Article(id=1149733274316092032, tenantId=1146029695717560320, journalId=1146031787341344770, issueId=1149733267617788430, articleNumber=1003-3033(2024)12-0048-08, orderNo=null, doi=10.16265/j.cnki.issn1003-3033.2024.12.0145, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1721145600000, receivedDateStr=2024-07-17, revisedDate=1726761600000, revisedDateStr=2024-09-20, acceptedDate=null, acceptedDateStr=null, onlineDate=1752047373608, onlineDateStr=2025-07-09, pubDate=1735315200000, pubDateStr=2024-12-28, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1752047373608, onlineIssueDateStr=2025-07-09, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1752047373608, creator=13701087609, updateTime=1752047373608, updator=13701087609, issue=Issue{id=1149733267617788430, tenantId=1146029695717560320, journalId=1146031787341344770, year='2024', volume='34', issue='12', pageStart='1', pageEnd='228', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=0, createTime=1752047372010, creator=13701087609, updateTime=1756361981736, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1167830052499628941, tenantId=1146029695717560320, journalId=1146031787341344770, issueId=1149733267617788430, language=EN, specialIssueTitle=, coverIllustrator=, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1167830052499628942, tenantId=1146029695717560320, journalId=1146031787341344770, issueId=1149733267617788430, language=CN, specialIssueTitle=, coverIllustrator=, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=48, endPage=55, ext={EN=ArticleExt(id=1149733274576138888, articleId=1149733274316092032, tenantId=1146029695717560320, journalId=1146031787341344770, language=EN, title=Prediction model of pilot maneuver stability based on LSTM, columnId=1149733269173878863, journalTitle=China Safety Science Journal, columnName=Safety engineering technology, runingTitle=null, highlight=null, articleAbstract=

To predict unsafe events for pilots in real time,a LSTM neural network was used to assess pilot maneuver stability and pilot maneuvering quality was improved by optimizing indicators. Firstly,a set of human-machine maneuvering factors presenting the pilot's maneuvering behavior characteristics was proposed by analyzing the pilot's stability maneuvering QAR data in flight. Secondly,the factors affecting the stability maneuvering of the aircraft were analyzed,and a gray correlation analysis method was used to determine the 15 characteristic parameters of associated risks from the 37 monitoring parameters closely related to the stability of the aircraft. Then,the LSTM model was used to train and test the data to predict the pilot's maneuvering stability,and indicators were proposed to evaluate safety stability quality. Finally,ML was used to rank the importance of relevant influencing factors to improve model validity. The results indicated that the time series model effectively eliminated the interference of parameters with little or no correlation with the prediction results in the original parameters. The stability model can predict risks with high accuracy and provide pilots with a 3-4 s time margin to take preventive measures and reduce unsafe incident occurrence during flight.

, 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=Wenchao WANG, Jian HE, Baisheng SONG, Lei WANG), CN=ArticleExt(id=1149733283908465651, articleId=1149733274316092032, tenantId=1146029695717560320, journalId=1146031787341344770, language=CN, title=基于LSTM的航线飞行员操纵平稳性预测模型, columnId=1149733269727526997, journalTitle=中国安全科学学报, columnName=安全工程技术, runingTitle=null, highlight=null, articleAbstract=

为实时预测飞行员不安全事件,使用长短期记忆神经网络(LSTM)评价飞行员操纵平稳性,并通过优化指标改进飞行员的操纵品质。首先,通过筛选飞行员在执飞中的平稳性操纵快速存取记录仪(QAR)数据,建立描述飞行员操纵行为特征的人机操纵因素集;其次,靶向分析影响飞机平稳操纵的因子,采用灰色关联度分析方法,从与飞机平稳性紧密相关的37个监测参数中定位关联风险的15个特征度量参数;然后,利用LSTM建立模型训练和测试所得数据预测飞行员的操纵平稳性,并制定指标评判标准评价安全平稳性品质;最后,通过机器学习(ML)对相关的影响因子进行重要度排序以改进模型效度。研究结果表明:时间序列模型可以有效剔除原始参数中与预测结果相关性小以及无相关的参数干扰;通过平稳性模型预测风险的精度较高,可为飞行员提供3~4 s的时间裕度采取预控措施,减少飞行过程中的不安全事件发生。

, correspAuthors=null, authorNote=null, correspAuthorsNote=null, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=sWdDZKg6CicahL/8QFvqdg==, magXml=krEcIGQAINmk86pXrGiDug==, pdfUrl=null, pdf=oR5jlf7+4o+gf9/7b/sakA==, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=kDvfqo77IV/9HRkwYzGiWw==, mapNumber=null, authorCompany=null, fund=null, authors=

王文超 (1982—),男,博士,河北承德人,副教授,主要从事民航安全风险管理及人因工程等方面的研究。E-mail:

汪磊,研究员。

, authorsList=王文超, 何健, 宋佰胜, 汪磊)}, authors=[Author(id=1167743004543558209, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149733274316092032, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=wenchaowang@163.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1167743004807799364, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149733274316092032, authorId=1167743004543558209, language=EN, stringName=Wenchao WANG, firstName=Wenchao, middleName=null, lastName=WANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 College of Safety Science and Engineering,Civil Aviation University of China,Tianjin 300300,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1167743004900074053, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149733274316092032, authorId=1167743004543558209, language=CN, stringName=王文超, 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 安全科学与工程学院,天津 300300, bio={"img":"W26NiQiSskpw2Jb5BkP5wQ==","content":"

王文超 (1982—),男,博士,河北承德人,副教授,主要从事民航安全风险管理及人因工程等方面的研究。E-mail:

"}, bioImg=W26NiQiSskpw2Jb5BkP5wQ==, bioContent=

王文超 (1982—),男,博士,河北承德人,副教授,主要从事民航安全风险管理及人因工程等方面的研究。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1167743004363203129, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149733274316092032, xref=1, ext=[AuthorCompanyExt(id=1167743004388368954, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149733274316092032, companyId=1167743004363203129, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 College of Safety Science and Engineering,Civil Aviation University of China,Tianjin 300300,China), AuthorCompanyExt(id=1167743004396757563, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149733274316092032, companyId=1167743004363203129, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 中国民航大学 安全科学与工程学院,天津 300300)])]), Author(id=1167743004971377223, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149733274316092032, 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=1167743005034291785, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149733274316092032, authorId=1167743004971377223, language=EN, stringName=Jian HE, firstName=Jian, middleName=null, lastName=HE, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 College of Safety Science and Engineering,Civil Aviation University of China,Tianjin 300300,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1167743005093012042, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149733274316092032, authorId=1167743004971377223, language=CN, stringName=何健, 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 安全科学与工程学院,天津 300300, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1167743004363203129, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149733274316092032, xref=1, ext=[AuthorCompanyExt(id=1167743004388368954, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149733274316092032, companyId=1167743004363203129, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 College of Safety Science and Engineering,Civil Aviation University of China,Tianjin 300300,China), AuthorCompanyExt(id=1167743004396757563, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149733274316092032, companyId=1167743004363203129, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 中国民航大学 安全科学与工程学院,天津 300300)])]), Author(id=1167743005155926604, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149733274316092032, 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=1167743005214646862, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149733274316092032, authorId=1167743005155926604, language=EN, stringName=Baisheng SONG, firstName=Baisheng, middleName=null, lastName=SONG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2 Flying Squadron Three,Shandong Airlines,Qingdao Shandong 266000,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1167743005260784207, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149733274316092032, authorId=1167743005155926604, language=CN, stringName=宋佰胜, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2 山东航空股份有限公司 飞行三大队,山东 青岛 266000, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1167743004468060732, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149733274316092032, xref=2, ext=[AuthorCompanyExt(id=1167743004476449341, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149733274316092032, companyId=1167743004468060732, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 Flying Squadron Three,Shandong Airlines,Qingdao Shandong 266000,China), AuthorCompanyExt(id=1167743004489032254, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149733274316092032, companyId=1167743004468060732, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 山东航空股份有限公司 飞行三大队,山东 青岛 266000)])]), Author(id=1167743005315310161, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149733274316092032, 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=1167743005378224723, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149733274316092032, authorId=1167743005315310161, language=EN, stringName=Lei WANG, firstName=Lei, middleName=null, lastName=WANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 College of Safety Science and Engineering,Civil Aviation University of China,Tianjin 300300,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1167743005436944980, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149733274316092032, authorId=1167743005315310161, language=CN, stringName=汪磊, 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 安全科学与工程学院,天津 300300, bio={"content":"

汪磊,研究员。

"}, bioImg=null, bioContent=

汪磊,研究员。

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1167743004363203129, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149733274316092032, xref=1, ext=[AuthorCompanyExt(id=1167743004388368954, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149733274316092032, companyId=1167743004363203129, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 College of Safety Science and Engineering,Civil Aviation University of China,Tianjin 300300,China), AuthorCompanyExt(id=1167743004396757563, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149733274316092032, companyId=1167743004363203129, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 中国民航大学 安全科学与工程学院,天津 300300)])])], keywords=[Keyword(id=1167743005579551317, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149733274316092032, language=EN, orderNo=1, keyword=long short-term memory (LSTM)), Keyword(id=1167743005646660182, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149733274316092032, language=EN, orderNo=2, keyword=pilot), Keyword(id=1167743005701186135, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149733274316092032, language=EN, orderNo=3, keyword=maneuvering stability), Keyword(id=1167743005764100696, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149733274316092032, language=EN, orderNo=4, keyword=prediction model), Keyword(id=1167743005885735513, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149733274316092032, language=EN, orderNo=5, keyword=quick access recorder (QAR)), Keyword(id=1167743005961232986, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149733274316092032, language=EN, orderNo=6, keyword=machine learning (ML)), Keyword(id=1167743006019953243, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149733274316092032, language=CN, orderNo=1, keyword=长短期记忆(LSTM)), Keyword(id=1167743006074479196, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149733274316092032, language=CN, orderNo=2, keyword=飞行员), Keyword(id=1167743006124810845, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149733274316092032, language=CN, orderNo=3, keyword=操纵平稳性), Keyword(id=1167743006179336798, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149733274316092032, language=CN, orderNo=4, keyword=预测模型), Keyword(id=1167743006242251359, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149733274316092032, language=CN, orderNo=5, keyword=快速存取记录仪(QAR)), Keyword(id=1167743006309360224, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149733274316092032, language=CN, orderNo=6, keyword=机器学习(ML))], refs=[Reference(id=1167743008351986294, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149733274316092032, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=中国民航总局航空安全办公室, journalName=2023, refType=null, unstructuredReference=中国民航总局航空安全办公室. 中国民航调查报告,2023[R], 2023., articleTitle=中国民航调查报告,2023, refAbstract=null), Reference(id=1167743008419095159, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149733274316092032, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[2], rfOrder=1, authorNames=中国民用航空局, journalName=2021, refType=null, unstructuredReference=中国民用航空局. 中国民用航空"十四五"发展规划,2021[R], 2021., articleTitle=中国民用航空"十四五"发展规划,2021, refAbstract=null), Reference(id=1167743008465232504, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149733274316092032, doi=null, pmid=null, pmcid=null, year=2011, volume=37, issue=10, pageStart=1207, pageEnd=1210, url=null, language=null, rfNumber=[3], rfOrder=2, authorNames=祁明亮, 邵雪焱, 池宏, journalName=北京航空航天大学学报, refType=null, unstructuredReference=祁明亮, 邵雪焱, 池宏. QAR超限事件飞行操作风险诊断方法[J]. 北京航空航天大学学报, 2011, 37(10):1207-1210., articleTitle=QAR超限事件飞行操作风险诊断方法, refAbstract=null), Reference(id=1167743008519758457, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149733274316092032, doi=null, pmid=null, pmcid=null, year=2011, volume=37, issue=10, pageStart=1207, pageEnd=1210, url=null, language=null, rfNumber=[3], rfOrder=3, authorNames=QI Mingliang, SHAO Xueyan, CHI Hong, journalName=Journal of Beijing University of Aeronautics and Astronautics, refType=null, unstructuredReference=QI Mingliang, SHAO Xueyan, CHI Hong. Flight operations risk diagnosis method on quick-access-record exceedance[J]. Journal of Beijing University of Aeronautics and Astronautics, 2011, 37(10):1207-1210., articleTitle=Flight operations risk diagnosis method on quick-access-record exceedance, refAbstract=null), Reference(id=1167743008582673018, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149733274316092032, doi=null, pmid=null, pmcid=null, year=2012, volume=7, issue=5, pageStart=35, pageEnd=37, url=null, language=null, rfNumber=[4], rfOrder=4, authorNames=邵雪焱, 池宏, 高敏刚, journalName=数理统计与管理, refType=null, unstructuredReference=邵雪焱, 池宏, 高敏刚. 基于copula函数的飞行操作风险分析[J]. 数理统计与管理, 2012, 7(5):35-37., articleTitle=基于copula函数的飞行操作风险分析, refAbstract=null), Reference(id=1167743008695919227, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149733274316092032, doi=null, pmid=null, pmcid=null, year=2012, volume=7, issue=5, pageStart=35, pageEnd=37, url=null, language=null, rfNumber=[4], rfOrder=5, authorNames=SHAO Xueyan, CHI Hong, GAO Mingang, journalName=Application of Statistics and Management, refType=null, unstructuredReference=SHAO Xueyan, CHI Hong, GAO Mingang. Risk analysis of operations in flight based on copula[J]. Application of Statistics and Management, 2012, 7(5):35-37., articleTitle=Risk analysis of operations in flight based on copula, refAbstract=null), Reference(id=1167743008788193916, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149733274316092032, doi=null, pmid=null, pmcid=null, year=2017, volume=53, issue=11, pageStart=90, pageEnd=94, url=null, language=null, rfNumber=[5], rfOrder=6, authorNames=冯兴杰, 吴稀钰, 赵杰, journalName=计算机工程与应用, refType=null, unstructuredReference=冯兴杰, 吴稀钰, 赵杰, 等. QAR数据仓库在Hive中的构建[J]. 计算机工程与应用, 2017, 53(11):90-94., articleTitle=QAR数据仓库在Hive中的构建, refAbstract=null), Reference(id=1167743008901440125, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149733274316092032, doi=null, pmid=null, pmcid=null, year=2017, volume=53, issue=11, pageStart=90, pageEnd=94, url=null, language=null, rfNumber=[5], rfOrder=7, authorNames=FENG Xingjie, WU Xiyu, ZHAO Jie, journalName=Computer Engineering and Applications, refType=null, unstructuredReference=FENG Xingjie, WU Xiyu, ZHAO Jie, et al. Data warehouse of QAR based on Hive[J]. Computer Engineering and Applications, 2017, 53(11):90-94., articleTitle=Data warehouse of QAR based on Hive, refAbstract=null), Reference(id=1167743008964354686, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149733274316092032, doi=null, pmid=null, pmcid=null, year=1948, volume=34, issue=20, pageStart=3271, pageEnd=3280, url=null, language=null, rfNumber=[6], rfOrder=8, authorNames=HUNTER P A, journalName=Atmospheric Environment, refType=null, unstructuredReference=HUNTER P A. Flight measurements of the flying qualities of five light airplanes[J]. Atmospheric Environment, 1948, 34(20):3271-3280., articleTitle=Flight measurements of the flying qualities of five light airplanes, refAbstract=null), Reference(id=1167743009023074943, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149733274316092032, doi=null, pmid=null, pmcid=null, year=1969, volume=36, issue=9, pageStart=1557, pageEnd=1562, url=null, language=null, rfNumber=[7], rfOrder=9, authorNames=COOPER G E, HARPER R P, journalName=Moffett Field,CA, refType=null, unstructuredReference=COOPER G E, HARPER R P. The use of pilot rating in the evaluation of aircraft handing qualities[J]. Moffett Field,CA, 1969, 36(9):1557-1562., articleTitle=The use of pilot rating in the evaluation of aircraft handing qualities, refAbstract=null), Reference(id=1167743009090183808, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149733274316092032, doi=null, pmid=null, pmcid=null, year=2009, volume=9, issue=5, pageStart=136, pageEnd=139, url=null, language=null, rfNumber=[8], rfOrder=10, authorNames=杜红兵, 王雪莉, journalName=安全与环境学报, refType=null, unstructuredReference=杜红兵, 王雪莉. 基于贝叶斯网络的可控飞行撞地事故原因分析方法[J]. 安全与环境学报, 2009, 9(5):136-139., articleTitle=基于贝叶斯网络的可控飞行撞地事故原因分析方法, refAbstract=null), Reference(id=1167743009144709761, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149733274316092032, doi=null, pmid=null, pmcid=null, year=2009, volume=9, issue=5, pageStart=136, pageEnd=139, url=null, language=null, rfNumber=[8], rfOrder=11, authorNames=DU Hongbing, WANG Xueli, journalName=Journal of Safety and Environment, refType=null, unstructuredReference=DU Hongbing, WANG Xueli. Cause analysis of the controlled flight bumping into terrain based on the Bayesian network[J]. Journal of Safety and Environment, 2009, 9(5):136-139., articleTitle=Cause analysis of the controlled flight bumping into terrain based on the Bayesian network, refAbstract=null), Reference(id=1167743009207624322, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149733274316092032, doi=null, pmid=null, pmcid=null, year=2023, volume=33, issue=7, pageStart=133, pageEnd=139, url=null, language=null, rfNumber=[9], rfOrder=12, authorNames=何鹏, 孙瑞山, journalName=中国安全科学学报, refType=null, unstructuredReference=何鹏, 孙瑞山. 中国民航典型征候的趋势研究[J]. 中国安全科学学报, 2023, 33(7):133-139., articleTitle=中国民航典型征候的趋势研究, refAbstract=null), Reference(id=1167743009257955971, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149733274316092032, doi=null, pmid=null, pmcid=null, year=2023, volume=33, issue=7, pageStart=133, pageEnd=139, url=null, language=null, rfNumber=[9], rfOrder=13, authorNames=HE Peng, SUN Ruishan, journalName=China Safety Science Journal, refType=null, unstructuredReference=HE Peng, SUN Ruishan. Study on trend of typical incidents of civil aviation in China[J]. China Safety Science Journal, 2023, 33(7):133-139., articleTitle=Study on trend of typical incidents of civil aviation in China, refAbstract=null), Reference(id=1167743009346036357, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149733274316092032, doi=null, pmid=null, pmcid=null, year=2024, volume=34, issue=6, pageStart=235, pageEnd=246, url=null, language=null, rfNumber=[10], rfOrder=14, authorNames=张光远, 邓龙, 王亚伟, journalName=中国安全科学学报, refType=null, unstructuredReference=张光远, 邓龙, 王亚伟, 等. 基于脑电信号特征的高铁调度员疲劳状态识别[J]. 中国安全科学学报, 2024, 34(6):235-246., articleTitle=基于脑电信号特征的高铁调度员疲劳状态识别, refAbstract=null), Reference(id=1167743009417339527, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149733274316092032, doi=null, pmid=null, pmcid=null, year=2024, volume=34, issue=6, pageStart=235, pageEnd=246, url=null, language=null, rfNumber=[10], rfOrder=15, authorNames=ZHANG Guangyuan, DENG Long, WANG Yawei, journalName=China Safety Science Journal, refType=null, unstructuredReference=ZHANG Guangyuan, DENG Long, WANG Yawei, et al. Recognition of fatigue state of high-speed rail dispatchers based on EEG signal characteristics[J]. China Safety Science Journal, 2024, 34(6):235-246., articleTitle=Recognition of fatigue state of high-speed rail dispatchers based on EEG signal characteristics, refAbstract=null), Reference(id=1167743009497031305, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149733274316092032, doi=null, pmid=null, pmcid=null, year=2022, volume=42, issue=1, pageStart=73, pageEnd=78, url=null, language=null, rfNumber=[11], rfOrder=16, authorNames=潘卫军, 张衡衡, 吴天祎, journalName=舰船电子工程, refType=null, unstructuredReference=潘卫军, 张衡衡, 吴天祎, 等. 基于神经网络的飞机着陆速度预测模型[J]. 舰船电子工程, 2022, 42(1):73-78., articleTitle=基于神经网络的飞机着陆速度预测模型, refAbstract=null), Reference(id=1167743009559945867, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149733274316092032, doi=null, pmid=null, pmcid=null, year=2022, volume=42, issue=1, pageStart=73, pageEnd=78, url=null, language=null, rfNumber=[11], rfOrder=17, authorNames=PAN Weijun, ZHANG Hengheng, WU Tianyi, journalName=Ship Electronic Engineering, refType=null, unstructuredReference=PAN Weijun, ZHANG Hengheng, WU Tianyi, et al. Prediction model of aircraft landing speed based on neural network[J]. Ship Electronic Engineering, 2022, 42(1):73-78., articleTitle=Prediction model of aircraft landing speed based on neural network, refAbstract=null), Reference(id=1167743009664803469, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149733274316092032, doi=null, pmid=null, pmcid=null, year=2014, volume=24, issue=2, pageStart=88, pageEnd=92, url=null, language=null, rfNumber=[12], rfOrder=18, authorNames=汪磊, 孙瑞山, 吴昌旭, journalName=中国安全科学学报, refType=null, unstructuredReference=汪磊, 孙瑞山, 吴昌旭, 等. 基于飞行QAR数据的重着陆风险定量评价模型[J]. 中国安全科学学报, 2014, 24(2):88-92., articleTitle=基于飞行QAR数据的重着陆风险定量评价模型, refAbstract=null), Reference(id=1167743009719329423, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149733274316092032, doi=null, pmid=null, pmcid=null, year=2014, volume=24, issue=2, pageStart=88, pageEnd=92, url=null, language=null, rfNumber=[12], rfOrder=19, authorNames=WANG Lei, SUN Ruishan, WU Changxu, journalName=China Safety Science Journal, refType=null, unstructuredReference=WANG Lei, SUN Ruishan, WU Changxu, et al. A flight QAR based model for hard landing risk quantitative evaluation[J]. China Safety Science Journal, 2014, 24(2):88-92., articleTitle=A flight QAR based model for hard landing risk quantitative evaluation, refAbstract=null), Reference(id=1167743009794826897, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149733274316092032, doi=null, pmid=null, pmcid=null, year=2018, volume=26, issue=8, pageStart=67, pageEnd=69, url=null, language=null, rfNumber=[13], rfOrder=20, authorNames=NAGI A, MOHAMED D, ISMAIL E, journalName=Journal of Ocean Engineering and Science, refType=null, unstructuredReference=NAGI A, MOHAMED D, ISMAIL E, et al. Risk assessment of LNG and FLNG vessels during manoeuvring in open sea[J]. Journal of Ocean Engineering and Science, 2018, 26(8):67-69., articleTitle=Risk assessment of LNG and FLNG vessels during manoeuvring in open sea, refAbstract=null), Reference(id=1167743009870324372, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149733274316092032, doi=null, pmid=null, pmcid=null, year=2014, volume=23, issue=11, pageStart=89, pageEnd=91, url=null, language=null, rfNumber=[14], rfOrder=21, authorNames=WANG Lei, SUN Ruishan, WU Changxu, journalName=Reliability Engineering and System Safety, refType=null, unstructuredReference=WANG Lei, SUN Ruishan, WU Changxu. An analysis of flight quick access recorder (QAR) data and its applications in preventing landing incidents[J]. Reliability Engineering and System Safety, 2014, 23(11):89-91., articleTitle=An analysis of flight quick access recorder (QAR) data and its applications in preventing landing incidents, refAbstract=null), Reference(id=1167743009954210454, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149733274316092032, doi=null, pmid=null, pmcid=null, year=2024, volume=12, issue=1, pageStart=85, pageEnd=105, url=null, language=null, rfNumber=[15], rfOrder=22, authorNames=ZAZZI A, DAS D, HUSSEN L, journalName=Photonics Research, refType=null, unstructuredReference=ZAZZI A, DAS D, HUSSEN L, et al. Scalable orthogonal delay-division multiplexed OEO artificial neural network trained for TI-ADC equalization[J]. Photonics Research, 2024, 12(1):85-105., articleTitle=Scalable orthogonal delay-division multiplexed OEO artificial neural network trained for TI-ADC equalization, refAbstract=null), Reference(id=1167743010042290840, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149733274316092032, doi=null, pmid=null, pmcid=null, year=2016, volume=38, issue=6, pageStart=1262, pageEnd=1268, url=null, language=null, rfNumber=[16], rfOrder=23, authorNames=刘莉雯, 张天伟, 茹斌, journalName=计算机工程与科学, refType=null, unstructuredReference=刘莉雯, 张天伟, 茹斌. 多参数融合的飞行品质评估模型的建立[J]. 计算机工程与科学, 2016, 38(6):1262-1268., articleTitle=多参数融合的飞行品质评估模型的建立, refAbstract=null), Reference(id=1167743010101011097, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149733274316092032, doi=null, pmid=null, pmcid=null, year=2016, volume=38, issue=6, pageStart=1262, pageEnd=1268, url=null, language=null, rfNumber=[16], rfOrder=24, authorNames=LIU Liwen, ZHANG Tianwei, RU Bin, journalName=Computer Engineering & Science, refType=null, unstructuredReference=LIU Liwen, ZHANG Tianwei, RU Bin. A flying qualities assessment model based on multi-parameter integration[J]. Computer Engineering & Science, 2016, 38(6):1262-1268., articleTitle=A flying qualities assessment model based on multi-parameter integration, refAbstract=null), Reference(id=1167743010168119962, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149733274316092032, doi=null, pmid=null, pmcid=null, year=2023, volume=23, issue=35, pageStart=684, pageEnd=686, url=null, language=null, rfNumber=[17], rfOrder=25, authorNames=LIU Jiaqi, FENG Yunwen, TENG Da, journalName=Reliability Engineering & System Safety, refType=null, unstructuredReference=LIU Jiaqi, FENG Yunwen, TENG Da, et al. Operational reliability evaluation and analysis framework of civil aircraft complex system based on intelligent extremum machine learning model[J]. Reliability Engineering & System Safety, 2023, 23(35):684-686., articleTitle=Operational reliability evaluation and analysis framework of civil aircraft complex system based on intelligent extremum machine learning model, refAbstract=null), Reference(id=1167743010226840219, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149733274316092032, doi=null, pmid=null, pmcid=null, year=2023, volume=158, issue=69, pageStart=533, pageEnd=536, url=null, language=null, rfNumber=[18], rfOrder=26, authorNames=LI Chongfeng, SUN Ruishan, PAN Xing, journalName=Safety Science, refType=null, unstructuredReference=LI Chongfeng, SUN Ruishan, PAN Xing. Takeoff runway overrun risk assessment in aviation safety based on human pilot behavioral characteristics from real flight data[J]. Safety Science, 2023, 158(69):533-536., articleTitle=Takeoff runway overrun risk assessment in aviation safety based on human pilot behavioral characteristics from real flight data, refAbstract=null), Reference(id=1167743010319114908, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149733274316092032, doi=null, pmid=null, pmcid=null, year=2023, volume=14, issue=1, pageStart=23, pageEnd=37, url=null, language=null, rfNumber=[19], rfOrder=27, authorNames=TANG Ziyang, LI Zuotian, HOU Tieying, journalName=Nature Communication, refType=null, unstructuredReference=TANG Ziyang, LI Zuotian, HOU Tieying. SiGra:single-cell spatial elucidation through an image-augmented graph transformer[J]. Nature Communication, 2023, 14(1):23-37., articleTitle=SiGra:single-cell spatial elucidation through an image-augmented graph transformer, refAbstract=null), Reference(id=1167743010369446557, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149733274316092032, doi=null, pmid=null, pmcid=null, year=2023, volume=23, issue=1, pageStart=314, pageEnd=323, url=null, language=null, rfNumber=[20], rfOrder=28, authorNames=戢晓峰, 乔新, journalName=交通运输系统工程与信息, refType=null, unstructuredReference=戢晓峰, 乔新. 建成环境对行人交通事故严重程度的非线性影响[J]. 交通运输系统工程与信息, 2023, 23(1):314-323., articleTitle=建成环境对行人交通事故严重程度的非线性影响, refAbstract=null), Reference(id=1167743010423972510, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149733274316092032, doi=null, pmid=null, pmcid=null, year=2023, volume=23, issue=1, pageStart=314, pageEnd=323, url=null, language=null, rfNumber=[20], rfOrder=29, authorNames=JI Xiaofeng, QIAO Xin, journalName=Journal of Transportation Systems Engineering and Information Technology, refType=null, unstructuredReference=JI Xiaofeng, QIAO Xin. Nonlinear influence of built environment on pedestrian traffic accident severity[J]. Journal of Transportation Systems Engineering and Information Technology, 2023, 23(1):314-323., articleTitle=Nonlinear influence of built environment on pedestrian traffic accident severity, refAbstract=null)], funds=[Fund(id=1167743008192602741, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149733274316092032, awardId=3122024053, language=CN, fundingSource=中央高校基本科研业务费自然科学重点项目(3122024053), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1167743004363203129, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149733274316092032, xref=1, ext=[AuthorCompanyExt(id=1167743004388368954, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149733274316092032, companyId=1167743004363203129, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 College of Safety Science and Engineering,Civil Aviation University of China,Tianjin 300300,China), AuthorCompanyExt(id=1167743004396757563, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149733274316092032, companyId=1167743004363203129, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 中国民航大学 安全科学与工程学院,天津 300300)]), AuthorCompany(id=1167743004468060732, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149733274316092032, xref=2, ext=[AuthorCompanyExt(id=1167743004476449341, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149733274316092032, companyId=1167743004468060732, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 Flying Squadron Three,Shandong Airlines,Qingdao Shandong 266000,China), AuthorCompanyExt(id=1167743004489032254, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149733274316092032, companyId=1167743004468060732, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 山东航空股份有限公司 飞行三大队,山东 青岛 266000)])], figs=[ArticleFig(id=1167743006489715297, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149733274316092032, language=EN, label=Fig.1, caption=Gray correlation analysis of stability monitoring parameters, figureFileSmall=rdubEJbq4HPFeL/v4mzDIA==, figureFileBig=Vrib74y5b4RNlb16lsB7Og==, tableContent=null), ArticleFig(id=1167743006573601378, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149733274316092032, language=CN, label=图1, caption=平稳性监测参数灰色关联度分析, figureFileSmall=rdubEJbq4HPFeL/v4mzDIA==, figureFileBig=Vrib74y5b4RNlb16lsB7Og==, tableContent=null), ArticleFig(id=1167743006665876067, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149733274316092032, language=EN, label=Fig.2, caption=Algorithmic flow of LSTM neural network model, figureFileSmall=ZxNihKiWczqphQRenIspdg==, figureFileBig=xDrc48yz9H5iXEg3RPY9ag==, tableContent=null), ArticleFig(id=1167743006737179236, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149733274316092032, language=CN, label=图2, caption=LSTM神经网络模型的算法流程, figureFileSmall=ZxNihKiWczqphQRenIspdg==, figureFileBig=xDrc48yz9H5iXEg3RPY9ag==, tableContent=null), ArticleFig(id=1167743006913340005, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149733274316092032, language=EN, label=Fig.3, caption=Time-series changes of five outputs, figureFileSmall=7eWD1lH2fWK4+gyGTNrFqA==, figureFileBig=Ifq/3rrivgCQSgsCspqMsw==, tableContent=null), ArticleFig(id=1167743007047557734, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149733274316092032, language=CN, label=图3, caption=5项输出指标时间序列变化, figureFileSmall=7eWD1lH2fWK4+gyGTNrFqA==, figureFileBig=Ifq/3rrivgCQSgsCspqMsw==, tableContent=null), ArticleFig(id=1167743007135638119, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149733274316092032, language=EN, label=Fig.4, caption=Parameter importance ranking, figureFileSmall=DiQNzSL5zVQ29sPRCu41Zw==, figureFileBig=iisBzzoz1NsrgOT7JHrWpQ==, tableContent=null), ArticleFig(id=1167743007236301416, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149733274316092032, language=CN, label=图4, caption=参数重要性排序, figureFileSmall=DiQNzSL5zVQ29sPRCu41Zw==, figureFileBig=iisBzzoz1NsrgOT7JHrWpQ==, tableContent=null), ArticleFig(id=1167743007290827369, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149733274316092032, language=EN, label=Fig.5, caption=Output prediction performance, figureFileSmall=xpuLr5aSFUc62keWnCDFMg==, figureFileBig=hlNDuwYNm4uLHrTrxZ1STw==, tableContent=null), ArticleFig(id=1167743007383102058, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149733274316092032, language=CN, label=图5, caption=输出参数预测效果, figureFileSmall=xpuLr5aSFUc62keWnCDFMg==, figureFileBig=hlNDuwYNm4uLHrTrxZ1STw==, tableContent=null), ArticleFig(id=1167743007458599531, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149733274316092032, language=EN, label=Table 1, caption=

Indicator structure

, figureFileSmall=null, figureFileBig=null, tableContent=
指标
类型
监控参数 指标
类型
监控参数
结构
襟翼位置 轨迹
航向道偏差
左发EGT 下滑道偏差
右发EGT 垂直偏差
左油门杆 左发N1转速
右油门杆 右发N1转速
方向舵 左发N2转速
左升降舵位置 右发N2转速
右升降舵位置 风速
左驾驶盘位置 风向
右驾驶盘位置 磁航向
左驾驶杆位置 姿态
飞行指引坡度偏差
右驾驶杆位置 飞行指引仰角偏差
限制
下降率 左攻角
升降率 右攻角
垂直载荷 坡度
气压高度 仰角
无线电高度 空速
经度 地速
纬度
), ArticleFig(id=1167743007584428652, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149733274316092032, language=CN, label=表1, caption=

指标结构

, figureFileSmall=null, figureFileBig=null, tableContent=
指标
类型
监控参数 指标
类型
监控参数
结构
襟翼位置 轨迹
航向道偏差
左发EGT 下滑道偏差
右发EGT 垂直偏差
左油门杆 左发N1转速
右油门杆 右发N1转速
方向舵 左发N2转速
左升降舵位置 右发N2转速
右升降舵位置 风速
左驾驶盘位置 风向
右驾驶盘位置 磁航向
左驾驶杆位置 姿态
飞行指引坡度偏差
右驾驶杆位置 飞行指引仰角偏差
限制
下降率 左攻角
升降率 右攻角
垂直载荷 坡度
气压高度 仰角
无线电高度 空速
经度 地速
纬度
), ArticleFig(id=1167743007668314733, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149733274316092032, language=EN, label=Table 2, caption=

Prediction model inputs

, figureFileSmall=null, figureFileBig=null, tableContent=
参数序号 参数名称 参数序号 参数名称
1 下降率 9 风速
2 地速 10 风向
3 空速 11 飞行指引仰角偏差
4 垂直载荷 12 飞行指引坡度偏差
5 仰角 13 襟翼位置
6 坡度 14 下滑道偏差
7 磁航向 15 航向道偏差
8 垂直偏差
), ArticleFig(id=1167743007722840686, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149733274316092032, language=CN, label=表2, caption=

预测模型的输入参数

, figureFileSmall=null, figureFileBig=null, tableContent=
参数序号 参数名称 参数序号 参数名称
1 下降率 9 风速
2 地速 10 风向
3 空速 11 飞行指引仰角偏差
4 垂直载荷 12 飞行指引坡度偏差
5 仰角 13 襟翼位置
6 坡度 14 下滑道偏差
7 磁航向 15 航向道偏差
8 垂直偏差
), ArticleFig(id=1167743007777366639, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149733274316092032, language=EN, label=Table 3, caption=

Stability evaluation criteria

, figureFileSmall=null, figureFileBig=null, tableContent=
平稳性等
级分类
指标标准
优秀 下滑道偏差在[-0.01,0.01],或垂直偏差为0,或飞行指引仰角偏差为0,或航向道偏差在[-0.005,0]∪[0,0.005],或飞行指引坡度偏差在[-0.2,-<0.1]∪[0.1,0.2]
良好 下滑道偏差在[-0.02,0.02],或垂直偏差为0,或飞行指引仰角偏差为0,或航向道偏差在[-0.007,0]∪[0,0.007],或飞行指引坡度偏差在[-0.3,-<0.2]∪[0.2,0.3]
一般 下滑道偏差在[-0.03,0.03],或垂直偏差为0,或飞行指引仰角偏差为0,或航向道偏差在[-0.009,0]∪[0,0.009],或飞行指引坡度偏差在[-0.4,-<0.3]∪[0.3,0.4]
需改进 下滑道偏差在[-0.04,0.04],或垂直偏差为0,或飞行指引仰角偏差为0,或航向道偏差在[-0.01,0]∪[0,0.01],或飞行指引坡度偏差在[-0.5,-<0.4]∪[0.4,0.5]
不合格 下滑道偏差在[-0.05,0.05],或垂直偏差为0,或飞行指引仰角偏差为0,或航向道偏差在[-∞,-0.01]∪[0.01,+∞],或飞行指引坡度偏差在[-∞,-<0.5]∪[0.5,+∞]
), ArticleFig(id=1167743007836086896, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149733274316092032, language=CN, label=表3, caption=

平稳性判定标准

, figureFileSmall=null, figureFileBig=null, tableContent=
平稳性等
级分类
指标标准
优秀 下滑道偏差在[-0.01,0.01],或垂直偏差为0,或飞行指引仰角偏差为0,或航向道偏差在[-0.005,0]∪[0,0.005],或飞行指引坡度偏差在[-0.2,-<0.1]∪[0.1,0.2]
良好 下滑道偏差在[-0.02,0.02],或垂直偏差为0,或飞行指引仰角偏差为0,或航向道偏差在[-0.007,0]∪[0,0.007],或飞行指引坡度偏差在[-0.3,-<0.2]∪[0.2,0.3]
一般 下滑道偏差在[-0.03,0.03],或垂直偏差为0,或飞行指引仰角偏差为0,或航向道偏差在[-0.009,0]∪[0,0.009],或飞行指引坡度偏差在[-0.4,-<0.3]∪[0.3,0.4]
需改进 下滑道偏差在[-0.04,0.04],或垂直偏差为0,或飞行指引仰角偏差为0,或航向道偏差在[-0.01,0]∪[0,0.01],或飞行指引坡度偏差在[-0.5,-<0.4]∪[0.4,0.5]
不合格 下滑道偏差在[-0.05,0.05],或垂直偏差为0,或飞行指引仰角偏差为0,或航向道偏差在[-∞,-0.01]∪[0.01,+∞],或飞行指引坡度偏差在[-∞,-<0.5]∪[0.5,+∞]
), ArticleFig(id=1167743007936750193, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149733274316092032, language=EN, label=Table 4, caption=

Comparison of training results with different time series step sizes

, figureFileSmall=null, figureFileBig=null, tableContent=
输入
步长
输出
步长
训练集
损失值
测试集
损失值
测试集平均
绝对误差
25 25 0.002 4 0.002 1 0.042 2
25 50 0.002 3 0.002 6 0.050 2
25 75 0.005 7 0.003 9 0.060 1
50 25 0.001 9 0.002 1 0.030 1
50 50 0.004 1 0.003 1 0.039 6
50 75 0.003 6 0.004 5 0.051 1
75 25 0.001 8 0.002 7 0.010 2
75 50 0.003 8 0.001 9 0.015 3
75 75 0.002 2 0.004 2 0.023 3
), ArticleFig(id=1167743007999664754, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149733274316092032, language=CN, label=表4, caption=

不同时间序列步长训练结果比较

, figureFileSmall=null, figureFileBig=null, tableContent=
输入
步长
输出
步长
训练集
损失值
测试集
损失值
测试集平均
绝对误差
25 25 0.002 4 0.002 1 0.042 2
25 50 0.002 3 0.002 6 0.050 2
25 75 0.005 7 0.003 9 0.060 1
50 25 0.001 9 0.002 1 0.030 1
50 50 0.004 1 0.003 1 0.039 6
50 75 0.003 6 0.004 5 0.051 1
75 25 0.001 8 0.002 7 0.010 2
75 50 0.003 8 0.001 9 0.015 3
75 75 0.002 2 0.004 2 0.023 3
), ArticleFig(id=1167743008054190707, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149733274316092032, language=EN, label=Table 5, caption=

Comparison of predictions with different parameter values

, figureFileSmall=null, figureFileBig=null, tableContent=
输入参数数量 测试集损失值 测试集平均绝对误差
37 0.010 2 0.021 5
15 0.000 9 0.011 2
), ArticleFig(id=1167743008100328052, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149733274316092032, language=CN, label=表5, caption=

不同参数量预测结果比较

, figureFileSmall=null, figureFileBig=null, tableContent=
输入参数数量 测试集损失值 测试集平均绝对误差
37 0.010 2 0.021 5
15 0.000 9 0.011 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.issn1003-3033.2024.12.0145, detailUrlEn=https://castjournals.cast.org.cn/joweb/zgaqkxxb/EN/10.16265/j.cnki.issn1003-3033.2024.12.0145, pdfUrlCn=https://castjournals.cast.org.cn/joweb/zgaqkxxb/CN/PDF/10.16265/j.cnki.issn1003-3033.2024.12.0145, pdfUrlEn=https://castjournals.cast.org.cn/joweb/zgaqkxxb/EN/PDF/10.16265/j.cnki.issn1003-3033.2024.12.0145, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于LSTM的航线飞行员操纵平稳性预测模型
收藏切换
PDF下载
王文超 1 , 何健 1 , 宋佰胜 2 , 汪磊 1
中国安全科学学报 | 安全工程技术 2024,34(12): 48-55
收起
收藏切换
中国安全科学学报 | 安全工程技术 2024, 34(12): 48-55
基于LSTM的航线飞行员操纵平稳性预测模型
全屏
王文超1 , 何健1, 宋佰胜2, 汪磊1
作者信息
  • 1 中国民航大学 安全科学与工程学院,天津 300300
  • 2 山东航空股份有限公司 飞行三大队,山东 青岛 266000
  • 王文超 (1982—),男,博士,河北承德人,副教授,主要从事民航安全风险管理及人因工程等方面的研究。E-mail:

    汪磊,研究员。

Prediction model of pilot maneuver stability based on LSTM
Wenchao WANG1 , Jian HE1, Baisheng SONG2, Lei WANG1
Affiliations
  • 1 College of Safety Science and Engineering,Civil Aviation University of China,Tianjin 300300,China
  • 2 Flying Squadron Three,Shandong Airlines,Qingdao Shandong 266000,China
出版时间: 2024-12-28 doi: 10.16265/j.cnki.issn1003-3033.2024.12.0145
文章导航
收藏切换

为实时预测飞行员不安全事件,使用长短期记忆神经网络(LSTM)评价飞行员操纵平稳性,并通过优化指标改进飞行员的操纵品质。首先,通过筛选飞行员在执飞中的平稳性操纵快速存取记录仪(QAR)数据,建立描述飞行员操纵行为特征的人机操纵因素集;其次,靶向分析影响飞机平稳操纵的因子,采用灰色关联度分析方法,从与飞机平稳性紧密相关的37个监测参数中定位关联风险的15个特征度量参数;然后,利用LSTM建立模型训练和测试所得数据预测飞行员的操纵平稳性,并制定指标评判标准评价安全平稳性品质;最后,通过机器学习(ML)对相关的影响因子进行重要度排序以改进模型效度。研究结果表明:时间序列模型可以有效剔除原始参数中与预测结果相关性小以及无相关的参数干扰;通过平稳性模型预测风险的精度较高,可为飞行员提供3~4 s的时间裕度采取预控措施,减少飞行过程中的不安全事件发生。

长短期记忆(LSTM)  /  飞行员  /  操纵平稳性  /  预测模型  /  快速存取记录仪(QAR)  /  机器学习(ML)

To predict unsafe events for pilots in real time,a LSTM neural network was used to assess pilot maneuver stability and pilot maneuvering quality was improved by optimizing indicators. Firstly,a set of human-machine maneuvering factors presenting the pilot's maneuvering behavior characteristics was proposed by analyzing the pilot's stability maneuvering QAR data in flight. Secondly,the factors affecting the stability maneuvering of the aircraft were analyzed,and a gray correlation analysis method was used to determine the 15 characteristic parameters of associated risks from the 37 monitoring parameters closely related to the stability of the aircraft. Then,the LSTM model was used to train and test the data to predict the pilot's maneuvering stability,and indicators were proposed to evaluate safety stability quality. Finally,ML was used to rank the importance of relevant influencing factors to improve model validity. The results indicated that the time series model effectively eliminated the interference of parameters with little or no correlation with the prediction results in the original parameters. The stability model can predict risks with high accuracy and provide pilots with a 3-4 s time margin to take preventive measures and reduce unsafe incident occurrence during flight.

long short-term memory (LSTM)  /  pilot  /  maneuvering stability  /  prediction model  /  quick access recorder (QAR)  /  machine learning (ML)
王文超, 何健, 宋佰胜, 汪磊. 基于LSTM的航线飞行员操纵平稳性预测模型. 中国安全科学学报, 2024 , 34 (12) : 48 -55 . DOI: 10.16265/j.cnki.issn1003-3033.2024.12.0145
Wenchao WANG, Jian HE, Baisheng SONG, Lei WANG. Prediction model of pilot maneuver stability based on LSTM[J]. China Safety Science Journal, 2024 , 34 (12) : 48 -55 . DOI: 10.16265/j.cnki.issn1003-3033.2024.12.0145
2023年7月30日,某航空公司B737飞机在济南机场着陆过程中,由于飞行员进近和着陆准备不充分,对夜间大雨天气应急响应不到位,导致飞机失稳并偏出跑道[1]。从上述事故看出,航线飞行员对飞机操纵平稳性把控不到位或胜任能力不达标,会引发严重的飞行安全事故及征候。事件案例表明:不平稳性问题是事故发生的关键致因,良好的操纵平稳性可以保障航空器运行的持续稳定,也有利于降低飞行事故的发生概率。《“十四五”民用航空发展规划》中指出,要严格把关航线飞行员技术素质,注重飞行员的操纵技能演练[2]。因此,研究航线飞行员对飞机操纵的平稳性不仅有助于优化飞行操作流程和提高飞行安全水平,还可为飞行员培训和飞行技能提升提供理论支持和实践指导。
目前,国内外在飞行员操纵平稳性研究方面已取得一定成果。如祁明亮[3]等通过分析多个航班的快速存取记录仪(Quick Access Recorder,QAR)数据,指出在高风险性子空间内会出现飞行质量监测超限事件。邵雪焱[4]利用Copula建立了风险分析模型来寻找飞行员的风险操纵行为。冯兴杰等[5]提出了将小波的尺度系数应用于分析飞行数据。HUNTER等[6]在飞机操纵和机动过程中评价了飞行员的平衡性、速度控制以及稳定性。COOPER等[7]提出了一种飞机操纵特性量表,并依据所选取的最佳指标划分飞行员的操作技能等级。依据国际民用航空组织的分析报告[2],着陆阶段是事故高发频发阶段,是运行安全平稳保证的关键阶段。着陆过程中的平稳性不仅关系到乘客的舒适度,更直接关系到飞行安全。通过总结国内外文献,专家学者借助对飞行数据的分析和模拟技术探寻改进方法和策略,然而,飞行员的个人技能和状态对操纵平稳性影响显著,且这些因素通常难以量化和控制,进而影响了研究的可靠性。综上所述,当前我国对于QAR数据的应用研究比较普遍,但从QAR数据中分析飞机进近着陆时的操纵表现鲜少将飞行姿态与飞行员的个人操纵技能联系起来进行分析并发现的其中关联。
鉴于此,笔者拟基于国内某航空公司提供的波音737的飞行数据,重点选取进近着陆过程中飞机的姿态数据作为研究,利用长短期记忆 (Long Short-Term Memory,LSTM)神经网络来预测和评价飞行员的操纵稳定性,以期更好地理解航线飞行员的操纵行为,提高飞行器自动化的程度。
国内公共运输飞机配备了QAR来记录和存储飞行数据[8],QAR数据能够为分析平稳性的影响因素提供科学依据。在机场进近着陆时,描述飞行员平稳性操作特性,发现QAR数据类型有限且可归类。相关研究指出,飞机的姿态角和坡度角变化体现了飞机姿态的变化程度[9];同时,飞机高度和指示空速的变化则反映了飞机的稳定状态。良好的进近点可确保飞行器在与地面相交之前刚好有一段最短的平飘距离[10]。将QAR数据分为限制、轨迹、姿态、结构4个类别。研究飞行平稳性的优劣最终是通过各个指标分量的量化结果来考察的。因此,将操作特性按照考察途径、监控参数、指标分量的模式进行分类总结,能够得到飞行员操作的具体量化分析结构,为定量分析奠定基础。表1展示了指标结构,其中,EGT(Exhaust Gas Temperature)为发动机气体温度,N1为左发动机,N2为右发动机。
当前基于QAR的监控方法,难以充分适应飞机复杂多变的运行环境,无法监测飞机是否处于安全状态[11]。根据QAR数据的时间序列特点,采用LSTM网络,建立一种飞行操纵平稳性的风险预测模型,实现不平稳性事件的风险预测。
基于飞行品质监控管理平台(Flight Operation Quality Assurance,FOQA)中规定的监控指标[12],从QAR数据中选取与飞机平稳性相关的37个监测参数,考虑到这些参数可能存在相关性,采用灰色关联度分析来剔除其中高相关性的参数[13]。计算过程为:
φ ( Y 0 Y i ) = 1 n m = 1 n φ [ Y 0 ( m ) Y i ( m )
式中: Y 0为参考序列, Y 0 = { Y 0 ( 1 ) Y 0 ( 2 ) Y 0 ( m ) }; Y i为第i个被比较数列(i=1,2,…,p), Y i = { Y i ( 1 ) Y i ( 2 ) Y i ( m ) }; φ ( Y 0 Y i ) Y 0 Y i的灰色关联度,记为 φ 0 i; φ [ Y 0 ( m ) Y i ( m ) ] k ( k = 1,2 m )点关联系数,记为 φ 0 i ( k )
选取参考数列:
Y 0 = { Y 0 ( 1 ) Y 0 ( 2 ) Y 0 ( m ) }
式中m为时刻,假设有n个比较数列。
Y i = { Y 0 ( 1 ) Y 0 ( 2 ) Y 0 ( n ) }
则比较数列 Y i对参考数列在m时刻的关联系数是:
δ j ( k ) = m i n i k Y 0 ( k ) - Y i ( k ) | + β m a x i k | Y 0 ( k ) - Y i ( k ) | | Y 0 ( k ) - Y i ( k ) | + β m a x i k | Y 0 ( k ) - Y i ( k ) |
式中: β [0,1]为分辨系数, β越大,分辨率越大;β越小,分辨率越小; m i n i k Y 0 ( k ) - Y i ( k ) | β m a x i k Y 0 ( k ) - Y i ( k ) |分别为2级最小差和2级最大差。 δ j ( k )反映了比较数列和参考数列在某一时刻的关联程度[14],为便于比较,求得各时刻关联系数的平均值,即为数列 Y i Y 0的关联度。
t i = 1 n k = 1 n δ j ( k )
对37个监测参数进行灰色关联度分析,当2个参数的相关系数低于0.30时,表明它们之间的关系为极弱;相关系数在[0.30~0.50]为低相关性;相关系数在[0.50,0.80]为中相关性;相关系数处于[0.80,0.95]为高相关性;相关系数达到0.95以上则存在显著的相关性[15]。计算结果如图1所示。
图1中,颜色越深代表负相关性越高,颜色越浅则代表正相关性越高。将图1中相关系数高于0.80的参数剔除,可以看出,下降率、地速、空速、垂直载荷、仰角、坡度、磁航向、垂直偏差、风速、风向、飞行指引仰角偏差、飞行指引坡度偏差、襟翼位置、下滑道偏差、航向道偏差这15项指标彼此间的相关系数较小,所以选取它们作为预测模型的输入参数,见表2
根据FOQA中涉及的监测参数,选择垂直偏差、飞行指引仰角偏差、飞行指引坡度偏差、下滑道偏差、航向道偏差等5个参数作为模型的监测指标,并结合刘莉雯等[16]制定飞行品质评价的方法,以及LIU Jiaqi等[17]构建的飞行参数评估模型,确立了一套适用于B737-800机型平稳性评价的判定标准,见表3
使用机器学习(Machine Learning,ML)中Python的库构建LSTM拓扑结构进行训练和测试,算法流程如图2所示。模型运行程如下:①输入目标监测点的时间序列数据集,即平稳性操纵的影响因子,如俯仰角等。②数据集按照7∶1∶2的比例划分。③将数据output1输入到LSTM层,利用其隐藏状态对时间序列进行计算,得到输出数据output2。利用框架提供的回调函数Model Checkpoint创建Checkpoint,在训练过程中保存最优模型,并在后续的风险预测中调用最优模型。④利用LSTM层计算出的数据output2输入到全连接层,从而得到output3。⑤判断训练是否结束的条件是训练次数是否达到设定的数值。如果达到设定的次数,停止模型训练;否则,重复进行训练。⑥使用model.predict()进行预测,对预测结果进行反向归一化处理并输出。⑦根据实际值与预测值计算平均绝对误差(Mean Absolute Error,MAE)以及决定系数 R 2。⑧评价模型训练拟合的效果。
根据2.3节确定的模型输出参数,采集进近着陆阶段100内5项指标的时间序列片段,图3为2.3节5项输出指标的变化情况,可以看出,飞行指引仰角偏差在前40s几乎没有变化,后60s变化幅度比较明显;飞行指引坡度偏差始终以一个较为缓慢的幅度变化;垂直偏差,下滑道偏差以及航向道偏差的波动幅度则较为明显。
输入和输出的序列步长均会影响模型的预测精度[18],输出序列的步长决定了模型能够提前多长时间预测风险,过短的预测步长不能及时地预测目标参数,从而无法提供宽裕的时间给飞行员作出对策。为确定最佳的时间序列步长,根据图3的指标变化趋势拟定9组测试区间,通过模型训练对比训练集和测试集的损失值与平均绝对误差,训练集和测试集的损失值和平均绝对误差越小则拟合度越高[19]。具体模型训练结果比较见表4
由于部分参数会干扰模型的预测效果,根据训练测试适应性场景选择模型的输入参数数量。利用2.2节中确定的优化预测模型,与之前没有进行参数优化的模型进行预测效果对比见表5
表5可以看出,采用灰色关联分析后得到的15个参数作为风险预测模型输入时,得到的预测效果更好,因为去除了原始37个参数中与预测结果相关性小的参数干扰。同时,由于输入参数数量的减少,缩短了训练和预测时间,因此,证实灰色关联分析有利于提高模型的预测效果。
ML模型中的库Shapley Additive exPlanations(SHAP)能够很好地处理高维输入特征,这对于QAR数据这种包含大量传感器数据的时间序列非常适用[20]。SHAP为每个特征提供具体的贡献度进行数值排序,用来表示该特征对着陆事件的影响程度。
根据SHAP计算结果,选取排名前10的重要特征,如图4所示。特征名从上至下是对预测结果重要性排序后的结果。
根据图4的结果分析可知:仰角对飞行员平稳性操纵影响最大,坡度对飞行员操纵平稳性的影响占第2位。风险预测模型根据以上特征值的结果调整训练集和预测集的参数权重来实现优化,并给出评价结果。
抽取B737-800的200个进近着陆的航段作为模型验证的事例,增大ML模型训练个数和训练时长,由前40s预测后60s的结果,根据重要度筛选影响飞行员平稳性操纵的因子。预测结果如图5所示。
图5可以看出,5个评价参数的真实值与预测值有较高的重合度,表现出较高的预测精度。根据特征重要度排序,针对性地优化模型结构,增加对重要特征的关注度,减少对不重要特征的依赖,提高了模型在有关时间序列的风险预测任务上的准确性和鲁棒性。通过关注这些关键参数,改进的模型可以更早地预测出可能出现的问题,为飞行员提供更多的反应时间。例如:模型发现某个传感器数据的突变是导致飞行状况恶化的主要原因,把重点放在这个传感器数据的实时监控上,则可以为飞行员争取到3~4s的预警时间。
1) 借助灰色关联度分析,自QAR数据中提取15个特征参数,预测不平稳着陆的5个评价参数的变化趋势,这样有助于提前预警飞机不平稳着陆。
2) 通过剖析时间区间异常的特性,构建一种基于历史数据训练的LSTM模型,通过分析真实值与预测值的差值来判别异常。结合指标分析与实用价值,克服了多参数计算消耗时间长的不足,有助于保持梯度流。所提算法具备一定的独特优势。
3) 运用ML中的SHAP对训练模型开展可解释性分析,能够将关键参数对不平稳着陆事件的边际贡献予以可视化,间接阐释不平稳着陆事件的成因,实现风险事件检测与风险原因解释这2方面的统一。
4) 采用QAR译码数据和标准超限参数库匹配获取的异常标签,在部分简单的异常检测场景中适用。然而,针对分析异常事件的严重程度,标准超限参数库并未明确某个单一航班的异常程度,如何在一个航班中区分异常的程度在数据集中未得到体现,需要进一步明晰风险事件严重程度之间的关联。
  • 中央高校基本科研业务费自然科学重点项目(3122024053)
参考文献 引证文献
排序方式:
[1]
中国民航总局航空安全办公室. 中国民航调查报告,2023[R], 2023.
[2]
中国民用航空局. 中国民用航空"十四五"发展规划,2021[R], 2021.
[3]
祁明亮, 邵雪焱, 池宏. QAR超限事件飞行操作风险诊断方法[J]. 北京航空航天大学学报, 2011, 37(10):1207-1210.
QI Mingliang, SHAO Xueyan, CHI Hong. Flight operations risk diagnosis method on quick-access-record exceedance[J]. Journal of Beijing University of Aeronautics and Astronautics, 2011, 37(10):1207-1210.
[4]
邵雪焱, 池宏, 高敏刚. 基于copula函数的飞行操作风险分析[J]. 数理统计与管理, 2012, 7(5):35-37.
SHAO Xueyan, CHI Hong, GAO Mingang. Risk analysis of operations in flight based on copula[J]. Application of Statistics and Management, 2012, 7(5):35-37.
[5]
冯兴杰, 吴稀钰, 赵杰, 等. QAR数据仓库在Hive中的构建[J]. 计算机工程与应用, 2017, 53(11):90-94.
FENG Xingjie, WU Xiyu, ZHAO Jie, et al. Data warehouse of QAR based on Hive[J]. Computer Engineering and Applications, 2017, 53(11):90-94.
[6]
HUNTER P A. Flight measurements of the flying qualities of five light airplanes[J]. Atmospheric Environment, 1948, 34(20):3271-3280.
[7]
COOPER G E, HARPER R P. The use of pilot rating in the evaluation of aircraft handing qualities[J]. Moffett Field,CA, 1969, 36(9):1557-1562.
[8]
杜红兵, 王雪莉. 基于贝叶斯网络的可控飞行撞地事故原因分析方法[J]. 安全与环境学报, 2009, 9(5):136-139.
DU Hongbing, WANG Xueli. Cause analysis of the controlled flight bumping into terrain based on the Bayesian network[J]. Journal of Safety and Environment, 2009, 9(5):136-139.
[9]
何鹏, 孙瑞山. 中国民航典型征候的趋势研究[J]. 中国安全科学学报, 2023, 33(7):133-139.
HE Peng, SUN Ruishan. Study on trend of typical incidents of civil aviation in China[J]. China Safety Science Journal, 2023, 33(7):133-139.
[10]
张光远, 邓龙, 王亚伟, 等. 基于脑电信号特征的高铁调度员疲劳状态识别[J]. 中国安全科学学报, 2024, 34(6):235-246.
ZHANG Guangyuan, DENG Long, WANG Yawei, et al. Recognition of fatigue state of high-speed rail dispatchers based on EEG signal characteristics[J]. China Safety Science Journal, 2024, 34(6):235-246.
[11]
潘卫军, 张衡衡, 吴天祎, 等. 基于神经网络的飞机着陆速度预测模型[J]. 舰船电子工程, 2022, 42(1):73-78.
PAN Weijun, ZHANG Hengheng, WU Tianyi, et al. Prediction model of aircraft landing speed based on neural network[J]. Ship Electronic Engineering, 2022, 42(1):73-78.
[12]
汪磊, 孙瑞山, 吴昌旭, 等. 基于飞行QAR数据的重着陆风险定量评价模型[J]. 中国安全科学学报, 2014, 24(2):88-92.
WANG Lei, SUN Ruishan, WU Changxu, et al. A flight QAR based model for hard landing risk quantitative evaluation[J]. China Safety Science Journal, 2014, 24(2):88-92.
[13]
NAGI A, MOHAMED D, ISMAIL E, et al. Risk assessment of LNG and FLNG vessels during manoeuvring in open sea[J]. Journal of Ocean Engineering and Science, 2018, 26(8):67-69.
[14]
WANG Lei, SUN Ruishan, WU Changxu. An analysis of flight quick access recorder (QAR) data and its applications in preventing landing incidents[J]. Reliability Engineering and System Safety, 2014, 23(11):89-91.
[15]
ZAZZI A, DAS D, HUSSEN L, et al. Scalable orthogonal delay-division multiplexed OEO artificial neural network trained for TI-ADC equalization[J]. Photonics Research, 2024, 12(1):85-105.
[16]
刘莉雯, 张天伟, 茹斌. 多参数融合的飞行品质评估模型的建立[J]. 计算机工程与科学, 2016, 38(6):1262-1268.
LIU Liwen, ZHANG Tianwei, RU Bin. A flying qualities assessment model based on multi-parameter integration[J]. Computer Engineering & Science, 2016, 38(6):1262-1268.
[17]
LIU Jiaqi, FENG Yunwen, TENG Da, et al. Operational reliability evaluation and analysis framework of civil aircraft complex system based on intelligent extremum machine learning model[J]. Reliability Engineering & System Safety, 2023, 23(35):684-686.
[18]
LI Chongfeng, SUN Ruishan, PAN Xing. Takeoff runway overrun risk assessment in aviation safety based on human pilot behavioral characteristics from real flight data[J]. Safety Science, 2023, 158(69):533-536.
[19]
TANG Ziyang, LI Zuotian, HOU Tieying. SiGra:single-cell spatial elucidation through an image-augmented graph transformer[J]. Nature Communication, 2023, 14(1):23-37.
[20]
戢晓峰, 乔新. 建成环境对行人交通事故严重程度的非线性影响[J]. 交通运输系统工程与信息, 2023, 23(1):314-323.
JI Xiaofeng, QIAO Xin. Nonlinear influence of built environment on pedestrian traffic accident severity[J]. Journal of Transportation Systems Engineering and Information Technology, 2023, 23(1):314-323.
2024年第34卷第12期
PDF下载
399
166
引用本文
BibTeX
文章信息
doi: 10.16265/j.cnki.issn1003-3033.2024.12.0145
  • 接收时间:2024-07-17
  • 首发时间:2025-07-09
  • 出版时间:2024-12-28
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2024-07-17
  • 修回日期:2024-09-20
基金
中央高校基本科研业务费自然科学重点项目(3122024053)
作者信息
    1 中国民航大学 安全科学与工程学院,天津 300300
    2 山东航空股份有限公司 飞行三大队,山东 青岛 266000
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/zgaqkxxb/CN/10.16265/j.cnki.issn1003-3033.2024.12.0145
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