慧舟. 基于机器视觉的安全隐患识别方法及其在油气站场的应用研究[D]. 北京: 中国石油大学(北京), 2022., articleTitle=null, refAbstract=null), Reference(id=1177977370322547459, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[4], rfOrder=7, authorNames=Liu Huizhou, journalName=Research on recognition method of safety hazards based on machine vision and its application in oil and gas stations, refType=null, unstructuredReference=Liu Huizhou. Research on recognition method of safety hazards based on machine vision and its application in oil and gas stations[D]. Beijing: China University of Petroleum(Beijing), 2022., articleTitle=null, refAbstract=null), Reference(id=1177977370385462020, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[5], rfOrder=8, authorNames=黄丹, journalName=基于改进的Apriori算法在钻井作业事故隐患识别中的研究, refType=null, unstructuredReference=黄丹. 基于改进的Apriori算法在钻井作业事故隐患识别中的研究[D]. 成都: 西南石油大学, 2020., articleTitle=null, refAbstract=null), Reference(id=1177977370465153797, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[5], rfOrder=9, authorNames=Huang Dan, journalName=Research on improved apriori algorithm based on the identification of accidental hazards in drilling operations, refType=null, unstructuredReference=Huang Dan. Research on improved apriori algorithm based on the identification of accidental hazards in drilling operations[D]. Chengdu: Southwest Petroleum University, 2020., articleTitle=null, refAbstract=null), Reference(id=1177977370528068358, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, doi=null, pmid=null, pmcid=null, year=2023, volume=37, issue=3, pageStart=120, pageEnd=124, url=null, language=null, rfNumber=[6], rfOrder=10, authorNames=肖天龙, 宫培松, 郭聖煜, journalName=工程管理学报, refType=null, unstructuredReference=肖天龙, 宫培松, 郭聖煜, 等. 基于机器视觉的施工现场安全隐患识别应用研究[J]. 工程管理学报, 2023, 37(3): 120-124., articleTitle=基于机器视觉的施工现场安全隐患识别应用研究, refAbstract=null), Reference(id=1177977370607760135, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, doi=null, pmid=null, pmcid=null, year=2023, volume=37, issue=3, pageStart=120, pageEnd=124, url=null, language=null, rfNumber=[6], rfOrder=11, authorNames=Xiao Tianlong, Gong Peisong, Guo Shengyu, journalName=Journal of Engineering Managemen, refType=null, unstructuredReference=Xiao Tianlong, Gong Peisong, Guo Shengyu, et al. Research on the application of construction site safety hazard identification based on the machine vision[J]. Journal of Engineering Managemen, 2023, 37(3): 120-124., articleTitle=Research on the application of construction site safety hazard identification based on the machine vision, refAbstract=null), Reference(id=1177977370683257608, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, doi=null, pmid=null, pmcid=null, year=2024, volume=40, issue=3, pageStart=58, pageEnd=63, url=null, language=null, rfNumber=[7], rfOrder=12, authorNames=程国建, 李嘉欣, 贾强, journalName=石油工业技术监督, refType=null, unstructuredReference=程国建, 李嘉欣, 贾强. 基于改进YOLOv5的井场作业风险智能识别与分类[J]. 石油工业技术监督, 2024, 40(3): 58-63., articleTitle=基于改进YOLOv5的井场作业风险智能识别与分类, refAbstract=null), Reference(id=1177977370754560777, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, doi=null, pmid=null, pmcid=null, year=2024, volume=40, issue=3, pageStart=58, pageEnd=63, url=null, language=null, rfNumber=[7], rfOrder=13, authorNames=Cheng Guojian, Li Jiaxin, Jia Qiang, journalName=Technology Supervision in Petroleum Industry, refType=null, unstructuredReference=Cheng Guojian, Li Jiaxin, Jia Qiang. Intelligent identification and classification of wellsite operation risk based on improved YOLOv5[J]. Technology Supervision in Petroleum Industry, 2024, 40(3): 58-63., articleTitle=Intelligent identification and classification of wellsite operation risk based on improved YOLOv5, refAbstract=null), Reference(id=1177977370842641162, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, doi=null, pmid=null, pmcid=null, year=2023, volume=33, issue=10, pageStart=16, pageEnd=22, url=null, language=null, rfNumber=[8], rfOrder=14, 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=1177977370922332939, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, doi=null, pmid=null, pmcid=null, year=2023, volume=33, issue=10, pageStart=16, pageEnd=22, url=null, language=null, rfNumber=[8], rfOrder=15, authorNames=Wang Jinjiang, Guan Pengting, Chen Zhuo, journalName=China Safety Science Journal, refType=null, unstructuredReference=Wang Jinjiang, Guan Pengting, Chen Zhuo, et al. Intelligent warning of risk during maintenance operations based on deep learning[J]. China Safety Science Journal, 2023, 33(10): 16-22., articleTitle=Intelligent warning of risk during maintenance operations based on deep learning, refAbstract=null), Reference(id=1177977371056550668, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, doi=null, pmid=null, pmcid=null, year=2021, volume=45, issue=1, pageStart=158, pageEnd=166, url=null, language=null, rfNumber=[9], rfOrder=16, authorNames=刘慧舟, 胡瑾秋, 张来斌, journalName=中国石油大学学报(自然科学版), refType=null, unstructuredReference=刘慧舟, 胡瑾秋, 张来斌, 等. 基于红外热成像与CNN的压裂装备故障精准识别及预警[J]. 中国石油大学学报(自然科学版), 2021, 45(1): 158-166., articleTitle=基于红外热成像与CNN的压裂装备故障精准识别及预警, refAbstract=null), Reference(id=1177977371127853837, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, doi=null, pmid=null, pmcid=null, year=2021, volume=45, issue=1, pageStart=158, pageEnd=166, url=null, language=null, rfNumber=[9], rfOrder=17, authorNames=Liu Huizhou, Hu Jinqiu, Zhang Laibin, journalName=Journal of China University of Petroleum(Edition of Natural Science), refType=null, unstructuredReference=Liu Huizhou, Hu Jinqiu, Zhang Laibin, et al. Accurate identification and early-warning of faults of fracturing equipments based on infrared thermal imaging and convolutional neural network[J]. Journal of China University of Petroleum(Edition of Natural Science), 2021, 45(1): 158-166., articleTitle=Accurate identification and early-warning of faults of fracturing equipments based on infrared thermal imaging and convolutional neural network, refAbstract=null), Reference(id=1177977371190768398, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, doi=null, pmid=null, pmcid=null, year=2023, volume=45, issue=6, pageStart=10, pageEnd=20, url=null, language=null, rfNumber=[10], rfOrder=18, authorNames=郭庆梅, 刘宁波, 王中训, journalName=探测与控制学报, refType=null, unstructuredReference=郭庆梅, 刘宁波, 王中训, 等. 基于深度学习的目标检测算法综述[J]. 探测与控制学报, 2023, 45(6): 10-20, 26., articleTitle=基于深度学习的目标检测算法综述, refAbstract=null), Reference(id=1177977371266265871, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, doi=null, pmid=null, pmcid=null, year=2023, volume=45, issue=6, pageStart=10, pageEnd=20, url=null, language=null, rfNumber=[10], rfOrder=19, authorNames=Guo Qingmei, Liu Ningbo, Wang Zhongxun, journalName=Journal of Detection & Control, refType=null, unstructuredReference=Guo Qingmei, Liu Ningbo, Wang Zhongxun, et al. Review of deep learning based object detection algorithms[J]. Journal of Detection & Control, 2023, 45(6): 10-20, 26., articleTitle=Review of deep learning based object detection algorithms, refAbstract=null), Reference(id=1177977371337569040, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, doi=null, pmid=null, pmcid=null, year=2023, volume=2, issue=1, pageStart=1, pageEnd=12, url=null, language=null, rfNumber=[11], rfOrder=20, authorNames=Olorunshola O E, Irhebhude M E, Evwiekpaefe A E, journalName=Journal of Computing and Social Informatics, refType=null, unstructuredReference=Olorunshola O E, Irhebhude M E, Evwiekpaefe A E. A comparative study of YOLOv5 and YOLOv7 object detection algorithms[J]. Journal of Computing and Social Informatics, 2023, 2(1): 1-12., articleTitle=A comparative study of YOLOv5 and YOLOv7 object detection algorithms, refAbstract=null), Reference(id=1177977371400483601, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, doi=null, pmid=null, pmcid=null, year=2021, volume=null, issue=null, pageStart=null, pageEnd=null, url=https://www.xueshufan.com/publication/3166716987, language=null, rfNumber=[12], rfOrder=21, authorNames=Yang L X, Zhang R Y, Li L D, journalName=International Conference on Machine Learning, refType=null, unstructuredReference=Yang L X, Zhang R Y, Li L D, et al. SimAM: a simple, parameter-free attention module for convolutional neural networks[C]// International Conference on Machine Learning. Huston: PMLR, 2021: https://www.xueshufan.com/publication/3166716987., articleTitle=SimAM: a simple, parameter-free attention module for convolutional neural networks, refAbstract=null), Reference(id=1177977371467592466, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, doi=null, pmid=null, pmcid=null, year=2023, volume=13, issue=21, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[13], rfOrder=22, authorNames=Cai Z Y, Qiao X Y, Zhang J W, journalName=Applied Sciences, refType=null, unstructuredReference=Cai Z Y, Qiao X Y, Zhang J W, et al. RepVGG-SimAM: an efficient bad image classification method based on repVGG with simple parameter-free attention module[J]. Applied Sciences, 2023, 13(21): DOI: 10.3390/app132111925., articleTitle=RepVGG-SimAM: an efficient bad image classification method based on repVGG with simple parameter-free attention module, refAbstract=null), Reference(id=1177977371538895635, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, doi=null, pmid=null, pmcid=null, year=2023, volume=54, issue=1, pageStart=88, pageEnd=96, url=null, language=null, rfNumber=[14], rfOrder=23, authorNames=耿艳利, 林彦伯, 付艳芳, journalName=东北农业大学学报, refType=null, unstructuredReference=耿艳利, 林彦伯, 付艳芳, 等. 基于Transformer与自适应空间特征融合的群猪目标检测算法研究[J]. 东北农业大学学报, 2023, 54(1): 88-96., articleTitle=基于Transformer与自适应空间特征融合的群猪目标检测算法研究, refAbstract=null), Reference(id=1177977371606004500, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, doi=null, pmid=null, pmcid=null, year=2023, volume=54, issue=1, pageStart=88, pageEnd=96, url=null, language=null, rfNumber=[14], rfOrder=24, authorNames=Geng Yanli, Lin Yanbo, Fu Yanfang, journalName=Journal of Northeast Agricultural University, refType=null, unstructuredReference=Geng Yanli, Lin Yanbo, Fu Yanfang, et al. Study on pigs target detection algorithm based on Transformer and adaptively spatial feature fusion[J]. Journal of Northeast Agricultural University, 2023, 54(1): 88-96., articleTitle=Study on pigs target detection algorithm based on Transformer and adaptively spatial feature fusion, refAbstract=null), Reference(id=1177977371664724757, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=null, pageStart=1056, pageEnd=null, url=null, language=null, rfNumber=[15], rfOrder=25, authorNames=Wen G, Shuang Q, Chenvi Z, journalName=Nuclear Inst and Methods in Physics Research A, refType=null, unstructuredReference=Wen G, Shuang Q, Chenvi Z, et al. Defect detection for industrial neutron radiographic images based on modified YOLO network[J]. Nuclear Inst and Methods in Physics Research A, 2023, 1056: DOI: 10.1016/j.nima.2023.168694., articleTitle=Defect detection for industrial neutron radiographic images based on modified YOLO network, refAbstract=null), Reference(id=1177977371731833622, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=24, pageStart=237, pageEnd=238, url=null, language=null, rfNumber=[16], rfOrder=26, authorNames=王雨辰, journalName=电子技术与软件工程, refType=null, unstructuredReference=王雨辰. 基于增强现实技术的电力设备故障识别方法研究[J]. 电子技术与软件工程, 2020(24): 237-238., articleTitle=基于增强现实技术的电力设备故障识别方法研究, refAbstract=null), Reference(id=1177977371786359575, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=24, pageStart=237, pageEnd=238, url=null, language=null, rfNumber=[16], rfOrder=27, authorNames=Wang Yuchen, journalName=Electronic Technology & Software Engineering, refType=null, unstructuredReference=Wang Yuchen. Research on fault identification method of electric equipment based on augmented reality technology[J]. Electronic Technology & Software Engineering, 2020(24): 237-238., articleTitle=Research on fault identification method of electric equipment based on augmented reality technology, refAbstract=null)], funds=[Fund(id=1177977369672430330, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, awardId=52074323, language=CN, fundingSource=国家自然科学基金面上项目(52074323), fundOrder=null, country=null), Fund(id=1177977369739539195, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, awardId=52234007, language=CN, fundingSource=国家自然科学基金重点项目(52234007), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1177977365499097773, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, xref=1, ext=[AuthorCompanyExt(id=1177977365507486382, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, companyId=1177977365499097773, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 College of Safety and Ocean Engineering, China University of Petroleum (Beijing), Beijing 102249, China), AuthorCompanyExt(id=1177977365520069295, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, companyId=1177977365499097773, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 中国石油大学(北京)安全与海洋工程学院, 北京 102249)]), AuthorCompany(id=1177977365599761072, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, xref=2, ext=[AuthorCompanyExt(id=1177977365612343985, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, companyId=1177977365599761072, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 Key Laboratory of Oil and Gas Safety and Emergency Technology, Ministry of Emergency Management, Beijing 102249, China), AuthorCompanyExt(id=1177977365620732594, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, companyId=1177977365599761072, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 应急管理部油气生产安全与应急技术重点实验室, 北京 102249)]), AuthorCompany(id=1177977365717201587, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, xref=3, ext=[AuthorCompanyExt(id=1177977365725590196, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, companyId=1177977365717201587, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 CNPC Research Institute of Safety & Environment Technology, Beijing 102206, China), AuthorCompanyExt(id=1177977365733978805, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, companyId=1177977365717201587, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 中国石油集团安全环保技术研究院有限公司, 北京 102206)])], figs=[ArticleFig(id=1177977367860490976, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, language=EN, label=Fig.1, caption=Diagram of YOLOv5 network structure, figureFileSmall=JbXmS6xIJpRQho6y0Y6oWw==, figureFileBig=qDWcr6HYkcECVeglxcLg6Q==, tableContent=null), ArticleFig(id=1177977367935988449, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, language=CN, label=图1, caption=YOLOv5网络结构图, figureFileSmall=JbXmS6xIJpRQho6y0Y6oWw==, figureFileBig=qDWcr6HYkcECVeglxcLg6Q==, tableContent=null), ArticleFig(id=1177977368011485922, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, language=EN, label=Fig.2, caption=SimAM attention mechanism structure, figureFileSmall=WyKCeWKyWxfGjPM/Krjttg==, figureFileBig=VLWkDWLCZcO/nxNyUxsblA==, tableContent=null), ArticleFig(id=1177977368074400483, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, language=CN, label=图2, caption=SimAM注意力机制结构

C为维度;W为宽度;H为高度

, figureFileSmall=WyKCeWKyWxfGjPM/Krjttg==, figureFileBig=VLWkDWLCZcO/nxNyUxsblA==, tableContent=null), ArticleFig(id=1177977368137315044, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, language=EN, label=Fig.3, caption=Adaptive fusion feature ASFF structure, figureFileSmall=ASzqELW37nFMgwpDqpSkvQ==, figureFileBig=dL86vtZ4Z4UVeKwJoYdzEg==, tableContent=null), ArticleFig(id=1177977368191840997, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, language=CN, label=图3, caption=自适应融合特征ASFF结构, figureFileSmall=ASzqELW37nFMgwpDqpSkvQ==, figureFileBig=dL86vtZ4Z4UVeKwJoYdzEg==, tableContent=null), ArticleFig(id=1177977368242172646, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, language=EN, label=Fig.4, caption=Structure of the improved YOLOv5 network, figureFileSmall=dIEuVjrh57ajWB+J+dt15A==, figureFileBig=oxd3BI/BYUD/zVTJ2wyy1A==, tableContent=null), ArticleFig(id=1177977368300892903, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, language=CN, label=图4, caption=改进后YOLOv5网络结构图, figureFileSmall=dIEuVjrh57ajWB+J+dt15A==, figureFileBig=oxd3BI/BYUD/zVTJ2wyy1A==, tableContent=null), ArticleFig(id=1177977368355418856, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, language=EN, label=Fig.5, caption=Flowchart for identifying safety hazards at oil and gas drilling and production well sites, figureFileSmall=Gq9Ty3DPmBKbR4iU0LA+LQ==, figureFileBig=sQBwePqnJEfXNrSMNYZnbg==, tableContent=null), ArticleFig(id=1177977368414139113, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, language=CN, label=图5, caption=油气钻采井场安全隐患识别流程图, figureFileSmall=Gq9Ty3DPmBKbR4iU0LA+LQ==, figureFileBig=sQBwePqnJEfXNrSMNYZnbg==, tableContent=null), ArticleFig(id=1177977368514802410, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, language=EN, label=Fig.6, caption=Wellsite corrosion data acquisition and pre-processing flow, figureFileSmall=oGD99TP4uKcipJaYv+91QA==, figureFileBig=UY7UisbUBhgXFhePUP4/WQ==, tableContent=null), ArticleFig(id=1177977368577716971, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, language=CN, label=图6, caption=井场腐蚀数据采集及预处理流程, figureFileSmall=oGD99TP4uKcipJaYv+91QA==, figureFileBig=UY7UisbUBhgXFhePUP4/WQ==, tableContent=null), ArticleFig(id=1177977368632242924, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, language=EN, label=Fig.7, caption=Improved YOLOv5 model training loss values, figureFileSmall=PhLhJHLMwGjPh+hNk1ul1A==, figureFileBig=FQEkXroc/0mEGsxNe7rwOw==, tableContent=null), ArticleFig(id=1177977368686768877, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, language=CN, label=图7, caption=改进YOLOv5模型训练损失值, figureFileSmall=PhLhJHLMwGjPh+hNk1ul1A==, figureFileBig=FQEkXroc/0mEGsxNe7rwOw==, tableContent=null), ArticleFig(id=1177977368745489134, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, language=EN, label=Fig.8, caption=Wellsite corrosion identification results, figureFileSmall=GLDstRpYqx7bD8rW3g8Bkw==, figureFileBig=aXs8UZz6DhFHfhzCKS+X7Q==, tableContent=null), ArticleFig(id=1177977368804209391, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, language=CN, label=图8, caption=井场腐蚀识别结果

Corrode为腐蚀

, figureFileSmall=GLDstRpYqx7bD8rW3g8Bkw==, figureFileBig=aXs8UZz6DhFHfhzCKS+X7Q==, tableContent=null), ArticleFig(id=1177977368867123952, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, language=EN, label=Fig.9, caption=Corrosion identification results for different modelled well sites, figureFileSmall=IChn/KtWEuJ7paRxkutUwQ==, figureFileBig=5kYyFQtsArTvu4pggB2nHw==, tableContent=null), ArticleFig(id=1177977368930038513, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, language=CN, label=图9, caption=不同模型井场腐蚀识别结果

Corrode为腐蚀

, figureFileSmall=IChn/KtWEuJ7paRxkutUwQ==, figureFileBig=5kYyFQtsArTvu4pggB2nHw==, tableContent=null), ArticleFig(id=1177977369013924594, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, language=EN, label=Fig.10, caption=Architecture of the oil and gas drilling and production well site safety hazard identification system, figureFileSmall=70SK1LWkT3fupRIP9hziJA==, figureFileBig=2EzIjgqVM56i1eAeC474zg==, tableContent=null), ArticleFig(id=1177977369097810675, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, language=CN, label=图10, caption=油气钻采井场安全隐患识别系统架构图, figureFileSmall=70SK1LWkT3fupRIP9hziJA==, figureFileBig=2EzIjgqVM56i1eAeC474zg==, tableContent=null), ArticleFig(id=1177977369160725236, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, language=EN, label=Fig.11, caption=Flowchart of the wearable device identifying safety hazards and displaying information about the hazards, figureFileSmall=YUT72KKBlsJoY8HTs55Apw==, figureFileBig=wGSmijQfvBZNHOGyLkRGiA==, tableContent=null), ArticleFig(id=1177977369223639797, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, language=CN, label=图11, caption=穿戴设备识别安全隐患并显示隐患信息流程图, figureFileSmall=YUT72KKBlsJoY8HTs55Apw==, figureFileBig=wGSmijQfvBZNHOGyLkRGiA==, tableContent=null), ArticleFig(id=1177977369299137270, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, language=EN, label=Fig.12, caption=Wearable device to identify wellsite corrosion and information display, figureFileSmall=Ns2IfwENjQMwctvXdDNvFg==, figureFileBig=J7e5Zg3qVmio4fupXjbijw==, tableContent=null), ArticleFig(id=1177977369378829047, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, language=CN, label=图12, caption=穿戴设备识别井场腐蚀及信息显示, figureFileSmall=Ns2IfwENjQMwctvXdDNvFg==, figureFileBig=J7e5Zg3qVmio4fupXjbijw==, tableContent=null), ArticleFig(id=1177977369466909432, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, language=EN, label=Table 1, caption=

Indicators for evaluating the recognition effect of different models

, figureFileSmall=null, figureFileBig=null, tableContent=
网络模型 P/% R/% mAP@0.5/%
YOLOv5s 80.7 81.2 82.0
YOLOv5s-ASFF 87.4 86.7 86.8
YOLOv5s-ECA-ASFF 93.3 86.8 84.9
本文模型 93.4 93.8 92.4
), ArticleFig(id=1177977369546601209, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789605853094502, language=CN, label=表1, caption=

不同模型识别效果评价指标

, figureFileSmall=null, figureFileBig=null, tableContent=
网络模型 P/% R/% mAP@0.5/%
YOLOv5s 80.7 81.2 82.0
YOLOv5s-ASFF 87.4 86.7 86.8
YOLOv5s-ECA-ASFF 93.3 86.8 84.9
本文模型 93.4 93.8 92.4
)], attaches=null, journal=Journal(id=1146119176004939786, delFlag=0, nameCn=科学技术与工程, nameEn=Science Technology and Engineering, nameHistory1=null, nameHistory2=null, issn=1671-1815, eissn=, cn=11-4688/T, coden=null, periodic=4, language=CN, oaType=是, 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=UKU/O7GSka5polgCTkbIIw==, journalPrice=null, startedYear=null, abbrevIsoEn=Sci Technol Eng, journalRemark=null, publicationField=null, createdTime=null, updatedTime=1754445529766, createdBy=null, updatedBy=13701087609, firstLetterCn=S, firstLetterEn=S, subjectCode=Natural Sciences, subjectName=自然科学, subjectCodeEn=Natural Sciences, subjectNameEn=null, picCn=UKU/O7GSka5polgCTkbIIw==, picEn=5hwlULoNwcbj3xUmVi9MAQ==, jcr=null, cjcr=null, exts=[JournalExt(id=1159791870395564357, language=CN, name=科学技术与工程, 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.stae.com.cn/jsygc/home, createdTime=1754445529793, updatedTime=1754445529793, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=http://www.stae.com.cn/jsygc/site/menus/20090429150146001, submissionAuthorUrl=http://www.stae.com.cn/jsygc/author/login, submissionEditorUrl=http://www.stae.com.cn/jsygc/editor/login, submissionReviewUrl=http://www.stae.com.cn/jsygc/reviewer/login, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1159791870441701702, language=EN, name=Science Technology and Engineering, 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.stae.com.cn/jsygc/home, createdTime=1754445529804, updatedTime=1754445529804, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=http://www.stae.com.cn/jsygc/author/login, submissionEditorUrl=http://www.stae.com.cn/jsygc/editor/login, submissionReviewUrl=http://www.stae.com.cn/jsygc/reviewer/login, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1146123166801305609, websiteList=[Website(id=1148243202391400884, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146123166801305609, 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/kxjsygc/CN, language=CN, createTime=1751692112777, createBy=18614031015, updateTime=1753520965431, updateBy=18614031015, name=科学技术与工程-中文站点, tplId=1146099689490845704, title=科学技术与工程, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1148622798802673703, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=articleTextType, value=kx, createTime=1751782615614, updateTime=1751782615614, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622798781702180, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=banner, value=null, createTime=1751782615609, updateTime=1751782615609, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622798769119267, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=j86gbwi+p0Idkyl5SzIlmQ==, createTime=1751782615606, updateTime=1751782615606, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622798794285094, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1751782615612, updateTime=1751782615612, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622798790090789, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1751782615611, updateTime=1751782615611, creator=18614031015, updator=18614031015)]), Website(id=1155914124811976731, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146123166801305609, 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/kxjsygc/EN, language=EN, createTime=1753521003206, createBy=18614031015, updateTime=1753521003206, updateBy=18614031015, name=科学技术与工程-英文站点, tplId=1146101810881728533, title=Science Technology and Engineering, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1155914371227308235, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=articleTextType, value=kx, createTime=1753521061952, updateTime=1753521061952, creator=18614031015, updator=18614031015), WebsiteProps(id=1155914371210531016, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=banner, value=null, createTime=1753521061947, updateTime=1753521061947, creator=18614031015, updator=18614031015), WebsiteProps(id=1155914371202142407, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=j86gbwi+p0Idkyl5SzIlmQ==, createTime=1753521061945, updateTime=1753521061945, creator=18614031015, updator=18614031015), WebsiteProps(id=1155914371223113930, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1753521061950, updateTime=1753521061950, creator=18614031015, updator=18614031015), WebsiteProps(id=1155914371218919625, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1753521061949, updateTime=1753521061949, creator=18614031015, updator=18614031015)])], journalTitle=科学技术与工程, weixinUrl=null, journalUrl=null, iacademicId=null, status=0, seqNo=null, journalTitleEn=Science Technology and Engineering, journalPhotoCn=UKU/O7GSka5polgCTkbIIw==, journalPhotoEn=5hwlULoNwcbj3xUmVi9MAQ==, journalFirstLetter=S, journalRecommend=null, journalNew=null, journalCollection=null, 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/kxjsygc/CN/10.12404/j.issn.1671-1815.2406188, detailUrlEn=https://castjournals.cast.org.cn/joweb/kxjsygc/EN/10.12404/j.issn.1671-1815.2406188, pdfUrlCn=https://castjournals.cast.org.cn/joweb/kxjsygc/CN/PDF/10.12404/j.issn.1671-1815.2406188, pdfUrlEn=https://castjournals.cast.org.cn/joweb/kxjsygc/EN/PDF/10.12404/j.issn.1671-1815.2406188, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于YOLOv5s-SimAM-ASFF的油气钻采井场安全隐患识别及智能穿戴设备研发
收藏切换
PDF下载
胡瑾秋 1, 2 , 张来斌 1, 2 , 胡洋柏 1, 2, * , 储胜利 3 , 孙秉才 3 , 黎泽森 1, 2
科学技术与工程 | 论文·环境科学、安全科学 2025,25(16): 7004-7012
收起
收藏切换
科学技术与工程 | 论文·环境科学、安全科学 2025, 25(16): 7004-7012
基于YOLOv5s-SimAM-ASFF的油气钻采井场安全隐患识别及智能穿戴设备研发
全屏
胡瑾秋1, 2 , 张来斌1, 2, 胡洋柏1, 2, * , 储胜利3, 孙秉才3, 黎泽森1, 2
作者信息
  • 1 中国石油大学(北京)安全与海洋工程学院, 北京 102249
  • 2 应急管理部油气生产安全与应急技术重点实验室, 北京 102249
  • 3 中国石油集团安全环保技术研究院有限公司, 北京 102206
  • 胡瑾秋(1983—),女,汉族,江苏南京人,博士,教授。研究方向:油气生产复杂系统安全预警技术、油气装备监测预警大数据科学与工程。E-mail:

通讯作者:

* 胡洋柏(2000—),男,汉族,江西上饶人,硕士研究生。研究方向:油气生产安全。E-mail:
YOLOv5s-SimAM-ASFF-based Oil and Gas Drilling and Production Wellsite Safety Hazard Identification and Smart Wearable Device Development
Jin-qiu HU1, 2 , Lai-bin ZHANG1, 2, Yang-bai HU1, 2, * , Sheng-li CHU3, Bing-cai SUN3, Ze-sen LI1, 2
Affiliations
  • 1 College of Safety and Ocean Engineering, China University of Petroleum (Beijing), Beijing 102249, China
  • 2 Key Laboratory of Oil and Gas Safety and Emergency Technology, Ministry of Emergency Management, Beijing 102249, China
  • 3 CNPC Research Institute of Safety & Environment Technology, Beijing 102206, China
出版时间: 2025-06-08 doi: 10.12404/j.issn.1671-1815.2406188
文章导航
收藏切换

油气钻采井场情况复杂且安全隐患种类多,为提高井场安全隐患识别的精确性,提出一种基于改进YOLOv5的油气钻采井场安全隐患识别方法。首先,为解决图片背景复杂,识别难度加大的问题,在骨干网络引进SimAM注意力机制;其次,为解决隐患类型的尺度差异较大且一张图片中存在多种尺度的问题,用自适应空间特征融合(ASFF)替换原有特征融合方式;最后,通过与其他模型进行比对来验证改进模型的隐患识别效果。结果表明:改进后的YOLOv5模型识别平均精确值提高了10.4%,对油气钻采井场安全隐患具有较好的识别效果。为解决油气钻采井场安全隐患视频监控识别的限制,研发一套智能穿戴设备,有效提高了井场安全隐患识别的便携性。

油气钻采井场  /  安全隐患  /  图像识别  /  YOLOv5

Oil and gas drilling and production wellsites are complex and have many types of potential safety hazards, in order to improve the accuracy of the identification of potential safety hazards in wellsites, an oil and gas drilling and production wellsite potential safety hazard identification method based on improved YOLOv5 was proposed. Firstly, in order to solve the problem that the background of the picture was complex and the recognition difficulty increased, the SimAM attention mechanism was introduced in the backbone network; secondly, in order to solve the problem that the scales of the types of hidden hazards were different and there were multiple scales in one picture, the original feature fusion was replaced by adaptive spatial fusion of features (ASFF). Lastly, the hidden hazard recognition effect of the improved model was validated by comparing the model with other models. The results show that the improved YOLOv5 model improves the average accuracy value of recognition by 10.4%, and has a better recognition effect on the safety hazards of oil and gas drilling and production well sites. In order to solve the limitation of video monitoring and identification of oil and gas drilling and production wellsite safety hazards, a set of intelligent wearable device was developed, which effectively improved the portability of the identification of wellsite safety hazards.

oil and gas drilling and extraction well sites  /  safety hazards  /  image recognition  /  YOLOv5
胡瑾秋, 张来斌, 胡洋柏, 储胜利, 孙秉才, 黎泽森. 基于YOLOv5s-SimAM-ASFF的油气钻采井场安全隐患识别及智能穿戴设备研发. 科学技术与工程, 2025 , 25 (16) : 7004 -7012 . DOI: 10.12404/j.issn.1671-1815.2406188
Jin-qiu HU, Lai-bin ZHANG, Yang-bai HU, Sheng-li CHU, Bing-cai SUN, Ze-sen LI. YOLOv5s-SimAM-ASFF-based Oil and Gas Drilling and Production Wellsite Safety Hazard Identification and Smart Wearable Device Development[J]. Science Technology and Engineering, 2025 , 25 (16) : 7004 -7012 . DOI: 10.12404/j.issn.1671-1815.2406188
油气钻采井场作为高危场景,情况复杂且安全隐患多,需要在事故发生前将安全隐患识别出来并及时整改,保证油气钻采井场能安全、可持续的运行。油气钻采井场存在的安全隐患主要有:一是管道损坏,钻井作业中涉及高压液体或气体,一旦管道或设备泄漏,可能造成严重伤害;二是机械故障,钻井设备和机械可能存在故障风险,导致意外发生;三是人为失误,操作人员的疏忽、疲劳或不当操作可能导致事故发生[1-2]。油气钻采井场安全性面临巨大挑战,急需在油气钻采井场进行安全隐患识别并及时采取相应措施消除安全隐患,确保作业安全。
唐强[3]提出一种基于关键区域特征匹配的生产现场隐患识别方法,可以准确识别出设备老化、操作不规范、物料储存不当等隐患问题。刘慧舟[4]提出一种基于机器视觉的安全隐患识别方法,识别油气站场存在的安全隐患。黄丹[5]提出一种基于改进Apriori算法的隐患识别方法,识别钻井作业事故中的安全隐患。肖天龙等[6]基于机器视觉,以施工现场配电箱的不安全状态为例,实现了对施工现场安全隐患的识别。程国建等[7]提出一种基于改进YOLOv5的井场作业风险智能识别方法,对井场作业中的不规范行为能进行有效的分类和识别。王金江等[8]构建了基于深度学习的智能风险识别模型,有效识别了压缩机检修作业过程中的风险。刘慧舟等[9]提出一种基于红外热成像与卷积神经网络(convolutional neural networks, CNN)的压裂装备故障精准识别方法,有效对压裂装备故障进行了识别。综上可知,油气领域安全隐患识别方法的研究取得了一定的成果,能够对井场现场的安全隐患进行有效的识别,但对井场安全隐患类型尺度差异大等情况还不能有效识别。
油气钻采井场多采用视频监控方式来识别井场的安全隐患,而由于作业现场视频监控摄像头安装数量的限制,容易产生遮挡与监控死角,井场某些区域的安全隐患无法识别,油气钻采井场安全隐患全部、有效、便捷的识别存在一定的不足。
鉴于此,针对油气钻采井场安全隐患复杂、隐患类型尺度差异大等问题,提出一种改进YOLOv5的安全隐患识别方法,进行油气钻采井场的安全隐患识别研究,并针对典型案例验证方法的适用性。针对油气钻采井场安全隐患识别存在的区域限制,并提高井场安全隐患识别的便携性,研发一套油气钻采井场安全隐患识别智能穿戴设备,并在现场应用验证穿戴设备的有效性。
YOLOv5的网络结构分为Input、Backbone、Neck、Prediction,其中,Input层进行图像输入,Backbone层负责特征提取,Neck层完成特征融合Prediction层完成最终的预测[10-11]
(1)输入端(Input)。输入端通过Mosaic数据增强方法,将4张图片进行组合,丰富图像背景。然后通过自适应锚框计算和自适应图片缩放,设定规定边框,将图片缩放成统一尺寸。对输入的图像进行预处理后,可提高目标检测速度。
(2)骨干网络(Backbone)。骨干网络包含Focus结构和CSP(cross-stage-partial-connection)结构,主要是通过切片操作和卷积操作得到采样特征图,通过归一化和激活函数处理后,提取图像特征信息。
(3)特征金字塔(Neck)。特征金字塔采用FPN+PAN的结构,FPN(feature pyramid network)由下至上将丰富的语义特征从深层特征传递给浅层特征,PAN(path aggregation network)则由上至下将细节特征从浅层特征传递给深层特征。对维度较大的特征图进行压缩,通过融合处理后输入到预测网络中。
(4)预测(Prediction)。预测层通过Bounding box损失函数和nms非极大值抑制方法对特征图像的信息进行预测,并进行标记。采用CIOU_Loss做Bounding box的损失函数,可表示为
CIOU-LOSS=1- I O U - D i s t a n c e 2 2 D i s t a n c e C 2 - v 2 ( 1 - I O U ) + v
v= 4 π 2 a r c t a n w g h g - a r c t a n w p h p 2
式中:v为衡量长宽比一致性的参数;wghg分别为真实框的宽和高;wphp分别为预测框的宽和高;$\text {Distance}_{\mathrm{2}^{2}}$为预测框和真实框中心点的距离;$\text {Distance}_{\mathrm{C}^{2}}$为最小外接矩形的对角线距离。
YOLOv5的网络结构图如图1所示。
油气钻采井场设备繁多、环境复杂,在井场现场采集的安全隐患图片背景复杂,加大模型对安全隐患的识别难度。在原有YOLOv5模型中引入注意力机制可提高网络对待检测目标的表达能力,更加聚焦于要识别的区域。故在YOLOv5模型原有的主干网络上加入注意力机制SimAM(a simple parameter-free attention module for convolutional neural networks),提高检测效果。
SimAM是一种基于通道注意力的无参注意力机制,其核心思想是通过计算特征图中每个通道的全局平均池化值,来捕捉通道间的重要信息。然后,将得到的通道注意力权重与原始特征图相乘,从而实现对特征图的加权调整。由于SimAM无需引入额外的参数,因此可以轻松地与现有模型进行融合[12-13]。SimAM注意力机制结构如图2所示。
SimAM注意力机制输出结果为增强后的特征,并通过sigmoid函数来限制每个通道上的能量函数E中可能出现的过大值。计算过程如式(3)~式(6)所示。
x ^=sigmoid 1 EΘX
E= 4 ( σ 2 + λ ) ( t - μ ) 2 + 2 σ + 2 λ
μ= 1 M i = 1 Mxi
σ2= 1 M i = 1 M ( x i - μ ) 2
式中:sigmoid为激活函数;Θ为计算过程;X为输入值;t为输入的特征值;M为输入的特征;μσ2分别为X中每个通道上的均值和方差;xiX中每个通道上的特征值。
金字塔特征表示法FPN是解决目标检测尺度变化挑战的常用方法,但油气钻采井场安全隐患类型多,且每种类型的尺度差异较大,一张图片中存在多种尺度的隐患目标。对于基于FPN的单级检测器来说,不同特征尺度之间的不一致限制其功能的发挥。因此将原有特征融合方式FPN替换为一种新的金字塔特征融合方式,即自适应空间特征融合(adaptively spatial feature fusion,ASFF),提高检测效果。
ASFF学习了在空间上过滤冲突信息以抑制梯度反向传播的时候不一致的方法,从而改善了特征比例的不变性,并且推理开销降低。ASFF简要思想就是:原来的FPN add方式现在变成了add基础上多了一个可学习系数,该参数是自动学习的,可以实现自适应融合效果,类似于全连接参数[14-15]。 ASFF结构如图3所示。
自适应融合特征ASFF是由不同层的特征乘上权重参数α3β3γ3并相加得到,如式(7)所示。
y i j l= α i j l X i j ( 1 l )+ β i j l X i j ( 2 l )+ γ i j l X i j ( 3 l )
式(7)中: y i j l为新的融合特征; α i j l β i j l γ i j l为不同层权重参数;Xij为不同层特征值。
权重参数αβγ是特征图经过1×1的卷积得到的,经过concat,通过softmax使得他们的范围都在0~1,并且和为1,如式(8)~式(11)所示。
α i j l= e λ α i j l e λ α i j l + e λ β i j l + e λ γ i j l
β i j l= e λ β i j l e λ α i j l + e λ β i j l + e λ γ i j l
γ i j l= e λ γ i j l e λ α i j l + e λ β i j l + e λ γ i j l
α i j l+ β i j l+ λ i j l=1
式中: λ α i j l λ β i j l λ γ i j l为1×1大小的卷积操作。
通过在骨干网络中引入SimAM注意力机制、用自适应空间特征融合(ASFF)替换原有特征融合方式,对原有YOLOv5模型进行改进。改进后的YOLOv5模型如图4所示。
通过现场拍照的方式收集油气钻采井场安全隐患的相关图片,确保数据集的丰富性,收集到的图片包含检测对象的特征;随后,对收集到的图片进行筛选,保留适合模型训练的图片。
步骤1 数据处理。
使用labellmg软件对图片中的检测对象用边界框标记目标类别,并将处理好的数据按照6∶1的比例划分为训练集和测试集。
步骤2 模型训练。
YOLOv5模型根据模型的大小分为n、s、m、l和x,5种模型的网络结构一样,但网络的宽度和深度不同。因为油气钻采井场安全隐患识别系统的实时性,故选用兼具较高精度和较快检测速度且参数量更少的YOLOv5s模型来进行训练。
模型训练平台为Windows10系统,开发环境为Pycharm2021、Python3.11,深度学习框架为Pytorch 2.1。模型训练迭代批次为20,共训练200轮。
步骤3 安全隐患识别。
将训练好的模型部署到油气钻采井场安全隐患识别智能穿戴设备上,实验人员佩戴穿戴设备在井场现场巡检,采集井场安全隐患的图片并输入到模型当中,对图片中存在的井场安全隐患进行识别。基于YOLOv5s-SimAM-ASFF的油气钻采井场安全隐患识别整体流程如图5所示。
采用精确率(Precision,记为P)、召回率(Recall,记为R)和平均精度均值(mAP)作为训练结果的评价指标,其计算公式分别为
P= T P T P + F P×100%
R= T P T P + F N×100%
mAP= 1 k i = 1 kAP(i)×100%
AP= 0 1 PdR
式中:P为被检出目标中井场安全隐患所占的比例;R为所有井场安全隐患目标中被正确检测出来的比例;TP为预测为正确的正样本目标个数;FP为预测为假的正样本目标个数;FN表示预测为错误的负样本目标个数;AP为一个类别的平均精度;mAP为k个AP值的均值;k为类别数;AP(i)为第i个类别的AP值。
为验证改进YOLOv5目标检测模型在油气钻采井场识别安全隐患的适用性,故对油气钻采井场典型的安全隐患进行识别,对井场腐蚀识别进行识别。
采集油气钻采井场腐蚀图片105张,使用labellmg软件对图片预处理后,构建井场腐蚀隐患数据集,其中90张作为训练集,15张图片作为测试集。处理流程如图6所示。
将训练集图片输入改进YOLOv5模型进行训练,训练迭代批次为20,共训练200轮,模型训练损失值如图7所示。
boundingbox损失值为GIoU损失函数均值,Objectness损失值为目标检测损失均值,二者值越小则检测目标的能力越强。由图7可知,bounding box损失值和Objectness损失值均下降至0.02,然后趋于稳定,说明改进YOLOv5模型检测目标的性能良好,可有效识别出井场腐蚀隐患。
将测试集图片输入训练好的模型中进行识别,井场腐蚀的识别结果(部分)如图8所示。
图8可知,改进后的模型能有效将图片中存在的腐蚀识别出来,尤其是对于小区域的腐蚀识别效果也较好,对于一张图片中出现多种不同的腐蚀形状也能很好地识别出来。可知,改进后的模型对于井场腐蚀的识别性能较好。
通过与其他模型识别的井场腐蚀结果进行对比,验证改进后模型的识别效果,不同模型识别结果(部分)如图9所示。可以看出,YOLOv5s模型对井场腐蚀的识别存在识别率较低、重复识别等问题,YOLOv5s-ECA-ASFF模型对井场腐蚀的识别存在遗漏的问题,改进后的YOLOv5s-SimAM-ASFF模型对井场腐蚀的识别准确率高,未出现重复识别和识别遗漏的现象。结果表明,改进后的模型对井场腐蚀的识别效果更好。
为验证改进后的模型识别效果,采用精确率、召回率和平均精度均值来对不同模型的测试结果进行评价,结果如表1所示。
表1可知,原始的YOLOv5s模型对井场腐蚀识别的精确率为80.7%、召回率为81.2%、平均精度值为82.0%,而改进后的YOLOv5s-SimAM-ASFF模型对井场腐蚀识别的精确率为93.4%、召回率为93.8%、平均精度值为92.4%。改进后的模型相比较原始模型平均精确值提高了10.4%,相比较YOLOv5s-ASFF模型和YOLOv5s-ECA-ASFF模型,平均精确值分别高5.6%和7.5%。可知改进后的YOLOv5s-SimAM-ASFF模型对井场腐蚀的识别效果最好,改进后的模型适用于油气钻采井场安全隐患的识别。
油气钻采井场多为视频监控方式来识别井场的安全隐患,而作业现场视频监控摄像头安装数量的限制,容易产生遮挡与监控死角,井场某些区域的安全隐患无法识别。为解决油气钻采井场现场传统视频监控方式对腐蚀识别的局限性,并提高现场安全隐患识别的便捷性,研发一套油气钻采井场安全隐患识别智能穿戴设备。
在对油气钻采井场安全隐患进行识别过程中,穿戴设备通过油气钻采井场安全隐患识别系统来实现其功能,该系统架构由3个层级组成,即数据库、服务器与智能终端[16]
数据库主要是储存好油气钻采井场的安全隐患等信息,模型识别出的结果与数据库储存的信息相匹配后,服务器随即调用数据库的信息发送给智能终端。服务器主要接受智能终端采集到的图片,将图片传给部署和训练好的YOLOv5s-SimAM-ASFF目标检测模型,模型识别出图像中存在的安全隐患并输出结果,服务器根据输出的识别结果在数据库中进行匹配,匹配成功后,将数据库中储存的信息传输给智能终端,并在智能终端中显示。智能终端主要功能是能够将采集到的信息传输到服务器,然后接收服务器传输过来的数据信息并显示,智能终端使用AR智能眼镜作为载体。油气钻采井场安全隐患识别系统整体架构如图10所示。
实验人员佩戴AR智能眼镜在油气钻采井场现场巡检,实验人员看向井场存在的安全隐患,AR智能眼镜摄像头采集完整的安全隐患图像并向服务器传输图片,经由服务器部署的YOLOv5s-SimAM-ASFF模型识别成功后,得到识别结果。服务器将识别结果与数据库中的数据匹配成功后,将数据库中相应的安全隐患信息传输到AR智能眼镜上。最后,AR智能眼镜通过虚实结合技术将服务器中传输过来的信息显示于智能眼镜的全息投影中。
使用穿戴设备识别安全隐患并显示隐患信息流程如图11所示。
将训练好的可识别井场腐蚀的YOLOv5s-SimAM-ASFF模型部署在穿戴设备服务器上,实验人员佩戴AR智能眼镜在井场巡检并看向井场存在腐蚀的地方,确保眼镜摄像头采集完整的井场腐蚀。采集井场腐蚀图片后,上传至穿戴设备系统识别,随后AR智能眼镜全息投影处显示井场腐蚀识别的结果。穿戴设备识别并显示井场腐蚀如图12所示。
图12可知,穿戴设备能成功识别AR智能眼镜采集的井场腐蚀照片,并且成功将识别出的结果及整改措施信息显示在AR智能眼镜上,及时提醒相关人员对井场腐蚀情况进行整改。
为提高油气钻采井场安全隐患识别的精确率,提出一个改进的YOLOv5目标检测模型,即YOLOv5s-SimAM-ASFF模型,并用案例验证了改进模型的适用性。得出如下结论。
(1)为解决图片背景复杂,识别难度加大的问题,YOLOv5s-SimAM-ASFF模型在原有YOLOv5s模型的基础上,在模型骨干网络中引入SimAM注意力机制,提高模型对图片细节特征的提取;为解决隐患类型的尺度差异较大且一张图片中存在多种尺度的问题,改进模型用自适应空间特征融合(ASFF)替换原有模型的特征融合方式,以提高网络对目标检测的能力。
(2)通过使用改进后的模型对油气钻采井场存在的腐蚀进行识别,验证模型的识别效果,结果表明:改进后的模型在识别效果、识别精确率、召回值、平均精确率等方面都优于其他模型,且改进后的模型平均识别精度相比较原始模型提升了10.4%。综上所述,改进后的模型对于油气钻采井场安全隐患的识别效果较好。
(3)为解决钻采井场安全隐患识别存在的局限,研发了一套油气钻采井场安全隐患识别智能穿戴设备,该设备由油气钻采井场安全隐患识别系统来实现其功能,系统由数据库、服务器和智能终端组成。改进后YOLOv5s-SimAM-ASFF模型部署在服务器上,使用AR智能眼镜作为穿戴设备的载体,采集安全隐患图片并显示安全隐患信息。通过使用该穿戴设备进行了井场腐蚀的识别,井场腐蚀识别及信息显示效果较好。
  • 国家自然科学基金面上项目(52074323)
  • 国家自然科学基金重点项目(52234007)
参考文献 引证文献
排序方式:
[1]
卢宁. 油气储运中的安全隐患及防范策略分析[J]. 石化技术, 2024, 31(4): 296-298.
Lu Ning. Analysis of safety hazards and prevention strategies in oil and gas storage and transportation[J]. Petrochemical Technology, 2024, 31(4): 296-298.
[2]
胡庆勇, 杜超, 李宝成, 等. 钻井作业安全隐患分类量化管理[J]. 化工管理, 2024(4): 115-117.
Hu Qingyong, Du Chao, Li Baocheng, et al. Classification and quantitative management of drilling operation safety hazards[J]. Chemical Engineering Management, 2024(4): 115-117.
[3]
唐强. 基于关键区域特征匹配的生产现场隐患识别方法[J]. 现代电子技术, 2024, 47(4): 143-147.
Tang Qiang. Hidden danger identification method of production site based on key region feature matching[J]. Modern Electronics Technique, 2024, 47(4): 143-147.
[4]
刘慧舟. 基于机器视觉的安全隐患识别方法及其在油气站场的应用研究[D]. 北京: 中国石油大学(北京), 2022.
Liu Huizhou. Research on recognition method of safety hazards based on machine vision and its application in oil and gas stations[D]. Beijing: China University of Petroleum(Beijing), 2022.
[5]
黄丹. 基于改进的Apriori算法在钻井作业事故隐患识别中的研究[D]. 成都: 西南石油大学, 2020.
Huang Dan. Research on improved apriori algorithm based on the identification of accidental hazards in drilling operations[D]. Chengdu: Southwest Petroleum University, 2020.
[6]
肖天龙, 宫培松, 郭聖煜, 等. 基于机器视觉的施工现场安全隐患识别应用研究[J]. 工程管理学报, 2023, 37(3): 120-124.
Xiao Tianlong, Gong Peisong, Guo Shengyu, et al. Research on the application of construction site safety hazard identification based on the machine vision[J]. Journal of Engineering Managemen, 2023, 37(3): 120-124.
[7]
程国建, 李嘉欣, 贾强. 基于改进YOLOv5的井场作业风险智能识别与分类[J]. 石油工业技术监督, 2024, 40(3): 58-63.
Cheng Guojian, Li Jiaxin, Jia Qiang. Intelligent identification and classification of wellsite operation risk based on improved YOLOv5[J]. Technology Supervision in Petroleum Industry, 2024, 40(3): 58-63.
[8]
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 warning of risk during maintenance operations based on deep learning[J]. China Safety Science Journal, 2023, 33(10): 16-22.
[9]
刘慧舟, 胡瑾秋, 张来斌, 等. 基于红外热成像与CNN的压裂装备故障精准识别及预警[J]. 中国石油大学学报(自然科学版), 2021, 45(1): 158-166.
Liu Huizhou, Hu Jinqiu, Zhang Laibin, et al. Accurate identification and early-warning of faults of fracturing equipments based on infrared thermal imaging and convolutional neural network[J]. Journal of China University of Petroleum(Edition of Natural Science), 2021, 45(1): 158-166.
[10]
郭庆梅, 刘宁波, 王中训, 等. 基于深度学习的目标检测算法综述[J]. 探测与控制学报, 2023, 45(6): 10-20, 26.
Guo Qingmei, Liu Ningbo, Wang Zhongxun, et al. Review of deep learning based object detection algorithms[J]. Journal of Detection & Control, 2023, 45(6): 10-20, 26.
[11]
Olorunshola O E, Irhebhude M E, Evwiekpaefe A E. A comparative study of YOLOv5 and YOLOv7 object detection algorithms[J]. Journal of Computing and Social Informatics, 2023, 2(1): 1-12.
[12]
Yang L X, Zhang R Y, Li L D, et al. SimAM: a simple, parameter-free attention module for convolutional neural networks[C]// International Conference on Machine Learning. Huston: PMLR, 2021: https://www.xueshufan.com/publication/3166716987. https://www.xueshufan.com/publication/3166716987
[13]
Cai Z Y, Qiao X Y, Zhang J W, et al. RepVGG-SimAM: an efficient bad image classification method based on repVGG with simple parameter-free attention module[J]. Applied Sciences, 2023, 13(21): DOI: 10.3390/app132111925.
[14]
耿艳利, 林彦伯, 付艳芳, 等. 基于Transformer与自适应空间特征融合的群猪目标检测算法研究[J]. 东北农业大学学报, 2023, 54(1): 88-96.
Geng Yanli, Lin Yanbo, Fu Yanfang, et al. Study on pigs target detection algorithm based on Transformer and adaptively spatial feature fusion[J]. Journal of Northeast Agricultural University, 2023, 54(1): 88-96.
[15]
Wen G, Shuang Q, Chenvi Z, et al. Defect detection for industrial neutron radiographic images based on modified YOLO network[J]. Nuclear Inst and Methods in Physics Research A, 2023, 1056: DOI: 10.1016/j.nima.2023.168694.
[16]
王雨辰. 基于增强现实技术的电力设备故障识别方法研究[J]. 电子技术与软件工程, 2020(24): 237-238.
Wang Yuchen. Research on fault identification method of electric equipment based on augmented reality technology[J]. Electronic Technology & Software Engineering, 2020(24): 237-238.
2025年第25卷第16期
PDF下载
346
131
引用本文
BibTeX
文章信息
doi: 10.12404/j.issn.1671-1815.2406188
  • 接收时间:2024-08-19
  • 首发时间:2025-07-09
  • 出版时间:2025-06-08
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2024-08-19
  • 修回日期:2025-03-18
基金
国家自然科学基金面上项目(52074323)
国家自然科学基金重点项目(52234007)
作者信息
    1 中国石油大学(北京)安全与海洋工程学院, 北京 102249
    2 应急管理部油气生产安全与应急技术重点实验室, 北京 102249
    3 中国石油集团安全环保技术研究院有限公司, 北京 102206

通讯作者:

* 胡洋柏(2000—),男,汉族,江西上饶人,硕士研究生。研究方向:油气生产安全。E-mail:
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/kxjsygc/CN/10.12404/j.issn.1671-1815.2406188
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