Article(id=1207343640846898064, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1207343627223802520, articleNumber=null, orderNo=null, doi=10.12404/j.issn.1671-1815.2406197, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=research-article, receivedDate=1723996800000, receivedDateStr=2024-08-19, revisedDate=null, revisedDateStr=null, acceptedDate=null, acceptedDateStr=null, onlineDate=1765782755338, onlineDateStr=2025-12-15, pubDate=1750176000000, pubDateStr=2025-06-18, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1765782755338, onlineIssueDateStr=2025-12-15, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1765782755337, creator=13701087609, updateTime=1765782755337, updator=13701087609, issue=Issue{id=1207343627223802520, tenantId=1146029695717560320, journalId=1146123166801305609, year='2025', volume='25', issue='17', pageStart='7023', pageEnd='7453', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1765782752085, creator=13701087609, updateTime=1765783816840, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1207348093192872694, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1207343627223802520, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1207348093192872695, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1207343627223802520, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=7417, endPage=7429, ext={EN=ArticleExt(id=1207343645041201228, articleId=1207343640846898064, tenantId=1146029695717560320, journalId=1146123166801305609, language=EN, title=Risk Topics Discovery and Trend in Air Traffic Control Operations, columnId=1207343633745941130, journalTitle=Science Technology and Engineering, columnName=Papers-Aeronautics and Astronautics, runingTitle=null, highlight=null, articleAbstract=

In order to address the challenges posed by multifaceted risk factors in air traffic control operations, a comprehensive analysis of unsafe operational incident reports was performed to extract risk-related information and identify underlying patterns. The latent Dirichlet allocation (LDA) model was utilized to uncover key risk topics and associated keywords, and the evolutionary relationships among different risk themes were systematically analyzed. A semantic network for the civil aviation air traffic control domain was constructed using the bidirectional encoder representation from Transformers(BERT) model to examine the interconnections and potential dependencies among risk topics. This network provides a theoretical foundation for quantifying the association between keywords. The findings indicate that the proposed approach enhances the digital representation of safety risks in air traffic control operations. It is concluded that the results offer valuable insights for advancing risk assessment and mitigation strategies in civil aviation air traffic control systems. The relevant research results can better mine air traffic control unsafe information and lay a foundation for accurately perceiving air traffic control operations risks.

, correspAuthors=Yi-ming DAI, 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=Hong-hai ZHANG, Yi-ming DAI, Wen-quan LIU, Zong-bei SHI, Yi-ke LI), CN=ArticleExt(id=1207343653337535091, articleId=1207343640846898064, tenantId=1146029695717560320, journalId=1146123166801305609, language=CN, title=民航管制运行风险主题发现及演化趋势, columnId=1156262731373208516, journalTitle=科学技术与工程, columnName=论文·航空、航天, runingTitle=null, highlight=null, articleAbstract=

空中交通管制运行安全正面临多元风险致因导致潜在危害的问题。为解决多元风险引发的管制不安全运行问题,基于对管制不安全运行事件报告的全面分析,对管制运行安全风险信息和潜在规则进行挖掘;通过对隐含狄利克雷分布(latent Dirichlet allocation,LDA)风险主题发现模型挖掘的风险主题和关键词进行分析,明确管制运行风险主题及不同风险主题间相互演化规律;针对风险主题关键词,构建了民航管制运行领域的基于BERT(bidirectional encoder representation from Transformers)模型的语义网络,分析风险主题相互关联的风险特征,得出风险主题间潜在关系,可为关键词间关联度的量化提供一定理论依据;促进民航管制运行安全风险的数字化呈现的发展,挖掘管制不安全信息,为准确感知管制运行风险奠定基础。

, correspAuthors=戴一鸣, authorNote=null, correspAuthorsNote=
*戴一鸣(2001—),男,汉族,辽宁沈阳人,硕士研究生。研究方向:空管协同化与智能化。E-mail:
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=tF58+hZNVQU33bDGCDgGMg==, magXml=hhOBzhplFQPL+WZUc4mtJQ==, pdfUrl=null, pdf=1d7C2MRvH+zoydPF5Lm2Tg==, pdfFileSize=23296362, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=svD3xHFO+g4UoVQF3DIIvg==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=14+fu8O7XoYQELzWawca1Q==, mapNumber=null, authorCompany=null, fund=null, authors=

张洪海(1979—),男,汉族,山东菏泽人,博士,教授,博士研究生导师。研究方向:空管协同化与智能化、城市空中交通、智慧低空物流。E-mail:

, authorsList=张洪海, 戴一鸣, 刘文泉, 石宗北, 李一可)}, authors=[Author(id=1207343653794714289, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=honghaizhang@nuaa.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1207343653924737732, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, authorId=1207343653794714289, language=EN, stringName=Hong-hai ZHANG, firstName=Hong-hai, middleName=null, lastName=ZHANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=Civil Aviation College, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1207343654092509911, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, authorId=1207343653794714289, language=CN, stringName=张洪海, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=南京航空航天大学民航学院, 南京 211106, bio={"content":"

张洪海(1979—),男,汉族,山东菏泽人,博士,教授,博士研究生导师。研究方向:空管协同化与智能化、城市空中交通、智慧低空物流。E-mail:

"}, bioImg=null, bioContent=

张洪海(1979—),男,汉族,山东菏泽人,博士,教授,博士研究生导师。研究方向:空管协同化与智能化、城市空中交通、智慧低空物流。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1207343653664690845, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, xref=null, ext=[AuthorCompanyExt(id=1207343653668885150, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, companyId=1207343653664690845, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Civil Aviation College, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, China), AuthorCompanyExt(id=1207343653677273763, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, companyId=1207343653664690845, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=南京航空航天大学民航学院, 南京 211106)])]), Author(id=1207343654239310572, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=22260195@nuaa.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1207343654411277057, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, authorId=1207343654239310572, language=EN, stringName=Yi-ming DAI, firstName=Yi-ming, middleName=null, lastName=DAI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=*, address=Civil Aviation College, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1207343654570660624, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, authorId=1207343654239310572, language=CN, stringName=戴一鸣, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=*, address=南京航空航天大学民航学院, 南京 211106, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1207343653664690845, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, xref=null, ext=[AuthorCompanyExt(id=1207343653668885150, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, companyId=1207343653664690845, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Civil Aviation College, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, China), AuthorCompanyExt(id=1207343653677273763, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, companyId=1207343653664690845, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=南京航空航天大学民航学院, 南京 211106)])]), Author(id=1207343654713266973, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, orderNo=2, 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=1207343654981702458, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, authorId=1207343654713266973, language=EN, stringName=Wen-quan LIU, firstName=Wen-quan, middleName=null, lastName=LIU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=Civil Aviation College, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1207343655111725895, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, authorId=1207343654713266973, language=CN, stringName=刘文泉, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=南京航空航天大学民航学院, 南京 211106, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1207343653664690845, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, xref=null, ext=[AuthorCompanyExt(id=1207343653668885150, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, companyId=1207343653664690845, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Civil Aviation College, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, China), AuthorCompanyExt(id=1207343653677273763, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, companyId=1207343653664690845, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=南京航空航天大学民航学院, 南京 211106)])]), Author(id=1207343655204000600, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, 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=1207343655342412651, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, authorId=1207343655204000600, language=EN, stringName=Zong-bei SHI, firstName=Zong-bei, middleName=null, lastName=SHI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=Civil Aviation College, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1207343655447270265, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, authorId=1207343655204000600, language=CN, stringName=石宗北, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=南京航空航天大学民航学院, 南京 211106, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1207343653664690845, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, xref=null, ext=[AuthorCompanyExt(id=1207343653668885150, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, companyId=1207343653664690845, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Civil Aviation College, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, China), AuthorCompanyExt(id=1207343653677273763, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, companyId=1207343653664690845, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=南京航空航天大学民航学院, 南京 211106)])]), Author(id=1207343655589876622, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, 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=1207343656911082415, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, authorId=1207343655589876622, language=EN, stringName=Yi-ke LI, firstName=Yi-ke, middleName=null, lastName=LI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=Civil Aviation College, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1207343657091437503, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, authorId=1207343655589876622, language=CN, stringName=李一可, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=南京航空航天大学民航学院, 南京 211106, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1207343653664690845, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, xref=null, ext=[AuthorCompanyExt(id=1207343653668885150, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, companyId=1207343653664690845, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Civil Aviation College, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, China), AuthorCompanyExt(id=1207343653677273763, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, companyId=1207343653664690845, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=南京航空航天大学民航学院, 南京 211106)])])], keywords=[Keyword(id=1207343657330512859, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, language=EN, orderNo=1, keyword=air traffic management(ATM)), Keyword(id=1207343657460536301, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, language=EN, orderNo=2, keyword=air traffic control operational safety), Keyword(id=1207343657577976823, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, language=EN, orderNo=3, keyword=risk management), Keyword(id=1207343657762525192, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, language=EN, orderNo=4, keyword=latent Dirichlet allocation (LDA) topics model), Keyword(id=1207343657875771414, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, language=EN, orderNo=5, keyword=semantic network), Keyword(id=1207343658009989157, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, language=CN, orderNo=1, keyword=空中交通管理), Keyword(id=1207343658156789811, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, language=CN, orderNo=2, keyword=管制运行安全), Keyword(id=1207343658282618946, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, language=CN, orderNo=3, keyword=风险管理), Keyword(id=1207343658400059463, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, language=CN, orderNo=4, keyword=LDA主题模型), Keyword(id=1207343658513305680, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, language=CN, orderNo=5, keyword=语义网络)], refs=[Reference(id=1207343664624407030, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, doi=null, pmid=null, pmcid=null, year=2000, volume=35, issue=1, pageStart=87, pageEnd=94, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=Andersen V, Bove T, journalName=Safety Science, refType=null, unstructuredReference=Andersen V, Bove T. A feasibility study of the use of incidents and accidents reports to evaluate effects of team resource management in air traffic control[J]. Safety Science, 2000, 35(1): 87-94., articleTitle=A feasibility study of the use of incidents and accidents reports to evaluate effects of team resource management in air traffic control, refAbstract=null), Reference(id=1207343665882698245, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, doi=null, pmid=null, pmcid=null, year=2011, volume=49, issue=10, pageStart=1365, pageEnd=1370, url=null, language=null, rfNumber=[2], rfOrder=1, authorNames=Olsen S N, journalName=Safety Science, refType=null, unstructuredReference=Olsen S N. Coding ATC incident data using HFACS: inter-coder consensus[J]. Safety Science, 2011, 49(10): 1365-1370., articleTitle=Coding ATC incident data using HFACS: inter-coder consensus, refAbstract=null), Reference(id=1207343666134356500, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, doi=null, pmid=null, pmcid=null, year=2023, volume=108, issue=null, pageStart=102374, pageEnd=null, url=null, language=null, rfNumber=[3], rfOrder=2, authorNames=Kang J, Yang S, Shan X, journalName=Journal of Air Transport Management, refType=null, unstructuredReference=Kang J, Yang S, Shan X, et al. Exploring topics and trends in Chinese ATC incident reports using a domain-knowledge driven topic model[J]. Journal of Air Transport Management, 2023, 108: 102374., articleTitle=Exploring topics and trends in Chinese ATC incident reports using a domain-knowledge driven topic model, refAbstract=null), Reference(id=1207343666260185629, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[4], rfOrder=3, authorNames=郭东岳, journalName=面向管制指挥的空中交通智能态势感知关键技术研究, refType=null, unstructuredReference=郭东岳. 面向管制指挥的空中交通智能态势感知关键技术研究[D]. 成都: 四川大学, 2023., articleTitle=null, refAbstract=null), Reference(id=1207343666398597676, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[4], rfOrder=4, authorNames=Guo Dongyue, journalName=Research on key technologies of intelligen, refType=null, unstructuredReference=Guo Dongyue. Research on key technologies of intelligen[D]. Chengdu: Sichuan University, 2023., articleTitle=null, refAbstract=null), Reference(id=1207343666528621109, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, doi=null, pmid=null, pmcid=null, year=2024, volume=24, issue=2, pageStart=587, pageEnd=595, url=null, language=null, rfNumber=[5], rfOrder=5, authorNames=陈芳, 温抗抗, 张亚博, journalName=安全与环境学报, refType=null, unstructuredReference=陈芳, 温抗抗, 张亚博, 等. 民航管制安全风险主题时空分布规律研究[J]. 安全与环境学报, 2024, 24(2): 587-595., articleTitle=民航管制安全风险主题时空分布规律研究, refAbstract=null), Reference(id=1207343666646061632, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, doi=null, pmid=null, pmcid=null, year=2024, volume=24, issue=2, pageStart=587, pageEnd=595, url=null, language=null, rfNumber=[5], rfOrder=6, authorNames=Chen Fang, Wen Kangkang, Zhang Yabo, journalName=Journal of Safety and Environment, refType=null, unstructuredReference=Chen Fang, Wen Kangkang, Zhang Yabo, et al. Spatial and temporal distribution of air traffic control (ATC) safety risk topic[J]. Journal of Safety and Environment, 2024, 24(2): 587-595., articleTitle=Spatial and temporal distribution of air traffic control (ATC) safety risk topic, refAbstract=null), Reference(id=1207343666780279371, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, doi=null, pmid=null, pmcid=null, year=2019, volume=112, issue=null, pageStart=90, pageEnd=95, url=null, language=null, rfNumber=[6], rfOrder=7, authorNames=Ni X, Wang H, Che C, journalName=Safety Science, refType=null, unstructuredReference=Ni X, Wang H, Che C, et al. Civil aviation safety evaluation based on deep belief network and principal component analysis[J]. Safety Science, 2019, 112: 90-95., articleTitle=Civil aviation safety evaluation based on deep belief network and principal component analysis, refAbstract=null), Reference(id=1207343666914497113, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, doi=null, pmid=null, pmcid=null, year=2020, volume=20, issue=30, pageStart=12636, pageEnd=12643, url=null, language=null, rfNumber=[7], rfOrder=8, authorNames=王润东, 潘卫军, 陈晓光, journalName=科学技术与工程, refType=null, unstructuredReference=王润东, 潘卫军, 陈晓光, 等. 基于博弈论集对分析模型的机坪管制运行风险评价[J]. 科学技术与工程, 2020, 20(30): 12636-12643., articleTitle=基于博弈论集对分析模型的机坪管制运行风险评价, refAbstract=null), Reference(id=1207343667178738284, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, doi=null, pmid=null, pmcid=null, year=2020, volume=20, issue=30, pageStart=12636, pageEnd=12643, url=null, language=null, rfNumber=[7], rfOrder=9, authorNames=Wang Rundong, Pan Weijun, Chen Xiaoguang, journalName=Science Technology and Engineering, refType=null, unstructuredReference=Wang Rundong, Pan Weijun, Chen Xiaoguang, et al. Risk assessment of apron control operation in entropy weight extension model[J]. Science Technology and Engineering, 2020, 20(30): 12636-12643., articleTitle=Risk assessment of apron control operation in entropy weight extension model, refAbstract=null), Reference(id=1207343667367481978, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, doi=null, pmid=null, pmcid=null, year=2024, volume=96, issue=6, pageStart=826, pageEnd=837, url=null, language=null, rfNumber=[8], rfOrder=10, authorNames=Chai Y, Wang Y G, Wang Y S, journalName=Aircraft Engineering and Aerospace Technology, refType=null, unstructuredReference=Chai Y, Wang Y G, Wang Y S, et al. Safety evaluation of human-caused errors in civil aviation based on analytic hierarchy process and fuzzy comprehensive evaluation method[J]. Aircraft Engineering and Aerospace Technology, 2024, 96(6) : 826-837., articleTitle=Safety evaluation of human-caused errors in civil aviation based on analytic hierarchy process and fuzzy comprehensive evaluation method, refAbstract=null), Reference(id=1207343667602363013, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, doi=null, pmid=null, pmcid=null, year=2024, volume=301, issue=1, pageStart=117559, pageEnd=null, url=null, language=null, rfNumber=[9], rfOrder=11, authorNames=Senol E Y, journalName=Ocean Engineering, refType=null, unstructuredReference=Senol E Y. Assessment of human factor contribution to risk analysis of chemical cargo shortage incidents by using intuitionistic fuzzy integrated fault tree analysis[J]. Ocean Engineering, 2024, 301(1): 117559., articleTitle=Assessment of human factor contribution to risk analysis of chemical cargo shortage incidents by using intuitionistic fuzzy integrated fault tree analysis, refAbstract=null), Reference(id=1207343667786912402, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, doi=null, pmid=null, pmcid=null, year=2019, volume=63, issue=1, pageStart=1849, pageEnd=1853, url=null, language=null, rfNumber=[10], rfOrder=12, authorNames=Adam H, Neville A S, Guy H W, journalName=Proceedings of the Human Factors and Ergonomics Society Annual Meeting, refType=null, unstructuredReference=Adam H, Neville A S, Guy H W, et al. Accident analysis in practice: a review of human factors analysis and classification system (HFACS) applications in the peer reviewed academic literature[J]. Proceedings of the Human Factors and Ergonomics Society Annual Meeting, 2019, 63(1): 1849-1853., articleTitle=Accident analysis in practice: a review of human factors analysis and classification system (HFACS) applications in the peer reviewed academic literature, refAbstract=null), Reference(id=1207343668046959268, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, doi=null, pmid=null, pmcid=null, year=2023, volume=53, issue=6, pageStart=35, pageEnd=39, url=null, language=null, rfNumber=[11], rfOrder=13, authorNames=蔡志鹏, 曾维理, 郭子逸, journalName=航空计算技术, refType=null, unstructuredReference=蔡志鹏, 曾维理, 郭子逸. 空中交通管制中的危险源关键特征提取[J]. 航空计算技术, 2023, 53(6): 35-39., articleTitle=空中交通管制中的危险源关键特征提取, refAbstract=null), Reference(id=1207343668281840315, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, doi=null, pmid=null, pmcid=null, year=2023, volume=53, issue=6, pageStart=35, pageEnd=39, url=null, language=null, rfNumber=[11], rfOrder=14, authorNames=Cai Zhipeng, Zeng Weili, Guo Ziyi, journalName=Aeronautical Computing Technique, refType=null, unstructuredReference=Cai Zhipeng, Zeng Weili, Guo Ziyi. Feature extraction of air traffic control hazard based on text[J]. Aeronautical Computing Technique, 2023, 53(6): 35-39., articleTitle=Feature extraction of air traffic control hazard based on text, refAbstract=null), Reference(id=1207343668399280839, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, doi=null, pmid=null, pmcid=null, year=2024, volume=52, issue=3, pageStart=814, pageEnd=820, url=null, language=null, rfNumber=[12], rfOrder=15, authorNames=牟奇锋, 郭花, 郝芮, journalName=计算机与数字工程, refType=null, unstructuredReference=牟奇锋, 郭花, 郝芮. 基于复杂网络的跑道侵入风险因素研究[J]. 计算机与数字工程, 2024, 52(3): 814-820., articleTitle=基于复杂网络的跑道侵入风险因素研究, refAbstract=null), Reference(id=1207343668520915668, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, doi=null, pmid=null, pmcid=null, year=2024, volume=52, issue=3, pageStart=814, pageEnd=820, url=null, language=null, rfNumber=[12], rfOrder=16, authorNames=Mou Qifeng, Guo Hua, Hao Rui, journalName=Computer & Digital Engineering, refType=null, unstructuredReference=Mou Qifeng, Guo Hua, Hao Rui. Research on risk factors of runway incursion based on complex network[J]. Computer & Digital Engineering, 2024, 52(3): 814-820., articleTitle=Research on risk factors of runway incursion based on complex network, refAbstract=null), Reference(id=1207343668638356190, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, doi=null, pmid=null, pmcid=null, year=2024, volume=24, issue=6, pageStart=2590, pageEnd=2600, url=null, language=null, rfNumber=[13], rfOrder=17, authorNames=康瑞, 李凌海, 牟睿聆, journalName=科学技术与工程, refType=null, unstructuredReference=康瑞, 李凌海, 牟睿聆, 等. 因天气影响的航空器绕飞管制安全评估及策略分析[J]. 科学技术与工程, 2024, 24(6): 2590-2600., articleTitle=因天气影响的航空器绕飞管制安全评估及策略分析, refAbstract=null), Reference(id=1207343668747408103, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, doi=null, pmid=null, pmcid=null, year=2024, volume=24, issue=6, pageStart=2590, pageEnd=2600, url=null, language=null, rfNumber=[13], rfOrder=18, authorNames=Kang Rui, Li Linghai, Mou Ruiling, journalName=Science Technology and Engineering, refType=null, unstructuredReference=Kang Rui, Li Linghai, Mou Ruiling, et al. Safety assessment and strategy analysis of aircraft fly-around control due to weather[J]. Science Technology and Engineering, 2024, 24(6): 2590-2600., articleTitle=Safety assessment and strategy analysis of aircraft fly-around control due to weather, refAbstract=null), Reference(id=1207343668902597363, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, doi=null, pmid=null, pmcid=null, year=2022, volume=9, issue=10, pageStart=591, pageEnd=612, url=null, language=null, rfNumber=[14], rfOrder=19, authorNames=Samuel K, Thierry K, Laurent L, journalName=Aerospace, refType=null, unstructuredReference=Samuel K, Thierry K, Laurent L. ASRS-CMFS vs. RoBERTa: comparing two pre-trained language models to predict anomalies in aviation occurrence reports with a low volume of in-domain data available[J]. Aerospace, 2022, 9(10): 591-612., articleTitle=ASRS-CMFS vs. RoBERTa: comparing two pre-trained language models to predict anomalies in aviation occurrence reports with a low volume of in-domain data available, refAbstract=null), Reference(id=1207343669082952447, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, doi=null, pmid=null, pmcid=null, year=2024, volume=11, issue=10, pageStart=837, pageEnd=837, url=null, language=null, rfNumber=[15], rfOrder=20, authorNames=Xu Y, Gan Z, Guo R, journalName=Aerospace, refType=null, unstructuredReference=Xu Y, Gan Z, Guo R, et al. Hazard analysis for massive civil aviation safety oversight reports using text classification and topic modeling[J]. Aerospace, 2024, 11(10): 837-837., articleTitle=Hazard analysis for massive civil aviation safety oversight reports using text classification and topic modeling, refAbstract=null), Reference(id=1207343670257357575, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, doi=null, pmid=null, pmcid=null, year=2003, volume=null, issue=3, pageStart=993, pageEnd=1022, url=null, language=null, rfNumber=[16], rfOrder=21, authorNames=Blei D M, Ng A, Jordan M I, journalName=Journal of Machine Learning Research, refType=null, unstructuredReference=Blei D M, Ng A, Jordan M I. Latent Dirichlet allocation[J]. Journal of Machine Learning Research, 2003(3): 993-1022., articleTitle=Latent Dirichlet allocation, refAbstract=null), Reference(id=1207343670378992401, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[17], rfOrder=22, authorNames=Grigorev A, Mihaita A S, Lee S, journalName=ArXiv, refType=null, unstructuredReference=Grigorev A, Mihaita A S, Lee S, et al. Incident duration prediction using a bi-level machine learning framework with outlier removal and intra-extra joint optimisation[J]. ArXiv, 2022: 2205.05197., articleTitle=Incident duration prediction using a bi-level machine learning framework with outlier removal and intra-extra joint optimisation, refAbstract=null), Reference(id=1207343670483850009, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, doi=null, pmid=null, pmcid=null, year=2018, volume=87, issue=null, pageStart=105, pageEnd=122, url=null, language=null, rfNumber=[18], rfOrder=23, authorNames=Kuhn D K, journalName=Transportation Research Part C, refType=null, unstructuredReference=Kuhn D K. Using structural topic modeling to identify latent topics and trends in aviation incident reports[J]. Transportation Research Part C, 2018, 87: 105-122., articleTitle=Using structural topic modeling to identify latent topics and trends in aviation incident reports, refAbstract=null), Reference(id=1207343670584513310, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, doi=null, pmid=null, pmcid=null, year=2017, volume=77, issue=null, pageStart=49, pageEnd=66, url=null, language=null, rfNumber=[19], rfOrder=24, authorNames=Sun L, Yin Y, journalName=Transportation Research Part C, refType=null, unstructuredReference=Sun L, Yin Y. Discovering themes and trends in transportation research using topic modeling[J]. Transportation Research Part C, 2017, 77: 49-66., articleTitle=Discovering themes and trends in transportation research using topic modeling, refAbstract=null), Reference(id=1207343670706148134, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, doi=null, pmid=null, pmcid=null, year=2021, volume=21, issue=29, pageStart=12631, pageEnd=12637, url=null, language=null, rfNumber=[20], rfOrder=25, authorNames=陈可嘉, 刘惠, journalName=科学技术与工程, refType=null, unstructuredReference=陈可嘉, 刘惠. 文本分类中基于单词表示的全局向量模型和隐含狄利克雷分布的文本表示改进方法[J]. 科学技术与工程, 2021, 21(29): 12631-12637., articleTitle=文本分类中基于单词表示的全局向量模型和隐含狄利克雷分布的文本表示改进方法, refAbstract=null), Reference(id=1207343670781645612, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, doi=null, pmid=null, pmcid=null, year=2021, volume=21, issue=29, pageStart=12631, pageEnd=12637, url=null, language=null, rfNumber=[20], rfOrder=26, authorNames=Chen Kejia, Liu Hui, journalName=Science Technology and Engineering, refType=null, unstructuredReference=Chen Kejia, Liu Hui. Improved text representation method based on GloVe and LDA for text classification[J]. Science Technology and Engineering, 2021, 21(29): 12631-12637., articleTitle=Improved text representation method based on GloVe and LDA for text classification, refAbstract=null), Reference(id=1207343670873920305, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, doi=null, pmid=null, pmcid=null, year=2022, volume=28, issue=2, pageStart=41, pageEnd=45, url=null, language=null, rfNumber=[21], rfOrder=27, authorNames=张思松, 陈文, journalName=安庆师范大学学报(自然科学版), refType=null, unstructuredReference=张思松, 陈文. 基于LDA模型和语义网络的线上文本挖掘方法[J]. 安庆师范大学学报(自然科学版), 2022, 28(2): 41-45., articleTitle=基于LDA模型和语义网络的线上文本挖掘方法, refAbstract=null), Reference(id=1207343670945223480, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, doi=null, pmid=null, pmcid=null, year=2022, volume=28, issue=2, pageStart=41, pageEnd=45, url=null, language=null, rfNumber=[21], rfOrder=28, authorNames=Zhang Sisong, Chen Wen, journalName=Journal of Anqing Normal University(Natural Science Edition), refType=null, unstructuredReference=Zhang Sisong, Chen Wen. Online text mining method based on LDA model and semantic network[J]. Journal of Anqing Normal University(Natural Science Edition), 2022, 28(2): 41-45., articleTitle=Online text mining method based on LDA model and semantic network, refAbstract=null), Reference(id=1207343671033303871, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, doi=null, pmid=null, pmcid=null, year=2023, volume=41, issue=3, pageStart=723, pageEnd=737, url=null, language=null, rfNumber=[22], rfOrder=29, authorNames=Atul G, Kalpana S, Kumar K G, journalName=New Generation Computing, refType=null, unstructuredReference=Atul G, Kalpana S, Kumar K G. Ontology-based similarity computation of two sentences using word-net database[J]. New Generation Computing, 2023, 41(3): 723-737., articleTitle=Ontology-based similarity computation of two sentences using word-net database, refAbstract=null), Reference(id=1207343671133967172, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, doi=null, pmid=null, pmcid=null, year=2020, volume=16, issue=11, pageStart=47, pageEnd=52, url=null, language=null, rfNumber=[23], rfOrder=30, authorNames=陈芳, 陈茜, 徐碧晨, journalName=中国安全生产科学技术, refType=null, unstructuredReference=陈芳, 陈茜, 徐碧晨. 基于文本挖掘的管制运行风险主题分析[J]. 中国安全生产科学技术, 2020, 16(11): 47-52., articleTitle=基于文本挖掘的管制运行风险主题分析, refAbstract=null), Reference(id=1207343671263990604, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, doi=null, pmid=null, pmcid=null, year=2020, volume=16, issue=11, pageStart=47, pageEnd=52, url=null, language=null, rfNumber=[23], rfOrder=31, authorNames=Chen Fang, Chen Xi, Xu Bichen, journalName=Journal of Safety Science and Technology, refType=null, unstructuredReference=Chen Fang, Chen Xi, Xu Bichen. Analysis on operation risk topics of air traffic control (ATC) based on text mining[J]. Journal of Safety Science and Technology, 2020, 16(11): 47-52., articleTitle=Analysis on operation risk topics of air traffic control (ATC) based on text mining, refAbstract=null), Reference(id=1207343671389819727, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, doi=null, pmid=null, pmcid=null, year=2019, volume=null, issue=null, pageStart=3498, pageEnd=4195, url=null, language=null, rfNumber=[24], rfOrder=32, authorNames=Devlin J, Chang M W, Lee K, journalName=Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies (NAACL-HLT), refType=null, unstructuredReference=Devlin J, Chang M W, Lee K. BERT: pre-training of deep bidirectional transformers for language understanding[C]// Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies (NAACL-HLT). Florence: IEEE, 2019: 3498-4195., articleTitle=BERT: pre-training of deep bidirectional transformers for language understanding, refAbstract=null), Reference(id=1207343671586952024, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, doi=null, pmid=null, pmcid=null, year=2020, volume=117, issue=4, pageStart=1910, pageEnd=1916, url=null, language=null, rfNumber=[25], rfOrder=33, authorNames=Mario K, Anton Z, journalName=Proceedings of the National Academy of Sciences of the United States of America, refType=null, unstructuredReference=Mario K, Anton Z. Predicting research trends with semantic and neural networks with an application in quantum physics[J]. Proceedings of the National Academy of Sciences of the United States of America, 2020, 117(4): 1910-1916., articleTitle=Predicting research trends with semantic and neural networks with an application in quantum physics, refAbstract=null), Reference(id=1207343671750529888, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, doi=null, pmid=null, pmcid=null, year=2021, volume=16, issue=null, pageStart=1290, pageEnd=1305, url=null, language=null, rfNumber=[26], rfOrder=34, authorNames=Zhao F Y, Ren X B, Yang S S, journalName=IEEE Transactions on Information Forensics and Security, refType=null, unstructuredReference=Zhao F Y, Ren X B, Yang S S, et al. Latent Dirichlet allocation model training with differential privacy[J]. IEEE Transactions on Information Forensics and Security, 2021, 16: 1290-1305., articleTitle=Latent Dirichlet allocation model training with differential privacy, refAbstract=null), Reference(id=1207343671851193189, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, doi=null, pmid=null, pmcid=null, year=2024, volume=79, issue=null, pageStart=102314, pageEnd=null, url=null, language=null, rfNumber=[27], rfOrder=35, authorNames=Chang A C, Lin J S, journalName=World Patent Information, refType=null, unstructuredReference=Chang A C, Lin J S. Exploring technological applications through LDA-based patent mining: a metaverse ontology construction[J]. World Patent Information, 2024, 79: 102314., articleTitle=Exploring technological applications through LDA-based patent mining: a metaverse ontology construction, refAbstract=null), Reference(id=1207343671956050797, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, doi=null, pmid=null, pmcid=null, year=2023, volume=15, issue=15, pageStart=12065, pageEnd=null, url=null, language=null, rfNumber=[28], rfOrder=36, authorNames=Liu W, Zhang H, Shi Z, journalName=Sustainability, refType=null, unstructuredReference=Liu W, Zhang H, Shi Z, et al. Risk topics discovery and trend analysis in air traffic control operations: air traffic control incident reports from 2000 to 2022[J]. Sustainability, 2023, 15(15): 12065., articleTitle=Risk topics discovery and trend analysis in air traffic control operations: air traffic control incident reports from 2000 to 2022, refAbstract=null), Reference(id=1207343672052519795, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, doi=null, pmid=null, pmcid=null, year=2019, volume=9, issue=23, pageStart=5049, pageEnd=null, url=null, language=null, rfNumber=[29], rfOrder=37, authorNames=Lü T, Song W, Du K, journalName=Applied Sciences, refType=null, unstructuredReference= T, Song W, Du K. Human factors analysis of air traffic safety based on HFACS-BN model[J]. Applied Sciences, 2019, 9(23): 5049., articleTitle=Human factors analysis of air traffic safety based on HFACS-BN model, refAbstract=null), Reference(id=1207343672144794489, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=289, pageEnd=295, url=null, language=null, rfNumber=[30], rfOrder=38, authorNames=Miller M, Holley S, Mrusek B, journalName=Advances in Human Factors and Systems Interaction:Proceedings of the AHFE 2020 Virtual Conference on Human Factors and Systems Interaction. Berlin:Springer International Publishing, refType=null, unstructuredReference=Miller M, Holley S, Mrusek B, et al. Assessing cognitive processing and human factors challenges in NextGen air traffic control tower team operations[C]// Advances in Human Factors and Systems Interaction:Proceedings of the AHFE 2020 Virtual Conference on Human Factors and Systems Interaction. Berlin:Springer International Publishing, 2020: 289-295., articleTitle=Assessing cognitive processing and human factors challenges in NextGen air traffic control tower team operations, refAbstract=null), Reference(id=1207343672249652094, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, doi=null, pmid=null, pmcid=null, year=2023, volume=11, issue=null, pageStart=134040, pageEnd=134057, url=null, language=null, rfNumber=[31], rfOrder=39, authorNames=Chi Y, Nie J, Zhong L, journalName=IEEE Access, refType=null, unstructuredReference=Chi Y, Nie J, Zhong L, et al. A review of situational awareness in air traffic control[J]. IEEE Access, 2023, 11: 134040-134057., articleTitle=A review of situational awareness in air traffic control, refAbstract=null), Reference(id=1207343672341926787, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, doi=null, pmid=null, pmcid=null, year=2024, volume=null, issue=10, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[32], rfOrder=40, authorNames=Blondel V, Guillaume L J, Lambiotte R, journalName=Journal of Statistical Mechanics: Theory and Experiment, refType=null, unstructuredReference=Blondel V, Guillaume L J, Lambiotte R. Fast unfolding of communities in large networks: 15 years later[J]. Journal of Statistical Mechanics: Theory and Experiment, 2024(10): 10R001., articleTitle=Fast unfolding of communities in large networks: 15 years later, refAbstract=null)], funds=[Fund(id=1207343664007844300, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, awardId=U2133207, language=CN, fundingSource=国家自然科学基金民航联合基金(U2133207), fundOrder=null, country=null), Fund(id=1207343664137867734, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, awardId=MJZ1-7N22, language=CN, fundingSource=中国工业和信息化部民用飞机专项科研(MJZ1-7N22), fundOrder=null, country=null), Fund(id=1207343664385331683, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, awardId=52202404, language=CN, fundingSource=国家自然科学基金(52202404), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1207343653664690845, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, xref=null, ext=[AuthorCompanyExt(id=1207343653668885150, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, companyId=1207343653664690845, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Civil Aviation College, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, China), AuthorCompanyExt(id=1207343653677273763, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, companyId=1207343653664690845, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=南京航空航天大学民航学院, 南京 211106)])], figs=[ArticleFig(id=1207343658764963943, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, language=EN, label=Fig.1, caption=Number of ATC incident reports and sample data, figureFileSmall=dvhZgkvfdcb63f/ONkK49A==, figureFileBig=svD3xHFO+g4UoVQF3DIIvg==, tableContent=null), ArticleFig(id=1207343658861432945, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, language=CN, label=图1, caption=管制不安全运行事件报告样例数据及数量统计, figureFileSmall=dvhZgkvfdcb63f/ONkK49A==, figureFileBig=svD3xHFO+g4UoVQF3DIIvg==, tableContent=null), ArticleFig(id=1207343659201171599, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, language=EN, label=Fig.2, caption=Model structure for LDA, figureFileSmall=gkhnXTB2KQ1drV4nnlytpA==, figureFileBig=znrdtgPzz8+JgiIez4nZiw==, tableContent=null), ArticleFig(id=1207343659427664032, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, language=CN, label=图2, caption=LDA模型结构, figureFileSmall=gkhnXTB2KQ1drV4nnlytpA==, figureFileBig=znrdtgPzz8+JgiIez4nZiw==, tableContent=null), ArticleFig(id=1207343659666739372, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, language=EN, label=Fig.3, caption=Change of the perplexity curve with the number of ATC incident reports, figureFileSmall=jlyIRWn2DwfFjzf37oRo8A==, figureFileBig=IT2N28SUXN5iy5iLoSqE+Q==, tableContent=null), ArticleFig(id=1207343659817734328, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, language=CN, label=图3, caption=主题困惑度随管制不安全事件报告数量变化曲线, figureFileSmall=jlyIRWn2DwfFjzf37oRo8A==, figureFileBig=IT2N28SUXN5iy5iLoSqE+Q==, tableContent=null), ArticleFig(id=1207343659968729285, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, language=EN, label=Fig.4, caption=Structure of the BERT language model, figureFileSmall=txpVYsZwrZGE1nQvVq44xw==, figureFileBig=SjXaeb4wew8aMgAk/MCpjQ==, tableContent=null), ArticleFig(id=1207343660098752722, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, language=CN, label=图4, caption=BERT语言模型结构, figureFileSmall=txpVYsZwrZGE1nQvVq44xw==, figureFileBig=SjXaeb4wew8aMgAk/MCpjQ==, tableContent=null), ArticleFig(id=1207343661566759143, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, language=EN, label=Fig.5, caption=Number of ATC incident reports for each risk topic, figureFileSmall=FN3xyB7C5w6JlgfGxcUpWg==, figureFileBig=mS5VVzDnoS99QHWAoE5iyg==, tableContent=null), ArticleFig(id=1207343661730337010, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, language=CN, label=图5, caption=每个风险主题下事件报告数量, figureFileSmall=FN3xyB7C5w6JlgfGxcUpWg==, figureFileBig=mS5VVzDnoS99QHWAoE5iyg==, tableContent=null), ArticleFig(id=1207343661835194624, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, language=EN, label=Fig.6, caption=The word cloud of risk topics, figureFileSmall=Ds8XQ7D882rfRCFQuoBYcA==, figureFileBig=AjLIJ8Gdtd9Ti9688eJCoA==, tableContent=null), ArticleFig(id=1207343661944246533, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, language=CN, label=图6, caption=风险主题词云, figureFileSmall=Ds8XQ7D882rfRCFQuoBYcA==, figureFileBig=AjLIJ8Gdtd9Ti9688eJCoA==, tableContent=null), ArticleFig(id=1207343662065881362, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, language=EN, label=Fig.7, caption=Distribution of risk topics over time, figureFileSmall=aC+NgnN7HKS0a53MhTRcTQ==, figureFileBig=GPOkOUdl5Mr03lkLphuq7g==, tableContent=null), ArticleFig(id=1207343662166544671, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, language=CN, label=图7, caption=风险主题变化趋势图, figureFileSmall=aC+NgnN7HKS0a53MhTRcTQ==, figureFileBig=GPOkOUdl5Mr03lkLphuq7g==, tableContent=null), ArticleFig(id=1207343662288179500, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, language=EN, label=Fig.8, caption=The proportion of the number of risk topics per year, figureFileSmall=B6Iom/NL2luBLNmavxMX3Q==, figureFileBig=rmEN+c4glIUzr7zqI/e7tA==, tableContent=null), ArticleFig(id=1207343662414008632, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, language=CN, label=图8, caption=风险主题百分比图, figureFileSmall=B6Iom/NL2luBLNmavxMX3Q==, figureFileBig=rmEN+c4glIUzr7zqI/e7tA==, tableContent=null), ArticleFig(id=1207343662548226374, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, language=EN, label=Fig.9, caption=Some risk themes change trend chart, figureFileSmall=6jHPHouu3ySZd6EpzX6Wqw==, figureFileBig=KUMn0uDHEU1wgGI+WwLd6A==, tableContent=null), ArticleFig(id=1207343662657278289, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, language=CN, label=图9, caption=部分风险主题变化趋势图, figureFileSmall=6jHPHouu3ySZd6EpzX6Wqw==, figureFileBig=KUMn0uDHEU1wgGI+WwLd6A==, tableContent=null), ArticleFig(id=1207343662833439069, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, language=EN, label=Fig.10, caption=Main reasons for ATC incidents, figureFileSmall=TYWFqfngnflUdStZQTTibA==, figureFileBig=epZHXh0Djae6thgzrKqdxQ==, tableContent=null), ArticleFig(id=1207343662925713767, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, language=CN, label=图10, caption=管制不安全运行事件主要原因统计, figureFileSmall=TYWFqfngnflUdStZQTTibA==, figureFileBig=epZHXh0Djae6thgzrKqdxQ==, tableContent=null), ArticleFig(id=1207343663034765682, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, language=EN, label=Fig.11, caption=Semantic network for ATC operations safety risk, figureFileSmall=IEfYKPdYXtWkvVrtQo2JXg==, figureFileBig=aSL8krJfCt2l1//O6OfDYA==, tableContent=null), ArticleFig(id=1207343663181566329, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, language=CN, label=图11, caption=民航管制运行风险语义网络, figureFileSmall=IEfYKPdYXtWkvVrtQo2JXg==, figureFileBig=aSL8krJfCt2l1//O6OfDYA==, tableContent=null), ArticleFig(id=1207343663370310022, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, language=EN, label=Table 1, caption=

Ring growth rate of each risk topic

, figureFileSmall=null, figureFileBig=null, tableContent=
主题 Di 主题 Di
主题一(指令偏差) -0.015 主题九(管理因素) 0.681
主题二(飞行高度) 0.942 主题十(飞行冲突) 0.236
主题三(冲/偏出跑道) -0.032 主题十一(飞行间隔) -0.241
主题四(起飞/离场阶段) -0.425 主题十二 (下降/着陆阶段) 0.339
主题五(跑道侵入) 0.067 主题十三(空域运行环境) 0.131
主题六(通信失联) -0.376 主题十四(气象因素) 0.268
主题七(进近/进场阶段) 0.469 主题十五(表达不准确) 0.041
主题八(人为差错) 0.436 主题十六(设施设备) 0.323
), ArticleFig(id=1207343663554859417, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, language=CN, label=表1, caption=

各风险主题环比增长率

, figureFileSmall=null, figureFileBig=null, tableContent=
主题 Di 主题 Di
主题一(指令偏差) -0.015 主题九(管理因素) 0.681
主题二(飞行高度) 0.942 主题十(飞行冲突) 0.236
主题三(冲/偏出跑道) -0.032 主题十一(飞行间隔) -0.241
主题四(起飞/离场阶段) -0.425 主题十二 (下降/着陆阶段) 0.339
主题五(跑道侵入) 0.067 主题十三(空域运行环境) 0.131
主题六(通信失联) -0.376 主题十四(气象因素) 0.268
主题七(进近/进场阶段) 0.469 主题十五(表达不准确) 0.041
主题八(人为差错) 0.436 主题十六(设施设备) 0.323
), ArticleFig(id=1207343663638745509, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, language=EN, label=Table 2, caption=

Main topological indicators of the semantic network

, figureFileSmall=null, figureFileBig=null, tableContent=
拓扑指标 数值
平均度 15.111
网络直径 6
图密度 0.099
平均聚类系数 0.492
平均路径长度 2.42
), ArticleFig(id=1207343663718437290, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, language=CN, label=表2, caption=

语义网络主要拓扑指标

, figureFileSmall=null, figureFileBig=null, tableContent=
拓扑指标 数值
平均度 15.111
网络直径 6
图密度 0.099
平均聚类系数 0.492
平均路径长度 2.42
), ArticleFig(id=1207343663802323382, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, language=EN, label=Table 3, caption=

Main risk topics contained in each module

, figureFileSmall=null, figureFileBig=null, tableContent=
模块序号 主要风险主题 关键词
模块一 主题二、主题三
主题四、主题五
飞行高度、飞行时间延长、进场飞机、起飞、冲/偏出跑道、复飞、中断起飞、跑道侵入、穿越跑道……
模块二 主题七、主题十
主题十一、主题十三
垂直间隔、空中接近、潜在冲突、最后进近阶段、复杂程度、航迹交叉、容量、扇区、空域……
模块三 主题六、主题九
主题十四、主题十六
通信强度高、管制频率饱和、空中防撞系统、地面迫近警告系统、气象雷达、安全管理体系、管理制度不完善、风切变、雷暴……
模块四 主题八、主题十一
主题十五
失去安全间隔、高度错误、操作不当、情景意识缺失、注意力分散、口误、错误印象、人为因素、理解偏差……
), ArticleFig(id=1207343663890403774, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1207343640846898064, language=CN, label=表3, caption=

各模块中主要涉及的风险主题及关键词

, figureFileSmall=null, figureFileBig=null, tableContent=
模块序号 主要风险主题 关键词
模块一 主题二、主题三
主题四、主题五
飞行高度、飞行时间延长、进场飞机、起飞、冲/偏出跑道、复飞、中断起飞、跑道侵入、穿越跑道……
模块二 主题七、主题十
主题十一、主题十三
垂直间隔、空中接近、潜在冲突、最后进近阶段、复杂程度、航迹交叉、容量、扇区、空域……
模块三 主题六、主题九
主题十四、主题十六
通信强度高、管制频率饱和、空中防撞系统、地面迫近警告系统、气象雷达、安全管理体系、管理制度不完善、风切变、雷暴……
模块四 主题八、主题十一
主题十五
失去安全间隔、高度错误、操作不当、情景意识缺失、注意力分散、口误、错误印象、人为因素、理解偏差……
)], 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.1671-1815.2406197, detailUrlEn=https://castjournals.cast.org.cn/joweb/kxjsygc/EN/10.12404/j.issn.1671-1815.2406197, pdfUrlCn=https://castjournals.cast.org.cn/joweb/kxjsygc/CN/PDF/10.12404/j.issn.1671-1815.2406197, pdfUrlEn=https://castjournals.cast.org.cn/joweb/kxjsygc/EN/PDF/10.12404/j.issn.1671-1815.2406197, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
民航管制运行风险主题发现及演化趋势
收藏切换
PDF下载
张洪海 , 戴一鸣 * , 刘文泉 , 石宗北 , 李一可
科学技术与工程 | 论文·航空、航天 2025,25(17): 7417-7429
收起
收藏切换
科学技术与工程 | 论文·航空、航天 2025, 25(17): 7417-7429
民航管制运行风险主题发现及演化趋势
全屏
张洪海 , 戴一鸣* , 刘文泉, 石宗北, 李一可
作者信息
  • 南京航空航天大学民航学院, 南京 211106
  • 张洪海(1979—),男,汉族,山东菏泽人,博士,教授,博士研究生导师。研究方向:空管协同化与智能化、城市空中交通、智慧低空物流。E-mail:

通讯作者:

*戴一鸣(2001—),男,汉族,辽宁沈阳人,硕士研究生。研究方向:空管协同化与智能化。E-mail:
Risk Topics Discovery and Trend in Air Traffic Control Operations
Hong-hai ZHANG , Yi-ming DAI* , Wen-quan LIU, Zong-bei SHI, Yi-ke LI
Affiliations
  • Civil Aviation College, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, China
出版时间: 2025-06-18 doi: 10.12404/j.issn.1671-1815.2406197
文章导航
收藏切换

空中交通管制运行安全正面临多元风险致因导致潜在危害的问题。为解决多元风险引发的管制不安全运行问题,基于对管制不安全运行事件报告的全面分析,对管制运行安全风险信息和潜在规则进行挖掘;通过对隐含狄利克雷分布(latent Dirichlet allocation,LDA)风险主题发现模型挖掘的风险主题和关键词进行分析,明确管制运行风险主题及不同风险主题间相互演化规律;针对风险主题关键词,构建了民航管制运行领域的基于BERT(bidirectional encoder representation from Transformers)模型的语义网络,分析风险主题相互关联的风险特征,得出风险主题间潜在关系,可为关键词间关联度的量化提供一定理论依据;促进民航管制运行安全风险的数字化呈现的发展,挖掘管制不安全信息,为准确感知管制运行风险奠定基础。

空中交通管理  /  管制运行安全  /  风险管理  /  LDA主题模型  /  语义网络

In order to address the challenges posed by multifaceted risk factors in air traffic control operations, a comprehensive analysis of unsafe operational incident reports was performed to extract risk-related information and identify underlying patterns. The latent Dirichlet allocation (LDA) model was utilized to uncover key risk topics and associated keywords, and the evolutionary relationships among different risk themes were systematically analyzed. A semantic network for the civil aviation air traffic control domain was constructed using the bidirectional encoder representation from Transformers(BERT) model to examine the interconnections and potential dependencies among risk topics. This network provides a theoretical foundation for quantifying the association between keywords. The findings indicate that the proposed approach enhances the digital representation of safety risks in air traffic control operations. It is concluded that the results offer valuable insights for advancing risk assessment and mitigation strategies in civil aviation air traffic control systems. The relevant research results can better mine air traffic control unsafe information and lay a foundation for accurately perceiving air traffic control operations risks.

air traffic management(ATM)  /  air traffic control operational safety  /  risk management  /  latent Dirichlet allocation (LDA) topics model  /  semantic network
张洪海, 戴一鸣, 刘文泉, 石宗北, 李一可. 民航管制运行风险主题发现及演化趋势. 科学技术与工程, 2025 , 25 (17) : 7417 -7429 . DOI: 10.12404/j.issn.1671-1815.2406197
Hong-hai ZHANG, Yi-ming DAI, Wen-quan LIU, Zong-bei SHI, Yi-ke LI. Risk Topics Discovery and Trend in Air Traffic Control Operations[J]. Science Technology and Engineering, 2025 , 25 (17) : 7417 -7429 . DOI: 10.12404/j.issn.1671-1815.2406197
安全是民航业的生命线,空中交通管制(air traffic control,ATC)部门在民航业运行安全保障方面发挥着至关重要的作用。随着中国民航业的快速发展,据统计,中国民航旅客运输量已占全球运输总量的13%,机场和空域空间变得愈发拥挤,为空中交通管制运行带来了压力,空中交通管制不安全运行事件时有发生。管制不安全运行事件被认为是民航事故率增长的主要原因之一,导致航空运输效率和安全绩效下降[1-2]。过去20年来,中国管制不安全运行事件数量持续增加,引起公众对民航安全高度关注[3],管制不安全事件的发生直接影响民航体系运行安全与效率,成为当前亟待解决的问题。
管制不安全运行事件因素复杂多样,包括人为失误、设备问题及恶劣天气等。中国民航近年来在管理体系、设备升级及管制员培训方面取得显著成效,然而高密度机场(如北京首都国际机场、上海浦东国际机场)在高负荷运行环境下,仍面临一系列复杂且不确定风险,引发诸如虹桥机场跑道入侵事件等管制不安全事件的发生。管制运行不安全事件致因呈现多样化与复杂化趋势,仍需进一步挖掘管制运行风险的深层次因素。
为明确管制不安全运行事件的发生机制和主要因素,有研究试图挖掘历史上众多管制不安全运行事件报告中潜在的安全风险及态势感知因素[4-5]。为预防各种管制不安全运行事件发生,一些学者对管制运行安全因素的检索以及风险演化规律的调查进行了探索[6]。其中,影响因素分析包括传统分析方法[7-8]和现代文本分析技术[9-10]。传统分析方法在揭示事件间潜在关联和风险演化规律方面存在一定局限性;现代文本分析技术能够提取控制操作风险因素,识别不同不安全事件属性之间的多级关联关系。风险演化规则主要面向分析跑道侵入、硬着陆、通信故障等不安全事件并跟踪航空事故调查报告[11-13],利用事故报告进行分析的方法已逐步发展为评估各个领域安全绩效的重要技术。Samuel等[14]将自然语言理解方法运用于航空安全数据分析,实现了从航空安全报告系统(aviation safety reporting system,ASRS)语料库中提取航空事件分类及文本挖掘;Xu等[15]通过文本分类技术对航空安全监督报告中叙述性文本进行分类,确定报告中人为因素主题,为自然语言处理在语义构建中的使用提供实例验证,并明确了优先考虑管制安全运行的方向。
机器学习和自然语言处理领域的进步促进了文本数据挖掘和语义关系分析的发展,主题模型和语义网络已成为自然语言处理领域内重要工具。隐含狄利克雷分布(latent Dirichlet allocation,LDA)主题模型[16]在文本数据挖掘方面具有强大性能,可以从大量文本数据中提取文档的主题信息。Grigorev等[17]提出了一种基于机器学习的事故持续时间预测模型,实现文本特征与非文本变量的结合;Kuhn等[18]对航空安全报告系统数据进行主题建模,揭示了隐藏的风险因素; Sun等[19]使用LDA 主题模型对22种交通方向的期刊17 163篇文章进行评估,推断出50个主要主题,实现了期刊与国家及地区在聚合主题分布中相似度的量化;陈可嘉等[20]针对文本表示中的问题,提出了一种基于LDA主题模型的文本表示改进方法;张思松等[21]利用语义网络构建线上文本的语义网络挖掘模型,实现了线上文本的有效挖掘;Atul等[22]利用语句中的潜在词序和上下文关系并结合语料库统计数据和分层数据库,确定了语句对间相似性的计算;陈芳等 [23]利用语义网络分析对269条管制不安全数据进行语料挖掘,将关联关系进行可视化并进行语义网络分析,实现对非结构化管制运行数据的充分利用。基于主题模型的挖掘方法虽可以从管制不安全运行事件报告中发现一般主题,但会忽略管制运行风险主题随时间变化的趋势和规律。
由于LDA模型只考虑了词频,没有考虑词序或语义关系,而语义网络缺乏对关键词间相似度的量化,使得在探索管制运行风险主题时,很难真实反映主题关键词间相互依赖程度。而深度双向预训练语言模型(bidirectional encoder representation from transformers,BERT)[24]则能够结合上下文语义信息,对词汇进行向量化,以揭示关键词之间的相关性。再通过结合语义网络[25],可以显著表示关键词间关联关系,从而更准确表示管制运行安全风险知识。
上述研究集中于探究特定不安全事件的影响因素关联性、特征规律等,并由此提出相应的改进措施,但对管制不安全运行事件分析大多泛化程度高、对文本数据探究不够彻底、不能够有效挖掘相应的风险因素,忽略了管制运行过程中各类风险主题的相互演化。为实现更准确高效地从海量数据中提取关键信息的要求,适应日益增长的民航运输量,现结合大量管制不安全运行事件报告,创建针对管制运行安全风险管理的分词语料库,有效解决分词歧义和特殊术语问题;构建管制运行安全风险主题模型,系统识别中国民航管制运行风险主题,弥补主题模型在探索管制运行安全风险主题方面的局限性,揭示不同管制运行风险主题的历史趋势和因素,并更准确地对这些风险主题中的主要风险因素进行定位;构建的民航管制语义网络提高对事件报告的专业理解,量化不同风险主题共性的演变,识别的风险主题不仅为管制运行风险态势感知和管制安全态势综合评估提供重要参考,还可为提升当前管制运行安全水平与推动民航安全管理现代化提供理论基础和技术支持。
在探究民航管制不安全运行事件事理逻辑前,需洞悉管制运行过程中存在的风险因素及主题。首先对管制不安全运行事件报告进行处理,然后构建民航管制运行风险主题发现模型,将处理好的文本数据输入,从而实现民航管制运行风险分类表征。
通过航空安全报告系统收集了2000—2022年共16 985份空中交通管制相关不安全运行事件报告。每份事件报告都包含事件报告编号、日期/时间、地点、运行环境、航空器信息、人员信息、原因分析和事件经过等信息,图1为经过处理的管制不安全运行事件报告样例数据及数量统计。
图1中统计了各个年份的报告数量,可以看出2010—2019年报告数量相对较多,2020—2022年由于全球受疫情的影响民航航班数量锐减,不安全事件报告呈现下降趋势。
风险主题发现前需将管制不安全运行事件报告整理成待输入的文本集。首先通过构建中文停用词词库,停用与空中交通管制运行无关的词语,如介词、代词和特殊符号等;其次向停用词词库中补充常出现在报告中但又不能表明管制不安全运行事件具体信息的词汇,如时间、跑道号、滑行道号、速度单位、高度单位等词汇;然后依据民航管制领域和安全领域的专业词汇,同时参照相关法规、文献及现有管制不安全运行事件报告构建空中交通管理领域词典,避免在分词过程中将领域专业词汇分割开来,从而进一步提高语义的准确性;最终所构建的停用词词库共含有2 536个词语,领域词典共含有4 819个词语。同时,在管制不安全运行事件报告中,由于中文的复杂性会出现多个词语表达同一个意思的情况,例如“分散了注意力”“注意力分散”“失去情景意识”与“丧失情景意识”等。因此,在对文本数据进行分词时,还需要构建同义词转换表对分词后的结果进行同义词转换。
利用Python中Jieba分词工具对管制不安全运行事件报告进行分词处理,在分词过程中通过对词语词性进行标注并对词性进行过滤。经上述预处理后最终生成能够输入LDA主题模型的语料数据。
LDA是一种主题建模技术,用于发现文本数据中隐藏的主题结构。它假设文档是由多个主题混合而成的,而每个主题又由一组关键词组成。通过分析文档中的关键词分布,LDA主题模型可以推断出主题与文档之间的概率关系,从而揭示文本数据中的潜在主题,其概率图模型如图2所示。
在LDA模型中,K为管制运行风险主题数量;M为管制不安全运行事件报告数量;αθm先验分布;θm为第m个不安全事件报告主题分布;Zm,n表示从θm中生成不安全事件报告m的第n个词的主题;wm,n表示最终生成第m个不安全事件报告的第n个词;βϕk先验分布;ϕk为词分布;Nm为不安全事件报告m中词语总数。在进行LDA主题模型训练前,需要预先指定超参数αβ和主题数K。参数α影响着事件报告的主题稀疏性,α越高对主题稀疏性的影响越小,主题分布越均匀,即生成的文档混合了大量主题,而α越低对主题稀疏性的影响越大,主题分布越稀疏,即生成的文档涵盖少量的主题数。参数β影响着每个主题下关键词的稀疏性,β越高意味着对关键词的稀疏性影响越小,即生成的每个主题下所包含语料库中大部分关键词,因此这些关键词所表明的主题更为一般,而β越低意味着对关键词的稀疏性影响越大,即每个主题下的关键词分布更不均匀,所表明的主题更为具体。在LDA主题模型训练的过程中,随着所发现的主题数量越来越多,研究期望生成的每个文档所包含的主题数量更少且更为具体。
对于主题数K的确定,将采用困惑度指标来度量最优的主题数,困惑度越小,则表明主题模型的效果越好,其计算公式为
$\mathrm{P}\mathrm{e}\mathrm{r}\mathrm{p}\mathrm{l}\mathrm{e}\mathrm{x}\mathrm{i}\mathrm{t}\mathrm{y}=\mathrm{e}\mathrm{x}\mathrm{p}\left\{\frac{1}{N}\stackrel{N}{\sum _{i=1}}\left[\mathrm{C}\mathrm{E}\right({p}_{i},{q}_{i}\left)\right]\right\}$
式(1)中:N为测试集中的样本数量;CE(pi,qi)为第i个样本的交叉熵,pi为真实的概率分布,qi为预测模型的概率分布。
在以往大多数LDA主题模型训练研究中[26-27],通常将α设置为α=50/K,β设置为β=0.01,此时模型生成的结果呈现了较其他参数值更好的效果。采用上述参数值时,对于主题数K的确定,困惑度计算公式为
$\mathrm{P}\mathrm{e}\mathrm{r}\mathrm{p}\mathrm{l}\mathrm{e}\mathrm{x}\mathrm{i}\mathrm{t}\mathrm{y}=\mathrm{e}\mathrm{x}\mathrm{p}\left[-\frac{\stackrel{M}{\sum _{m=1}}\mathrm{l}\mathrm{o}{\mathrm{g}}_{2}p\left({w}_{m}\right)}{\stackrel{M}{\sum _{m=1}}{N}_{m}}\right]$
式(2)中:Perplexity为困惑度;P(wm)为文档m中词wm的概率;Nm为文档m的字数。
为探究主题模型结果的稳定性和一致性,对不安全事件报告进行管制运行风险主题提取。将16 985份不安全事件报告打乱,分别计算出2 500、5 000、7 500、10 000、12 500和16 985份空管不安全事件报告的困惑度曲线,如图3所示。在6组对照实验中,可以看出,随着不安全事件报告数量的增加,困惑度曲线的最小值稳定在K=16处。因此,从事件报告中共发现16个主题。
为探究主题模型结果的稳定性和一致性,对不安全事件报告进行管制运行风险主题提取。将16 985份不安全事件报告打乱,分别计算出2 500、5 000、7 500、10 000、12 500和16 985份空管不安全事件报告的困惑度曲线,如图3所示。在6组对照实验中,可以看出随着不安全事件报告数量的增加,困惑度曲线的最小值稳定在K=16处。因此,从事件报告中共发现16个主题。
在原始数据集中,每篇不安全事件报告都有对应的时间信息,通过结合LDA主题模型识别结果,对风险主题随时间的变化趋势及演化规律进行进一步探讨。对主题变化趋势的分析,采用主题强度指标来度量风险主题的变化趋势,计算出不同时间窗口下不同风险主题强度并绘制风险主题变化趋势图与风险主题百分比图,以便进一步分析风险主题变化趋势。其计算公式为
${\partial }_{z}^{t}=\frac{\stackrel{{p}^{t}}{\sum _{p=1}}{\partial }_{z}^{p}}{T}$
式(3)中:${\partial }_{z}^{t}$为不安全事故报告p中风险主题z所占比例;pt为时间窗口t中的文本报告数据集。
为进一步细化风险主题的变化趋势,在较长时间跨度内设置时间节点Tmid,将数据按时间节点划分为两部分,即分为Tstart~TmidTmid~Tend的数据,分别计算各风险主题在这两个时间段内的环比增长率Di,其计算公式为
${D}_{i}=\frac{\stackrel{{T}_{\mathrm{e}\mathrm{n}\mathrm{d}}}{\sum _{y={T}_{\mathrm{m}\mathrm{i}\mathrm{d}}}}{\delta }_{yi}-\stackrel{{T}_{\mathrm{m}\mathrm{i}\mathrm{d}}}{\sum _{y={T}_{\mathrm{s}\mathrm{t}\mathrm{a}\mathrm{r}\mathrm{t}}}}{\delta }_{yi}}{\stackrel{{T}_{\mathrm{m}\mathrm{i}\mathrm{d}}}{\sum _{y={T}_{\mathrm{s}\mathrm{t}\mathrm{a}\mathrm{r}\mathrm{t}}}}{\delta }_{yi}}$
式(4)中:Di为风险主题i的环比增长率;δyi为风险主题i在第y年的数量。
通过上述计算公式,可以得出各风险主题的环比增长率Di
LDA模型是一种文本语料库挖掘算法,对于从长文本中提取主题信息特别有效,然而LDA模型只考虑了词频,没有考虑词序或语义关系,缺乏关键词之间关联的描述与模型有效性。因此,在探索管制运行领域的风险主题时,很难真实反映主题关键词之间相互依赖程度。为更好结合上下文语义信息,对词汇进行向量化,以揭示关键词之间的相关性,将使用BERT语言模型构建语义网络模型,进而显著地表示关键词之间的关联关系,更准确地表示管制运行安全风险知识。
BERT是一种基于深度学习的预训练语言模型,采用Transformer架构并通过大规模无监督学习从大量文本中抽取出丰富的语言表示,其结构如图4所示。与传统语言模型相比,BERT语言模型不仅能够双向理解上下文,还能捕捉更复杂的语义信息,使其在各种自然语言处理任务中取得了显著的性能提升。BERT的模型结构和预训练策略使其成为当前自然语言处理领域的主流技术之一。与LDA模型相比,BERT的优势主要体现在深度神经网络架构使BERT能够学习更复杂的语言特征和语境信息;无须标注数据即可进行无监督预训练,适用性更广;能够全局感知语境并更好地理解和生成文本;可通过微调适应特定任务,具有更强泛化能力等方面。
采用BERT模型计算的关键词向量将会更加贴合民航管制领域,利用民航管制领域BERT模型对关键词进行数字化表征并通过式(5)计算关键词之间的词语相似度。具体计算过程如下。
步骤1 利用空中交通管理领域BERT模型计算关键词ABn维词向量为Ai=(x1,x2,…,xn),Bi=(x1,x2,…,xn)。
步骤2 利用式(5)计算词向量间的余弦相似度。
$\mathrm{c}\mathrm{o}\mathrm{s}(\mathit{A},\mathit{B})=\frac{AB}{\Vert A\Vert \Vert B\Vert }=\frac{\stackrel{n}{\sum _{i=1}}{A}_{\mathrm{i}}{B}_{\mathrm{i}}}{\sqrt{\stackrel{n}{\sum _{i=1}}({A}_{\mathrm{i}}{)}^{2}}\sqrt{\stackrel{n}{\sum _{i=1}}({B}_{\mathrm{i}}{)}^{2}}}$
式(5)中:cos(A,B)为关键词A和关键词B的余弦相似度;Ai为关键词A的词向量第i个分量;Bi为关键词B的词向量第i个分量。
步骤3 利用式(5)计算得出的词语间相似度,可以得到m个关键词的相似度矩阵S,如式(6)所示。
$\mathit{S}=\left[\begin{array}{llll}{s}_{11}& {s}_{12}& \dots & {s}_{1m}\\ {s}_{21}& {s}_{22}& \dots & {s}_{2m}\\ ︙& ︙& & ︙\\ {s}_{m1}& {s}_{m2}& \dots & {s}_{mm}\end{array}\right]$
式(6)中:S为关键词的相似度矩阵;sij为第i个关键词和第j个关键词间的余弦相似度。
步骤4 引入语义网络图G=(V,E),其中V={V1,V2,…,Vn}。其邻接矩阵及相似度矩阵S
$\mathit{S}=\left\{\begin{array}{l}1,\mathrm{c}\mathrm{o}\mathrm{s}(A,B)\ge \varphi \\ 0,\mathrm{c}\mathrm{o}\mathrm{s}(A,B)<\varphi \end{array}\right.$
式(7)中:ϕ为临界相似度,结合现有研究成果决定设置ϕ=0.8[28]
依据LDA主题模型得出事件报告的主题编号,并统计每个主题下事件报告数量如图5所示。
为更清晰地表示每个主题的关键词信息,对关键词重要度进行排序并显示前30个关键词,绘制词云图如图6所示。
图6中,颜色越深,字体越大的词语表明在该主题中较为重要,在图中确定的主题揭示了民航管制运行时存在的潜在风险。结合图5图6所示信息,如主题十六(设施设备)中包含雷达、仪表着陆系统、编码有误、甚高频全向信标(VHF omnidirectional radio range, VOR)、故障、空中防撞系统(traffic collision avoidance system, TCAS)等关键词,该主题突出显示了民航管制运行过程中空管设施设备的良好性将会直接影响到管制运行的安全性。主题四(起飞/离场阶段)涉及航班起飞/离场阶段,该主题包含起飞、起飞许可、放行许可、中断起飞、起飞间隔、起飞许可助记符、尾流、检查清单等关键词。主题七(进近/进场阶段)包含进近、进近过程不稳定、最后进近阶段、进场飞机、工作负荷、操作不当、排序、缺乏整体战略等关键词,介绍了飞机在进近进场阶段时的运行情况。同时,主题十二(下降/着陆阶段)中包含着陆、下降率、交叉检查、着陆许可、垂直速度、擦机尾等关键词,这些关键词集中表明飞机在下降/着陆阶段的运行情况。在图5中,主题四(起飞/离场阶段)、主题七(进近/进场阶段)和主题十二(下降/着陆阶段)的事件报告数量总和占全部事件报告的23%,故民用航空器起飞、下降和进近着陆阶段是管制安全事故多发阶段,相关研究表明在民用航空器起飞、下降和进近着陆阶段需要频繁的进行人工操作,而不合时宜的指令和机动动作会造成管制不安全运行事件发生[29-31]
主题三(冲/偏出跑道)在所有风险主题中数量最多,包含冲/偏出跑道、交叉检查、复飞、减速过晚、风向变化、滑水现象、湿雪、所需距离等关键词,反映了冲/偏出跑道等方面的风险因素。主题五(跑道侵入)反映了跑道侵入风险,其中包含进入跑道、跑道侵入、注意力分散、情景意识缺失、穿越跑道、脱离跑道、滑行道布局、跑道警戒灯等关键词。主题十(飞行冲突)所包含的关键词为冲突、航迹交叉、飞行冲突、空中接近、告警、轨迹相对、危险接近等,主要反映了管制运行过程中飞行冲突风险。冲/偏出跑道、跑道侵入和飞行冲突这三类风险在管制运行过程中往往所造成的后果较为严重,同时结合相应空管不安全事件报告可以看出这三类运行风险大多都是由多因素共同作用所导致。
一些风险主题还涉及相关的人为因素,例如主题八(人为差错)和主题十五(表达不准确)表明在管制运行过程中出现疲劳、紧张、习惯性差错、错误印象、口误、未遵守标准操作程序、复诵错误等情况时会造成不安全事件的发生,因此在面对这类风险主题时需相关人员着重提高专业技能和专注度,以避免类似事件的发生。还有一些风险主题涉及不安全事件发生时的空域运行状况、空域结构或运行规则/程序、运行模式等,从这些主题中可以发现不合理的空域结构、复杂的运行规则/程序以及运行模式的改变都会影响管制运行的安全性。
此外,主题九(管理因素)表明了一些国家或地区的安全管理体系不完善、监管水平过低,导致管制团队整体职责体系失效,从而引发管制不安全运行事件的发生。同时,主题九(管理因素)也反映了机组资源管理的重要性。因此,完善管理制度、遵守标准操作程序、明确岗位职责等能够有效提高民航管制运行的安全性。主题十四(气象因素)则反映了管制运行过程中恶劣的天气条件、低能见度运行、各类天气现象等都会增加管制和机组的工作压力与工作负荷,直接或间接造成不安全事件的发生。
从16 985份不安全事件报告中提取出的风险主题,揭示了管制运行过程中潜在危险因素,这些风险主题直接或间接影响着民航管制运行的安全性。
为揭示近年来风险主题的变化,截取2009—2022年的数据研究风险主题变化趋势,其结果如图7所示。同时进一步统计并计算各类风险主题在每一年占比情况,以明确风险主题趋势与风险主题间的相关性,如图8所示。由图7图8可以看出,一些风险主题随时间呈现下降趋势,如主题四、主题六、主题十一和主题十四,这四类风险主题分别表示起飞/离场阶段、通信失联、飞行间隔和气象因素。一些风险主题呈现上升趋势,如主题二和主题八,这两类风险主题分别表示飞行高度和人为差错。一些风险主题随时间呈现先上升后下降的趋势,如主题三(冲/偏出跑道)、主题五(跑道侵入)、主题十二(下降/着陆阶段)和主题十三(空域运行环境)。其余大部分风险主题在本研究中随时间呈现明显的上下波动。同时,由于受全球疫情影响民航航班数量大规模减少,因此在近三年中各类风险主题数量都有所下降。
基于式(4),将数据分为2010—2014年和2015—2019年的数据,分别计算各风险主题在两个时间段内的环比增长率Di,其计算公式为
${D}_{i}=\frac{\stackrel{2019}{\sum _{y=2015}}{\delta }_{yi}-\stackrel{2014}{\sum _{y=2010}}{\delta }_{yi}}{\stackrel{2014}{\sum _{y=2010}}{\delta }_{yi}}$
通过式(8),得出各风险主题的环比增长率Di,其计算结果如表1所示,主题四、主题六和主题十一同比下降幅度最大,这些主题分别涉及起飞/离场阶段、通信失联和飞行间隔等方面;主题二、主题七和主题九同比增长幅度最大,其中主题二主要涉及飞行高度相关风险因素,主题七主要涉及进近/进场阶段相关风险因素,主题九主要涉及管制运行管理相关风险因素;其余大部分风险主题同比变化幅度不大,但也呈现上升趋势。
图9具体展示了主题二(飞行高度)、主题四(起飞/离场阶段)、主题六(通信失联)、主题七(进近/进场阶段)、主题九(管理因素)和主题十一(飞行间隔)随时间的变化趋势。
依据以上结果,对主题二(飞行高度)、主题四(起飞/离场阶段)、主题六(通信失联)、主题七(进近/进场阶段)、主题九(管理因素)和主题十一(飞行间隔)主要原因进行统计分析。在图10中,2015—2019年主题四(起飞/离场阶段)、主题六(通信失联)和主题十一(飞行间隔)中造成不安全事件的各主要原因相比前五年均有大幅减少,而主题二(飞行高度)、主题七(进近/进场阶段)和主题九(管理因素)则有大幅增加,可见在所有风险主题的主要原因中占比较大的是人为因素和运行规则/程序等原因。
依据表1图10的结果并结合具体事件报告,风险主题随时间变化的趋势很大程度上受人为因素(如管制员业务技能或工作负荷及疲劳度等)和管制运行规则/程序(如不合理的管制移交程序或空域设计不合理等)的影响。同时,随通信、导航和监视系统性能和精度的提高,在一定程度上降低了管制不安全运行事件的发生频率。
依据风险主题识别结果,将空管不安全运行事件报告输入BERT语言模型中,基于Gephi软件选取相似度来构建语义网络,可视化展示词语之间关联关系并计算出各拓扑指标数值。在构建的语义网络图中,共有155个节点和1 239条边。语义网络中节点为各类风险主题的关键词,边为各关键词之间的相似度。每个节点的大小与其在语义网络中的平均度值成正相关,节点越大则表明与其相连的词语越多;边的宽度与关键词之间的相似度成正相关,边越宽则表明两个关键词越为相近。各个拓扑指标如表2所示。
根据计算得出的拓扑指标,对构建的语义网络进行综合分析。首先,该网络的平均度达到15.111,表明网络中的平均节点与其他节点有着大约15.111个连接,每个节点平均与其他节点有相对较多的关联,节点之间存在相对密集的连接关系,表现网络中关键词之间多样而丰富的语义关联,不同关键词间存在较强烈的相似性。其次,网络的直径为6,表明任意两个节点之间最短路径长度最多为6,网络具有较好的全局连通性,信息传递路径相对较短,信息传播相对迅速,因信息可通过较短路径在网络中传播,有利于信息的快速传播和交流。 然而,图密度仅为0.099,表明图中实际存在边的数量仅占可能存在边的数量约9.9%,网络中实际连接相对较少,可能存在着一些未被发现或未被建立的潜在连接。平均聚类系数达到0.492,表明网络中节点具有较强的聚类特性,节点倾向于形成闭合的三角形结构,即各节点与邻居节点之间存在较多连接,存在比较密集的子图或社区结构,节点之间的关联性比较紧密。最后,网络的平均路径长度为2.428,表明任意两个节点之间平均最短路径长度大约为2.428,表明节点之间连接较紧密,信息传播速度较快,因信息传播或者搜索路径相对较短,较小的平均路径长度可以提高网络效率,加速信息传输或挖掘。
上述构建的语义网络表现出一定的稠密性和聚类性,表明部分关键词间具有相似关系,反映出空管不安全运行事件报告中事件主要原因存在共通性。但该网络也存在一定程度的网络稀疏性,这些特征对网络信息传播和语义关联产生重要影响。
为揭示各类风险主题间的潜在关系,使用基于多层次模块化优化社群识别算法的Louvain聚类算法[32]对民航管制运行安全风险语义网络进行聚类分析。将图中节点划分为具有高内聚性和低耦合性的社群,最大化社群内部连接强度并最小化不同社群之间的连接,在不指定具体社群数量的情况下短时间内实现不同粒度的大规模网络社群划分。
利用Louvain聚类算法将构建的语义网络中关键词分为不同模块,使用相同的颜色表示同一模块中的关键词。最终,共计算出4个模块,如图11所示。可见同一模块内关键词之间的连接相对密集,而不同模块中关键词间的连接相对稀疏。
民航管制运行安全风险语义网络不仅表示了关键词间的相互联系,同时还揭示了风险主题间的潜在关系。在图11中,模块一(橙色区域)的节点主要涉及主题二(飞行高度)、主题三(冲/偏出跑道)、主题四(起飞/离场阶段)和主题五(跑道侵入)的关键词;模块二(紫色区域)的节点主要涉及主题七(进近/进场阶段)、主题十(飞行冲突)、主题十一(飞行间隔)和主题十三(空域运行环境)的关键词;模块三(绿色区域)的节点主要涉及主题六(通信失联)、主题九(管理因素)、主题十四(气象因素)和主题十六(设施设备)的关键词;模块四(蓝色区域)的节点主要涉及主题八(人为差错)、主题十一(飞行间隔)和主题十五(表达不准确)的关键词。可以看出在相同颜色区域内的风险主题有着更为紧密的联系。根据风险主题关键词,对每个模块中所包含的风险主题进行统计分析,如表3所示。
结合图11表3,在同一模块中的风险主题具有相互关联的风险特征并且其关键词间联系更为密集。例如,模块二中主题十(飞行冲突)和主题十一(飞行间隔),反映了当管制运行过程中出现飞行冲突时可能会导致违反飞行安全间隔的情况,进而导致不安全事件的发生。模块四种主题八(人为因素)和主题十五(表达不准确)联系比较密集,这就表明这两个主题间存在相互演化的规律。因此,对管制运行风险进行控制时需要持续关注风险演化,从而做到提前掐断风险传播路径。
通过民航管制运行安全风险语义网络可以量化关键词之间关联度,揭示各类风险主题之间相关性,在处理非结构化文本数据方面也具有很大潜力。
针对空中交通管制运行风险主题分析问题聚焦于空管不安全事件文本数据,对16 985份管制运行不安全事件报告风险类别进行提取,发现16类主题揭示了过去二十年民航管制运行过程中的风险因素,实现了以数据驱动的风险管理。挖掘管制运行风险,构建民航运行风险语义网络,能够为管制运行风险的精准防控提供参考,协助空中交通管理单位进一步探究不安全事件的形成原因,进而对管制流程、空域结构、人员管理等方面进行优化。
(1)通过LDA主题模型民航管制不安全运行事件报告风险类别进行主题提取,揭示了过去二十年民航管制运行过程中的风险因素,实现了以数据驱动的风险管理。
(2)探究近年来每个风险主题随时间变化的趋势,对不安全事件主要原因进一步分析,表明人为因素在所有主要原因中所占比例最大。
(3)提出民航管制运行风险语义网络构建方法,基于各类风险主题关键词,构建了民航管制运行风险领域的BERT语言模型及语义网络,揭示各类风险主题及关键词间潜在的关联关系和相似的风险特征,表明一些风险主题具有相互关联的风险特征及相互演化的规律。
针对揭示的关键风险主题及其演化规律,建议通过系统性改进以提升我国民航管制运行安全水平。针对高频风险,如冲/偏出跑道与跑道侵入,优化滑行路径,提升指令执行精度与可靠性。考虑人为差错与表达不准确等风险,在高密度运行环境下,建议加强疲劳管理,减轻长时间工作对判断力的影响并规范管制通话用语。为应对设备故障和极端天气条件导致的风险,应加快导航与监控设备优化升级,加强对雷暴和风切变等恶劣天气的监测预警能力。优化空域管理与管制移交程序,简化复杂运行环境,有助于提高运行效率。相关改进措施的推广将进一步提升中国民航管制运行安全及效率。
由于在实时监测风险主题方面尚有不足,因此在后期研究中,将考虑对管制运行风险的实时监测、评估与预警,并集成先进信息技术以提升管制运行风险管理效率,进一步提升空中交通管制运行安全性,为民航业可持续发展做出更大贡献。
  • 国家自然科学基金民航联合基金(U2133207)
  • 中国工业和信息化部民用飞机专项科研(MJZ1-7N22)
  • 国家自然科学基金(52202404)
参考文献 引证文献
排序方式:
[1]
Andersen V, Bove T. A feasibility study of the use of incidents and accidents reports to evaluate effects of team resource management in air traffic control[J]. Safety Science, 2000, 35(1): 87-94.
[2]
Olsen S N. Coding ATC incident data using HFACS: inter-coder consensus[J]. Safety Science, 2011, 49(10): 1365-1370.
[3]
Kang J, Yang S, Shan X, et al. Exploring topics and trends in Chinese ATC incident reports using a domain-knowledge driven topic model[J]. Journal of Air Transport Management, 2023, 108: 102374.
[4]
郭东岳. 面向管制指挥的空中交通智能态势感知关键技术研究[D]. 成都: 四川大学, 2023.
Guo Dongyue. Research on key technologies of intelligen[D]. Chengdu: Sichuan University, 2023.
[5]
陈芳, 温抗抗, 张亚博, 等. 民航管制安全风险主题时空分布规律研究[J]. 安全与环境学报, 2024, 24(2): 587-595.
Chen Fang, Wen Kangkang, Zhang Yabo, et al. Spatial and temporal distribution of air traffic control (ATC) safety risk topic[J]. Journal of Safety and Environment, 2024, 24(2): 587-595.
[6]
Ni X, Wang H, Che C, et al. Civil aviation safety evaluation based on deep belief network and principal component analysis[J]. Safety Science, 2019, 112: 90-95.
[7]
王润东, 潘卫军, 陈晓光, 等. 基于博弈论集对分析模型的机坪管制运行风险评价[J]. 科学技术与工程, 2020, 20(30): 12636-12643.
Wang Rundong, Pan Weijun, Chen Xiaoguang, et al. Risk assessment of apron control operation in entropy weight extension model[J]. Science Technology and Engineering, 2020, 20(30): 12636-12643.
[8]
Chai Y, Wang Y G, Wang Y S, et al. Safety evaluation of human-caused errors in civil aviation based on analytic hierarchy process and fuzzy comprehensive evaluation method[J]. Aircraft Engineering and Aerospace Technology, 2024, 96(6) : 826-837.
[9]
Senol E Y. Assessment of human factor contribution to risk analysis of chemical cargo shortage incidents by using intuitionistic fuzzy integrated fault tree analysis[J]. Ocean Engineering, 2024, 301(1): 117559.
[10]
Adam H, Neville A S, Guy H W, et al. Accident analysis in practice: a review of human factors analysis and classification system (HFACS) applications in the peer reviewed academic literature[J]. Proceedings of the Human Factors and Ergonomics Society Annual Meeting, 2019, 63(1): 1849-1853.
[11]
蔡志鹏, 曾维理, 郭子逸. 空中交通管制中的危险源关键特征提取[J]. 航空计算技术, 2023, 53(6): 35-39.
Cai Zhipeng, Zeng Weili, Guo Ziyi. Feature extraction of air traffic control hazard based on text[J]. Aeronautical Computing Technique, 2023, 53(6): 35-39.
[12]
牟奇锋, 郭花, 郝芮. 基于复杂网络的跑道侵入风险因素研究[J]. 计算机与数字工程, 2024, 52(3): 814-820.
Mou Qifeng, Guo Hua, Hao Rui. Research on risk factors of runway incursion based on complex network[J]. Computer & Digital Engineering, 2024, 52(3): 814-820.
[13]
康瑞, 李凌海, 牟睿聆, 等. 因天气影响的航空器绕飞管制安全评估及策略分析[J]. 科学技术与工程, 2024, 24(6): 2590-2600.
Kang Rui, Li Linghai, Mou Ruiling, et al. Safety assessment and strategy analysis of aircraft fly-around control due to weather[J]. Science Technology and Engineering, 2024, 24(6): 2590-2600.
[14]
Samuel K, Thierry K, Laurent L. ASRS-CMFS vs. RoBERTa: comparing two pre-trained language models to predict anomalies in aviation occurrence reports with a low volume of in-domain data available[J]. Aerospace, 2022, 9(10): 591-612.
[15]
Xu Y, Gan Z, Guo R, et al. Hazard analysis for massive civil aviation safety oversight reports using text classification and topic modeling[J]. Aerospace, 2024, 11(10): 837-837.
[16]
Blei D M, Ng A, Jordan M I. Latent Dirichlet allocation[J]. Journal of Machine Learning Research, 2003(3): 993-1022.
[17]
Grigorev A, Mihaita A S, Lee S, et al. Incident duration prediction using a bi-level machine learning framework with outlier removal and intra-extra joint optimisation[J]. ArXiv, 2022: 2205.05197.
[18]
Kuhn D K. Using structural topic modeling to identify latent topics and trends in aviation incident reports[J]. Transportation Research Part C, 2018, 87: 105-122.
[19]
Sun L, Yin Y. Discovering themes and trends in transportation research using topic modeling[J]. Transportation Research Part C, 2017, 77: 49-66.
[20]
陈可嘉, 刘惠. 文本分类中基于单词表示的全局向量模型和隐含狄利克雷分布的文本表示改进方法[J]. 科学技术与工程, 2021, 21(29): 12631-12637.
Chen Kejia, Liu Hui. Improved text representation method based on GloVe and LDA for text classification[J]. Science Technology and Engineering, 2021, 21(29): 12631-12637.
[21]
张思松, 陈文. 基于LDA模型和语义网络的线上文本挖掘方法[J]. 安庆师范大学学报(自然科学版), 2022, 28(2): 41-45.
Zhang Sisong, Chen Wen. Online text mining method based on LDA model and semantic network[J]. Journal of Anqing Normal University(Natural Science Edition), 2022, 28(2): 41-45.
[22]
Atul G, Kalpana S, Kumar K G. Ontology-based similarity computation of two sentences using word-net database[J]. New Generation Computing, 2023, 41(3): 723-737.
[23]
陈芳, 陈茜, 徐碧晨. 基于文本挖掘的管制运行风险主题分析[J]. 中国安全生产科学技术, 2020, 16(11): 47-52.
Chen Fang, Chen Xi, Xu Bichen. Analysis on operation risk topics of air traffic control (ATC) based on text mining[J]. Journal of Safety Science and Technology, 2020, 16(11): 47-52.
[24]
Devlin J, Chang M W, Lee K. BERT: pre-training of deep bidirectional transformers for language understanding[C]// Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies (NAACL-HLT). Florence: IEEE, 2019: 3498-4195.
[25]
Mario K, Anton Z. Predicting research trends with semantic and neural networks with an application in quantum physics[J]. Proceedings of the National Academy of Sciences of the United States of America, 2020, 117(4): 1910-1916.
[26]
Zhao F Y, Ren X B, Yang S S, et al. Latent Dirichlet allocation model training with differential privacy[J]. IEEE Transactions on Information Forensics and Security, 2021, 16: 1290-1305.
[27]
Chang A C, Lin J S. Exploring technological applications through LDA-based patent mining: a metaverse ontology construction[J]. World Patent Information, 2024, 79: 102314.
[28]
Liu W, Zhang H, Shi Z, et al. Risk topics discovery and trend analysis in air traffic control operations: air traffic control incident reports from 2000 to 2022[J]. Sustainability, 2023, 15(15): 12065.
[29]
T, Song W, Du K. Human factors analysis of air traffic safety based on HFACS-BN model[J]. Applied Sciences, 2019, 9(23): 5049.
[30]
Miller M, Holley S, Mrusek B, et al. Assessing cognitive processing and human factors challenges in NextGen air traffic control tower team operations[C]// Advances in Human Factors and Systems Interaction:Proceedings of the AHFE 2020 Virtual Conference on Human Factors and Systems Interaction. Berlin:Springer International Publishing, 2020: 289-295.
[31]
Chi Y, Nie J, Zhong L, et al. A review of situational awareness in air traffic control[J]. IEEE Access, 2023, 11: 134040-134057.
[32]
Blondel V, Guillaume L J, Lambiotte R. Fast unfolding of communities in large networks: 15 years later[J]. Journal of Statistical Mechanics: Theory and Experiment, 2024(10): 10R001.
2025年第25卷第17期
PDF下载
215
102
引用本文
BibTeX
文章信息
doi: 10.12404/j.issn.1671-1815.2406197
  • 接收时间:2024-08-19
  • 首发时间:2025-12-15
  • 出版时间:2025-06-18
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
基金
国家自然科学基金民航联合基金(U2133207)
中国工业和信息化部民用飞机专项科研(MJZ1-7N22)
国家自然科学基金(52202404)
作者信息
    南京航空航天大学民航学院, 南京 211106

通讯作者:

*戴一鸣(2001—),男,汉族,辽宁沈阳人,硕士研究生。研究方向:空管协同化与智能化。E-mail:
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/kxjsygc/CN/10.12404/j.issn.1671-1815.2406197
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