Article(id=1149741818184642928, tenantId=1146029695717560320, journalId=1146031787341344770, issueId=1149741815273800564, articleNumber=1003-3033(2024)01-0116-09, orderNo=null, doi=10.16265/j.cnki.issn1003-3033.2024.01.1517, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=null, receivedDateStr=null, revisedDate=null, revisedDateStr=null, acceptedDate=null, acceptedDateStr=null, onlineDate=1752049410624, onlineDateStr=2025-07-09, pubDate=1706371200000, pubDateStr=2024-01-28, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1752049410624, onlineIssueDateStr=2025-07-09, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1752049410624, creator=13701087609, updateTime=1752049410624, updator=13701087609, issue=Issue{id=1149741815273800564, tenantId=1146029695717560320, journalId=1146031787341344770, year='2024', volume='34', issue='1', 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=1752049409931, creator=13701087609, updateTime=1756468937446, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1168278657316430156, tenantId=1146029695717560320, journalId=1146031787341344770, issueId=1149741815273800564, language=EN, specialIssueTitle=, coverIllustrator=, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1168278657316430157, tenantId=1146029695717560320, journalId=1146031787341344770, issueId=1149741815273800564, language=CN, specialIssueTitle=, coverIllustrator=, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=116, endPage=124, ext={EN=ArticleExt(id=1149741818390163827, articleId=1149741818184642928, tenantId=1146029695717560320, journalId=1146031787341344770, language=EN, title=Aircraft taxiing trajectory prediction and conflict risk identification in airfield area based on AM-LSTM, columnId=1149733269173878863, journalTitle=China Safety Science Journal, columnName=Safety engineering technology, runingTitle=null, highlight=null, articleAbstract=

In order to address the increasing risk of conflict caused by the difficulty in effectively predicting aircraft point source localization,a time series trajectory prediction model AM-LSTM based on AM and LSTM was constructed,to predict the instantaneous point source location of the aircraft in the airfield area in a short time in the future. On this basis,the contour was expanded according to the aircraft type and glide heading,the aircraft speed was used as the safety distance weight,and the ray method was used to realize the determination of the contour conflict. Urumqi Dewopu Airport was used as an example for validation,and the trained trajectory prediction model was utilized to predict aircraft taxiing trajectories in the airfield area and identified taxiing conflicts between aircraft profiles. The results show that the AM-LSTM prediction model can accurately predict the aircraft movement trajectory in the airfield area,and the average displacement error of the trajectory position prediction in the next 3 s is 1.05 m,and the accuracy of trajectory point position prediction can reach 94.37%. Therefore,it can accurately identify the risk of taxiing conflict on the basis of trajectory prediction,which is conducive to guaranteeing the safe operation of the airfield area.

, 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=Xinglong WANG, Yanfeng XU), CN=ArticleExt(id=1149741835632948116, articleId=1149741818184642928, tenantId=1146029695717560320, journalId=1146031787341344770, language=CN, title=基于AM-LSTM的飞行区航空器滑行轨迹预测与冲突识别, columnId=1149733269727526997, journalTitle=中国安全科学学报, columnName=安全工程技术, runingTitle=null, highlight=null, articleAbstract=

为解决航空器点源定位难以有效预测而引发冲突风险愈来愈多的问题,构建基于注意力机制(AM)和长短期记忆网络(LSTM)的时间序列轨迹预测模型AM-LSTM,预测未来短时间内飞行区航空器的瞬时点源位置;在此基础上,根据航空器型号和滑行航向对其进行轮廓扩展,以航空器速度作为安全距离权重,通过射线法实现轮廓冲突的判定;并以乌鲁木齐地窝堡机场为例进行验证,利用训练完成的轨迹预测模型预测飞行区航空器滑行轨迹,以识别航空器轮廓间的滑行冲突。结果表明:AM-LSTM预测模型能够准确预测飞行区航空器运动轨迹。未来3 s内轨迹位置预测的平均位移误差为1.05 m,轨迹点位置预测精准性可达94.37%,故能在轨迹预测的基础上精确识别滑行冲突风险,有利于保障飞行区的安全运行。

, correspAuthors=null, authorNote=null, correspAuthorsNote=null, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=7q/wFpoM7zLPGa1qhSL1yA==, magXml=L+S5VFGzyp6yuHU/bHU2CA==, pdfUrl=null, pdf=NPWvhtUmN2MQllnRyGxbLA==, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=/iziol0957x1uLpdsXZciA==, mapNumber=null, authorCompany=null, fund=null, authors=

王兴隆 (1979—),男,黑龙江北安人,硕士,研究员,主要从事空域运行安全、空中交通流量管理等方面的研究。E-mail:

, authorsList=王兴隆, 许晏丰)}, authors=[Author(id=1168122918824321337, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741818184642928, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=xinglong1979@163.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1168122918899818811, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741818184642928, authorId=1168122918824321337, language=EN, stringName=Xinglong WANG, firstName=Xinglong, middleName=null, lastName=WANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=Key Laboratory of Internet of Aircrafts,Civil Aviation University of China,Tianjin 300300,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1168122918958539068, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741818184642928, authorId=1168122918824321337, 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=null, address=中国民航大学 民航飞联网重点实验室,天津 300300, bio={"img":"72ukNoh4MxU6E/910qVEBw==","content":"

王兴隆 (1979—),男,黑龙江北安人,硕士,研究员,主要从事空域运行安全、空中交通流量管理等方面的研究。E-mail:

"}, bioImg=72ukNoh4MxU6E/910qVEBw==, bioContent=

王兴隆 (1979—),男,黑龙江北安人,硕士,研究员,主要从事空域运行安全、空中交通流量管理等方面的研究。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1168122918753018165, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741818184642928, xref=null, ext=[AuthorCompanyExt(id=1168122918761406774, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741818184642928, companyId=1168122918753018165, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Key Laboratory of Internet of Aircrafts,Civil Aviation University of China,Tianjin 300300,China), AuthorCompanyExt(id=1168122918765601079, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741818184642928, companyId=1168122918753018165, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=中国民航大学 民航飞联网重点实验室,天津 300300)])]), Author(id=1168122919013065022, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741818184642928, 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=1168122919084368192, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741818184642928, authorId=1168122919013065022, language=EN, stringName=Yanfeng XU, firstName=Yanfeng, middleName=null, lastName=XU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=Key Laboratory of Internet of Aircrafts,Civil Aviation University of China,Tianjin 300300,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1168122919155671361, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741818184642928, authorId=1168122919013065022, language=CN, stringName=许晏丰, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=中国民航大学 民航飞联网重点实验室,天津 300300, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1168122918753018165, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741818184642928, xref=null, ext=[AuthorCompanyExt(id=1168122918761406774, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741818184642928, companyId=1168122918753018165, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Key Laboratory of Internet of Aircrafts,Civil Aviation University of China,Tianjin 300300,China), AuthorCompanyExt(id=1168122918765601079, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741818184642928, companyId=1168122918753018165, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=中国民航大学 民航飞联网重点实验室,天津 300300)])])], keywords=[Keyword(id=1168122919327637826, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741818184642928, language=EN, orderNo=1, keyword=attention mechanism(AM)), Keyword(id=1168122919407329603, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741818184642928, language=EN, orderNo=2, keyword=long short term memory(LSTM)), Keyword(id=1168122919461855556, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741818184642928, language=EN, orderNo=3, keyword=airfield area), Keyword(id=1168122919545741637, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741818184642928, language=EN, orderNo=4, keyword=aircraft taxiing), Keyword(id=1168122919684153670, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741818184642928, language=EN, orderNo=5, keyword=taxiing trajectory), Keyword(id=1168122919864508743, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741818184642928, language=CN, orderNo=1, keyword=注意力机制(AM)), Keyword(id=1168122920103584072, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741818184642928, language=CN, orderNo=2, keyword=长短期记忆网络(LSTM)), Keyword(id=1168122920200053065, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741818184642928, language=CN, orderNo=3, keyword=飞行区), Keyword(id=1168122920250384714, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741818184642928, language=CN, orderNo=4, keyword=航空器滑行), Keyword(id=1168122920409768267, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741818184642928, language=CN, orderNo=5, keyword=滑行轨迹)], refs=[Reference(id=1168122922876019050, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741818184642928, doi=null, pmid=null, pmcid=null, year=2016, volume=null, issue=null, pageStart=1523, pageEnd=1527, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=ZHOU Zhijing, CHEN Jinliang, SHEN Beibei, journalName=2016 IEEE Advanced Information Management, Communicates, Electronic and Automation Control Conference (IMCEC), refType=null, unstructuredReference=ZHOU Zhijing, CHEN Jinliang, SHEN Beibei, et al. A trajectory prediction method based on aircraft motion model and grey theory[C]. 2016 IEEE Advanced Information Management, Communicates, Electronic and Automation Control Conference (IMCEC), 2016:1523-1527., articleTitle=A trajectory prediction method based on aircraft motion model and grey theory, refAbstract=null), Reference(id=1168122922938933611, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741818184642928, doi=null, pmid=null, pmcid=null, year=2012, volume=null, issue=null, pageStart=981, pageEnd=986, url=null, language=null, rfNumber=[2], rfOrder=1, authorNames=YUE Song, PENG Cheng, MU Chundi, journalName=International Conference on Information & Automation, refType=null, unstructuredReference=YUE Song, PENG Cheng, MU Chundi. An improved trajectory prediction algorithm based on trajectory data mining for air traffic management[C]. International Conference on Information & Automation, 2012:981-986., articleTitle=An improved trajectory prediction algorithm based on trajectory data mining for air traffic management, refAbstract=null), Reference(id=1168122923006042476, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741818184642928, doi=null, pmid=null, pmcid=null, year=2016, volume=null, issue=null, pageStart=158, pageEnd=162, url=null, language=null, rfNumber=[3], rfOrder=2, authorNames=ZHANG Caikun, ZHANG Xuan, SHI Chuan, journalName=2016 3rd International Conference on Information Science and Control Engineering (ICISCE), refType=null, unstructuredReference=ZHANG Caikun, ZHANG Xuan, SHI Chuan, et al. Aircraft trajectory prediction based on genetic programming[C]. 2016 3rd International Conference on Information Science and Control Engineering (ICISCE), 2016:158-162., articleTitle=Aircraft trajectory prediction based on genetic programming, refAbstract=null), Reference(id=1168122923077345645, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741818184642928, doi=null, pmid=null, pmcid=null, year=2016, volume=null, issue=null, pageStart=21, pageEnd=30, url=null, language=null, rfNumber=[4], rfOrder=3, authorNames=AYHAN S, SAMET H, journalName=22nd ACM SIGKDD International Conference, refType=null, unstructuredReference=AYHAN S, SAMET H. Aircraft trajectory prediction made easy with predictive analytics[C]. 22nd ACM SIGKDD International Conference, 2016:21-30., articleTitle=Aircraft trajectory prediction made easy with predictive analytics, refAbstract=null), Reference(id=1168122923140260206, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741818184642928, doi=null, pmid=null, pmcid=null, year=2022, volume=32, issue=5, pageStart=170, pageEnd=176, url=null, language=null, rfNumber=[5], rfOrder=4, authorNames=熊晓夏, 刘擎超, 沈钰杰, journalName=中国安全科学学报, refType=null, unstructuredReference=熊晓夏, 刘擎超, 沈钰杰, 等. 基于LSTM-BF的高速公路交通事故风险模型[J]. 中国安全科学学报, 2022, 32(5):170-176., articleTitle=基于LSTM-BF的高速公路交通事故风险模型, refAbstract=null), Reference(id=1168122923232534895, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741818184642928, doi=null, pmid=null, pmcid=null, year=2022, volume=32, issue=5, pageStart=170, pageEnd=176, url=null, language=null, rfNumber=[5], rfOrder=5, authorNames=XIONG Xiaoxia, LIU Qingchao, SHEN Yujie, journalName=China Safety Science Journal, refType=null, unstructuredReference=XIONG Xiaoxia, LIU Qingchao, SHEN Yujie, et al. Study on risk model of highway traffic accidents based on LSTM-BF[J]. China Safety Science Journal, 2022, 32(5):170-176., articleTitle=Study on risk model of highway traffic accidents based on LSTM-BF, refAbstract=null), Reference(id=1168122923291255152, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741818184642928, doi=null, pmid=null, pmcid=null, year=2021, volume=31, issue=9, pageStart=1, pageEnd=7, url=null, language=null, rfNumber=[6], rfOrder=6, authorNames=冯文刚, journalName=中国安全科学学报, refType=null, unstructuredReference=冯文刚. 基于深度长短记忆模型的民航安保事件分析[J]. 中国安全科学学报, 2021, 31(9):1-7., articleTitle=基于深度长短记忆模型的民航安保事件分析, refAbstract=null), Reference(id=1168122923366752625, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741818184642928, doi=null, pmid=null, pmcid=null, year=2021, volume=31, issue=9, pageStart=1, pageEnd=7, url=null, language=null, rfNumber=[6], rfOrder=7, authorNames=FENG Wen'gang, journalName=China Safety Science Journal, refType=null, unstructuredReference=FENG Wen'gang. Research on civil aviation security event analysis based on deep LSTM model[J]. China Safety Science Journal, 2021, 31(9):1-7., articleTitle=Research on civil aviation security event analysis based on deep LSTM model, refAbstract=null), Reference(id=1168122923425472882, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741818184642928, doi=null, pmid=null, pmcid=null, year=2021, volume=31, issue=7, pageStart=82, pageEnd=89, url=null, language=null, rfNumber=[7], rfOrder=8, authorNames=赵江平, 徐恒, 党悦悦, journalName=中国安全科学学报, refType=null, unstructuredReference=赵江平, 徐恒, 党悦悦. 基于改进Faster R-CNN的铁路客车螺栓检测研究[J]. 中国安全科学学报, 2021, 31(7):82-89., articleTitle=基于改进Faster R-CNN的铁路客车螺栓检测研究, refAbstract=null), Reference(id=1168122923521941875, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741818184642928, doi=null, pmid=null, pmcid=null, year=2021, volume=31, issue=7, pageStart=82, pageEnd=89, url=null, language=null, rfNumber=[7], rfOrder=9, authorNames=ZHAO Jiangping, XU Heng, DANG Yueyue, journalName=China Safety Science Journal, refType=null, unstructuredReference=ZHAO Jiangping, XU Heng, DANG Yueyue. Research on bolt detection of railway passenger cars based on improved Faster R-CNN[J]. China Safety Science Journal, 2021, 31(7):82-89., articleTitle=Research on bolt detection of railway passenger cars based on improved Faster R-CNN, refAbstract=null), Reference(id=1168122923593245044, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741818184642928, doi=null, pmid=null, pmcid=null, year=2021, volume=26, issue=1, pageStart=87, pageEnd=107, url=null, language=null, rfNumber=[8], rfOrder=10, authorNames=MAO Yao, QIN Guojin, NI Pingan, journalName=International Journal of Urban Sciences, refType=null, unstructuredReference=MAO Yao, QIN Guojin, NI Pingan, et al. Analysis of road traffic speed in Kunming plateau mountains: a fusion PSO-LSTM algorithm[J]. International Journal of Urban Sciences, 2021, 26(1):87-107., articleTitle=Analysis of road traffic speed in Kunming plateau mountains: a fusion PSO-LSTM algorithm, refAbstract=null), Reference(id=1168122923681325429, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741818184642928, doi=null, pmid=null, pmcid=null, year=2022, volume=44, issue=3, pageStart=939, pageEnd=947, url=null, language=null, rfNumber=[9], rfOrder=11, authorNames=张心宇, 刘源, 宋佳凝, journalName=系统工程与电子技术, refType=null, unstructuredReference=张心宇, 刘源, 宋佳凝. 基于LSTM神经网络的短期轨道预报[J]. 系统工程与电子技术, 2022, 44(3): 939-947., articleTitle=基于LSTM神经网络的短期轨道预报, refAbstract=null), Reference(id=1168122923761017206, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741818184642928, doi=null, pmid=null, pmcid=null, year=2022, volume=44, issue=3, pageStart=939, pageEnd=947, url=null, language=null, rfNumber=[9], rfOrder=12, authorNames=ZHANG Xinyu, LIU Yuan, SONG Jianing, journalName=Systems Engineering and Electronics, refType=null, unstructuredReference=ZHANG Xinyu, LIU Yuan, SONG Jianing. Short-term orbit prediction based on LSTM neural network[J]. Systems Engineering and Electronics, 2022, 44(3): 939-947., articleTitle=Short-term orbit prediction based on LSTM neural network, refAbstract=null), Reference(id=1168122923815543159, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741818184642928, doi=null, pmid=null, pmcid=null, year=2021, volume=50, issue=6, pageStart=147, pageEnd=152, url=null, language=null, rfNumber=[10], rfOrder=13, authorNames=于琛, 付玉慧, 张逸飞, journalName=船海工程, refType=null, unstructuredReference=于琛, 付玉慧, 张逸飞, 等. 基于ARIMA-BIGRU的船舶航迹预测[J]. 船海工程, 2021, 50(6):147-152., articleTitle=基于ARIMA-BIGRU的船舶航迹预测, refAbstract=null), Reference(id=1168122923878457720, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741818184642928, doi=null, pmid=null, pmcid=null, year=2021, volume=50, issue=6, pageStart=147, pageEnd=152, url=null, language=null, rfNumber=[10], rfOrder=14, authorNames=YU Chen, FU Yuhui, ZHANG Yifei, journalName=Ship & Ocean Engineering, refType=null, unstructuredReference=YU Chen, FU Yuhui, ZHANG Yifei, et al. The track prediction method based on ARIMA-BIGRU neural network[J]. Ship & Ocean Engineering, 2021, 50(6):147-152., articleTitle=The track prediction method based on ARIMA-BIGRU neural network, refAbstract=null), Reference(id=1168122923932983673, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741818184642928, doi=null, pmid=null, pmcid=null, year=2020, volume=8, issue=null, pageStart=668, pageEnd=134, url=null, language=null, rfNumber=[11], rfOrder=15, authorNames=MA Lan, TIAN Shan, journalName=IEEE Access, refType=null, unstructuredReference=MA Lan, TIAN Shan. A hybrid CNN-LSTM model for aircraft 4D trajectory prediction[J]. IEEE Access, 2020, 8: 134 668-134 680., articleTitle=A hybrid CNN-LSTM model for aircraft 4D trajectory prediction, refAbstract=null), Reference(id=1168122924075590010, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741818184642928, doi=null, pmid=null, pmcid=null, year=2020, volume=22, issue=11, pageStart=7242, pageEnd=7255, url=null, language=null, rfNumber=[12], rfOrder=16, authorNames=SHI Zhiyuan, XU Min, PAN Quan, journalName=IEEE Transactions on Intelligent Transportation Systems, refType=null, unstructuredReference=SHI Zhiyuan, XU Min, PAN Quan. 4-D flight trajectory prediction with constrained LSTM network[J]. IEEE Transactions on Intelligent Transportation Systems, 2020, 22(11): 7242-7255., articleTitle=4-D flight trajectory prediction with constrained LSTM network, refAbstract=null), Reference(id=1168122924159476091, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741818184642928, doi=null, pmid=null, pmcid=null, year=2020, volume=8, issue=null, pageStart=250, pageEnd=151, url=null, language=null, rfNumber=[13], rfOrder=17, authorNames=ZENG Weili, QUAN Zhibin, ZHAO Ziyu, journalName=IEEE Access, refType=null, unstructuredReference=ZENG Weili, QUAN Zhibin, ZHAO Ziyu, et al. A deep learning approach for aircraft trajectory prediction in terminal airspace[J]. IEEE Access, 2020, 8: 151 250-151 266., articleTitle=A deep learning approach for aircraft trajectory prediction in terminal airspace, refAbstract=null), Reference(id=1168122924306276732, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741818184642928, doi=null, pmid=null, pmcid=null, year=2022, volume=47, issue=1, pageStart=149, pageEnd=155, url=null, language=null, rfNumber=[14], rfOrder=18, authorNames=张卫华, 陶虎, 陈乾, journalName=公路工程, refType=null, unstructuredReference=张卫华, 陶虎, 陈乾. 城市快速路互通立交分流区交通冲突预测模型[J]. 公路工程, 2022, 47(1):149-155., articleTitle=城市快速路互通立交分流区交通冲突预测模型, refAbstract=null), Reference(id=1168122924411134333, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741818184642928, doi=null, pmid=null, pmcid=null, year=2022, volume=47, issue=1, pageStart=149, pageEnd=155, url=null, language=null, rfNumber=[14], rfOrder=19, authorNames=ZHANG Weihua, TAO Hu, CHEN Qian, journalName=Highway Engineering, refType=null, unstructuredReference=ZHANG Weihua, TAO Hu, CHEN Qian. The predicting model of traffic conflicts in diverging segments of expressway interchange[J]. Highway Engineering, 2022, 47(1):149-155., articleTitle=The predicting model of traffic conflicts in diverging segments of expressway interchange, refAbstract=null), Reference(id=1168122924528574846, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741818184642928, doi=null, pmid=null, pmcid=null, year=2019, volume=31, issue=8, pageStart=1627, pageEnd=1635, url=null, language=null, rfNumber=[15], rfOrder=20, authorNames=张思远, 李仙颖, 沈笑云, journalName=系统仿真学报, refType=null, unstructuredReference=张思远, 李仙颖, 沈笑云. 基于ADS-B IN的冲突预测与多机无冲突航迹规划[J]. 系统仿真学报, 2019, 31(8): 1627-1635., articleTitle=基于ADS-B IN的冲突预测与多机无冲突航迹规划, refAbstract=null), Reference(id=1168122924578906495, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741818184642928, doi=null, pmid=null, pmcid=null, year=2019, volume=31, issue=8, pageStart=1627, pageEnd=1635, url=null, language=null, rfNumber=[15], rfOrder=21, authorNames=ZHANG Siyuan, LI Xianying, SHEN Xiaoyun, journalName=Journal of System Simulation, refType=null, unstructuredReference=ZHANG Siyuan, LI Xianying, SHEN Xiaoyun. ADS-B in based conflict prediction and conflict-free trajectory planning for multi-aircraft[J]. Journal of System Simulation, 2019, 31(8): 1627-1635., articleTitle=ADS-B in based conflict prediction and conflict-free trajectory planning for multi-aircraft, refAbstract=null), Reference(id=1168122924662792576, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741818184642928, doi=null, pmid=null, pmcid=null, year=2012, volume=29, issue=4, pageStart=388, pageEnd=394, url=null, language=null, rfNumber=[16], rfOrder=22, authorNames=LI Shanmei, XU Xiaohao, MENG Linghang, journalName=Transactions of Nanjing University of Aeronautics & Astronautics, refType=null, unstructuredReference=LI Shanmei, XU Xiaohao, MENG Linghang. Flight conflict of recasting based on chaotic time series[J]. Transactions of Nanjing University of Aeronautics & Astronautics, 2012, 29(4):388-394., articleTitle=Flight conflict of recasting based on chaotic time series, refAbstract=null), Reference(id=1168122924729901441, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741818184642928, doi=null, pmid=null, pmcid=null, year=2020, volume=2020, issue=null, pageStart=1, pageEnd=14, url=null, language=null, rfNumber=[17], rfOrder=23, authorNames=QU Zhaowei, GAO Yuhong, SONG Xianmin, journalName=Transport, refType=null, unstructuredReference=QU Zhaowei, GAO Yuhong, SONG Xianmin, et al. Traffic conflict identification of E-BIKES at signalized intersections[J]. Transport, 2020, 2020:1-14., articleTitle=Traffic conflict identification of E-BIKES at signalized intersections, refAbstract=null), Reference(id=1168122924830564738, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741818184642928, doi=null, pmid=null, pmcid=null, year=2021, volume=11, issue=11, pageStart=1076, pageEnd=1093, url=null, language=null, rfNumber=[18], rfOrder=24, authorNames=LYU Wenying, ZHANG Honghai, WAN Junqiang, journalName=Applied Sciences-BASEL, refType=null, unstructuredReference=LYU Wenying, ZHANG Honghai, WAN Junqiang, et al. Research on safety prediction of sector traffic operation based on a long short term memory model[J]. Applied Sciences-BASEL, 2021, 11(11):1076-1093., articleTitle=Research on safety prediction of sector traffic operation based on a long short term memory model, refAbstract=null), Reference(id=1168122924901867907, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741818184642928, doi=null, pmid=null, pmcid=null, year=2021, volume=42, issue=8, pageStart=262, pageEnd=271, url=null, language=null, rfNumber=[19], rfOrder=25, authorNames=王志刚, 王业光, 杨宁, journalName=航空学报, refType=null, unstructuredReference=王志刚, 王业光, 杨宁, 等. 基于LSTM的飞行数据挖掘模型构建方法[J]. 航空学报, 2021, 42(8): 262-271., articleTitle=基于LSTM的飞行数据挖掘模型构建方法, refAbstract=null), Reference(id=1168122924956393860, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741818184642928, doi=null, pmid=null, pmcid=null, year=2021, volume=42, issue=8, pageStart=262, pageEnd=271, url=null, language=null, rfNumber=[19], rfOrder=26, authorNames=WANG Zhigang, WANG Yeguang, YANG Ning, journalName=Acta Aeronautica et Astronautica Sinica, refType=null, unstructuredReference=WANG Zhigang, WANG Yeguang, YANG Ning, et al. Construction method of flight data mining model based on LSTM[J]. Acta Aeronautica et Astronautica Sinica, 2021, 42(8): 262-271., articleTitle=Construction method of flight data mining model based on LSTM, refAbstract=null), Reference(id=1168122925015114117, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741818184642928, doi=null, pmid=null, pmcid=null, year=2021, volume=42, issue=3, pageStart=435, pageEnd=445, url=null, language=null, rfNumber=[20], rfOrder=27, authorNames=魏晓良, 潮群, 陶建峰, journalName=航空学报, refType=null, unstructuredReference=魏晓良, 潮群, 陶建峰, 等. 基于LSTM和CNN的高速柱塞泵故障诊断[J]. 航空学报, 2021, 42(3):435-445., articleTitle=基于LSTM和CNN的高速柱塞泵故障诊断, refAbstract=null), Reference(id=1168122925069640070, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741818184642928, doi=null, pmid=null, pmcid=null, year=2021, volume=42, issue=3, pageStart=435, pageEnd=445, url=null, language=null, rfNumber=[20], rfOrder=28, authorNames=WEI Xiaoliang, CHAO Qun, TAO Jianfeng, journalName=Acta Aeronautica et Astronautica Sinica, refType=null, unstructuredReference=WEI Xiaoliang, CHAO Qun, TAO Jianfeng, et al. Cavitation fault diagnosis method for high-speed plunger pumps based on LSTM and CNN[J]. Acta Aeronautica et Astronautica Sinica, 2021, 42(3): 435-445., articleTitle=Cavitation fault diagnosis method for high-speed plunger pumps based on LSTM and CNN, refAbstract=null), Reference(id=1168122925132554631, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741818184642928, doi=null, pmid=null, pmcid=null, year=2021, volume=50, issue=6, pageStart=141, pageEnd=146, url=null, language=null, rfNumber=[21], rfOrder=29, authorNames=吴春鹏, 冯姣, journalName=船海工程, refType=null, unstructuredReference=吴春鹏, 冯姣. 结合AMS的C-LSTM船舶轨迹预测[J]. 船海工程, 2021, 50(6):141-146,152., articleTitle=结合AMS的C-LSTM船舶轨迹预测, refAbstract=null), Reference(id=1168122925212246408, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741818184642928, doi=null, pmid=null, pmcid=null, year=2021, volume=50, issue=6, pageStart=141, pageEnd=146, url=null, language=null, rfNumber=[21], rfOrder=30, authorNames=WU Chunpeng, FENG Jiao, journalName=Ship & Ocean Engineering, refType=null, unstructuredReference=WU Chunpeng, FENG Jiao. Ship trajectory prediction based on C-LSTM combined with AMS[J]. Ship & Ocean Engineering, 2021, 50(6):141-146,152., articleTitle=Ship trajectory prediction based on C-LSTM combined with AMS, refAbstract=null), Reference(id=1168122925329686921, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741818184642928, doi=null, pmid=null, pmcid=null, year=2019, volume=32, issue=6, pageStart=105, pageEnd=113, url=null, language=null, rfNumber=[22], rfOrder=31, authorNames=吴明先, 许甜, 刘建蓓, journalName=中国公路学报, refType=null, unstructuredReference=吴明先, 许甜, 刘建蓓, 等. 基于高频高精度定位信息的车辆轮廓冲突瞬时预测方法[J]. 中国公路学报, 2019, 32(6):105-113., articleTitle=基于高频高精度定位信息的车辆轮廓冲突瞬时预测方法, refAbstract=null), Reference(id=1168122925396795786, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741818184642928, doi=null, pmid=null, pmcid=null, year=2019, volume=32, issue=6, pageStart=105, pageEnd=113, url=null, language=null, rfNumber=[22], rfOrder=32, authorNames=WU Mingxian, XU Tian, LIU Jianbei, journalName=China Journal of Highway and Transport, refType=null, unstructuredReference=WU Mingxian, XU Tian, LIU Jianbei, et al. Instantaneous prediction of vehicle outline conflict using high-frequency and high-precision position information[J]. China Journal of Highway and Transport, 2019, 32(6): 105-113., articleTitle=Instantaneous prediction of vehicle outline conflict using high-frequency and high-precision position information, refAbstract=null)], funds=[Fund(id=1168122922565640550, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741818184642928, awardId=U2133207, language=CN, fundingSource=国家自然科学基金资助(U2133207), fundOrder=null, country=null), Fund(id=1168122922620166503, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741818184642928, awardId=62173332, language=CN, fundingSource=国家自然科学基金资助(62173332), fundOrder=null, country=null), Fund(id=1168122922678886760, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741818184642928, awardId=3122019191, language=CN, fundingSource=中央高校基金重点项目(3122019191), fundOrder=null, country=null), Fund(id=1168122922733412713, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741818184642928, awardId=21JCYBJC00700, language=CN, fundingSource=天津市科技计划项目(21JCYBJC00700), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1168122918753018165, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741818184642928, xref=null, ext=[AuthorCompanyExt(id=1168122918761406774, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741818184642928, companyId=1168122918753018165, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Key Laboratory of Internet of Aircrafts,Civil Aviation University of China,Tianjin 300300,China), AuthorCompanyExt(id=1168122918765601079, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741818184642928, companyId=1168122918753018165, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=中国民航大学 民航飞联网重点实验室,天津 300300)])], figs=[ArticleFig(id=1168122920732729676, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741818184642928, language=EN, label=Fig.1, caption=Overall architecture of AM-LSTM model, figureFileSmall=hoI1oDX9KLUkWBGdDvxliw==, figureFileBig=E3GB3eIiw4ZbUo0v0FCKiQ==, tableContent=null), ArticleFig(id=1168122920795644237, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741818184642928, language=CN, label=图1, caption=AM-LSTM模型整体架构, figureFileSmall=hoI1oDX9KLUkWBGdDvxliw==, figureFileBig=E3GB3eIiw4ZbUo0v0FCKiQ==, tableContent=null), ArticleFig(id=1168122920858558798, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741818184642928, language=EN, label=Fig.2, caption=Target local coordinate system, figureFileSmall=aqBIglx+5OQppyg4/wUsdg==, figureFileBig=hbGOBkjkpGqS9C7GWMZPpQ==, tableContent=null), ArticleFig(id=1168122920942444879, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741818184642928, language=CN, label=图2, caption=目标局部坐标系, figureFileSmall=aqBIglx+5OQppyg4/wUsdg==, figureFileBig=hbGOBkjkpGqS9C7GWMZPpQ==, tableContent=null), ArticleFig(id=1168122921001165136, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741818184642928, language=EN, label=Fig.3, caption=Apron conflict determination, figureFileSmall=unmPJK4c1bXYlDyfMvh1lQ==, figureFileBig=nwizwq/7pJD/CWUF6wMf3A==, tableContent=null), ArticleFig(id=1168122921068274001, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741818184642928, language=CN, label=图3, caption=航空器间冲突判定, figureFileSmall=unmPJK4c1bXYlDyfMvh1lQ==, figureFileBig=nwizwq/7pJD/CWUF6wMf3A==, tableContent=null), ArticleFig(id=1168122921131188562, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741818184642928, language=EN, label=Fig.4, caption=Configuration diagram of taxiway of Diwopu airport, figureFileSmall=5eRdphlpm7ewTFfzj8slbg==, figureFileBig=N7YYV8Jpua8fkFGFtawDYg==, tableContent=null), ArticleFig(id=1168122921189908819, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741818184642928, language=CN, label=图4, caption=地窝堡机场滑行道构型, figureFileSmall=5eRdphlpm7ewTFfzj8slbg==, figureFileBig=N7YYV8Jpua8fkFGFtawDYg==, tableContent=null), ArticleFig(id=1168122921244434772, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741818184642928, language=EN, label=Fig.5, caption=Comparison of trajectory prediction results, figureFileSmall=41xAxqdYMcDavIXQn+dWJg==, figureFileBig=TckfH8rSiAWUcpVp9miXDw==, tableContent=null), ArticleFig(id=1168122921324126549, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741818184642928, language=CN, label=图5, caption=轨迹预测结果对比, figureFileSmall=41xAxqdYMcDavIXQn+dWJg==, figureFileBig=TckfH8rSiAWUcpVp9miXDw==, tableContent=null), ArticleFig(id=1168122921374458198, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741818184642928, language=EN, label=Fig.6, caption=Loss function when learning rate is 0.001, figureFileSmall=wJuDncAtY7FQwc7fC0gixg==, figureFileBig=9nfu23CCKo+CAbHm6qS0Vg==, tableContent=null), ArticleFig(id=1168122921441567063, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741818184642928, language=CN, label=图6, caption=学习率取0.001时的损失函数, figureFileSmall=wJuDncAtY7FQwc7fC0gixg==, figureFileBig=9nfu23CCKo+CAbHm6qS0Vg==, tableContent=null), ArticleFig(id=1168122921500287320, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741818184642928, language=EN, label=Fig.7, caption=Trajectory prediction results after parameter adjustment, figureFileSmall=5luY2gDWtBv+10l0qnboyw==, figureFileBig=V9g4sWzhjtqVdRjZ9e/IHg==, tableContent=null), ArticleFig(id=1168122921554813273, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741818184642928, language=CN, label=图7, caption=调参后轨迹预测结果, figureFileSmall=5luY2gDWtBv+10l0qnboyw==, figureFileBig=V9g4sWzhjtqVdRjZ9e/IHg==, tableContent=null), ArticleFig(id=1168122921630310746, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741818184642928, language=EN, label=Tab.1, caption=

Data of flight CSN6883 operation

, figureFileSmall=null, figureFileBig=null, tableContent=
数据时间 航向/(°) 速度/(m·s-1) 经度/(°) 纬度/(°) 地点
10:47:00 344 7 43.902 879 8 87.479 057 2 A102_3
10:47:01 344 7 43.902 911 87.479 044 8 A102_3
10:47:02 344 7 43.902 942 1 87.479 032 3 A102_3
11:06:27 254 141 43.911 533 6 87.494 969 6 RW26L
11:06:30 254 141 43.908 444 8 87.480 043 2 uncontrolled
), ArticleFig(id=1168122921697419611, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741818184642928, language=CN, label=表1, caption=

航班CSN6883运行数据

, figureFileSmall=null, figureFileBig=null, tableContent=
数据时间 航向/(°) 速度/(m·s-1) 经度/(°) 纬度/(°) 地点
10:47:00 344 7 43.902 879 8 87.479 057 2 A102_3
10:47:01 344 7 43.902 911 87.479 044 8 A102_3
10:47:02 344 7 43.902 942 1 87.479 032 3 A102_3
11:06:27 254 141 43.911 533 6 87.494 969 6 RW26L
11:06:30 254 141 43.908 444 8 87.480 043 2 uncontrolled
), ArticleFig(id=1168122921777111388, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741818184642928, language=EN, label=Tab.2, caption=

Optimization process of parameters

, figureFileSmall=null, figureFileBig=null, tableContent=
批量
大小
神经元=20 神经元=30 神经元=40
损失率 准确率 损失率 准确率 损失率 准确率
80 0.14 0.89 0.08 0.92 0.08 0.91
120 0.06 0.91 0.03 0.94 0.04 0.93
160 0.09 0.88 0.06 0.91 0.06 0.92
), ArticleFig(id=1168122921831637341, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741818184642928, language=CN, label=表2, caption=

参数优化过程

, figureFileSmall=null, figureFileBig=null, tableContent=
批量
大小
神经元=20 神经元=30 神经元=40
损失率 准确率 损失率 准确率 损失率 准确率
80 0.14 0.89 0.08 0.92 0.08 0.91
120 0.06 0.91 0.03 0.94 0.04 0.93
160 0.09 0.88 0.06 0.91 0.06 0.92
), ArticleFig(id=1168122921898746206, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741818184642928, language=EN, label=Tab.3, caption=

Influence of different prediction steps on prediction results

, figureFileSmall=null, figureFileBig=null, tableContent=
预测步长 时间步长 预测精度/% ADE/m FDE/m
3 9 94.37 1.05 1.71
4 12 92.81 1.17 1.94
5 15 89.39 1.31 2.05
6 18 86.83 1.38 2.13
), ArticleFig(id=1168122921991020895, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741818184642928, language=CN, label=表3, caption=

不同预测步长对预测结果影响

, figureFileSmall=null, figureFileBig=null, tableContent=
预测步长 时间步长 预测精度/% ADE/m FDE/m
3 9 94.37 1.05 1.71
4 12 92.81 1.17 1.94
5 15 89.39 1.31 2.05
6 18 86.83 1.38 2.13
), ArticleFig(id=1168122922053935456, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741818184642928, language=EN, label=Tab.4, caption=

Flight CSN6883 contour vertex

, figureFileSmall=null, figureFileBig=null, tableContent=
时间 (a1b1) (a2b2) (a3b3) (a4b4)
10:27:00 (43.914 643,87.455 138) (43.880 229,87.465 006) (43.891 117,87.502 976) (43.925 530,87.493 108)
10:27:01 (43.914 674,87.455 126) (43.880 260,87.464 994) (43.891 148,87.502 964) (43.925 561,87.493 096)
10:27:02 (43.914 705,87.455 113) (43.880 292,87.464 981) (43.891 179,87.502 951) (43.925 593,87.493 083)
11:06:30 (43.884 526,87.468 280) (43.894 394,87.502 694) (43.932 364,87.491 806) (43.922 496,87.457 393)
), ArticleFig(id=1168122922129432929, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741818184642928, language=CN, label=表4, caption=

航班CSN6883轮廓顶点

, figureFileSmall=null, figureFileBig=null, tableContent=
时间 (a1b1) (a2b2) (a3b3) (a4b4)
10:27:00 (43.914 643,87.455 138) (43.880 229,87.465 006) (43.891 117,87.502 976) (43.925 530,87.493 108)
10:27:01 (43.914 674,87.455 126) (43.880 260,87.464 994) (43.891 148,87.502 964) (43.925 561,87.493 096)
10:27:02 (43.914 705,87.455 113) (43.880 292,87.464 981) (43.891 179,87.502 951) (43.925 593,87.493 083)
11:06:30 (43.884 526,87.468 280) (43.894 394,87.502 694) (43.932 364,87.491 806) (43.922 496,87.457 393)
), ArticleFig(id=1168122922200736098, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741818184642928, language=EN, label=Tab.5, caption=

Flight CSN6883 conflict risk prediction

, figureFileSmall=null, figureFileBig=null, tableContent=
冲突航班 冲突时间 冲突地点 2机关系
CSN6645 10:48:57 TB_16_2 turning
CSN6645 10:51:08 TB_21_2 same
CSN6645 10:53:46 TB_21_2 same
GCR7591 10:56:04 TB_24_2 turning
CHB6357 10:51:01 TB_21_2 turning
CHB6357 10:51:38 TB_21_2 same
CHB6357 10:51:51 TB_22 same
CHB6357 10:53:43 TB_23 same
CHB6357 10:53:51 TB_24_2 same
CHB6357 10:55:39 TB_25 same
CHB6357 10:55:47 TB_D1_1 same
CHB6421 10:59:58 TD1_10_1 turning
CHB6421 11:02:13 TD1_10 opposite
), ArticleFig(id=1168122922263650659, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741818184642928, language=CN, label=表5, caption=

航班CSN6883冲突风险识别

, figureFileSmall=null, figureFileBig=null, tableContent=
冲突航班 冲突时间 冲突地点 2机关系
CSN6645 10:48:57 TB_16_2 turning
CSN6645 10:51:08 TB_21_2 same
CSN6645 10:53:46 TB_21_2 same
GCR7591 10:56:04 TB_24_2 turning
CHB6357 10:51:01 TB_21_2 turning
CHB6357 10:51:38 TB_21_2 same
CHB6357 10:51:51 TB_22 same
CHB6357 10:53:43 TB_23 same
CHB6357 10:53:51 TB_24_2 same
CHB6357 10:55:39 TB_25 same
CHB6357 10:55:47 TB_D1_1 same
CHB6421 10:59:58 TD1_10_1 turning
CHB6421 11:02:13 TD1_10 opposite
), ArticleFig(id=1168122922330759524, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741818184642928, language=EN, label=Tab.6, caption=

Actual conflict risk of flight CSN6883

, figureFileSmall=null, figureFileBig=null, tableContent=
冲突航班 冲突时间 冲突地点 2机关系
CSN6645 10:48:57 TB_16_2 turning
CSN6645 10:51:46 TB_21_2 same
GCR7591 10:56:04 TB_24_2 turning
CHB6357 10:51:01 TB_21_2 turning
CHB6357 10:51:51 TB_22 same
CHB6357 10:53:51 TB_24_2 same
CHB6357 10:55:47 TB_D1_1 same
CHB6421 10:59:58 TD1_10_1 turning
CHB6421 11:02:13 TD1_10 opposite
), ArticleFig(id=1168122922406256997, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149741818184642928, language=CN, label=表6, caption=

航班CSN6883实际冲突风险

, figureFileSmall=null, figureFileBig=null, tableContent=
冲突航班 冲突时间 冲突地点 2机关系
CSN6645 10:48:57 TB_16_2 turning
CSN6645 10:51:46 TB_21_2 same
GCR7591 10:56:04 TB_24_2 turning
CHB6357 10:51:01 TB_21_2 turning
CHB6357 10:51:51 TB_22 same
CHB6357 10:53:51 TB_24_2 same
CHB6357 10:55:47 TB_D1_1 same
CHB6421 10:59:58 TD1_10_1 turning
CHB6421 11:02:13 TD1_10 opposite
)], 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.issn1003-3033.2024.01.1517, detailUrlEn=https://castjournals.cast.org.cn/joweb/zgaqkxxb/EN/10.16265/j.cnki.issn1003-3033.2024.01.1517, pdfUrlCn=https://castjournals.cast.org.cn/joweb/zgaqkxxb/CN/PDF/10.16265/j.cnki.issn1003-3033.2024.01.1517, pdfUrlEn=https://castjournals.cast.org.cn/joweb/zgaqkxxb/EN/PDF/10.16265/j.cnki.issn1003-3033.2024.01.1517, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于AM-LSTM的飞行区航空器滑行轨迹预测与冲突识别
收藏切换
PDF下载
王兴隆 , 许晏丰
中国安全科学学报 | 安全工程技术 2024,34(1): 116-124
收起
收藏切换
中国安全科学学报 | 安全工程技术 2024, 34(1): 116-124
基于AM-LSTM的飞行区航空器滑行轨迹预测与冲突识别
全屏
王兴隆 , 许晏丰
作者信息
  • 中国民航大学 民航飞联网重点实验室,天津 300300
  • 王兴隆 (1979—),男,黑龙江北安人,硕士,研究员,主要从事空域运行安全、空中交通流量管理等方面的研究。E-mail:

Aircraft taxiing trajectory prediction and conflict risk identification in airfield area based on AM-LSTM
Xinglong WANG , Yanfeng XU
Affiliations
  • Key Laboratory of Internet of Aircrafts,Civil Aviation University of China,Tianjin 300300,China
出版时间: 2024-01-28 doi: 10.16265/j.cnki.issn1003-3033.2024.01.1517
文章导航
收藏切换

为解决航空器点源定位难以有效预测而引发冲突风险愈来愈多的问题,构建基于注意力机制(AM)和长短期记忆网络(LSTM)的时间序列轨迹预测模型AM-LSTM,预测未来短时间内飞行区航空器的瞬时点源位置;在此基础上,根据航空器型号和滑行航向对其进行轮廓扩展,以航空器速度作为安全距离权重,通过射线法实现轮廓冲突的判定;并以乌鲁木齐地窝堡机场为例进行验证,利用训练完成的轨迹预测模型预测飞行区航空器滑行轨迹,以识别航空器轮廓间的滑行冲突。结果表明:AM-LSTM预测模型能够准确预测飞行区航空器运动轨迹。未来3 s内轨迹位置预测的平均位移误差为1.05 m,轨迹点位置预测精准性可达94.37%,故能在轨迹预测的基础上精确识别滑行冲突风险,有利于保障飞行区的安全运行。

注意力机制(AM)  /  长短期记忆网络(LSTM)  /  飞行区  /  航空器滑行  /  滑行轨迹

In order to address the increasing risk of conflict caused by the difficulty in effectively predicting aircraft point source localization,a time series trajectory prediction model AM-LSTM based on AM and LSTM was constructed,to predict the instantaneous point source location of the aircraft in the airfield area in a short time in the future. On this basis,the contour was expanded according to the aircraft type and glide heading,the aircraft speed was used as the safety distance weight,and the ray method was used to realize the determination of the contour conflict. Urumqi Dewopu Airport was used as an example for validation,and the trained trajectory prediction model was utilized to predict aircraft taxiing trajectories in the airfield area and identified taxiing conflicts between aircraft profiles. The results show that the AM-LSTM prediction model can accurately predict the aircraft movement trajectory in the airfield area,and the average displacement error of the trajectory position prediction in the next 3 s is 1.05 m,and the accuracy of trajectory point position prediction can reach 94.37%. Therefore,it can accurately identify the risk of taxiing conflict on the basis of trajectory prediction,which is conducive to guaranteeing the safe operation of the airfield area.

attention mechanism(AM)  /  long short term memory(LSTM)  /  airfield area  /  aircraft taxiing  /  taxiing trajectory
王兴隆, 许晏丰. 基于AM-LSTM的飞行区航空器滑行轨迹预测与冲突识别. 中国安全科学学报, 2024 , 34 (1) : 116 -124 . DOI: 10.16265/j.cnki.issn1003-3033.2024.01.1517
Xinglong WANG, Yanfeng XU. Aircraft taxiing trajectory prediction and conflict risk identification in airfield area based on AM-LSTM[J]. China Safety Science Journal, 2024 , 34 (1) : 116 -124 . DOI: 10.16265/j.cnki.issn1003-3033.2024.01.1517
近年来,我国民用机场飞行区内运行的航空器数量及相匹配的保障设备快速增多,导致航空器滑行冲突风险日益增加。但是现使用的场面监视系统,如广播式自动相关监视系统或多点定位系统(Mulilateration,MLAT)等,存在着数据跳变或质点漂移等问题,且都是点源监视,难以体现飞机的翼展、机长等关键信息。而在点源定位的基础上构建航空器轮廓,可以更加精准地判断滑行冲突,提高机场飞行区的运行安全。
精准预测活动目标轨迹是现代智能交通系统中防止交通堵塞和冲突的重要手段之一。ZHOU Zhijing等[1]提出一种基于飞机运动模型和灰色理论的航迹预测方法,实现了实时在线轨迹预测;YUE Song等[2]在典型轨迹的基础上,提出一种改进的轨迹预测算法,将标称轨迹代替飞行计划路径进行传播,提高了航迹预测的精准度;ZHANG Caikun等[3]提出基于遗传规划的飞机轨迹预测方法,用来求解复杂的轨迹拟合函数,提高了传统轨迹预测方法精度不足的问题;AYHAN等[4]利用机器学习技术从历史数据中训练推理模型,在考虑环境不确定性的情况下提出一种新的空中交通管理下飞机随机轨迹预测方法。其中,循环神经网络(Recurrent Neural Network,RNN)和长短期记忆网络(Long Short Term Memory,LSTM)以序列数据处理的能力和性能出色[5-7],已经在公路交通[8]、卫星运行[9]和水路运输[10]等方面实现了应用。在航空应用方面,MA Lan等[11]提出一种将卷积神经网络(Convolutional Neural Networks,CNN)和LSTM相结合的4D轨迹预测混合结构,实现了4D轨迹的高精度预测;SHI Zhiyuan等[12]提出一种适用于飞行轨迹预测的约束长时间记忆网络,根据飞机的动态特性,提出不同的约束条件,有助于保持轨迹的连续精准预测;ZENG Weili等[13]将4D轨迹预测问题转化为序列对序列学习问题,提出一种用于轨迹预测的序列对序列深长短时记忆网络。在冲突预测方面,张卫华等[14]选取碰撞时间和模式利用训练模型作为判定追尾冲突和换道冲突的标准,进行冲突预测;张思远等[15]针对自由飞行中复杂的多机冲突场景,通过将冲突区域网格化,根据冲突危险系数并结合遗传算法规划出全局最优的无冲突航迹;李善梅等[16]研究了飞行冲突的混沌问题,利用混沌预测方法预测模拟数据,并通过灰色误差检验方法评价冲突预测结果;QU Zhaowei等[17]提出一种多变量冲突指标,并建立了一种向同一方向移动的电动自行车的冲突识别方法;LU Wenying等[18]旨在通过开发飞行冲突预测模型来提高途中飞行的安全性,通过历史数据进行飞行冲突识别。
综合现有研究文献,对于活动目标轨迹预测的研究仍有如下问题:①对于飞行区航空器的滑行预测不同于航路轨迹预测,需要考虑滑行道对于航空器运行的约束;②对航空器冲突预测研究主要是将航空器视作质点,较少利用到飞行计划和飞机型号数据来体现航空器轮廓。鉴于此,笔者拟引入LSTM算法来优化航空器滑行轨迹预测模型,通过对航空器质点构建轮廓,识别航空器的滑行冲突风险,以期提高飞行区运行安全。
LSTM是一种改进过的时间算法[19],是为解决一般RNN存在的长期依赖问题而专门设计出来的[20],因此,适合进行时间序列上的轨迹预测问题。但未来轨迹不仅仅取决于运动目标本身,也受到其他目标以及静态环境的极大影响,在飞行区中滑行道极大地约束着航空器的运行。故为体现滑行道对航空器运行态势的影响,引入注意力机制(Attention Mechanism,AM),构建滑行轨迹预测模型,以便精确预测航空器滑行轨迹。
LSTM是由MLAT数据中获取航空器运动轨迹MM={m1m2,…,mi},其中,mi为目标轨迹点,包含时间、经纬度、速度、航向等信息。设 m i j表示第i个轨迹点的第j种属性。拟采用时间间隔Δt对运动轨迹数据进行采样。
输入样本xt-k~t时刻的活动目标运动轨迹点,含有属性j,即( m t j - k m t j - k + 1,…, m t j)。输出预测值y根据预测步长m,通过作递归处理,预测出t+m时刻的轨迹点 m t j + m
AM用于计算航空器每一次改变滑行道与当前位置的相关性,从而构建当前时刻的前后特征向量。AM的加入弥补了LSTM无法处理过长序列的缺陷,也体现了滑行道对航空器运动的约束。
AM-LSTM预测模型的总体架构如图1所示。该系统由轨迹编码器、滑行道编码器、滑行道选择Attention模块和生成未来轨迹的轨迹解码器4个主要模块组成。输入数据是1组轨迹数据和滑行道构型相关数据。
1) 轨迹编码器。轨迹数据集将被输入轨迹编码器,为每个运动航空器提取特征。使用标准的LSTM对航空器的运动进行编码。由于航空器的位置、速度和航向对于预测都很重要,因此,在该体系结构中,轨迹编码器由3个LSTM组成。分别对位置历史、速度历史和航向历史编码,再将3个提取的特征拼接为航空器运动特征,作为输出。如下式:
f T R i = g 1 ( χ i ) | | g 2 ( ν i ) | | g 3 ( α i )
式中:fTRi为输出的运动特征;χiνiαi分别为第i航空器的位置、速度和航向序列;| |为特征拼接。
2) 滑行道选择。对于每个航空器轨迹,使用一个注意力机制模块来预测它的未来滑行道选择,以图1为例,即为判断该航空器为直行或右转。
以历史滑行数据为训练集,获取不同滑行道被选择的相关历史概率,并以此概率作为注意力权重分配标准,特殊训练Attention模块,输出将经过Softmax层以获得每个滑行道的特征权重,该权重将用于后续路径特征计算。
通过AM获得的特征权重和运动特征,计算出每个滑行道的路径特征,如下式:
l n = e x p ( ( W T t f T R i ) · ( W T l f l n ) ) j = 1 n e x p ( ( W T t f T R i ) T · ( W T l f l j ) )
式中:ln为第n条滑行道的路径特征;Wt为当前航迹对应滑行道特征权重;Wl为所选第n条滑行道的特征权重。
根据计算的路径特征,最终得到一条最可能的轨迹。
3) 解码器。解码器网络的结构也是一个标准的LSTM网络,其输入包括目标航空器的轨迹特征和滑行道选择的路径特征,用于最终预测航空器轨迹,输出一条预测轨迹。
在模型构建的基础上,通过以下4个步骤实现对模型的训练:
步骤1:数据选择与处理。选取MLAT数据作为试验数据,数据信息同时包含目标编号、位置(经度、纬度)、速度、航向和监视时间等基本属性,也将根据这些基本属性实现对航空器场面运行轨迹的预测。
但由于系统误差、信号遮挡等原因,MLAT数据存在重复、跳变等问题,从而对模型训练造成不同情况的影响,故需先预处理数据。数据预处理主要包括数据误差检测、数据归一化、划分数据集等。实现异常数据剔除、丢失数据线性补充和绝对值小的数据不被大数据“吃掉”[21]的目标。
步骤2:模型参数的初始化。包括确定LSTM的序列长度、网络层的数量、每层中的神经元的数量,每个批次的样本量、最大历元数和初始学习率等。除这些参数外,在区间[0,1]中随机选择初始化模型权重。
步骤3:更新训练集权重。在每个历元期间,从训练数据集中随机选择指定数量的轨迹,并根据输入序列和预测序列的长度划分这些轨迹。再通过输出来计算损失函数。如果丢失函数已达到最大历元数,则转至步骤4,否则,通过梯度下降法调整权重。
步骤4:验证集验证。将验证集输入到训练集的学习模型中。如果估计输出与实际输出之间的误差在预期范围内,则输出最优预测模型;否则,重复步骤2—步骤4的过程,直到满足停止标准。
对AM-LSTM模型的相应参数设置如下:由于要求时间间隔相等,结合轨迹预测意义和数据质量,确定时间间隔为1s;数据80%作为训练集,20%作测试集;初始dropout=0.5,防止随机梯度下降过程中过拟合;优化器设定为Adam。其余相关参数在实例验证中结合试验情况确定。
基于MLAT获取的目标定位信息实质上是定位点源的位置信息,但为更加准确识别滑行冲突条件,需将点源定位信息扩展为目标轮廓定位信息。因此,将利用机场飞行计划信息,在预测航空器瞬时点源位置的基础上,将定位点与飞行计划相结合,扩展航空器轮廓,实现对滑行冲突的识别。
因为航空器的安全运行需要一定的安全阈度,故以一个标准凸多边形为外轮廓完全可以满足航空器的滑行安全需求,若是精确到航空器的具体轮廓,在增加定位难度的情况下反而降低航空器的安全阈度。故将航空器轮廓假设为带有长宽特征的矩形,其轮廓尺寸数据由航班型号获得。
对航空器建立以定位点位置为原点的局部坐标系,其中,航空器以机身轴向为X轴,以机翼轴向为Y轴;保障车辆以平面投影左右对称方向为X轴。建立的局部坐标系如图2所示。图2中,FBLR分别为原点与目标前、后、左、右轮廓的垂直距离,均为已知参数。
该顶点计算是二维平面的旋转平移,且在二维平面的旋转本质是绕自身坐标原点进行的旋转,X轴方向上的旋转必然会带动Y轴方向上的旋转,因此,不会产生万向节死锁情况,故直接采用旋转平移公式[22]即可得到目标外轮廓在局部坐标系下的坐标。
飞行区活动目标间的冲突风险多发生在航空器与航空器之间,车辆与车辆之间,航空器与车辆之间。但是,车辆间冲突并不太影响飞行区运行效率,车辆运行于车行道,而航空器则在航行道运动,故冲突极少。因此,文中主要研究航空器间的冲突识别,这也是对飞行区安全和运行效率影响最大的冲突情况。
一般情况,滑行规定为航空器滑行速度不超过50km/h;2机距离≥50m。当2滑行中的航空器间距离<50m时,则视为具有滑行冲突风险。基于滑行冲突风险的规定和定义,以滑行速度为权重,建立航空器外轮廓的安全区域。
航空器间冲突风险判断如图3所示。图3中,虚线范围内即为航空器的安全区域,安全区域范围的确认由滑行速度加权得出,根据滑行规定,采用滑行速度每增加10km/h,安全区域轮廓距离航空器外轮廓增加5m的标准。若2航空器的安全区域有所重合,则说明存在滑行冲突风险;若航空器外轮廓重合,则说明存在滑行冲突。出现上述2种情况,需要立即管控滑行航空器。
采用射线法判断是否存在冲突风险,该方法常用水平扫描线法或垂直线法判断某点是否在特定区域内。与其他检测方法相比,该方法准确、简单、适应性强。具体为遍历判断目标航空器(即航空器B)轮廓的4个顶点,判断其轮廓与基准目标航空器(即航空器A)轮廓的位置关系。如果交点数为奇数,说明判断航空器轮廓点在基准航空器轮廓内部,则识别为存在冲突风险;如果交点数为偶数,说明判断航空器轮廓点在基准航空器轮廓外部,则识别为冲突不存在冲突风险。
图3中垂直射线为例,判定冲突风险方法具体步骤为:
1) 判断目标航空器(即航空器B)安全区域一个顶点横纵坐标是否均小于航空器A安全区域 4个顶点最小值或大于最大值,若是,则判断滑行冲突风险不发生;否则进入第2步。
2) 判断航空器B的安全区域轮廓点是否与航空器A安全区域顶点重复,重复则判断滑行冲突风险存在;不重复进入第3步。
3) 若航空器B的安全区域轮廓点横坐标位于
航空器A的安全区域轮廓任一边横坐标范围内,则计算垂直射线与轮廓边交点的纵坐标。
y = b + b i + 1 - b i a i + 1 - a i ( x 0 - a i )
其中,i=1~4;a5=a1;b5=b1。若y∈[min(bibi+1),max(bibi+1)],则存在1个交点,否则无交点。
4) 判断交点个数,若为奇数,则存在滑行冲突风险;若为偶数,则不存在滑行冲突风险。
在判断出具有滑行冲突风险的情况下,还需要根据飞行计划数据,进一步判定冲突风险,因为在有些情况下,即便2航空器距离较近,也并不会产生冲突,如2较近滑行道的平行滑行、背向滑行等情况。因此,需要根据飞行情报中的航空器目标时刻所在地点和MLAT数据中的航向信息,再次判定冲突风险。
选取2021年5月4日乌鲁木齐地窝堡机场的飞行区高峰时段MLAT监控数据作为实例验证数据。其涉及航班数据801503条,实例验证以CSN6883为例,进行航迹预测及冲突识别验证,进行数据处理后,其航班时刻运行数据见表1
此外,AM模块需要使用到滑行道构型数据,地窝堡机场的现行滑行道构型如图4所示。该机场北侧2条跑道为改扩建工程,暂未使用,故根据地窝堡机场南侧的滑行道构型和跑道布局。同时,结合地窝堡机场的地面滑行规则,可以得出,地窝堡机场的相关滑行路径在得出滑行路径的情况下,可以基于AM模块对滑行道的选择作出预测。
对比AM-LSTM和标准LSTM,2种模型的轨迹预测结果与真实轨迹的比较情况散点如图5所示。
图5可知:标准LSTM模型因为模型结构较简单,所以虽然在直线时预测精准,但在转向处难以保证预测准确性。甚至在训练量较少的前期,在转弯处一度出现难以预测的情况。而增加AM模块的AM-LSTM预测模型,很好地弥补了这一不足,无论在直行还是转向阶段,都有很好的预测表现。即使在滑行后期,在长期预测时精度稍有下降,但是,可以通过调整参数和增加迭代次数实现优化,提高模型预测精度。
AM-LSTM模型的参数设置主要为优化模型中LSTM的参数,采用网格搜索法对比选取模型中的关键参数包括神经元数量、批量大小和学习速率。参数优化过程见表2
表2的损失率和准确率可确定,LSTM模型最终的参数取值为批量大小为120,每层的神经元数量为30。因为当批量大小和神经元数量继续增加时,模型计算结果并无明显提升。
最后,还需确认学习率大小,当学习速率取为0.01时,迭代结果虽快速收敛,但难以稳定,故表示学习率取值过大。而当学习速率取为0.000 1时,损失率并无可观降低,但计算速度大幅变慢,浪费机器算力。
当学习速率取为0.001时,迭代结果较好,计算速度较快,如图6所示。综上,文中选取学习速率为0.001。
调整参数后,用最优的关键参数重新计算,最终得出航空器滑行轨迹预测结果,轨迹对比结果如图7 所示。
经调参后的预测结果明显更加优秀,但为进行量化说明,引入平均位移误差(Average Displacement Error,ADE)和最终位移误差(Final Displacement Error,FDE)来计算预测结果的准确性,如下式:
$\mathrm{ADE}=\frac{1}{T} \sum_{t=t_{0}}^{t_{h}}\left\|\hat{Y}_{t}-Y_{t}\right\|$
$\mathrm{FDE}=\left\|\hat{Y}_{t}-Y_{t}\right\|$
式中 Y ^ t为预测目标时间t时的预测位置。不同步长设置的预测结果见表3
表3可以看出,当选取时间步长为9,预测步长为3,即每9s的轨迹预测后3s的轨迹,对轨迹预测的精度最高,能够达到94.37%,进行预测所产生的ADE为1.05m,而FDE为1.71m。考虑到即使以50km/h的最快限定速度滑行,3s的时间单个航空器有将近40m的预测运动距离,2航空器间隔都会大于安全间隔标准,即便操作人员有反应时间,也能够实现冲突解脱。再短时间的预测步长或许可以提高预测精度,但是在时间上难以保证能够实现冲突解脱。
随着预测步长的增加,预测精度开始下降,这是可以预期的。同时,过长时间的预测信息会给管制员及机长带来更多工作负荷,反而不利于飞行区的安全运行。综上,最终确定时间步长为9,预测步长为3。
在精准预测航空器位置的前提下,实现对CSN6883航班的轮廓确定,该航班所使用飞机型号为B737-800型飞机,机身长39.5m,翼展为35.8m。即F=B=19.75m,L=R=17.9,由此计算得出的航空器轮廓顶点见表4
分别以CSN6883航班为基准目标和判断目标,判断其他航空器与该航班滑行过程中的可能冲突风险。在根据速度构建安全区域的基础上,通过射线法判断不同航班间的轮廓关系,并排除虽位置过近但不存在冲突风险的情况,可以最终识别出CSN6883航班的潜在滑行冲突风险,冲突风险识别情况见表5
对比识别出的冲突风险与地窝堡机场的塔台电子进程单的实际冲突情况。实际冲突情况见表6
对比表5表6,并比较当日地窝堡机场的全部滑行冲突风险识别结果和实际冲突风险,可得出,航空器在滑行过程中,绝大多数的滑行冲突风险存在于跟随滑行中,但是该种风险对于管制来说并不重要,因为跟随航空器可以自行调节滑行速度,从而保障滑行安全。当滑行冲突风险发生在航空器穿越滑行道道口或转向时,此时滑行冲突风险往往会导致航空器过久停留,也会占用管制人员大量精力。而且,滑行冲突风险大多集中发生在11—13时这段时间,这是由于在高峰时段,离场和进场的航班量都较大,造成滑行道资源紧张。
总的来说,在精准预测滑行冲突风险的基础上,若能提前识别相关滑行冲突风险,并提前管制调控,便可以在保障飞行区安全运行的同时,提高飞行区的运行效率。
1) AM-LSTM预测模型能够准确地预测未来 3s 内航空器的轨迹位置,ADE为1.05m,精准性可达94.37%。对比预测冲突结果与地窝堡机场的塔台电子进程单的实际冲突情况,验证了该方法能够准确预测场面滑行冲突。
2) 在飞行区建立的AM-LSTM轨迹预测模型,能够综合考虑航空器滑行时的自身运动态势与滑行道构型对轨迹的限制,提高对航空器位置的实时动态预测精度,帮助管制人员实现对冲突的提前告警,具有良好的应用价值。
3) 文中在选择预测轨迹时仅考虑了航空器,其实对飞行区安全运行造成影响的包括车辆、人员及无动力设备。在进行冲突判定时未考虑场面障碍物对航空器的影响,未来将对这些内容作进一步研究。
  • 国家自然科学基金资助(U2133207)
  • 国家自然科学基金资助(62173332)
  • 中央高校基金重点项目(3122019191)
  • 天津市科技计划项目(21JCYBJC00700)
参考文献 引证文献
排序方式:
[1]
ZHOU Zhijing, CHEN Jinliang, SHEN Beibei, et al. A trajectory prediction method based on aircraft motion model and grey theory[C]. 2016 IEEE Advanced Information Management, Communicates, Electronic and Automation Control Conference (IMCEC), 2016:1523-1527.
[2]
YUE Song, PENG Cheng, MU Chundi. An improved trajectory prediction algorithm based on trajectory data mining for air traffic management[C]. International Conference on Information & Automation, 2012:981-986.
[3]
ZHANG Caikun, ZHANG Xuan, SHI Chuan, et al. Aircraft trajectory prediction based on genetic programming[C]. 2016 3rd International Conference on Information Science and Control Engineering (ICISCE), 2016:158-162.
[4]
AYHAN S, SAMET H. Aircraft trajectory prediction made easy with predictive analytics[C]. 22nd ACM SIGKDD International Conference, 2016:21-30.
[5]
熊晓夏, 刘擎超, 沈钰杰, 等. 基于LSTM-BF的高速公路交通事故风险模型[J]. 中国安全科学学报, 2022, 32(5):170-176.
XIONG Xiaoxia, LIU Qingchao, SHEN Yujie, et al. Study on risk model of highway traffic accidents based on LSTM-BF[J]. China Safety Science Journal, 2022, 32(5):170-176.
[6]
冯文刚. 基于深度长短记忆模型的民航安保事件分析[J]. 中国安全科学学报, 2021, 31(9):1-7.
FENG Wen'gang. Research on civil aviation security event analysis based on deep LSTM model[J]. China Safety Science Journal, 2021, 31(9):1-7.
[7]
赵江平, 徐恒, 党悦悦. 基于改进Faster R-CNN的铁路客车螺栓检测研究[J]. 中国安全科学学报, 2021, 31(7):82-89.
ZHAO Jiangping, XU Heng, DANG Yueyue. Research on bolt detection of railway passenger cars based on improved Faster R-CNN[J]. China Safety Science Journal, 2021, 31(7):82-89.
[8]
MAO Yao, QIN Guojin, NI Pingan, et al. Analysis of road traffic speed in Kunming plateau mountains: a fusion PSO-LSTM algorithm[J]. International Journal of Urban Sciences, 2021, 26(1):87-107.
[9]
张心宇, 刘源, 宋佳凝. 基于LSTM神经网络的短期轨道预报[J]. 系统工程与电子技术, 2022, 44(3): 939-947.
ZHANG Xinyu, LIU Yuan, SONG Jianing. Short-term orbit prediction based on LSTM neural network[J]. Systems Engineering and Electronics, 2022, 44(3): 939-947.
[10]
于琛, 付玉慧, 张逸飞, 等. 基于ARIMA-BIGRU的船舶航迹预测[J]. 船海工程, 2021, 50(6):147-152.
YU Chen, FU Yuhui, ZHANG Yifei, et al. The track prediction method based on ARIMA-BIGRU neural network[J]. Ship & Ocean Engineering, 2021, 50(6):147-152.
[11]
MA Lan, TIAN Shan. A hybrid CNN-LSTM model for aircraft 4D trajectory prediction[J]. IEEE Access, 2020, 8: 134 668-134 680.
[12]
SHI Zhiyuan, XU Min, PAN Quan. 4-D flight trajectory prediction with constrained LSTM network[J]. IEEE Transactions on Intelligent Transportation Systems, 2020, 22(11): 7242-7255.
[13]
ZENG Weili, QUAN Zhibin, ZHAO Ziyu, et al. A deep learning approach for aircraft trajectory prediction in terminal airspace[J]. IEEE Access, 2020, 8: 151 250-151 266.
[14]
张卫华, 陶虎, 陈乾. 城市快速路互通立交分流区交通冲突预测模型[J]. 公路工程, 2022, 47(1):149-155.
ZHANG Weihua, TAO Hu, CHEN Qian. The predicting model of traffic conflicts in diverging segments of expressway interchange[J]. Highway Engineering, 2022, 47(1):149-155.
[15]
张思远, 李仙颖, 沈笑云. 基于ADS-B IN的冲突预测与多机无冲突航迹规划[J]. 系统仿真学报, 2019, 31(8): 1627-1635.
ZHANG Siyuan, LI Xianying, SHEN Xiaoyun. ADS-B in based conflict prediction and conflict-free trajectory planning for multi-aircraft[J]. Journal of System Simulation, 2019, 31(8): 1627-1635.
[16]
LI Shanmei, XU Xiaohao, MENG Linghang. Flight conflict of recasting based on chaotic time series[J]. Transactions of Nanjing University of Aeronautics & Astronautics, 2012, 29(4):388-394.
[17]
QU Zhaowei, GAO Yuhong, SONG Xianmin, et al. Traffic conflict identification of E-BIKES at signalized intersections[J]. Transport, 2020, 2020:1-14.
[18]
LYU Wenying, ZHANG Honghai, WAN Junqiang, et al. Research on safety prediction of sector traffic operation based on a long short term memory model[J]. Applied Sciences-BASEL, 2021, 11(11):1076-1093.
[19]
王志刚, 王业光, 杨宁, 等. 基于LSTM的飞行数据挖掘模型构建方法[J]. 航空学报, 2021, 42(8): 262-271.
WANG Zhigang, WANG Yeguang, YANG Ning, et al. Construction method of flight data mining model based on LSTM[J]. Acta Aeronautica et Astronautica Sinica, 2021, 42(8): 262-271.
[20]
魏晓良, 潮群, 陶建峰, 等. 基于LSTM和CNN的高速柱塞泵故障诊断[J]. 航空学报, 2021, 42(3):435-445.
WEI Xiaoliang, CHAO Qun, TAO Jianfeng, et al. Cavitation fault diagnosis method for high-speed plunger pumps based on LSTM and CNN[J]. Acta Aeronautica et Astronautica Sinica, 2021, 42(3): 435-445.
[21]
吴春鹏, 冯姣. 结合AMS的C-LSTM船舶轨迹预测[J]. 船海工程, 2021, 50(6):141-146,152.
WU Chunpeng, FENG Jiao. Ship trajectory prediction based on C-LSTM combined with AMS[J]. Ship & Ocean Engineering, 2021, 50(6):141-146,152.
[22]
吴明先, 许甜, 刘建蓓, 等. 基于高频高精度定位信息的车辆轮廓冲突瞬时预测方法[J]. 中国公路学报, 2019, 32(6):105-113.
WU Mingxian, XU Tian, LIU Jianbei, et al. Instantaneous prediction of vehicle outline conflict using high-frequency and high-precision position information[J]. China Journal of Highway and Transport, 2019, 32(6): 105-113.
2024年第34卷第1期
PDF下载
359
161
引用本文
BibTeX
文章信息
doi: 10.16265/j.cnki.issn1003-3033.2024.01.1517
  • 首发时间:2025-07-09
  • 出版时间:2024-01-28
补充材料
相关文章
文章信息
作者
出版历史
基金
国家自然科学基金资助(U2133207)
国家自然科学基金资助(62173332)
中央高校基金重点项目(3122019191)
天津市科技计划项目(21JCYBJC00700)
作者信息
    中国民航大学 民航飞联网重点实验室,天津 300300
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/zgaqkxxb/CN/10.16265/j.cnki.issn1003-3033.2024.01.1517
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