Article(id=1149738767801565331, tenantId=1146029695717560320, journalId=1146031787341344770, issueId=1149738762382524507, articleNumber=1003-3033(2024)07-0020-08, orderNo=null, doi=10.16265/j.cnki.issn1003-3033.2024.07.0229, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1705593600000, receivedDateStr=2024-01-19, revisedDate=1713542400000, revisedDateStr=2024-04-20, acceptedDate=null, acceptedDateStr=null, onlineDate=1752048683357, onlineDateStr=2025-07-09, pubDate=1722096000000, pubDateStr=2024-07-28, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1752048683357, onlineIssueDateStr=2025-07-09, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1752048683357, creator=13701087609, updateTime=1752048683357, updator=13701087609, issue=Issue{id=1149738762382524507, tenantId=1146029695717560320, journalId=1146031787341344770, year='2024', volume='34', issue='7', pageStart='1', pageEnd='252', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=0, createTime=1752048682065, creator=13701087609, updateTime=1757316437713, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1171833331021824745, tenantId=1146029695717560320, journalId=1146031787341344770, issueId=1149738762382524507, language=EN, specialIssueTitle=, coverIllustrator=, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1171833331021824746, tenantId=1146029695717560320, journalId=1146031787341344770, issueId=1149738762382524507, language=CN, specialIssueTitle=, coverIllustrator=, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=20, endPage=27, ext={EN=ArticleExt(id=1149738768036446363, articleId=1149738767801565331, tenantId=1146029695717560320, journalId=1146031787341344770, language=EN, title=Research on DBN incorporating reinforcement learning for runway intrusion risk prediction, columnId=1149733271128420907, journalTitle=China Safety Science Journal, columnName=Safety social science and safety management, runingTitle=null, highlight=null, articleAbstract=

In order to solve the problems of difficulty in quantifying the risk of airport runway incursion events,poor timeliness and low accuracy,and to enhance the capability of predicting runway incursion risks,a DBN model incorporating reinforcement learning for risk prediction was constructed. Firstly,causal inference theory was combined with grey relational analysis to analyze historical runway incursion events and identify the underlying risk factors. Secondly,Bayesian network(BN) theory was applied to explore the correlations among these factors and quantify these correlations using the Pearson linear correlation coefficient. This process helped in constructing a causation correlations network that effectively represented the propagation of risks associated with runway incursions. Then,the triangular fuzzy method and Hidden Markov Models (HMMs) were utilized to further refine and optimize the DBN parameter learning mechanism. Finally,the model's accuracy was validated using historical data. The results demonstrate that the proposed model's predictions of runway incursion risks closely align with the statistical values of historical data,achieving an accuracy rate of 84%,which represents a significant 10% improvement over Bayesian network predictions. Additionally,the use of mutual information to identify key nodes is found to effectively improve accuracy and discrimination compared to the degree value evaluation method.

, correspAuthors=null, 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=Wei WU, Zexuan WU, Xinglong WANG, Longfei ZHU), CN=ArticleExt(id=1149738777020645921, articleId=1149738767801565331, tenantId=1146029695717560320, journalId=1146031787341344770, language=CN, title=融合强化学习的DBN跑道侵入风险预测, columnId=1149733271296193071, journalTitle=中国安全科学学报, columnName=安全社会科学与安全管理, runingTitle=null, highlight=null, articleAbstract=

为解决机场跑道侵入事件风险量化难度大、时效性差、精准性低等问题,提升跑道侵入风险预警能力,构建融合强化学习的动态贝叶斯网络(DBN)风险预测模型。首先,结合因果推断理论与灰色关联分析法分析跑道侵入历史事件,识别跑道侵入事件风险致因;其次,运用贝叶斯网络(BN)理论挖掘各风险因素间的关联性,并利用皮尔逊线性相关系数量化各因素间的关联关系,构建表征风险传播的致因关系网络;然后,利用三角模糊方法与隐马尔可夫模型(HMMs)优化DBN参数学习机制;最后,利用历史数据验证基于融合强化学习的DBN预测结果准确性。结果表明:基于融合强化学习的DBN预测结果与历史数据统计数值的拟合较好,准确率为84 %,与单独DBN预测结果相比准确性提升10 %;相比于采用度值评价法,通过互信息识别关键节点可有效提升预测准确率和区分度。

, correspAuthors=null, authorNote=null, correspAuthorsNote=null, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=k+rsK24OnjLekkCfLbrKWA==, magXml=j0mP/AIfrSh9ET9RkLudLA==, pdfUrl=null, pdf=jk8ZQuFZSsXPyZubT3J5KQ==, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=RFcnJmMMAHSebg5OynJ4+w==, mapNumber=null, authorCompany=null, fund=null, authors=

吴 维 (1982—),男,河北承德人,硕士,讲师,主要从事空中交通系统优化与管理方面的研究。E-mail:

王兴隆 教授

, authorsList=吴维, 吴泽萱, 王兴隆, 祝龙飞)}, authors=[Author(id=1168186499263639978, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738767801565331, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=wuwei8209@163.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1168186499330748844, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738767801565331, authorId=1168186499263639978, language=EN, stringName=Wei WU, firstName=Wei, middleName=null, lastName=WU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 Key Laboratory of Internet of Aircraft,Civil Aviation University of China,Tianjin 300300,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1168186499406246317, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738767801565331, authorId=1168186499263639978, language=CN, stringName=吴维, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 中国民航大学 民航飞联网重点实验室,天津 300300, bio={"content":"

吴 维 (1982—),男,河北承德人,硕士,讲师,主要从事空中交通系统优化与管理方面的研究。E-mail:

"}, bioImg=null, bioContent=

吴 维 (1982—),男,河北承德人,硕士,讲师,主要从事空中交通系统优化与管理方面的研究。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1168186499121033635, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738767801565331, xref=1, ext=[AuthorCompanyExt(id=1168186499125227940, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738767801565331, companyId=1168186499121033635, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 Key Laboratory of Internet of Aircraft,Civil Aviation University of China,Tianjin 300300,China), AuthorCompanyExt(id=1168186499133616549, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738767801565331, companyId=1168186499121033635, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 中国民航大学 民航飞联网重点实验室,天津 300300)])]), Author(id=1168186499477549487, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738767801565331, 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=1168186499536269745, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738767801565331, authorId=1168186499477549487, language=EN, stringName=Zexuan WU, firstName=Zexuan, middleName=null, lastName=WU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2 College of Air Traffic Management,Civil Aviation University of China,Tianjin 300300,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1168186499594990002, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738767801565331, authorId=1168186499477549487, language=CN, stringName=吴泽萱, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2 中国民航大学 空中交通管理学院,天津 300300, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1168186499183948198, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738767801565331, xref=2, ext=[AuthorCompanyExt(id=1168186499192336807, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738767801565331, companyId=1168186499183948198, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 College of Air Traffic Management,Civil Aviation University of China,Tianjin 300300,China), AuthorCompanyExt(id=1168186499196531112, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738767801565331, companyId=1168186499183948198, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 中国民航大学 空中交通管理学院,天津 300300)])]), Author(id=1168186499641127348, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738767801565331, 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=1168186499804705206, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738767801565331, authorId=1168186499641127348, language=EN, stringName=Xinglong WANG, firstName=Xinglong, middleName=null, lastName=WANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 Key Laboratory of Internet of Aircraft,Civil Aviation University of China,Tianjin 300300,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1168186499867619767, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738767801565331, authorId=1168186499641127348, language=CN, stringName=王兴隆, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 中国民航大学 民航飞联网重点实验室,天津 300300, bio={"content":"

王兴隆 教授

"}, bioImg=null, bioContent=

王兴隆 教授

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1168186499121033635, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738767801565331, xref=1, ext=[AuthorCompanyExt(id=1168186499125227940, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738767801565331, companyId=1168186499121033635, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 Key Laboratory of Internet of Aircraft,Civil Aviation University of China,Tianjin 300300,China), AuthorCompanyExt(id=1168186499133616549, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738767801565331, companyId=1168186499121033635, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 中国民航大学 民航飞联网重点实验室,天津 300300)])]), Author(id=1168186499938922937, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738767801565331, 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=1168186500001837499, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738767801565331, authorId=1168186499938922937, language=EN, stringName=Longfei ZHU, firstName=Longfei, middleName=null, lastName=ZHU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2 College of Air Traffic Management,Civil Aviation University of China,Tianjin 300300,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1168186500140249532, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738767801565331, authorId=1168186499938922937, language=CN, stringName=祝龙飞, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2 中国民航大学 空中交通管理学院,天津 300300, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1168186499183948198, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738767801565331, xref=2, ext=[AuthorCompanyExt(id=1168186499192336807, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738767801565331, companyId=1168186499183948198, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 College of Air Traffic Management,Civil Aviation University of China,Tianjin 300300,China), AuthorCompanyExt(id=1168186499196531112, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738767801565331, companyId=1168186499183948198, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 中国民航大学 空中交通管理学院,天津 300300)])])], keywords=[Keyword(id=1168186500417073597, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738767801565331, language=EN, orderNo=1, keyword=reinforcement learning), Keyword(id=1168186500500959678, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738767801565331, language=EN, orderNo=2, keyword=dynamic Bayesian network (DBN)), Keyword(id=1168186500555485631, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738767801565331, language=EN, orderNo=3, keyword=runway incursion), Keyword(id=1168186500689703360, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738767801565331, language=EN, orderNo=4, keyword=risk prediction), Keyword(id=1168186500752617921, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738767801565331, language=EN, orderNo=5, keyword=grey correlation analysis), Keyword(id=1168186500811338178, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738767801565331, language=CN, orderNo=1, keyword=强化学习), Keyword(id=1168186500870058435, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738767801565331, language=CN, orderNo=2, keyword=动态贝叶斯网络(DBN)), Keyword(id=1168186500928778692, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738767801565331, language=CN, orderNo=3, keyword=跑道侵入), Keyword(id=1168186500987498949, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738767801565331, language=CN, orderNo=4, keyword=风险预测), Keyword(id=1168186501046219207, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738767801565331, language=CN, orderNo=5, keyword=灰色关联分析)], refs=[Reference(id=1168186502870741479, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738767801565331, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=null, journalName=null, refType=null, unstructuredReference=United States Department of Transportation of Federal Aviation Aadministration. Runway safety statistics[R], 2022., articleTitle=Runway safety statistics, refAbstract=null), Reference(id=1168186502937850344, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738767801565331, doi=null, pmid=null, pmcid=null, year=2021, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[2], rfOrder=1, authorNames=null, journalName=null, refType=null, unstructuredReference=中国民用航空局航空安全办公室. 中国民航航空安全报告[R], 2021., articleTitle=中国民航航空安全报告, refAbstract=null), Reference(id=1168186502983987689, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738767801565331, doi=null, pmid=null, pmcid=null, year=2012, volume=103, issue=3, pageStart=22, pageEnd=34, url=null, language=null, rfNumber=[3], rfOrder=2, authorNames=ROGERSON E C, LAMBERT J H, journalName=Reliability Engineering and System Safety, refType=null, unstructuredReference=ROGERSON E C, LAMBERT J H. Prioritizing risks via several expert perspectives with application to runway safety[J]. Reliability Engineering and System Safety, 2012, 103(3):22-34., articleTitle=Prioritizing risks via several expert perspectives with application to runway safety, refAbstract=null), Reference(id=1168186503072068074, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738767801565331, doi=null, pmid=null, pmcid=null, year=2017, volume=65, issue=6, pageStart=54, pageEnd=62, url=null, language=null, rfNumber=[4], rfOrder=3, authorNames=JIJOK M, WESLEY L B, MAJOR B, et al, journalName=Journal of Air Transport Management, refType=null, unstructuredReference=JIJOK M, WESLEY L B, MAJOR B, et al. Statistical modelling of runway incursion occurrences in the United States - science direct[J]. Journal of Air Transport Management, 2017, 65(6):54-62., articleTitle=Statistical modelling of runway incursion occurrences in the United States - science direct, refAbstract=null), Reference(id=1168186503155954155, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738767801565331, doi=null, pmid=null, pmcid=null, year=2012, volume=12, issue=4, pageStart=192, pageEnd=196, url=null, language=null, rfNumber=[5], rfOrder=4, authorNames=霍志勤, 韩松臣, journalName=安全与环境学报, refType=null, unstructuredReference=霍志勤, 韩松臣. 跑道侵入的威胁与差错分析及控制研究[J]. 安全与环境学报, 2012, 12(4):192-196., articleTitle=跑道侵入的威胁与差错分析及控制研究, refAbstract=null), Reference(id=1168186503206285804, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738767801565331, doi=null, pmid=null, pmcid=null, year=2012, volume=12, issue=4, pageStart=192, pageEnd=196, url=null, language=null, rfNumber=[5], rfOrder=5, authorNames=HUO Zhiqin, HAN Songchen, journalName=Journal of Safety and Environment, refType=null, unstructuredReference=HUO Zhiqin, HAN Songchen. Analysis on the threats and errors caused by the runway incursions and the corresponding controlling ways[J]. Journal of Safety and Environment, 2012, 12(4):192-196., articleTitle=Analysis on the threats and errors caused by the runway incursions and the corresponding controlling ways, refAbstract=null), Reference(id=1168186503256617453, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738767801565331, doi=null, pmid=null, pmcid=null, year=2012, volume=22, issue=7, pageStart=53, pageEnd=58, url=null, language=null, rfNumber=[6], rfOrder=6, authorNames=霍志勤, 韩松臣, journalName=中国安全科学学报, refType=null, unstructuredReference=霍志勤, 韩松臣. 基于案例推理和规则推理融合的跑道侵入事件调查[J]. 中国安全科学学报, 2012, 22(7):53-58., articleTitle=基于案例推理和规则推理融合的跑道侵入事件调查, refAbstract=null), Reference(id=1168186503332114926, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738767801565331, doi=null, pmid=null, pmcid=null, year=2012, volume=22, issue=7, pageStart=53, pageEnd=58, url=null, language=null, rfNumber=[6], rfOrder=7, authorNames=HUO Zhiqin, HAN Songchen, journalName=China Safety Science Journal, refType=null, unstructuredReference=HUO Zhiqin, HAN Songchen. Runway incursions investigation based on integration of rule-based reasoning and case-based reasoning[J]. China Safety Science Journal, 2012, 22(7):53-58., articleTitle=Runway incursions investigation based on integration of rule-based reasoning and case-based reasoning, refAbstract=null), Reference(id=1168186503386640879, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738767801565331, doi=null, pmid=null, pmcid=null, year=2018, volume=28, issue=1, pageStart=93, pageEnd=98, url=null, language=null, rfNumber=[7], rfOrder=8, authorNames=夏正洪, 万健, 朱新平, journalName=中国安全科学学报, refType=null, unstructuredReference=夏正洪, 万健, 朱新平. 机场热点时空分布特征及运行风险评价[J]. 中国安全科学学报, 2018, 28(1):93-98., articleTitle=机场热点时空分布特征及运行风险评价, refAbstract=null), Reference(id=1168186503449555440, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738767801565331, doi=null, pmid=null, pmcid=null, year=2018, volume=28, issue=1, pageStart=93, pageEnd=98, url=null, language=null, rfNumber=[7], rfOrder=9, authorNames=XIA Zhenghong, WAN Jian, ZHU Xinping, journalName=China Safety Science Journal, refType=null, unstructuredReference=XIA Zhenghong, WAN Jian, ZHU Xinping. Research on spatial and temporal distribution characteristics of airport hotspots and airport operational risk assessment[J]. China Safety Science Journal, 2018, 28(1):93-98., articleTitle=Research on spatial and temporal distribution characteristics of airport hotspots and airport operational risk assessment, refAbstract=null), Reference(id=1168186503499887089, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738767801565331, doi=null, pmid=null, pmcid=null, year=2016, volume=147, issue=8, pageStart=93, pageEnd=108, url=null, language=null, rfNumber=[8], rfOrder=10, authorNames=STROEVE S H, SOM P, DOORN B A V, journalName=Reliability Engineering & System Safety, refType=null, unstructuredReference=STROEVE S H, SOM P, DOORN B A V, et al. Strengthening air traffic safety management by moving from outcome-based towards risk-based evaluation of runway incursions[J]. Reliability Engineering & System Safety, 2016, 147(8):93-108., articleTitle=Strengthening air traffic safety management by moving from outcome-based towards risk-based evaluation of runway incursions, refAbstract=null), Reference(id=1168186503575384562, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738767801565331, doi=null, pmid=null, pmcid=null, year=2023, volume=19, issue=8, pageStart=32, pageEnd=38, url=null, language=null, rfNumber=[9], rfOrder=11, authorNames=王兴隆, 周督异, journalName=中国安全生产科学技术, refType=null, unstructuredReference=王兴隆, 周督异. 基于复杂网络的飞行区冲突关键栅格区识别[J]. 中国安全生产科学技术, 2023, 19(8):32-38., articleTitle=基于复杂网络的飞行区冲突关键栅格区识别, refAbstract=null), Reference(id=1168186503692825075, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738767801565331, doi=null, pmid=null, pmcid=null, year=2023, volume=19, issue=8, pageStart=32, pageEnd=38, url=null, language=null, rfNumber=[9], rfOrder=12, authorNames=WANG Xinglong, ZHOU Duyi, journalName=Journal of Safety Science and Technology, refType=null, unstructuredReference=WANG Xinglong, ZHOU Duyi. Identification of critical grid areas in flight area conflicts based on complex network[J]. Journal of Safety Science and Technology, 2023, 19(8):32-38., articleTitle=Identification of critical grid areas in flight area conflicts based on complex network, refAbstract=null), Reference(id=1168186503797682676, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738767801565331, doi=null, pmid=null, pmcid=null, year=2012, volume=22, issue=12, pageStart=116, pageEnd=121, url=null, language=null, rfNumber=[10], rfOrder=13, authorNames=罗军, 林雪宁, journalName=中国安全科学学报, refType=null, unstructuredReference=罗军, 林雪宁. 基于模糊集和改进TOPSIS方法的跑道侵入风险评估[J]. 中国安全科学学报, 2012, 22(12):116-121., articleTitle=基于模糊集和改进TOPSIS方法的跑道侵入风险评估, refAbstract=null), Reference(id=1168186503910928885, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738767801565331, doi=null, pmid=null, pmcid=null, year=2012, volume=22, issue=12, pageStart=116, pageEnd=121, url=null, language=null, rfNumber=[10], rfOrder=14, authorNames=LUO Jun, journalName=China Safety Science Journal, refType=null, unstructuredReference=LUO Jun, LIN Xuening. Runway incursion risk assessment based on fuzzy sets theory and improved TOPSIS method[J]. China Safety Science Journal, 2012, 22(12):116-121., articleTitle=Runway incursion risk assessment based on fuzzy sets theory and improved TOPSIS method, refAbstract=null), Reference(id=1168186503999009270, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738767801565331, doi=null, pmid=null, pmcid=null, year=2012, volume=12, issue=3, pageStart=196, pageEnd=199, url=null, language=null, rfNumber=[11], rfOrder=15, authorNames=罗军, 林雪宁, 闫永刚, journalName=安全与环境学报, refType=null, unstructuredReference=罗军, 林雪宁, 闫永刚. 基于高斯贝叶斯网络模型的跑道侵入影响因素研究[J]. 安全与环境学报, 2012, 12(3):196-199., articleTitle=基于高斯贝叶斯网络模型的跑道侵入影响因素研究, refAbstract=null), Reference(id=1168186504049340919, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738767801565331, doi=null, pmid=null, pmcid=null, year=2012, volume=12, issue=3, pageStart=196, pageEnd=199, url=null, language=null, rfNumber=[11], rfOrder=16, authorNames=LUO Jun, journalName=Journal of Safety and Environment, refType=null, unstructuredReference=LUO Jun, LIN Xuening, YAN Yonggang. Analysis of runway incursion influence factors based on gaussian bayesian network model[J]. Journal of Safety and Environment, 2012, 12(3):196-199., articleTitle=Analysis of runway incursion influence factors based on gaussian bayesian network model, refAbstract=null), Reference(id=1168186504108061176, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738767801565331, doi=null, pmid=null, pmcid=null, year=2017, volume=29, issue=4, pageStart=910, pageEnd=917, url=null, language=null, rfNumber=[12], rfOrder=17, authorNames=黄宝军, 房晓丹, 王洁宁, journalName=系统仿真学报, refType=null, unstructuredReference=黄宝军, 房晓丹, 王洁宁. 基于多agent的跑道侵入风险分析建模及仿真[J]. 系统仿真学报, 2017, 29(4):910-917,925., articleTitle=基于多agent的跑道侵入风险分析建模及仿真, refAbstract=null), Reference(id=1168186504166781433, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738767801565331, doi=null, pmid=null, pmcid=null, year=2017, volume=29, issue=4, pageStart=910, pageEnd=917, url=null, language=null, rfNumber=[12], rfOrder=18, authorNames=HUANG Baojun, FANG Xiaodan, WANG Jiening, journalName=Journal of System Simulation, refType=null, unstructuredReference=HUANG Baojun, FANG Xiaodan, WANG Jiening. Risk simulation analysis of runway incursions based on multi agents[J]. Journal of System Simulation, 2017, 29(4):910-917,925., articleTitle=Risk simulation analysis of runway incursions based on multi agents, refAbstract=null), Reference(id=1168186504221307386, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738767801565331, doi=null, pmid=null, pmcid=null, year=2022, volume=43, issue=5, pageStart=483, pageEnd=492, url=null, language=null, rfNumber=[13], rfOrder=19, authorNames=焦卫东, 王瑞冬, 姚军强, journalName=航空学报, refType=null, unstructuredReference=焦卫东, 王瑞冬, 姚军强, 等. 跑道侵入与冲突检测的共形几何代数描述[J]. 航空学报, 2022, 43(5):483-492., articleTitle=跑道侵入与冲突检测的共形几何代数描述, refAbstract=null), Reference(id=1168186504296804859, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738767801565331, doi=null, pmid=null, pmcid=null, year=2022, volume=43, issue=5, pageStart=483, pageEnd=492, url=null, language=null, rfNumber=[13], rfOrder=20, authorNames=JIAO Weidong, WANG Ruidong, YAO Junqiang, journalName=Acta Aeronautica et Astronautica Sinica, refType=null, unstructuredReference=JIAO Weidong, WANG Ruidong, YAO Junqiang, et al. Conformal geometric algebraic description of runway incursion and conflict detection[J]. Acta Aeronautica et Astronautica Sinica, 2022, 43(5):483-492., articleTitle=Conformal geometric algebraic description of runway incursion and conflict detection, refAbstract=null), Reference(id=1168186504347136508, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738767801565331, doi=null, pmid=null, pmcid=null, year=2019, volume=36, issue=12, pageStart=3773, pageEnd=3776, url=null, language=null, rfNumber=[14], rfOrder=21, authorNames=王洁宁, 庾睿, journalName=计算机应用研究, refType=null, unstructuredReference=王洁宁, 庾睿. 集成本体和BN的跑道侵入态势评估方法[J]. 计算机应用研究, 2019, 36(12):3773-3776., articleTitle=集成本体和BN的跑道侵入态势评估方法, refAbstract=null), Reference(id=1168186504422633981, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738767801565331, doi=null, pmid=null, pmcid=null, year=2019, volume=36, issue=12, pageStart=3773, pageEnd=3776, url=null, language=null, rfNumber=[14], rfOrder=22, authorNames=WANG Jiening, YU Rui, journalName=Application Research of Computers, refType=null, unstructuredReference=WANG Jiening, YU Rui. Situation assessment method of runway incursion based on combination of ontology and BN[J]. Application Research of Computers, 2019, 36(12):3773-3776., articleTitle=Situation assessment method of runway incursion based on combination of ontology and BN, refAbstract=null), Reference(id=1168186504481354238, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738767801565331, doi=null, pmid=null, pmcid=null, year=2023, volume=23, issue=5, pageStart=1368, pageEnd=1375, url=null, language=null, rfNumber=[15], rfOrder=23, authorNames=袁乐平, 赵力梵, 张文东, journalName=安全与环境学报, refType=null, unstructuredReference=袁乐平, 赵力梵, 张文东, 等. 基于复杂网络的民航跑道侵入事件分析[J]. 安全与环境学报, 2023, 23(5):1368-1375., articleTitle=基于复杂网络的民航跑道侵入事件分析, refAbstract=null), Reference(id=1168186504535880191, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738767801565331, doi=null, pmid=null, pmcid=null, year=2023, volume=23, issue=5, pageStart=1368, pageEnd=1375, url=null, language=null, rfNumber=[15], rfOrder=24, authorNames=YUAN Leping, ZHAO Lifan, ZHANG Wendong, journalName=Journal of Safety and Environment, refType=null, unstructuredReference=YUAN Leping, ZHAO Lifan, ZHANG Wendong, et al. Analysis of civil aviation runway incursion incident based on complex network[J]. Journal of Safety and Environment, 2023, 23(5):1368-1375., articleTitle=Analysis of civil aviation runway incursion incident based on complex network, refAbstract=null), Reference(id=1168186504590406144, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738767801565331, doi=null, pmid=null, pmcid=null, year=2019, volume=29, issue=9, pageStart=119, pageEnd=124, url=null, language=null, rfNumber=[16], rfOrder=25, authorNames=沈笑云, 张肖艳, 张思远, journalName=中国安全科学学报, refType=null, unstructuredReference=沈笑云, 张肖艳, 张思远. 基于ADS-B的跑道侵入冲突检测与告警研究[J]. 中国安全科学学报, 2019, 29(9):119-124., articleTitle=基于ADS-B的跑道侵入冲突检测与告警研究, refAbstract=null), Reference(id=1168186504644932097, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738767801565331, doi=null, pmid=null, pmcid=null, year=2019, volume=29, issue=9, pageStart=119, pageEnd=124, url=null, language=null, rfNumber=[16], rfOrder=26, authorNames=SHEN Xiaoyun, ZHANG Xiaoyan, ZHANG Siyuan, journalName=China Safety Science Journal, refType=null, unstructuredReference=SHEN Xiaoyun, ZHANG Xiaoyan, ZHANG Siyuan. Research on runway incursion conflict detection and alarm based on ADS-B[J]. China Safety Science Journal, 2019, 29(9):119-124., articleTitle=Research on runway incursion conflict detection and alarm based on ADS-B, refAbstract=null), Reference(id=1168186504716235266, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738767801565331, doi=null, pmid=null, pmcid=null, year=2021, volume=31, issue=4, pageStart=41, pageEnd=48, url=null, language=null, rfNumber=[17], rfOrder=27, authorNames=吴维, 罗欣然, 魏明, journalName=中国安全科学学报, refType=null, unstructuredReference=吴维, 罗欣然, 魏明. 基于SD模型的跑道侵入风控网络脆弱性分析[J]. 中国安全科学学报, 2021, 31(4):41-48., articleTitle=基于SD模型的跑道侵入风控网络脆弱性分析, refAbstract=null), Reference(id=1168186504774955523, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738767801565331, doi=null, pmid=null, pmcid=null, year=2021, volume=31, issue=4, pageStart=41, pageEnd=48, url=null, language=null, rfNumber=[17], rfOrder=28, authorNames=WU Wei, journalName=China Safety Science Journal, refType=null, unstructuredReference=WU Wei, LUO Xinran, WEI Ming. Vulnerability assessment of runway intrusion risk control network based on SD model[J]. China Safety Science Journal, 2021, 31(4):41-48., articleTitle=Vulnerability assessment of runway intrusion risk control network based on SD model, refAbstract=null), Reference(id=1168186504837870084, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738767801565331, doi=null, pmid=null, pmcid=null, year=2004, volume=8, issue=5, pageStart=1, pageEnd=21, url=null, language=null, rfNumber=[18], rfOrder=29, authorNames=STAMP M, journalName=Leee Assp Magruine, refType=null, unstructuredReference=STAMP M. A revealing introduction to hidden markov models[J]. Leee Assp Magruine, 2004, 8(5):1-21., articleTitle=A revealing introduction to hidden markov models, refAbstract=null), Reference(id=1168186504913367557, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738767801565331, doi=null, pmid=null, pmcid=null, year=2023, volume=46, issue=10, pageStart=2066, pageEnd=2083, url=null, language=null, rfNumber=[19], rfOrder=30, authorNames=乌兰, 刘全, 黄志刚, journalName=计算机学报, refType=null, unstructuredReference=乌兰, 刘全, 黄志刚, 等. 优势加权互信息最大化的最大熵分层强化学习[J]. 计算机学报, 2023, 46(10):2066-2083., articleTitle=优势加权互信息最大化的最大熵分层强化学习, refAbstract=null), Reference(id=1168186504976282118, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738767801565331, doi=null, pmid=null, pmcid=null, year=2023, volume=46, issue=10, pageStart=2066, pageEnd=2083, url=null, language=null, rfNumber=[19], rfOrder=31, authorNames=WU Lan, LIU Quan, HUANG Zhigang, journalName=Chinese Journal of Computers, refType=null, unstructuredReference=WU Lan, LIU Quan, HUANG Zhigang, et al. Maximum entropy hierarchical reinforcement learning with advantage-weighted mutual information maximization[J]. Chinese Journal of Computers, 2023, 46(10):2066-2083., articleTitle=Maximum entropy hierarchical reinforcement learning with advantage-weighted mutual information maximization, refAbstract=null)], funds=[Fund(id=1168186502732329446, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738767801565331, awardId=3122025098, language=CN, fundingSource=中央高校基本科研业务费项目中国民航大学专项(3122025098), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1168186499121033635, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738767801565331, xref=1, ext=[AuthorCompanyExt(id=1168186499125227940, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738767801565331, companyId=1168186499121033635, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 Key Laboratory of Internet of Aircraft,Civil Aviation University of China,Tianjin 300300,China), AuthorCompanyExt(id=1168186499133616549, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738767801565331, companyId=1168186499121033635, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 中国民航大学 民航飞联网重点实验室,天津 300300)]), AuthorCompany(id=1168186499183948198, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738767801565331, xref=2, ext=[AuthorCompanyExt(id=1168186499192336807, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738767801565331, companyId=1168186499183948198, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 College of Air Traffic Management,Civil Aviation University of China,Tianjin 300300,China), AuthorCompanyExt(id=1168186499196531112, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738767801565331, companyId=1168186499183948198, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 中国民航大学 空中交通管理学院,天津 300300)])], figs=[ArticleFig(id=1168186501247545802, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738767801565331, language=EN, label=Fig.1, caption=DBN of runway incursion risk propagation, figureFileSmall=JswwjcVGJn/acxYkedeILQ==, figureFileBig=aq3Sx0NS6c5NR5w3xWLl9w==, tableContent=null), ArticleFig(id=1168186501310460364, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738767801565331, language=CN, label=图1, caption=跑道侵入风险传播DBN, figureFileSmall=JswwjcVGJn/acxYkedeILQ==, figureFileBig=aq3Sx0NS6c5NR5w3xWLl9w==, tableContent=null), ArticleFig(id=1168186501377569231, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738767801565331, language=EN, label=Fig.2, caption=DBN runway incursion risk prediction, figureFileSmall=ovlFmZ4jVtmsK0by21M1NA==, figureFileBig=su1Fkn2niUZcAcFUp4+XAA==, tableContent=null), ArticleFig(id=1168186501461455313, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738767801565331, language=CN, label=图2, caption=DBN跑道侵入风险预测, figureFileSmall=ovlFmZ4jVtmsK0by21M1NA==, figureFileBig=su1Fkn2niUZcAcFUp4+XAA==, tableContent=null), ArticleFig(id=1168186501520175572, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738767801565331, language=EN, label=Fig.3, caption=Comparison of risk prediction results using different methods, figureFileSmall=dZeq2RXFfR3RIYnMoIMg6w==, figureFileBig=AiKB5ABCMDvSqXYBqJleOg==, tableContent=null), ArticleFig(id=1168186501566312918, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738767801565331, language=CN, label=图3, caption=不同风险预测方法预测结果对比, figureFileSmall=dZeq2RXFfR3RIYnMoIMg6w==, figureFileBig=AiKB5ABCMDvSqXYBqJleOg==, tableContent=null), ArticleFig(id=1168186501650199000, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738767801565331, language=EN, label=Fig.4, caption=Sensitivity analysis of observation nodes, figureFileSmall=rtwPObpfjFPhbBBNTb3lzw==, figureFileBig=6B74ZOmyF97u4SGOsMz1NQ==, tableContent=null), ArticleFig(id=1168186501746667993, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738767801565331, language=CN, label=图4, caption=观测节点灵敏度分析, figureFileSmall=rtwPObpfjFPhbBBNTb3lzw==, figureFileBig=6B74ZOmyF97u4SGOsMz1NQ==, tableContent=null), ArticleFig(id=1168186501817971162, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738767801565331, language=EN, label=Fig.5, caption=Change curve of mutual information at different time slots, figureFileSmall=gN3XxtCJmg2AzGUPmCYi3w==, figureFileBig=qi9fRFRFNh4qbIj+mRVcfw==, tableContent=null), ArticleFig(id=1168186501989937627, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738767801565331, language=CN, label=图5, caption=不同时间片下互信息变化曲线, figureFileSmall=gN3XxtCJmg2AzGUPmCYi3w==, figureFileBig=qi9fRFRFNh4qbIj+mRVcfw==, tableContent=null), ArticleFig(id=1168186502036074972, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738767801565331, language=EN, label=Fig.6, caption=Comparison of different methods for key point identification, figureFileSmall=8ealsA1GTKY9sU/SoRrmGw==, figureFileBig=cO+p4ellyo83yqf62elDmg==, tableContent=null), ArticleFig(id=1168186502098989533, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738767801565331, language=CN, label=图6, caption=不同方法识别关键点对比情况, figureFileSmall=8ealsA1GTKY9sU/SoRrmGw==, figureFileBig=cO+p4ellyo83yqf62elDmg==, tableContent=null), ArticleFig(id=1168186502149321182, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738767801565331, language=EN, label=Table 1, caption=

List of causal nodes

, figureFileSmall=null, figureFileBig=null, tableContent=
符号 名称 符号 名称 符号 名称
a1 人的因素 a22 管制人员培训工作不到位 b7 降水
a2 场面保障人员和车辆驾驶员差错 a 2 3 管制人员工作年限低 b8 沙尘
a3 管制人员差错 a24 管制人员工作强度高 c1 设备因素
a4 飞行人员因素 a25 管制人员人数少 c2 监视设备故障
a5 场面人员未及时发现危险 a26 复诵错误 c3 通信设备故障
a6 场面人员未经许可进入跑道 a27 飞行人员对机场不熟悉 c4 地面标志有误
a7 进入错误跑道 a28 飞行人员未听指令进入跑道 c5 场面灯光中断
a8 场面人员和车辆驾驶员反应迟钝 a29 飞行人员处置不及时 c6 场面灯光故障
a9 场面人员和车辆驾驶员业务素质差 a30 飞行人员未及时发现错误 c7 设备可靠性差
a10 场面人员和车辆驾驶员对机场熟悉程度低 a31 飞行人员陆空通话水平低 c8 通信中断
a11 场面人员和车辆驾驶员工作经验低 a32 飞行人员反应时间长 c9 标志模糊不清或不合理
a12 场面人员和车辆驾驶员工作年限 a33 飞行人员业务素质差 c10 设备质量差
a13 场面人员和车辆驾驶员培训工作不到位 a34 飞行人员工作年限低 c11 检修频率低
a14 未发现飞行人员复诵错误并纠正 a35 飞行员经验少 d1 监管因素
a15 未发现飞行人员、车辆等异常并及时处置 a36 飞行人员培训不到位 d2 监管频次低
a16 管制员未按规定操作 b1 环境因素 d3 规章执行率低
a17 管制指令不及时 b2 地面湿滑 d4 监控手段不足
a18 管制人员陆空通话水平低 b3 低能见度 d5 监管人员不足
a19 管制人员业务素质差 b4 航班流量大 d6 监管投入不足
a20 管制人员工作经验不足 b5 跑滑布局复杂
a21 管制人员反应时间长 b6 夜间
), ArticleFig(id=1168186502212235743, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738767801565331, language=CN, label=表1, caption=

致因节点

, figureFileSmall=null, figureFileBig=null, tableContent=
符号 名称 符号 名称 符号 名称
a1 人的因素 a22 管制人员培训工作不到位 b7 降水
a2 场面保障人员和车辆驾驶员差错 a 2 3 管制人员工作年限低 b8 沙尘
a3 管制人员差错 a24 管制人员工作强度高 c1 设备因素
a4 飞行人员因素 a25 管制人员人数少 c2 监视设备故障
a5 场面人员未及时发现危险 a26 复诵错误 c3 通信设备故障
a6 场面人员未经许可进入跑道 a27 飞行人员对机场不熟悉 c4 地面标志有误
a7 进入错误跑道 a28 飞行人员未听指令进入跑道 c5 场面灯光中断
a8 场面人员和车辆驾驶员反应迟钝 a29 飞行人员处置不及时 c6 场面灯光故障
a9 场面人员和车辆驾驶员业务素质差 a30 飞行人员未及时发现错误 c7 设备可靠性差
a10 场面人员和车辆驾驶员对机场熟悉程度低 a31 飞行人员陆空通话水平低 c8 通信中断
a11 场面人员和车辆驾驶员工作经验低 a32 飞行人员反应时间长 c9 标志模糊不清或不合理
a12 场面人员和车辆驾驶员工作年限 a33 飞行人员业务素质差 c10 设备质量差
a13 场面人员和车辆驾驶员培训工作不到位 a34 飞行人员工作年限低 c11 检修频率低
a14 未发现飞行人员复诵错误并纠正 a35 飞行员经验少 d1 监管因素
a15 未发现飞行人员、车辆等异常并及时处置 a36 飞行人员培训不到位 d2 监管频次低
a16 管制员未按规定操作 b1 环境因素 d3 规章执行率低
a17 管制指令不及时 b2 地面湿滑 d4 监控手段不足
a18 管制人员陆空通话水平低 b3 低能见度 d5 监管人员不足
a19 管制人员业务素质差 b4 航班流量大 d6 监管投入不足
a20 管制人员工作经验不足 b5 跑滑布局复杂
a21 管制人员反应时间长 b6 夜间
), ArticleFig(id=1168186502291927520, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738767801565331, language=EN, label=Table 2, caption=

Eighteen risk values corresponding to a17

, figureFileSmall=null, figureFileBig=null, tableContent=
风险 F 1 F 2 F 3 F 4 F 5 F 6
取值 28.6 28.3 27.7 27.6 27.3 26.7
风险 F 7 F 8 F 9 F 10 F 11 F 12
取值 24.7 24.4 23.8 23.9 23.5 22.9
风险 F 13 F 14 F 15 F 16 F 17 F 18
取值 29.7 29.5 28.9 25.7 25.4 24.9
), ArticleFig(id=1168186502359036385, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738767801565331, language=CN, label=表2, caption=

a17对应的18种风险值

, figureFileSmall=null, figureFileBig=null, tableContent=
风险 F 1 F 2 F 3 F 4 F 5 F 6
取值 28.6 28.3 27.7 27.6 27.3 26.7
风险 F 7 F 8 F 9 F 10 F 11 F 12
取值 24.7 24.4 23.8 23.9 23.5 22.9
风险 F 13 F 14 F 15 F 16 F 17 F 18
取值 29.7 29.5 28.9 25.7 25.4 24.9
), ArticleFig(id=1168186502426145250, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738767801565331, language=EN, label=Table 3, caption=

Membership functions

, figureFileSmall=null, figureFileBig=null, tableContent=
节点状态 概率范围 模糊数集
极低 0.1 (0.1,0.1,0.2)
0.3 (0.2,0.3,0.4)
一般 0.5 (0.4,0.5,0.6)
0.7 (0.6,0.7,0.8)
极高 0.9 (0.8,0.9,0.9)
), ArticleFig(id=1168186502472282595, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738767801565331, language=CN, label=表3, caption=

隶属度函数

, figureFileSmall=null, figureFileBig=null, tableContent=
节点状态 概率范围 模糊数集
极低 0.1 (0.1,0.1,0.2)
0.3 (0.2,0.3,0.4)
一般 0.5 (0.4,0.5,0.6)
0.7 (0.6,0.7,0.8)
极高 0.9 (0.8,0.9,0.9)
), ArticleFig(id=1168186502539391460, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738767801565331, language=EN, label=Table 4, caption=

Distribution of risk prediction results using different methods

, figureFileSmall=null, figureFileBig=null, tableContent=
预测结果
概率值
预测结果占比分布情况/%
BN DBN HMMs学习的DBN
[0,0.5) 6.4 5.5 2.0
[0.5,0.85] 19.2 14.2 13.8
(0.85,1] 74.4 80.3 84.2
), ArticleFig(id=1168186502614888933, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738767801565331, language=CN, label=表4, caption=

不同风险预测方法的结果

, figureFileSmall=null, figureFileBig=null, tableContent=
预测结果
概率值
预测结果占比分布情况/%
BN DBN HMMs学习的DBN
[0,0.5) 6.4 5.5 2.0
[0.5,0.85] 19.2 14.2 13.8
(0.85,1] 74.4 80.3 84.2
)], attaches=null, journal=Journal(id=1123942128916217864, delFlag=0, nameCn=中国安全科学学报, nameEn=China Safety Science Journal, nameHistory1=null, nameHistory2=null, issn=1003-3033, eissn=, cn=11-2865/X, coden=null, periodic=0, language=CN, oaType=0, ccby=null, superviseOffice=null, ownerOffice=null, pubOffice=null, editorOffice=null, officeType=null, aims=null, clcCode=null, officeProv=null, officeCity=null, officeAddr=null, officeZip=null, officeEmail=null, officePhone=null, editDirector=null, officeDirector=null, officeDirectorPhone=null, officeStaffNum=null, officeEmpNum=null, coverPicUrl=fkqsFM6VKlHC4gCtS5XqTw==, journalPrice=null, startedYear=null, abbrevIsoEn=Chin Saf Sci J, journalRemark=null, publicationField=null, createdTime=null, updatedTime=1754269350027, createdBy=null, updatedBy=13701087609, firstLetterCn=C, firstLetterEn=C, subjectCode=Engineering, subjectName=工程, subjectCodeEn=Engineering, subjectNameEn=null, picCn=fkqsFM6VKlHC4gCtS5XqTw==, picEn=SHn9HgqSxtJrOcAxqD++4Q==, jcr=null, cjcr=null, exts=[JournalExt(id=1159052918994595848, language=CN, name=中国安全科学学报, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=null, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=http://www.cssjj.com.cn/, createdTime=1754269350050, updatedTime=1754269350050, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=http://www.cssjj.com.cn/CN/column/item15.shtml, submissionAuthorUrl=https://zgaqkxxbauthor.manuscriptcloud.com/login, submissionEditorUrl=https://zgaqkxxbeditor.manuscriptcloud.com/login, submissionReviewUrl=https://zgaqkxxbauthor.manuscriptcloud.com/login, submissionCeEditorUrl=https://zgaqkxxbeditor.manuscriptcloud.com/login, submissionAeEditorUrl=https://zgaqkxxbeditor.manuscriptcloud.com/login, option={"copyright":""}), JournalExt(id=1159052919040733193, language=EN, name=China Safety Science Journal, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=null, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=http://www.cssjj.com.cn/EN/1003-3033/home.shtml, createdTime=1754269350061, updatedTime=1754269350061, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=https://synbioj.cip.com.cn/EN/column/column3.shtml, submissionAuthorUrl=https://zgaqkxxbauthor.manuscriptcloud.com/login, submissionEditorUrl=https://zgaqkxxbeditor.manuscriptcloud.com/login, submissionReviewUrl=https://zgaqkxxbauthor.manuscriptcloud.com/login, submissionCeEditorUrl=https://zgaqkxxbeditor.manuscriptcloud.com/login, submissionAeEditorUrl=https://zgaqkxxbeditor.manuscriptcloud.com/login, option={"copyright":""})], databaseList=null, tenantJournalId=1146031787341344770, websiteList=[Website(id=1148243202345263519, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146031787341344770, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/zgaqkxxb/CN, language=CN, createTime=1751692112766, createBy=18614031015, updateTime=1753502583634, updateBy=18614031015, name=《中国安全科学学报》中文站点, tplId=1146099689490845704, title=中国安全科学学报, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1148618794941046792, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202345263519, code=articleTextType, value=kx, createTime=1751781661020, updateTime=1751781661020, creator=18614031015, updator=18614031015), WebsiteProps(id=1148618794911686661, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202345263519, code=banner, value=null, createTime=1751781661012, updateTime=1751781661012, creator=18614031015, updator=18614031015), WebsiteProps(id=1148618794894909444, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202345263519, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=tui0IVO9FMwB61HHtX5scg==, createTime=1751781661008, updateTime=1751781661008, creator=18614031015, updator=18614031015), WebsiteProps(id=1148618794932658183, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202345263519, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1751781661017, updateTime=1751781661017, creator=18614031015, updator=18614031015), WebsiteProps(id=1148618794924269574, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202345263519, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1751781661015, updateTime=1751781661015, creator=18614031015, updator=18614031015)]), Website(id=1155836763751993353, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146031787341344770, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/zgaqkxxb/EN, language=EN, createTime=1753502558893, createBy=18614031015, updateTime=1753524450387, updateBy=18614031015, name=《中国安全科学学报》英文站点, tplId=1146101810881728533, title=China Safety Science Journal, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1155895925743669425, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155836763751993353, code=articleTextType, value=kx, createTime=1753516664205, updateTime=1753516664205, creator=18614031015, updator=18614031015), WebsiteProps(id=1155895925722697902, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155836763751993353, code=banner, value=null, createTime=1753516664200, updateTime=1753516664200, creator=18614031015, updator=18614031015), WebsiteProps(id=1155895925714309293, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155836763751993353, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=tui0IVO9FMwB61HHtX5scg==, createTime=1753516664198, updateTime=1753516664198, creator=18614031015, updator=18614031015), WebsiteProps(id=1155895925735280816, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155836763751993353, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1753516664203, updateTime=1753516664203, creator=18614031015, updator=18614031015), WebsiteProps(id=1155895925731086511, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155836763751993353, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1753516664202, updateTime=1753516664202, creator=18614031015, updator=18614031015)])], journalTitle=中国安全科学学报, weixinUrl=null, journalUrl=null, iacademicId=null, status=0, seqNo=null, journalTitleEn=China Safety Science Journal, journalPhotoCn=fkqsFM6VKlHC4gCtS5XqTw==, journalPhotoEn=SHn9HgqSxtJrOcAxqD++4Q==, journalFirstLetter=C, journalRecommend=null, journalNew=null, journalCollection=1, jcrJf=null, cjcrJf=null, jcrJfStr=null, cjcrJfStr=null, submissionFirstDecision=null, sciSubjectClassification=null, casSubjectClassification=null, citeScore=null, totalCitationFrequency=null, icpCode=null, psCode=null, advertisingLicenseCode=null, copyrightInformation=null, country=null, option=null, provinceCode=null, provinceName=null, collectFlag=false), detailUrlCn=https://castjournals.cast.org.cn/joweb/zgaqkxxb/CN/10.16265/j.cnki.issn1003-3033.2024.07.0229, detailUrlEn=https://castjournals.cast.org.cn/joweb/zgaqkxxb/EN/10.16265/j.cnki.issn1003-3033.2024.07.0229, pdfUrlCn=https://castjournals.cast.org.cn/joweb/zgaqkxxb/CN/PDF/10.16265/j.cnki.issn1003-3033.2024.07.0229, pdfUrlEn=https://castjournals.cast.org.cn/joweb/zgaqkxxb/EN/PDF/10.16265/j.cnki.issn1003-3033.2024.07.0229, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
融合强化学习的DBN跑道侵入风险预测
收藏切换
PDF下载
吴维 1 , 吴泽萱 2 , 王兴隆 1 , 祝龙飞 2
中国安全科学学报 | 安全社会科学与安全管理 2024,34(7): 20-27
收起
收藏切换
中国安全科学学报 | 安全社会科学与安全管理 2024, 34(7): 20-27
融合强化学习的DBN跑道侵入风险预测
全屏
吴维1 , 吴泽萱2, 王兴隆1, 祝龙飞2
作者信息
  • 1 中国民航大学 民航飞联网重点实验室,天津 300300
  • 2 中国民航大学 空中交通管理学院,天津 300300
  • 吴 维 (1982—),男,河北承德人,硕士,讲师,主要从事空中交通系统优化与管理方面的研究。E-mail:

    王兴隆 教授

Research on DBN incorporating reinforcement learning for runway intrusion risk prediction
Wei WU1 , Zexuan WU2, Xinglong WANG1, Longfei ZHU2
Affiliations
  • 1 Key Laboratory of Internet of Aircraft,Civil Aviation University of China,Tianjin 300300,China
  • 2 College of Air Traffic Management,Civil Aviation University of China,Tianjin 300300,China
出版时间: 2024-07-28 doi: 10.16265/j.cnki.issn1003-3033.2024.07.0229
文章导航
收藏切换

为解决机场跑道侵入事件风险量化难度大、时效性差、精准性低等问题,提升跑道侵入风险预警能力,构建融合强化学习的动态贝叶斯网络(DBN)风险预测模型。首先,结合因果推断理论与灰色关联分析法分析跑道侵入历史事件,识别跑道侵入事件风险致因;其次,运用贝叶斯网络(BN)理论挖掘各风险因素间的关联性,并利用皮尔逊线性相关系数量化各因素间的关联关系,构建表征风险传播的致因关系网络;然后,利用三角模糊方法与隐马尔可夫模型(HMMs)优化DBN参数学习机制;最后,利用历史数据验证基于融合强化学习的DBN预测结果准确性。结果表明:基于融合强化学习的DBN预测结果与历史数据统计数值的拟合较好,准确率为84 %,与单独DBN预测结果相比准确性提升10 %;相比于采用度值评价法,通过互信息识别关键节点可有效提升预测准确率和区分度。

强化学习  /  动态贝叶斯网络(DBN)  /  跑道侵入  /  风险预测  /  灰色关联分析

In order to solve the problems of difficulty in quantifying the risk of airport runway incursion events,poor timeliness and low accuracy,and to enhance the capability of predicting runway incursion risks,a DBN model incorporating reinforcement learning for risk prediction was constructed. Firstly,causal inference theory was combined with grey relational analysis to analyze historical runway incursion events and identify the underlying risk factors. Secondly,Bayesian network(BN) theory was applied to explore the correlations among these factors and quantify these correlations using the Pearson linear correlation coefficient. This process helped in constructing a causation correlations network that effectively represented the propagation of risks associated with runway incursions. Then,the triangular fuzzy method and Hidden Markov Models (HMMs) were utilized to further refine and optimize the DBN parameter learning mechanism. Finally,the model's accuracy was validated using historical data. The results demonstrate that the proposed model's predictions of runway incursion risks closely align with the statistical values of historical data,achieving an accuracy rate of 84%,which represents a significant 10% improvement over Bayesian network predictions. Additionally,the use of mutual information to identify key nodes is found to effectively improve accuracy and discrimination compared to the degree value evaluation method.

reinforcement learning  /  dynamic Bayesian network (DBN)  /  runway incursion  /  risk prediction  /  grey correlation analysis
吴维, 吴泽萱, 王兴隆, 祝龙飞. 融合强化学习的DBN跑道侵入风险预测. 中国安全科学学报, 2024 , 34 (7) : 20 -27 . DOI: 10.16265/j.cnki.issn1003-3033.2024.07.0229
Wei WU, Zexuan WU, Xinglong WANG, Longfei ZHU. Research on DBN incorporating reinforcement learning for runway intrusion risk prediction[J]. China Safety Science Journal, 2024 , 34 (7) : 20 -27 . DOI: 10.16265/j.cnki.issn1003-3033.2024.07.0229
随着航空业的快速发展,多跑道机场面临的风险日益严峻,据美国联邦航空管理局[1]与中国民航局网站[2]公布数据显示,仅2008—2020年,涉及跑道侵入事件近5 600多件,跑道侵入已成为影响机场安全运行的关键事件之一。因此,厘清跑道侵入风险影响因素,识别风险传播过程并预测风险水平,对于预防此类事故发生,减少跑道侵入诱发的人员伤亡及经济损失,具有重要意义。
目前,国内外学者围绕跑道侵入等飞行区域不安全事件开展了大量研究。ROGERSON等[3]统计分析跑道侵入事件原因,并将机场物理特征、运行特点和天气环境融入事件诱因范畴,拓展了跑道侵入致因分析的范畴。AJKM等[4]通过计量经济学方法探究美国2002—2015年间跑道侵入事件诱因,识别不同场景下影响跑道侵入的关键性因素,明晰各因素间的关联关系。霍志勤等[5-6]采用统计回归方法,分析跑道侵入影响因素及其相互作用关系,进而确定影响跑道侵入的关键致因,并据此厘清各因素间的因果关系;夏正洪等[7]通过分析机场热点的时空特征,构建机场热点的风险评价模型,为分析机场跑道侵入风险等级提供了新思路;STROEVE等[8]构建跑道侵入碰撞风险模型,量化分析了跑道侵入风险水平;王兴隆等[9]利用复杂网络理论,构建了机场飞行区航空器冲突探测的栅格识别方法;罗军等[10-11]构建了跑道侵入风险贝叶斯模型,结合模糊集和改进优劣解距离法计算贝叶斯模型参数,预测了跑道侵入发生的风险概率;黄宝军等[12]针对跑道侵入多主体相互作用的过程,引入多智能体模型与时态逻辑交互语言构建了跑道侵入的仿真模型;焦卫东等[13]提出了能够检测航空器跑道侵入风险的共形几何代数方法;王洁宁等[14]系统分析了机场飞行区保障业务流程,并结合本体识别理论与贝叶斯理论分析跑道侵入事件风险水平;袁乐平等[15]采用统计分析方法结合复杂网络,构建了跑道侵入致因网络模型;沈笑云等[16]利用自动相关监视技术实时感知跑道侵入风险态势,并建立了多级跑道侵入告警机制;吴维等[17]基于风险识别方法构建跑道侵入风险传播模型,从网络脆弱性角度分析了风险推演过程。
综上,国内外专家系统研究了跑道侵入事件的风险要素,探析了各要素间的相互作用关系,并建立了多种跑道侵入风险评估模型。然而,由于跑道侵入事件的偶发性以及诱因复杂性,跑道侵入风险量化难度较大。为此,笔者拟基于融合强化学习的动态贝叶斯网络(Dynamic Bayesian Network,DBN),构建跑道侵入风险预测模型,以量化分析该类时间风险程度。
跑道侵入事件通常是由于人员、设备、管理和运行环境某项发生变化导致的,而且,其中一项变化后会时序衍生其他风险事件,体现传播的时序特征。据此,可将历次跑道侵入的风险事件诱因设为节点,进而结合节点间的因果关系构建风险网络。
由于跑道侵入事件存在偶发性强、致因链长、隐藏性强等特点,仅采用统计历史数据无法精准识别诱因。为此,可通过采用因果推断与灰色关联分析相结合的方式识别诱因及其相互关系。
1) 识别风险致因链。根据美国联邦航空管理局[1]和中国民航局网站[2]公布的跑道侵入不安全事件数据,选取2008—2020年间典型的2 626件跑道侵入不安全事件为样本,分析样本数据。首先,提取分类不安全事件中涉及的要素,包括人员、设备、环境和管理等,并按照上述要素发生的时序特征,筛选出每次跑道侵入事件因果链条;其次,对因果链条的相似性进行聚类分析,构建典型因果链;最后,将典型的因果链条进行组合,形成因果链网,并利用因果推断理论分析验证链条的逻辑性和准确性。
从数据以及因果推断发现,跑道侵入致因事件中人的因素主要包括管制人员差错、飞行人员差错、场面保障人员、车辆驾驶员差错、工作年限高、反应时间长、陆空通话水平低、培训工作不到位、业务素质差及不安全行为等事件;设备因素主要包括监视设备差错、通信设备差错和地面标志差错等事件;环境因素主要包括低能见度、地面湿滑、航班量大等事件;监管因素主要包括监管人员不足、规章制度不完善、监管频次低等事件。
2) 计算风险致因节点关联性。由于统计分析与因果推断形成的风险链条网络节点过于庞大,不利于风险快速精准识别,因此,需对风险链条网络进行优化。首先,基于灰色关联理论,计算致因间的关联系数;然后,对致因间的关联系数依次排序,分析关联度较低的因素对风险链条网络的影响程度,并对其进行优化;最后,形成核心跑道侵入风险传播网络,具体可表示为:
σ c k = c m i n | μ c k - μ c 0 | + ρ c m a x | μ c k - μ c 0 | | μ c k - μ c 0 | + ρ c m a x | μ c k - μ c 0 | c = 1,2 m ; k = 1,2 n
r k = c = 1 m σ c k m c = 1,2 m ; k = 1,2 n
式中: σ c k为灰色关联系数;c为跑道侵入致因的种类;k为同一致因种类中的评价指标类别; μ c k为致因种类 c对应评价指标k的值; μ c 0为同一致因种类下评价指标的参考值; c m i n为同一致因种类下评价指标的最小值; c m a x为同一致因种类下评价指标的最大值;ρ为削弱最大最小化极差导致关联系数失真而引入分辨系数,取 ρ = 0.5[15];m为跑道侵入致因分类总数;rk 为灰色关联度。
以运行环境因素为例,计算出的致因灰色关联度为:rk = (0.73,0.74,0.82,0.63,0.21,0.71,0.58,0.23,0.43),从大到小依次为:跑滑布局复杂、航班量过大、低能见度、地面湿滑、夜间、降水、沙尘、低温、高原机场,其中低温与高原机场作为环境致因对跑道侵入关联性最小。因此,删除上述2种因素,并保留关联度高的致因构建风险传播网络。采用上述方法,优化已有因果链条,最终确定涵盖人员、设备、环境和管理4个类别的61个致因节点,见表1
统计历史数据发现,由于跑道侵入偶发性因果链条中致因间的风险作用机制存在一定的因果关系不确定性[15]。为此,基于历史数据并利用BN挖掘各致因间的作用过程和风险传播程度,并据此进一步构建风险传播因果链序网络。以管制指令不及时风险值 F g ( a 17 )为例,使用BN计算关联致因对其所属分类形成风险的贡献度,根据事件分析致因节点间关联关系确定概率 p ( a 17 )需要先计算出 p ( a 19 ) p ( a 20 ) p ( a 21 ) p ( a 22 ) p ( a 24 ) p ( b 4 )。其中, p ( a 17 )a21相关,根据管制单位对人员素质的分类规则将a21分高、中、低3档,分别为30、20和10 s,所对应 p ( a 21 )分别为0.05、0.3、0.6; p ( a 24 )b4相关,根据实际运行情况将b4分为高、中、低3档,所对应 p ( b 4 )分别为0.05、0.15、0.2; p ( a 19 )a22有关,将 p ( a 22 )分为高、低2档,所对应 p ( a 22 )分别为0.1、0.3。按照初始的状态不同,有18种概率计算组合。因此,需要计算出18种组合对应的p(a17),具体如下:
F g ( a 17 ) = k - = 1 n θ k - g P ( a 17 / A k - g )
θ k - g = 1   000 k - A + 100 k - B + 10 k - C + k - D k - A + k - B + k - C + k - D
式中: F g ( a 17 )为致因 a 17在第 g种条件下的风险值; g = 1,2 18为18种不同条件概率的组合;P为条件概率; A k - g为导致 a 17发生第 g种条件下的前序致因集合; k -为前序致因节点对应的事件编号; θ k - g为第 g种组合下第 k -节点事件发生所导致 a 17发生的风险值;将前序致因节点导致 a 17发生概率分为A、B、C、D等4个等级,A为最高影响等级,D为最低影响等级; k - A k - B k - C k - D k -节点发生导致 a 17分属A、B、C、D不同等级的对应次数,将不同前序致因节点导致该节点发生的概率转变为风险值。
根据上述公式计算 F g ( a 17 )风险值,见表2。同理,可算出其他节点的风险值。
由于跑道侵入事件通常是由因多种风险叠加耦合形成,同时,跑道侵入事件往往是具有时序关系的动态风险传播特性,因此需要综合考虑因素的时序关系。为进一步剖析跑道侵入事件中节点的耦合关系,需要将跑道侵入事件因果链中节点被触发的时间顺序进行划分,进而得到跑道侵入事件的时序数据,并采用皮尔逊线性相关系数优化跑道侵入的致因网络,计算节点在不同事件下不同时段的风险变化相关性,最终得出表征节点风险时序关系的皮尔逊相关系数,具体如下:
ω - i j = n ^ = 1 N ^ t = 1 T ( F ^ n ^ t ( i ) - F ¯ t ( i ) ) · ( F ^ t n ^ ( j ) - F ¯ t ( j ) ) n ^ = 1 N ^ t = 1 T ( F ^ t n ^ ( i ) - F ¯ t ( i ) ) 2 n ^ = 1 N ^ t = 1 T ( F ^ t n ^ ( j ) - F ¯ t ( j ) ) 2
式中: ω - i j为节点 i与节点 j的皮尔逊线性相关系数值,当 ω - i j ϕ时,节点 i与节点 j具有连边, ϕ为设定的阈值; n ^为某个跑道侵入事件, N ^为跑道侵入事件总数; F ^ n ^ t ( i )为节点 i在第 n ^个事件中 t时刻的风险值, F ¯ t ( i )为节点 i t时刻所有事件中的平均风险值; F ^ t n ^ ( j )为节点 j在第 n ^个事件中 t时刻的风险值; F ¯ t ( j )为节点 j t时刻所有事件中的平均风险值。
由于监管因素存在历史数据不足、关联程度不够明晰的问题,故结合专家经验与业务知识对根节点的先验概率进行修正和完善。为消除不同专家认识偏差和主观性,采用模糊综合评价方法计算根节点的先验概率。模糊综合评价方法主要步骤如下:
步骤1:确定评价对象根节点种类以及在实际运行中所处的概率水平。
步骤2:依据跟节点种类,收集专家意见。设定5个不同等级的评价结果,即 L = { 1,2 5 },分别表示发生概率极低、低、一般、高、很高。
步骤3:建立模糊逻辑规则。为便于专家进行客观、科学评价,构建隶属度函数,见表3
步骤4:建立逻辑规则处理专家意见。利用权重化运算规则处理专家意见,获取专家对不同根节点意见集,具体如下:
M = e = 1 E η e · M e e = 1 E η e = ( M i j 1 M i j 2 M i j 3 )
式中: M为专家意见先验概率的综合模糊数; M e为第 e个专家对各个节点先验概率的模糊数;E为专家总数; M i j 1为集成专家意见在不同隶属度下的模糊数均值;ηee专家意见对应权重。
步骤5:解模糊化。利用期望值规则将模糊数均值转变为先验概率值,具体如下:
P c l σ = ε 1 M i j 1 + ε 2 M i j 2 + ε 3 M i j 3
式中: P c l为解模糊化的概率值; ε为对应解模糊数均值的权重; σ为对节点所处的状态水平,共分为5个状态水平。
步骤6:综合评价。将解模糊化的概率值进行归一化处理,得到根节点概率值,具体如下:
P ^ g = P c l σ = 1 5 P c l σ
式中 P ^ g为综合处理的根节点概率值。
DBN参数学习通常在给定事件因果关系的基础上,从训练数据中学习,进而计算节点间条件概率和转移概率。现有方法中主要采用专家评价、半定量分析等方式,但也存在难以通过上述方式确定其条件概率的情况,如a29a30a35等节点,这使得在DBN参数计算时存在准确性不高、颗粒度不足和时序特征不强等问题。由于隐马尔可夫模型(Hidden Markov Models,HMMs)具有较强学习能力,可有效分析隐含的随机过程,为此,采用HMMs[18]计算DBN模型参数。根据2.1和2.2参数学习确定DBN参数,利用DBN专业软件GeNle构建相应动态风险传播网络,根据收集到的信息完成动态参数学习,并对网络进行更新,进而实现风险传播概率的精准推算。
基于1.2与1.3节进一步构建跑道侵入的DBN结构,如图1所示。该图将统计的跑道侵入事故以及事故症候涉及的风险因素分为4个类别61个节点,连边呈现节点间的因果链序关系。
选取2008—2020年间2 626件跑道侵入不安全事件数据作为样本[1-2],并选取2008—2013年的1 608个事件作为参数学习样本,分别采用BN、DBN和HMMs学习DBN,预测2014—2020年发生的1 018起跑道侵入事件风险。
针对致因节点的相同变化,分别采用3种方法对跑道侵入事件的发生概率进行预测,根据专家意见和实际运行经验将风险概率高于0.85视为高风险,即会发生侵入事件如实际发生侵入事件认为预测准确,其余为中低风险,即可能发生如实际发生侵入事件认为预测不准确。
采用DBN,以年为单位将2014—2020年间的跑道侵入数据划分为7个时间片,由于获取的跑道侵入历史事件数据是文本数据,将文本数据转化为跑道侵入致因链的61个节点的离散化数据(节点风险程度),预测跑道侵入风险程度。DBN是在BN基础上引入时间变量,通过历史数据表达节点间推理关系,对将来趋势进行预测,根据图1的风险传播网络图和历史数据,预测目标时间片的跑道侵入风险,将发生、不发生分别记为True、False,预测过程如图2所示。
利用HMMs参数学习DBN进行预测时,首先按照历史数据时序关系,并采用模糊综合评价与HMMs计算先验概率和条件概率,最后更新DBN参数以预测结果。采用3种方法预测2014—2020年跑道侵入事件发生情况,上述3种方法预测准确率如图3所示。
上述3种方法预测准确率的中位数分别为0.74,0.80和0.84,采取HMMs强化学习DBN比DBN和BN预测模型精度分别提升4 %和10 %,而且具有良好的预测稳定性,其预测偏离程度及波动程度最小,说明该方法在强时序关系风险事件预测中具有较强的稳定性,见表4
为分析跑道侵入网络中观测节点(根节点)对风险预测结果的影响情况,以及不同时序条件下风险节点与风险预测结果相关程度,对节点进行灵敏度分析。首先采用先验知识法,分析观测节点对风险预测灵敏性,随后通过调整观测节点的风险发生概率计算跑道侵入事件的风险变化情况,计算结果如图4所示。
图4可知:多数观测节点风险增加并未使得跑道侵入风险显著波动,整体与跑道侵入风险呈正向关系,跑道侵入风险概率变化在30 %以内。
为确定不同时序条件下,节点间敏感度变化情况,采用互信息法对网络中节点进行灵敏度分析。互信息是衡量随机变量之间相互依赖程度的度量,可挖掘节点间关联关系[19]。采用互信息法表征 2个节点间相互关系、信息共享程度以及风险波动对彼此的影响情况,计算式为:
I ( i ; j ) = i j p ( i j ) l o g 2 p ( i j ) p ( i ) p ( j )
式中: I ( i ; j )为两个节点间互信息; p ( i j )为节点ij联合概率; p ( i ) p ( j )为对应节点的边缘概率。
由于网络节点数量较多,仅展示互信息前7位的节点随时间步长下互信息值的变化情况,如图5所示。
图5可知:网络节点的互信息值随时间步长增加并没有发生明显变化,其波动范围在13 %以内。
识别风险网络关键节点是制定有效控制策略的基础,传统复杂网络主要采用度值评价节点重要性,而这种方法会造成评价客观性低。为此,提出采用互信息作为识别风险网络关键节点的方法,该方法通过对比复杂网络中节点度值、互信息值与历史事件中节点致灾性,得出互信息值表征历史事件中节点致灾性准确程度更高。然而,度值、互信息值和历史事件发生次数占比量纲不一致。为此,对互信息值扩大1 000倍,对历史事件发生次数占比扩大100倍,由于图幅限制按照度值排序取17个节点,在不同方法下的对比情况如图6所示。
相比于度值识别风险网络关键节点,互信息法可以提升识别准确率,并增强不同节点重要程度的分辨能力。
1) 融合灰色关联理论与BN等强化学习方法,有助于降低跑道侵入偶发性强对致因网络构建的干扰,厘清跑道侵入致因间关联关系,增强致因网络构建的精准性。
2) 采用三角模糊方法与HMMs算法优化DBN参数学习,有效利用时变信息,使跑道侵入风险的预测准确率相比于传统方法提升10 %,达到84 %。
3) 引入互信息方法分析节点间灵敏度,相比与传统复杂网络度评价方法,其识别风险网络中关键节点的准确率显著提升。
  • 中央高校基本科研业务费项目中国民航大学专项(3122025098)
参考文献 引证文献
排序方式:
[1]
United States Department of Transportation of Federal Aviation Aadministration. Runway safety statistics[R], 2022.
[2]
中国民用航空局航空安全办公室. 中国民航航空安全报告[R], 2021.
[3]
ROGERSON E C, LAMBERT J H. Prioritizing risks via several expert perspectives with application to runway safety[J]. Reliability Engineering and System Safety, 2012, 103(3):22-34.
[4]
JIJOK M, WESLEY L B, MAJOR B, et al. Statistical modelling of runway incursion occurrences in the United States - science direct[J]. Journal of Air Transport Management, 2017, 65(6):54-62.
[5]
霍志勤, 韩松臣. 跑道侵入的威胁与差错分析及控制研究[J]. 安全与环境学报, 2012, 12(4):192-196.
HUO Zhiqin, HAN Songchen. Analysis on the threats and errors caused by the runway incursions and the corresponding controlling ways[J]. Journal of Safety and Environment, 2012, 12(4):192-196.
[6]
霍志勤, 韩松臣. 基于案例推理和规则推理融合的跑道侵入事件调查[J]. 中国安全科学学报, 2012, 22(7):53-58.
HUO Zhiqin, HAN Songchen. Runway incursions investigation based on integration of rule-based reasoning and case-based reasoning[J]. China Safety Science Journal, 2012, 22(7):53-58.
[7]
夏正洪, 万健, 朱新平. 机场热点时空分布特征及运行风险评价[J]. 中国安全科学学报, 2018, 28(1):93-98.
XIA Zhenghong, WAN Jian, ZHU Xinping. Research on spatial and temporal distribution characteristics of airport hotspots and airport operational risk assessment[J]. China Safety Science Journal, 2018, 28(1):93-98.
[8]
STROEVE S H, SOM P, DOORN B A V, et al. Strengthening air traffic safety management by moving from outcome-based towards risk-based evaluation of runway incursions[J]. Reliability Engineering & System Safety, 2016, 147(8):93-108.
[9]
王兴隆, 周督异. 基于复杂网络的飞行区冲突关键栅格区识别[J]. 中国安全生产科学技术, 2023, 19(8):32-38.
WANG Xinglong, ZHOU Duyi. Identification of critical grid areas in flight area conflicts based on complex network[J]. Journal of Safety Science and Technology, 2023, 19(8):32-38.
[10]
罗军, 林雪宁. 基于模糊集和改进TOPSIS方法的跑道侵入风险评估[J]. 中国安全科学学报, 2012, 22(12):116-121.
LUO Jun, LIN Xuening. Runway incursion risk assessment based on fuzzy sets theory and improved TOPSIS method[J]. China Safety Science Journal, 2012, 22(12):116-121.
[11]
罗军, 林雪宁, 闫永刚. 基于高斯贝叶斯网络模型的跑道侵入影响因素研究[J]. 安全与环境学报, 2012, 12(3):196-199.
LUO Jun, LIN Xuening, YAN Yonggang. Analysis of runway incursion influence factors based on gaussian bayesian network model[J]. Journal of Safety and Environment, 2012, 12(3):196-199.
[12]
黄宝军, 房晓丹, 王洁宁. 基于多agent的跑道侵入风险分析建模及仿真[J]. 系统仿真学报, 2017, 29(4):910-917,925.
HUANG Baojun, FANG Xiaodan, WANG Jiening. Risk simulation analysis of runway incursions based on multi agents[J]. Journal of System Simulation, 2017, 29(4):910-917,925.
[13]
焦卫东, 王瑞冬, 姚军强, 等. 跑道侵入与冲突检测的共形几何代数描述[J]. 航空学报, 2022, 43(5):483-492.
JIAO Weidong, WANG Ruidong, YAO Junqiang, et al. Conformal geometric algebraic description of runway incursion and conflict detection[J]. Acta Aeronautica et Astronautica Sinica, 2022, 43(5):483-492.
[14]
王洁宁, 庾睿. 集成本体和BN的跑道侵入态势评估方法[J]. 计算机应用研究, 2019, 36(12):3773-3776.
WANG Jiening, YU Rui. Situation assessment method of runway incursion based on combination of ontology and BN[J]. Application Research of Computers, 2019, 36(12):3773-3776.
[15]
袁乐平, 赵力梵, 张文东, 等. 基于复杂网络的民航跑道侵入事件分析[J]. 安全与环境学报, 2023, 23(5):1368-1375.
YUAN Leping, ZHAO Lifan, ZHANG Wendong, et al. Analysis of civil aviation runway incursion incident based on complex network[J]. Journal of Safety and Environment, 2023, 23(5):1368-1375.
[16]
沈笑云, 张肖艳, 张思远. 基于ADS-B的跑道侵入冲突检测与告警研究[J]. 中国安全科学学报, 2019, 29(9):119-124.
SHEN Xiaoyun, ZHANG Xiaoyan, ZHANG Siyuan. Research on runway incursion conflict detection and alarm based on ADS-B[J]. China Safety Science Journal, 2019, 29(9):119-124.
[17]
吴维, 罗欣然, 魏明. 基于SD模型的跑道侵入风控网络脆弱性分析[J]. 中国安全科学学报, 2021, 31(4):41-48.
WU Wei, LUO Xinran, WEI Ming. Vulnerability assessment of runway intrusion risk control network based on SD model[J]. China Safety Science Journal, 2021, 31(4):41-48.
[18]
STAMP M. A revealing introduction to hidden markov models[J]. Leee Assp Magruine, 2004, 8(5):1-21.
[19]
乌兰, 刘全, 黄志刚, 等. 优势加权互信息最大化的最大熵分层强化学习[J]. 计算机学报, 2023, 46(10):2066-2083.
WU Lan, LIU Quan, HUANG Zhigang, et al. Maximum entropy hierarchical reinforcement learning with advantage-weighted mutual information maximization[J]. Chinese Journal of Computers, 2023, 46(10):2066-2083.
2024年第34卷第7期
PDF下载
366
152
引用本文
BibTeX
文章信息
doi: 10.16265/j.cnki.issn1003-3033.2024.07.0229
  • 接收时间:2024-01-19
  • 首发时间:2025-07-09
  • 出版时间:2024-07-28
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2024-01-19
  • 修回日期:2024-04-20
基金
中央高校基本科研业务费项目中国民航大学专项(3122025098)
作者信息
    1 中国民航大学 民航飞联网重点实验室,天津 300300
    2 中国民航大学 空中交通管理学院,天津 300300
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/zgaqkxxb/CN/10.16265/j.cnki.issn1003-3033.2024.07.0229
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