Article(id=1208051031078965976, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1208051024368083510, articleNumber=null, orderNo=null, doi=10.12404/j.issn.1671-1815.2404967, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=research-article, receivedDate=1719936000000, receivedDateStr=2024-07-03, revisedDate=1742313600000, revisedDateStr=2025-03-19, acceptedDate=null, acceptedDateStr=null, onlineDate=1765951410312, onlineDateStr=2025-12-17, pubDate=1751040000000, pubDateStr=2025-06-28, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1765951410312, onlineIssueDateStr=2025-12-17, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1765951410312, creator=13701087609, updateTime=1765951410312, updator=13701087609, issue=Issue{id=1208051024368083510, tenantId=1146029695717560320, journalId=1146123166801305609, year='2025', volume='25', issue='18', pageStart='7455', pageEnd='7883', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1765951408712, creator=13701087609, updateTime=1765951896766, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1208053071507198943, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1208051024368083510, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1208053071507198944, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1208051024368083510, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=7859, endPage=7865, ext={EN=ArticleExt(id=1208051033171923738, articleId=1208051031078965976, tenantId=1146029695717560320, journalId=1146123166801305609, language=EN, title=Extremely Short-term Prediction Method and Applicability Analysis of Seaplane Motion Based on Time Series Model, columnId=1156262731079607234, journalTitle=Science Technology and Engineering, columnName=Papers·Aeronautics and Astronautics, runingTitle=null, highlight=null, articleAbstract=

The extremely short-term prediction of seaplane motion can provide the rocking motion posture over the next few seconds, which is considered essential for ensuring safety during take-off and landing phases under adverse wind and wave conditions. Although some research has been conducted on extremely short-term prediction methods for seaplane motion, limited attention has been given to analyzing differences in the applicability of various methods. In this context, the NACA TN 2929 aircraft was taken as an example, and the three degree of freedom motion simulation data under typical working conditions were calculated based on potential flow theory. To compare the forecasting performance under different forecasting conditions, three typical extremely short-term prediction of seaplane motion models, namely AR (auto-regressive), LSTM (long short term memory), and TCN (temporal convolutional network), were constructed. The results show that compared to the AR model, the LSTM and TCN neural network models exhibit superior forecasting accuracy for longer prediction durations, effectively enabling accurate predictions of the heave, roll, and pitch motions of the seaplane at the ten-second level, providing a valuable theoretical reference for the selection of seaplane motion prediction algorithms.

, correspAuthors=Jue GONG, 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=Run-song ZHOU, Ai-hua WU, Wei ZHANG, Jue GONG), CN=ArticleExt(id=1208051040000249978, articleId=1208051031078965976, tenantId=1146029695717560320, journalId=1146123166801305609, language=CN, title=基于时序模型的水上飞机运动极短期预报方法及适用性分析, columnId=1156262731373208516, journalTitle=科学技术与工程, columnName=论文·航空、航天, runingTitle=null, highlight=null, articleAbstract=

水上飞机运动极短期预报可以提供未来数秒的摇荡运动姿态,对确保大风浪条件下的起飞与降落阶段的安全有重要意义。目前已有相关水上飞机运动极短期预报方法研究,但是对不同方法适用性差异分析的研究较少。针对该情况,以NACA TN 2929飞机为例,基于势流理论计算其在典型工况下三自由度运动仿真数据,通过构建AR(auto regressive)、LSTM(long short term memory)和TCN(temporal convolutional network)三种典型运动极短期预报模型,对比三种模型在不同预报条件下的预报性能。结果表明: 与AR模型相比,以LSTM、TCN为代表的神经网络模型在预报时长较长时具有更好的预报精度,可较好地实现对水上飞机的垂荡、横摇和纵摇运动十秒级的准确预报,为水上飞机运动预报算法的选取提供较好的理论参考价值。

, correspAuthors=宫珏, authorNote=null, correspAuthorsNote=
* 宫珏(1995—),女,汉族,辽宁庄河人,硕士,工程师。研究方向:系统对准、组合导航及完好性。E-mail:
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=q+3VC+0+3jr/VAHmkk/PGA==, magXml=a5HWWcLPthfF3akvqbKYOg==, pdfUrl=null, pdf=mu5JUYP4kOzUBWSmHbqUMg==, pdfFileSize=7352821, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=Kxug8+WJA5HNMnJCC5Ir6w==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=F+CwC4bF70p/zEBhhaYLaQ==, mapNumber=null, authorCompany=null, fund=null, authors=

周润松(2001—),男,汉族,山东泰安人,硕士研究生。研究方向:水面目标物运动极短期预报。E-mail:

, authorsList=周润松, 武爱华, 张伟, 宫珏)}, authors=[Author(id=1208085584170554058, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051031078965976, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=runsong@hrbeu.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1208085584279605972, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051031078965976, authorId=1208085584170554058, language=EN, stringName=Run-song ZHOU, firstName=Run-song, middleName=null, lastName=ZHOU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 Qingdao Innovation and Development Base, Harbin Engineering University, Qingdao 266000, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1208085584438989537, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051031078965976, authorId=1208085584170554058, language=CN, stringName=周润松, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 哈尔滨工程大学青岛创新发展基地, 青岛 266000, bio={"content":"

周润松(2001—),男,汉族,山东泰安人,硕士研究生。研究方向:水面目标物运动极短期预报。E-mail:

"}, bioImg=null, bioContent=

周润松(2001—),男,汉族,山东泰安人,硕士研究生。研究方向:水面目标物运动极短期预报。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1208085583717569181, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051031078965976, xref=1, ext=[AuthorCompanyExt(id=1208085583721763487, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051031078965976, companyId=1208085583717569181, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 Qingdao Innovation and Development Base, Harbin Engineering University, Qingdao 266000, China), AuthorCompanyExt(id=1208085583730152095, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051031078965976, companyId=1208085583717569181, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 哈尔滨工程大学青岛创新发展基地, 青岛 266000)])]), Author(id=1208085584573207282, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051031078965976, 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=1208085584812282632, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051031078965976, authorId=1208085584573207282, language=EN, stringName=Ai-hua WU, firstName=Ai-hua, middleName=null, lastName=WU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2 The Fifth Military Representative Office Stationed in Xi’an with Empty Equipment, Xi’an 710000, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1208085584908751638, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051031078965976, authorId=1208085584573207282, language=CN, stringName=武爱华, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2 空装驻西安地区第五军事代表室, 西安 710000, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1208085583885341355, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051031078965976, xref=2, ext=[AuthorCompanyExt(id=1208085583906312875, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051031078965976, companyId=1208085583885341355, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 The Fifth Military Representative Office Stationed in Xi’an with Empty Equipment, Xi’an 710000, China), AuthorCompanyExt(id=1208085583918895788, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051031078965976, companyId=1208085583885341355, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 空装驻西安地区第五军事代表室, 西安 710000)])]), Author(id=1208085586108322604, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051031078965976, 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=1208085586200597304, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051031078965976, authorId=1208085586108322604, language=EN, stringName=Wei ZHANG, firstName=Wei, middleName=null, lastName=ZHANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2 The Fifth Military Representative Office Stationed in Xi’an with Empty Equipment, Xi’an 710000, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1208085586313843525, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051031078965976, authorId=1208085586108322604, language=CN, stringName=张伟, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2 空装驻西安地区第五军事代表室, 西安 710000, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1208085583885341355, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051031078965976, xref=2, ext=[AuthorCompanyExt(id=1208085583906312875, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051031078965976, companyId=1208085583885341355, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 The Fifth Military Representative Office Stationed in Xi’an with Empty Equipment, Xi’an 710000, China), AuthorCompanyExt(id=1208085583918895788, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051031078965976, companyId=1208085583885341355, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 空装驻西安地区第五军事代表室, 西安 710000)])]), Author(id=1208085586586473295, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051031078965976, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=Gjue1010@163.com, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1208085586712302427, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051031078965976, authorId=1208085586586473295, language=EN, stringName=Jue GONG, firstName=Jue, middleName=null, lastName=GONG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, *, address=3 AVIC Xi’an Flight Automatic Control Research Institute, Xi’an 710076, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1208085586859103087, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051031078965976, authorId=1208085586586473295, language=CN, stringName=宫珏, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, *, address=3 中航工业西安飞行自动控制研究所, 西安 710076, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1208085584036336310, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051031078965976, xref=3, ext=[AuthorCompanyExt(id=1208085584057307833, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051031078965976, companyId=1208085584036336310, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 AVIC Xi’an Flight Automatic Control Research Institute, Xi’an 710076, China), AuthorCompanyExt(id=1208085584078279357, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051031078965976, companyId=1208085584036336310, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 中航工业西安飞行自动控制研究所, 西安 710076)])])], keywords=[Keyword(id=1208085587144315787, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051031078965976, language=EN, orderNo=1, keyword=extremely short-term prediction of seaplane motion), Keyword(id=1208085587253367709, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051031078965976, language=EN, orderNo=2, keyword=auto-regressive model), Keyword(id=1208085587429528491, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051031078965976, language=EN, orderNo=3, keyword=long short term memory network), Keyword(id=1208085587538580410, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051031078965976, language=EN, orderNo=4, keyword=temporal convolutional network), Keyword(id=1208085587685381066, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051031078965976, language=CN, orderNo=1, keyword=水上飞机运动极短期预报), Keyword(id=1208085587861541858, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051031078965976, language=CN, orderNo=2, keyword=自回归模型), Keyword(id=1208085587995759597, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051031078965976, language=CN, orderNo=3, keyword=长短期记忆网络), Keyword(id=1208085588176114684, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051031078965976, language=CN, orderNo=4, keyword=时间卷积网络)], refs=[Reference(id=1208085593154752899, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051031078965976, doi=null, pmid=null, pmcid=null, year=2020, volume=61, issue=S2, pageStart=254, pageEnd=261, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=胡开业, 南春, 石林飞, journalName=中国造船, refType=null, unstructuredReference=胡开业, 南春, 石林飞, 等. 水陆两栖飞机规则波中滑行运动数值仿真研究[J]. 中国造船, 2020, 61(S2): 254-261., articleTitle=水陆两栖飞机规则波中滑行运动数值仿真研究, refAbstract=null), Reference(id=1208085593276387726, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051031078965976, doi=null, pmid=null, pmcid=null, year=2020, volume=61, issue=S2, pageStart=254, pageEnd=261, url=null, language=null, rfNumber=[1], rfOrder=1, authorNames=Hu Kaiye, Nan Chun, Shi Linfei, journalName=Shipbuilding of China, refType=null, unstructuredReference=Hu Kaiye, Nan Chun, Shi Linfei, et al. Numerical simulation research on planing motion of amphibious aircraft in regular waves[J]. Shipbuilding of China, 2020, 61(S2): 254-261., articleTitle=Numerical simulation research on planing motion of amphibious aircraft in regular waves, refAbstract=null), Reference(id=1208085593465131416, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051031078965976, doi=null, pmid=null, pmcid=null, year=2023, volume=44, issue=21, pageStart=528665, pageEnd=528665, url=null, language=null, rfNumber=[2], rfOrder=2, authorNames=张永杰, 崔博, 王明振, journalName=航空学报, refType=null, unstructuredReference=张永杰, 崔博, 王明振, 等. 水陆两栖飞机着水试验与理论分析方法研究进展[J]. 航空学报, 2023, 44(21): 528665-528665., articleTitle=水陆两栖飞机着水试验与理论分析方法研究进展, refAbstract=null), Reference(id=1208085593578377630, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051031078965976, doi=null, pmid=null, pmcid=null, year=2023, volume=44, issue=21, pageStart=528665, pageEnd=528665, url=null, language=null, rfNumber=[2], rfOrder=3, authorNames=Zhang Yongjie, Cui Bo, Wang Mingzhen, journalName=Acta Aeronautica et Astronautica Sinica, refType=null, unstructuredReference=Zhang Yongjie, Cui Bo, Wang Mingzhen, et al. Research progress of amphibious aircraft water landing test and theoretical analysis methods[J]. Acta Aeronautica et Astronautica Sinica, 2023, 44(21): 528665-528665., articleTitle=Research progress of amphibious aircraft water landing test and theoretical analysis methods, refAbstract=null), Reference(id=1208085593779704236, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051031078965976, doi=null, pmid=null, pmcid=null, year=2024, volume=24, issue=6, pageStart=2581, pageEnd=2589, url=null, language=null, rfNumber=[3], rfOrder=4, authorNames=张杜文, 李新颖, 吴彬, journalName=科学技术与工程, refType=null, unstructuredReference=张杜文, 李新颖, 吴彬, 等. 水陆两栖飞机全机模型静水滑行水动性能预报[J]. 科学技术与工程, 2024, 24(6): 2581-2589., articleTitle=水陆两栖飞机全机模型静水滑行水动性能预报, refAbstract=null), Reference(id=1208085595025412532, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051031078965976, doi=null, pmid=null, pmcid=null, year=2024, volume=24, issue=6, pageStart=2581, pageEnd=2589, url=null, language=null, rfNumber=[3], rfOrder=5, authorNames=Zhang Duwen, Li Xinying, Wu Bin, journalName=Science Technology and Engineering, refType=null, unstructuredReference=Zhang Duwen, Li Xinying, Wu Bin, et al. Hydrodynamic performance prediction of full-aircraft model of amphibious hydroplane[J]. Science Technology and Engineering, 2024, 24(6): 2581-2589., articleTitle=Hydrodynamic performance prediction of full-aircraft model of amphibious hydroplane, refAbstract=null), Reference(id=1208085595151241662, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051031078965976, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=380, pageEnd=null, url=null, language=null, rfNumber=[4], rfOrder=6, authorNames=胡奇, 吴彬, 王明振, journalName=null, refType=null, unstructuredReference=胡奇, 吴彬, 王明振, 等. 水陆两栖飞机静水滑行特性仿真分析[C]// 第十一届全国流体力学学术会议论文摘要集. 深圳: 中国力学学会流体力学专业委员会, 2020: 380., articleTitle=水陆两栖飞机静水滑行特性仿真分析, refAbstract=null), Reference(id=1208085595268682184, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051031078965976, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=380, pageEnd=null, url=null, language=null, rfNumber=[4], rfOrder=7, authorNames=HuQi, WuBin, WangMingzhen, journalName=Abstracts of the 11th National Conference on Fluid Mechanics, refType=null, unstructuredReference=HuQi, WuBin, WangMingzhen, et al. Simulation analysis of hydro static sliding characteristics of amphibious aircraft[C]// Abstracts of the 11th National Conference on Fluid Mechanics. Shenzhen: Chinese Society of Theoretical and Applied Mechanics Fluid Mechanics Professional Committee, 2020: 380., articleTitle=Simulation analysis of hydro static sliding characteristics of amphibious aircraft, refAbstract=null), Reference(id=1208085595402899921, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051031078965976, doi=null, pmid=null, pmcid=null, year=2024, volume=45, issue=1, pageStart=44, pageEnd=52, url=null, language=null, rfNumber=[5], rfOrder=8, authorNames=胡开业, 石林飞, 周辉, journalName=哈尔滨工程大学学报, refType=null, unstructuredReference=胡开业, 石林飞, 周辉, 等. 基于计算流体动力学方法的两栖飞机规则波中运动特性研究[J]. 哈尔滨工程大学学报, 2024, 45(1): 44-52., articleTitle=基于计算流体动力学方法的两栖飞机规则波中运动特性研究, refAbstract=null), Reference(id=1208085595545506267, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051031078965976, doi=null, pmid=null, pmcid=null, year=2024, volume=45, issue=1, pageStart=44, pageEnd=52, url=null, language=null, rfNumber=[5], rfOrder=9, authorNames=Hu Kaiye, Shi Linfei, Zhou Hui, journalName=Journal of Harbin Engineering University, refType=null, unstructuredReference=Hu Kaiye, Shi Linfei, Zhou Hui, et al. Research on the take-off motion characteristics of amphibious aircraft in regular waves based on the computational fluid dynamics method[J]. Journal of Harbin Engineering University, 2024, 45(1): 44-52., articleTitle=Research on the take-off motion characteristics of amphibious aircraft in regular waves based on the computational fluid dynamics method, refAbstract=null), Reference(id=1208085595654558181, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051031078965976, doi=null, pmid=null, pmcid=null, year=2016, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[6], rfOrder=10, authorNames=黄礼敏, journalName=海浪中非平稳非线性舰船运动在线预报研究, refType=null, unstructuredReference=黄礼敏. 海浪中非平稳非线性舰船运动在线预报研究[D]. 哈尔滨: 哈尔滨工程大学, 2016., articleTitle=null, refAbstract=null), Reference(id=1208085595788775916, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051031078965976, doi=null, pmid=null, pmcid=null, year=2016, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[6], rfOrder=11, authorNames=Huang Limin, journalName=On-line prediction of non-stationary and nonlinear ship motions at sea, refType=null, unstructuredReference=Huang Limin. On-line prediction of non-stationary and nonlinear ship motions at sea[D]. Harbin: Harbin Engineering University, 2016., articleTitle=null, refAbstract=null), Reference(id=1208085595927187965, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051031078965976, doi=null, pmid=null, pmcid=null, year=2012, volume=16, issue=S1, pageStart=44, pageEnd=51, url=null, language=null, rfNumber=[7], rfOrder=12, authorNames=彭秀艳, 刘长德, journalName=船舶力学, refType=null, unstructuredReference=彭秀艳, 刘长德. 基于格型递归最小二乘算法的船舶运动极短期预报[J]. 船舶力学, 2012, 16(S1): 44-51., articleTitle=基于格型递归最小二乘算法的船舶运动极短期预报, refAbstract=null), Reference(id=1208085596078182920, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051031078965976, doi=null, pmid=null, pmcid=null, year=2012, volume=16, issue=S1, pageStart=44, pageEnd=51, url=null, language=null, rfNumber=[7], rfOrder=13, authorNames=Peng Xiuyan, Liu Changde, journalName=Journal of Ship Mechanics, refType=null, unstructuredReference=Peng Xiuyan, Liu Changde. Extreme short time prediction of ship motion based on lattice recursive least square[J]. Journal of Ship Mechanics, 2012, 16(S1): 44-51., articleTitle=Extreme short time prediction of ship motion based on lattice recursive least square, refAbstract=null), Reference(id=1208085596224983578, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051031078965976, doi=null, pmid=null, pmcid=null, year=2020, volume=7, issue=null, pageStart=66, pageEnd=74, url=null, language=null, rfNumber=[8], rfOrder=14, authorNames=Wang W, Li M, journalName=International Journal of Science, refType=null, unstructuredReference=Wang W, Li M. A short-time prediction method of ship motion attitude based on EEMD-LSSVM[J]. International Journal of Science, 2020, 7: 66-74., articleTitle=A short-time prediction method of ship motion attitude based on EEMD-LSSVM, refAbstract=null), Reference(id=1208085596355007007, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051031078965976, doi=null, pmid=null, pmcid=null, year=2022, volume=10, issue=7, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[9], rfOrder=15, authorNames=Fu H, Gu Z, Wang Y, journalName=Journal of Marine Science and Engineering, refType=null, unstructuredReference=Fu H, Gu Z, Wang Y. Ship pitch prediction based on Bi-ConvLSTM-CA model[J]. Journal of Marine Science and Engineering, 2022, 10(7): 840., articleTitle=Ship pitch prediction based on Bi-ConvLSTM-CA model, refAbstract=null), Reference(id=1208085596506001957, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051031078965976, doi=null, pmid=null, pmcid=null, year=2023, volume=270, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[10], rfOrder=16, authorNames=Wei Y, Chen Z, Zhao C, journalName=Ocean Engineering, refType=null, unstructuredReference=Wei Y, Chen Z, Zhao C, et al. A time-varying ensemble model for ship motion prediction based on feature selection and clustering methods[J]. Ocean Engineering, 2023, 270. DOI: 10.1016/j.oceaneng.2023.113659., articleTitle=A time-varying ensemble model for ship motion prediction based on feature selection and clustering methods, refAbstract=null), Reference(id=1208085596715717173, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051031078965976, doi=null, pmid=null, pmcid=null, year=2023, volume=280, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[11], rfOrder=17, authorNames=Gao N, Hu A, Hou L, journalName=Ocean Engineering, refType=null, unstructuredReference=Gao N, Hu A, Hou L, et al. Real-time ship motion prediction based on adaptive wavelet transform and dynamic neural network[J]. Ocean Engineering, 2023, 280. DOI: 10.1016/j.oceaneng.2023.114466., articleTitle=Real-time ship motion prediction based on adaptive wavelet transform and dynamic neural network, refAbstract=null), Reference(id=1208085596824769087, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051031078965976, doi=null, pmid=null, pmcid=null, year=2019, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[12], rfOrder=18, authorNames=刘煜城, journalName=基于深度学习的船舶运动极短期预报方法研究, refType=null, unstructuredReference=刘煜城. 基于深度学习的船舶运动极短期预报方法研究[D]. 哈尔滨: 哈尔滨工程大学, 2019., articleTitle=null, refAbstract=null), Reference(id=1208085596938015300, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051031078965976, doi=null, pmid=null, pmcid=null, year=2019, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[12], rfOrder=19, authorNames=Liu Yucheng, journalName=Research on short-term forecasting method of ship motion based on deep learning, refType=null, unstructuredReference=Liu Yucheng. Research on short-term forecasting method of ship motion based on deep learning[D]. Harbin: Harbin Engineering University, 2019., articleTitle=null, refAbstract=null), Reference(id=1208085597038678600, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051031078965976, doi=null, pmid=null, pmcid=null, year=2021, volume=25, issue=3, pageStart=299, pageEnd=310, url=null, language=null, rfNumber=[13], rfOrder=20, authorNames=刘长德, 顾宇翔, 张进丰, journalName=船舶力学, refType=null, unstructuredReference=刘长德, 顾宇翔, 张进丰. 基于小波滤波和LSTM神经网络的船舶运动极短期预报研究[J]. 船舶力学, 2021, 25(3): 299-310., articleTitle=基于小波滤波和LSTM神经网络的船舶运动极短期预报研究, refAbstract=null), Reference(id=1208085597193867861, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051031078965976, doi=null, pmid=null, pmcid=null, year=2021, volume=25, issue=3, pageStart=299, pageEnd=310, url=null, language=null, rfNumber=[13], rfOrder=21, authorNames=Liu Changde, Gu Yuxiang, Zhang Jinfeng, journalName=Journal of Ship Mechanics, refType=null, unstructuredReference=Liu Changde, Gu Yuxiang, Zhang Jinfeng. Extreme short-term prediction of ship motions based on wavelet filter and LSTM neural network[J]. Journal of Ship Mechanics, 2021, 25(3): 299-310., articleTitle=Extreme short-term prediction of ship motions based on wavelet filter and LSTM neural network, refAbstract=null), Reference(id=1208085597281948250, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051031078965976, doi=null, pmid=null, pmcid=null, year=2021, volume=45, issue=6, pageStart=1113, pageEnd=1117, url=null, language=null, rfNumber=[14], rfOrder=22, authorNames=易文海, 高志亮, journalName=武汉理工大学学报(交通科学与工程版), refType=null, unstructuredReference=易文海, 高志亮. 基于LSTM神经网络的随机横浪中船舶横摇运动极短期预报[J]. 武汉理工大学学报(交通科学与工程版), 2021, 45(6): 1113-1117., articleTitle=基于LSTM神经网络的随机横浪中船舶横摇运动极短期预报, refAbstract=null), Reference(id=1208085597395194468, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051031078965976, doi=null, pmid=null, pmcid=null, year=2021, volume=45, issue=6, pageStart=1113, pageEnd=1117, url=null, language=null, rfNumber=[14], rfOrder=23, authorNames=Yi Wenhai, Gao Zhiliang, journalName=Journal of Wuhan University of Technology(Transportation Science & Engineering Edition), refType=null, unstructuredReference=Yi Wenhai, Gao Zhiliang. Very short-term prediction of ship rolling motion in random transverse waves based on LSTM neural network[J]. Journal of Wuhan University of Technology(Transportation Science & Engineering Edition), 2021, 45(6): 1113-1117., articleTitle=Very short-term prediction of ship rolling motion in random transverse waves based on LSTM neural network, refAbstract=null), Reference(id=1208085597537800811, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051031078965976, doi=null, pmid=null, pmcid=null, year=2024, volume=12, issue=1, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[15], rfOrder=24, authorNames=Hou X, Xia S, journalName=Journal of Marine Science and Engineering, refType=null, unstructuredReference=Hou X, Xia S. Short-term prediction of ship roll motion in waves based on convolutional neural network[J]. Journal of Marine Science and Engineering, 2024, 12(1).DOI: 10.3390/jmse12010102., articleTitle=Short-term prediction of ship roll motion in waves based on convolutional neural network, refAbstract=null), Reference(id=1208085597655241329, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051031078965976, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[16], rfOrder=25, authorNames=杨冰华, journalName=基于深度学习的船舶运动姿态极短期预报研究, refType=null, unstructuredReference=杨冰华. 基于深度学习的船舶运动姿态极短期预报研究[D]. 镇江: 江苏科技大学, 2022., articleTitle=null, refAbstract=null), Reference(id=1208085597823013498, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051031078965976, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[16], rfOrder=26, authorNames=Yang Binghua, journalName=Research on very short-term prediction of ship motion attitude based on deep learning, refType=null, unstructuredReference=Yang Binghua. Research on very short-term prediction of ship motion attitude based on deep learning[D]. Zhenjiang: Jiangsu University of Science and Technology, 2022., articleTitle=null, refAbstract=null), Reference(id=1208085597961425540, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051031078965976, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[17], rfOrder=27, authorNames=薛兴, journalName=船舶运动极短期预报研究, refType=null, unstructuredReference=薛兴. 船舶运动极短期预报研究[D]. 大连: 大连海事大学, 2022., articleTitle=null, refAbstract=null), Reference(id=1208085598141780616, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051031078965976, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[17], rfOrder=28, authorNames=Xue Xing, journalName=Research on extreme short-term prediction of ship motions, refType=null, unstructuredReference=Xue Xing. Research on extreme short-term prediction of ship motions[D]. Dalian: Dalian Maritime University, 2022., articleTitle=null, refAbstract=null), Reference(id=1208085598296969872, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051031078965976, doi=null, pmid=null, pmcid=null, year=2015, volume=16, issue=2, pageStart=865, pageEnd=873, url=null, language=null, rfNumber=[18], rfOrder=29, authorNames=Lü Y, Duan Y, Kang W, journalName=Intelligent Transportation Systems, IEEE Transactionson, refType=null, unstructuredReference= Y, Duan Y, Kang W, et al. Traffic flow prediction with big data: a deep learning approach[J]. Intelligent Transportation Systems, IEEE Transactionson, 2015, 16(2): 865-873., articleTitle=Traffic flow prediction with big data: a deep learning approach, refAbstract=null), Reference(id=1208085599542678172, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051031078965976, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[19], rfOrder=30, authorNames=Bai S, Kolter J Z, Koltun V, journalName=arXiv preprint arXiv: 1803. 01271, 2018, refType=null, unstructuredReference=Bai S, Kolter J Z, Koltun V. An empirical evaluation of generic convolutional and recurrent networks for sequence modeling[J]. arXiv preprint arXiv: 1803. 01271, 2018., articleTitle=An empirical evaluation of generic convolutional and recurrent networks for sequence modeling, refAbstract=null)], funds=[Fund(id=1208085592915677544, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051031078965976, awardId=YESS20220013, language=CN, fundingSource=中国科协青年人才托举工程(YESS20220013), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1208085583717569181, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051031078965976, xref=1, ext=[AuthorCompanyExt(id=1208085583721763487, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051031078965976, companyId=1208085583717569181, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 Qingdao Innovation and Development Base, Harbin Engineering University, Qingdao 266000, China), AuthorCompanyExt(id=1208085583730152095, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051031078965976, companyId=1208085583717569181, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 哈尔滨工程大学青岛创新发展基地, 青岛 266000)]), AuthorCompany(id=1208085583885341355, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051031078965976, xref=2, ext=[AuthorCompanyExt(id=1208085583906312875, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051031078965976, companyId=1208085583885341355, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 The Fifth Military Representative Office Stationed in Xi’an with Empty Equipment, Xi’an 710000, China), AuthorCompanyExt(id=1208085583918895788, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051031078965976, companyId=1208085583885341355, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 空装驻西安地区第五军事代表室, 西安 710000)]), AuthorCompany(id=1208085584036336310, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051031078965976, xref=3, ext=[AuthorCompanyExt(id=1208085584057307833, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051031078965976, companyId=1208085584036336310, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 AVIC Xi’an Flight Automatic Control Research Institute, Xi’an 710076, China), AuthorCompanyExt(id=1208085584078279357, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051031078965976, companyId=1208085584036336310, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 中航工业西安飞行自动控制研究所, 西安 710076)])], figs=[ArticleFig(id=1208085588469714974, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051031078965976, language=EN, label=Fig.1, caption=Structure of neuron of LSTM, figureFileSmall=rTU7NmL1TDcKlDeeguF1/A==, figureFileBig=gnkQZyfqJB7Zu1YlazkGXQ==, tableContent=null), ArticleFig(id=1208085588561989677, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051031078965976, language=CN, label=图1, caption=LSTM神经元结构, figureFileSmall=rTU7NmL1TDcKlDeeguF1/A==, figureFileBig=gnkQZyfqJB7Zu1YlazkGXQ==, tableContent=null), ArticleFig(id=1208085588817842243, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051031078965976, language=EN, label=Fig.2, caption=Structure of TCN model, figureFileSmall=mqg5ada5ogdswaWzA5+arA==, figureFileBig=whbvAP5Wrf/U92QPqMV1Zw==, tableContent=null), ArticleFig(id=1208085588973031509, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051031078965976, language=CN, label=图2, caption=TCN模型结构

k为卷积核大小,即每次卷积操作中,网络能够感知的连续时间步的数量;d为扩张率,是指在卷积操作中,相邻卷积核元素之间的间隔距离

, figureFileSmall=mqg5ada5ogdswaWzA5+arA==, figureFileBig=whbvAP5Wrf/U92QPqMV1Zw==, tableContent=null), ArticleFig(id=1208085589153386601, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051031078965976, language=EN, label=Fig.3, caption=Numerical simulation sequence of heave motion, figureFileSmall=hxE3Fi3sHgjm7tjzedVW/g==, figureFileBig=OTh05VnAxRNPS5wZlAlI2Q==, tableContent=null), ArticleFig(id=1208085589262438517, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051031078965976, language=CN, label=图3, caption=垂荡运动数值仿真序列, figureFileSmall=hxE3Fi3sHgjm7tjzedVW/g==, figureFileBig=OTh05VnAxRNPS5wZlAlI2Q==, tableContent=null), ArticleFig(id=1208085590516535425, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051031078965976, language=EN, label=Fig.4, caption=Numerical simulation sequence of roll motion, figureFileSmall=BtHV1bhO1gPNUcsiyJpgIw==, figureFileBig=6q/cIi1E/DphI4yUvOAH/A==, tableContent=null), ArticleFig(id=1208085590701084810, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051031078965976, language=CN, label=图4, caption=横摇运动数值仿真序列, figureFileSmall=BtHV1bhO1gPNUcsiyJpgIw==, figureFileBig=6q/cIi1E/DphI4yUvOAH/A==, tableContent=null), ArticleFig(id=1208085590914994334, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051031078965976, language=EN, label=Fig.5, caption=Numerical simulation sequence of pitch motion, figureFileSmall=1he2PjJ/3bFf21KZcj6yIA==, figureFileBig=jhfkM7MgTDyFzVpJMBelcA==, tableContent=null), ArticleFig(id=1208085591086960812, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051031078965976, language=CN, label=图5, caption=纵摇运动数值仿真序列, figureFileSmall=1he2PjJ/3bFf21KZcj6yIA==, figureFileBig=jhfkM7MgTDyFzVpJMBelcA==, tableContent=null), ArticleFig(id=1208085591233761465, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051031078965976, language=EN, label=Fig.6, caption=Prediction results of heave in three prediction models, figureFileSmall=DM9kmFvJyIu8HzRUh9r0yg==, figureFileBig=gePK/vkh1nRN2wiuwEIm/g==, tableContent=null), ArticleFig(id=1208085591342813382, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051031078965976, language=CN, label=图6, caption=垂荡运动在三种模型下的预报结果, figureFileSmall=DM9kmFvJyIu8HzRUh9r0yg==, figureFileBig=gePK/vkh1nRN2wiuwEIm/g==, tableContent=null), ArticleFig(id=1208085591464448211, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051031078965976, language=EN, label=Fig.7, caption=Comparison of prediction results of heave, pitch and roll in three prediction models, figureFileSmall=CygVCiPRSA3BVywo4ORuHw==, figureFileBig=hl8pMME4LqvU80MjDsXX7Q==, tableContent=null), ArticleFig(id=1208085591611248867, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051031078965976, language=CN, label=图7, caption=垂荡、纵摇和横摇运动在三种模型下预报效果对比, figureFileSmall=CygVCiPRSA3BVywo4ORuHw==, figureFileBig=hl8pMME4LqvU80MjDsXX7Q==, tableContent=null), ArticleFig(id=1208085591758049519, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051031078965976, language=EN, label=Fig.8, caption=Comparison of RMSE for different prediction durations, figureFileSmall=IQrpXmjxaEmtBwqDYSEUsw==, figureFileBig=fs8qp+Y/06zsH+slOGCLPw==, tableContent=null), ArticleFig(id=1208085591875490043, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051031078965976, language=CN, label=图8, caption=不同预报时长下RMSE对比, figureFileSmall=IQrpXmjxaEmtBwqDYSEUsw==, figureFileBig=fs8qp+Y/06zsH+slOGCLPw==, tableContent=null), ArticleFig(id=1208085591988736265, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051031078965976, language=EN, label=Table 1, caption=

The main scale parameters of NACA TN 2929 aircraft model

, figureFileSmall=null, figureFileBig=null, tableContent=
机身长度
L/m
翼展
B/m
质量
M/kg
重心纵向
位置Xg/m
惯性矩Iyy/
(kg·m2)
1.220 1.680 1.489 0.492L 0.242
), ArticleFig(id=1208085592152314133, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051031078965976, language=CN, label=表1, caption=

NACA TN 2929水上飞机模型主尺度参数

, figureFileSmall=null, figureFileBig=null, tableContent=
机身长度
L/m
翼展
B/m
质量
M/kg
重心纵向
位置Xg/m
惯性矩Iyy/
(kg·m2)
1.220 1.680 1.489 0.492L 0.242
), ArticleFig(id=1208085592261366052, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051031078965976, language=EN, label=Table 2, caption=

The sea state parameters for numerical simulation

, figureFileSmall=null, figureFileBig=null, tableContent=
海况
等级
有义
波高/m
平均
周期/s
航速/
(m·s-1)
浪向角/
(°)
五级 2.5 7 15 135
), ArticleFig(id=1208085592370417967, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051031078965976, language=CN, label=表2, caption=

数值仿真的海况参数

, figureFileSmall=null, figureFileBig=null, tableContent=
海况
等级
有义
波高/m
平均
周期/s
航速/
(m·s-1)
浪向角/
(°)
五级 2.5 7 15 135
), ArticleFig(id=1208085592496247104, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051031078965976, language=EN, label=Table 3, caption=

The prediction errors for heave motion

, figureFileSmall=null, figureFileBig=null, tableContent=
预报
时长/s
RMSE /m NRMSE/%
AR TCN LSTM AR TCN LSTM
2 0.444 0.123 0.206 10.39 2.88 4.82
6 1.051 0.047 0.155 24.60 1.10 3.63
12 1.289 0.074 0.153 30.17 1.73 3.58
20 1.322 0.096 0.187 30.94 2.25 4.38
), ArticleFig(id=1208085592668213582, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1208051031078965976, language=CN, label=表3, caption=

垂荡运动预报误差结果

, figureFileSmall=null, figureFileBig=null, tableContent=
预报
时长/s
RMSE /m NRMSE/%
AR TCN LSTM AR TCN LSTM
2 0.444 0.123 0.206 10.39 2.88 4.82
6 1.051 0.047 0.155 24.60 1.10 3.63
12 1.289 0.074 0.153 30.17 1.73 3.58
20 1.322 0.096 0.187 30.94 2.25 4.38
)], attaches=null, journal=Journal(id=1146119176004939786, delFlag=0, nameCn=科学技术与工程, nameEn=Science Technology and Engineering, nameHistory1=null, nameHistory2=null, issn=1671-1815, eissn=, cn=11-4688/T, coden=null, periodic=4, language=CN, oaType=是, ccby=null, superviseOffice=null, ownerOffice=null, pubOffice=null, editorOffice=null, officeType=null, aims=null, clcCode=null, officeProv=null, officeCity=null, officeAddr=null, officeZip=null, officeEmail=null, officePhone=null, editDirector=null, officeDirector=null, officeDirectorPhone=null, officeStaffNum=null, officeEmpNum=null, coverPicUrl=UKU/O7GSka5polgCTkbIIw==, journalPrice=null, startedYear=null, abbrevIsoEn=Sci Technol Eng, journalRemark=null, publicationField=null, createdTime=null, updatedTime=1754445529766, createdBy=null, updatedBy=13701087609, firstLetterCn=S, firstLetterEn=S, subjectCode=Natural Sciences, subjectName=自然科学, subjectCodeEn=Natural Sciences, subjectNameEn=null, picCn=UKU/O7GSka5polgCTkbIIw==, picEn=5hwlULoNwcbj3xUmVi9MAQ==, jcr=null, cjcr=null, exts=[JournalExt(id=1159791870395564357, language=CN, name=科学技术与工程, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=null, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=http://www.stae.com.cn/jsygc/home, createdTime=1754445529793, updatedTime=1754445529793, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=http://www.stae.com.cn/jsygc/site/menus/20090429150146001, submissionAuthorUrl=http://www.stae.com.cn/jsygc/author/login, submissionEditorUrl=http://www.stae.com.cn/jsygc/editor/login, submissionReviewUrl=http://www.stae.com.cn/jsygc/reviewer/login, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1159791870441701702, language=EN, name=Science Technology and Engineering, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=null, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=http://www.stae.com.cn/jsygc/home, createdTime=1754445529804, updatedTime=1754445529804, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=http://www.stae.com.cn/jsygc/author/login, submissionEditorUrl=http://www.stae.com.cn/jsygc/editor/login, submissionReviewUrl=http://www.stae.com.cn/jsygc/reviewer/login, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1146123166801305609, websiteList=[Website(id=1148243202391400884, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146123166801305609, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/kxjsygc/CN, language=CN, createTime=1751692112777, createBy=18614031015, updateTime=1753520965431, updateBy=18614031015, name=科学技术与工程-中文站点, tplId=1146099689490845704, title=科学技术与工程, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1148622798802673703, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=articleTextType, value=kx, createTime=1751782615614, updateTime=1751782615614, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622798781702180, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=banner, value=null, createTime=1751782615609, updateTime=1751782615609, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622798769119267, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=j86gbwi+p0Idkyl5SzIlmQ==, createTime=1751782615606, updateTime=1751782615606, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622798794285094, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1751782615612, updateTime=1751782615612, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622798790090789, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1751782615611, updateTime=1751782615611, creator=18614031015, updator=18614031015)]), Website(id=1155914124811976731, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146123166801305609, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/kxjsygc/EN, language=EN, createTime=1753521003206, createBy=18614031015, updateTime=1753521003206, updateBy=18614031015, name=科学技术与工程-英文站点, tplId=1146101810881728533, title=Science Technology and Engineering, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1155914371227308235, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=articleTextType, value=kx, createTime=1753521061952, updateTime=1753521061952, creator=18614031015, updator=18614031015), WebsiteProps(id=1155914371210531016, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=banner, value=null, createTime=1753521061947, updateTime=1753521061947, creator=18614031015, updator=18614031015), WebsiteProps(id=1155914371202142407, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=j86gbwi+p0Idkyl5SzIlmQ==, createTime=1753521061945, updateTime=1753521061945, creator=18614031015, updator=18614031015), WebsiteProps(id=1155914371223113930, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1753521061950, updateTime=1753521061950, creator=18614031015, updator=18614031015), WebsiteProps(id=1155914371218919625, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1753521061949, updateTime=1753521061949, creator=18614031015, updator=18614031015)])], journalTitle=科学技术与工程, weixinUrl=null, journalUrl=null, iacademicId=null, status=0, seqNo=null, journalTitleEn=Science Technology and Engineering, journalPhotoCn=UKU/O7GSka5polgCTkbIIw==, journalPhotoEn=5hwlULoNwcbj3xUmVi9MAQ==, journalFirstLetter=S, journalRecommend=null, journalNew=null, journalCollection=null, jcrJf=null, cjcrJf=null, jcrJfStr=null, cjcrJfStr=null, submissionFirstDecision=null, sciSubjectClassification=null, casSubjectClassification=null, citeScore=null, totalCitationFrequency=null, icpCode=null, psCode=null, advertisingLicenseCode=null, copyrightInformation=null, country=null, option=null, provinceCode=null, provinceName=null, collectFlag=false), detailUrlCn=https://castjournals.cast.org.cn/joweb/kxjsygc/CN/10.12404/j.issn.1671-1815.2404967, detailUrlEn=https://castjournals.cast.org.cn/joweb/kxjsygc/EN/10.12404/j.issn.1671-1815.2404967, pdfUrlCn=https://castjournals.cast.org.cn/joweb/kxjsygc/CN/PDF/10.12404/j.issn.1671-1815.2404967, pdfUrlEn=https://castjournals.cast.org.cn/joweb/kxjsygc/EN/PDF/10.12404/j.issn.1671-1815.2404967, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于时序模型的水上飞机运动极短期预报方法及适用性分析
收藏切换
PDF下载
周润松 1 , 武爱华 2 , 张伟 2 , 宫珏 3, *
科学技术与工程 | 论文·航空、航天 2025,25(18): 7859-7865
收起
收藏切换
科学技术与工程 | 论文·航空、航天 2025, 25(18): 7859-7865
基于时序模型的水上飞机运动极短期预报方法及适用性分析
全屏
周润松1 , 武爱华2, 张伟2, 宫珏3, *
作者信息
  • 1 哈尔滨工程大学青岛创新发展基地, 青岛 266000
  • 2 空装驻西安地区第五军事代表室, 西安 710000
  • 3 中航工业西安飞行自动控制研究所, 西安 710076
  • 周润松(2001—),男,汉族,山东泰安人,硕士研究生。研究方向:水面目标物运动极短期预报。E-mail:

通讯作者:

* 宫珏(1995—),女,汉族,辽宁庄河人,硕士,工程师。研究方向:系统对准、组合导航及完好性。E-mail:
Extremely Short-term Prediction Method and Applicability Analysis of Seaplane Motion Based on Time Series Model
Run-song ZHOU1 , Ai-hua WU2, Wei ZHANG2, Jue GONG3, *
Affiliations
  • 1 Qingdao Innovation and Development Base, Harbin Engineering University, Qingdao 266000, China
  • 2 The Fifth Military Representative Office Stationed in Xi’an with Empty Equipment, Xi’an 710000, China
  • 3 AVIC Xi’an Flight Automatic Control Research Institute, Xi’an 710076, China
出版时间: 2025-06-28 doi: 10.12404/j.issn.1671-1815.2404967
文章导航
收藏切换

水上飞机运动极短期预报可以提供未来数秒的摇荡运动姿态,对确保大风浪条件下的起飞与降落阶段的安全有重要意义。目前已有相关水上飞机运动极短期预报方法研究,但是对不同方法适用性差异分析的研究较少。针对该情况,以NACA TN 2929飞机为例,基于势流理论计算其在典型工况下三自由度运动仿真数据,通过构建AR(auto regressive)、LSTM(long short term memory)和TCN(temporal convolutional network)三种典型运动极短期预报模型,对比三种模型在不同预报条件下的预报性能。结果表明: 与AR模型相比,以LSTM、TCN为代表的神经网络模型在预报时长较长时具有更好的预报精度,可较好地实现对水上飞机的垂荡、横摇和纵摇运动十秒级的准确预报,为水上飞机运动预报算法的选取提供较好的理论参考价值。

水上飞机运动极短期预报  /  自回归模型  /  长短期记忆网络  /  时间卷积网络

The extremely short-term prediction of seaplane motion can provide the rocking motion posture over the next few seconds, which is considered essential for ensuring safety during take-off and landing phases under adverse wind and wave conditions. Although some research has been conducted on extremely short-term prediction methods for seaplane motion, limited attention has been given to analyzing differences in the applicability of various methods. In this context, the NACA TN 2929 aircraft was taken as an example, and the three degree of freedom motion simulation data under typical working conditions were calculated based on potential flow theory. To compare the forecasting performance under different forecasting conditions, three typical extremely short-term prediction of seaplane motion models, namely AR (auto-regressive), LSTM (long short term memory), and TCN (temporal convolutional network), were constructed. The results show that compared to the AR model, the LSTM and TCN neural network models exhibit superior forecasting accuracy for longer prediction durations, effectively enabling accurate predictions of the heave, roll, and pitch motions of the seaplane at the ten-second level, providing a valuable theoretical reference for the selection of seaplane motion prediction algorithms.

extremely short-term prediction of seaplane motion  /  auto-regressive model  /  long short term memory network  /  temporal convolutional network
周润松, 武爱华, 张伟, 宫珏. 基于时序模型的水上飞机运动极短期预报方法及适用性分析. 科学技术与工程, 2025 , 25 (18) : 7859 -7865 . DOI: 10.12404/j.issn.1671-1815.2404967
Run-song ZHOU, Ai-hua WU, Wei ZHANG, Jue GONG. Extremely Short-term Prediction Method and Applicability Analysis of Seaplane Motion Based on Time Series Model[J]. Science Technology and Engineering, 2025 , 25 (18) : 7859 -7865 . DOI: 10.12404/j.issn.1671-1815.2404967
水上飞机作为一种特殊的飞机,可实现水面条件下的起降,具有机动性好、环境适应性强、快速抵达等独特优势,能够完成海上消防、应急救援等特种作业任务[1],世界各国十分注重该类飞机的研制。当前水陆两栖飞机研究领域在基于数值计算方法模拟和研究波浪因素对水陆两栖飞机水动力性能的影响方面已有较多的成果[2]。张杜文等[3]采用RANS方法和重叠网格技术模拟水陆两栖飞机水面滑行,为水动性能预测提供技术基础。胡奇等[4]通过STARCCM+平台对水陆两栖飞机静水面滑行特性进行数值仿真,并与试验结果对比验证了仿真的准确性。胡开业等[5]开发了一种研究水陆两栖飞机在波浪环境中加速滑行和起飞动态特性的方法。而中外学者针对水上飞机运动极短期预报研究相对较少,水上飞机在海面滑翔过程中,会不可避免地产生六自由度摇荡运动,其中横摇、纵摇和垂荡运动会对其进行各类水上作业产生较大的影响。合理的对水上飞机运动进行秒级至十秒级的运动极短期预报,对其在大风浪下的起降安全有重要意义。
运动极短期预报是指通过当前或历史的运动状态,结合一些已知的外部条件,使用某种确定性的方法预测未来一段时间内的运动状态[6]。基于运动时历进行外推的时序预报方法是目前较为成熟的运动极短期预报方法,该方法本质是根据波浪场的记忆效应,不需要外界波浪环境输入,仅需历史运动数据便可实现时历外推预报。
传统时序预报方法主要是通过使用统计学和数学模型对运动数据进行建模和预测,如自回归(auto regressive,AR)模型和自回归滑动平均(autoregressive moving average,ARMA)模型等。AR模型算法简单,自适应性强,在水面目标物运动预报领域中得到了广泛应用。黄礼敏[6]在AR模型中通过流场的记忆效应,给出了针对船舶运动预报的定阶方法,优化了计算效率与精度。彭秀艳等[7]采用格型递推最小二次算法对AR模型参数估计做出优化,改善了预报效果。
伴随着近几年深度学习技术的飞速发展,多种深度学习模型被用于运动极短期预报研究。基于深度学习的时序预报方法具有较强的非线性拟合能力与时序特征提取能力,该方法采用复杂的神经网络模型对历史时历数据进行训练与学习,通过神经网络提取时序变化的内部关联性特征。
Wang等[8]通过经验模态分解(empirical mode decomposition,EMD)方法将运动信号解构为高、中、低频分量,建立最小二乘支持向量机预测模型,减少了复杂非线性时间序列预测的难度。Fu等[9]构建了一种结合双向卷积长短期记忆神经网络与通道注意力机制的复合模型,实现了对水面目标物转向角、相对风速与风向等运动数据的空间和时间信息的共同利用。Wei等[10]提出基于特征选择和聚类方法的集成模型,能够解决复杂环境下的多输入运动预测问题。Gao等[11]提出了一种基于自适应离散小波变换算法和残差递归神经网络的运动时历预报模型,在恶劣海况下表现出显著性能优势。刘煜城[12]提出了一种从历史运动数据出发的、基于自相关函数的模型定阶方法,并将其与长短期记忆神经网络(long short-term memory,LSTM)模型结合,取得了较好的预报结果。刘长德等[13]利用小波滤波和LSTM神经网络建立运动预报模型,并验证了模型的可行性。易文海等[14]使用LSTM神经网络建立了波浪与横摇运动之间的映射关系,基于波高历时数据实现运动预报。Hou等[15]利用卷积神经网络(convolutional neural networks,CNN)实现了水面目标物在波浪中横摇运动的准确预报。杨冰华[16]和薛兴[17]分别开展了基于组合预报模型的水面目标物运动极短期预报方法研究。
上述方法对船舶一类的水面目标物运动特性预报有着丰富的研究,但目前针对水上飞机运动极短期预报的多种方法适用性分析研究较少,因此现构建基于自回归AR模型、长短期记忆神经网络LSTM和时域卷积网络(temporal convolutional network,TCN)的3种的运动极短期预报模型,通过预报时历对比与误差统计进行3种典型预报模型适用分析,以期为水上飞机运动极短期预报相关算法的选取提供较好的理论参考价值。
在时间序列分析方法中,回归算法被广泛地应用于提取各变量之间的关系,其中自回归AR模型是用自身做回归变量的过程,其利用过去一段时间的随机变量的线性组合来确定未来某时刻的随机变量,可以反映单独一组时间序列的内部变化规律。与其他时序预报模型相比,AR模型算法复杂程度较低,计算效率高,同时具有较强的自适应性,是工程领域应用范围较广的一种时序预报模型。
对于给定的一组离散时间序列X={x1,x2,…,xn-1,xn},AR模型的标准方程式为
$ x_{t}-\varphi_{1} x_{t-1}-\varphi_{2} x_{t-2}-\cdots-\varphi_{p} x_{t-p}=a_{t}$
式(1)中:p为模型阶数;φ1,φ2,…,φp为各阶项待定系数,该模型即为AR(p)模型。
AR模型的构建过程即为求解式(1)中各模型参数的过程,具体可分为两步,分别为求解模型阶数的模型定阶过程和求解各阶项系数的参数估计过程,然后采用滑动窗口的形式将长度为p的运动时历依次从整体时历中分离,输入到AR模型中进行求解预报。
长短期记忆网络模型(LSTM)是建立在传统循环神经网络(recurrent neural network, RNN)基础之上的一种新型网络模型[18]。LSTM引入了门控单元来控制信息的流动,通过门的连接在输入、反馈和防止梯度爆炸之间建立时滞,在记忆单元内部强制性的保持一个持续误差流,最终保证梯度既不爆发也不消失,有效改善深度学习网络的记忆能力。单个LSTM神经元内部网络结构如图1所示。
LSTM模型中一共有3种类型门控,分别为输入门、遗忘门和输出门。其中遗忘门用于决定神经元之间在传递信息的过程中是否要保留信息,输入门用于计算有多少新信息添加到当前的细胞状态中。首先该部分将前一层隐藏状态的信息和当前输入信息传递至激活函数,之后以此来计算需要更
新的信息。输出门用于决定当前神经元的输出值。首先通过激活函数决定输出单元的哪个部分,之后通过前一层的隐藏状态选择细胞状态,并将其与激活函数的输出相乘。整体计算过程为
$ \boldsymbol{f}_{t}=\sigma\left(\boldsymbol{W}_{\mathrm{f}}\left[\boldsymbol{x}_{t}, \boldsymbol{h}_{t-1}\right]+\boldsymbol{b}_{\mathrm{f}}\right)$
$ \boldsymbol{i}_{t}=\sigma\left(\boldsymbol{W}_{\mathrm{i}}\left[\boldsymbol{x}_{t}, \boldsymbol{h}_{t-1}\right]+\boldsymbol{b}_{\mathrm{i}}\right)$
$ \boldsymbol{C}_{t}=\tanh \left(\boldsymbol{W}_{\mathrm{c}}\left[\boldsymbol{x}_{t}, \boldsymbol{h}_{t-1}\right]+\boldsymbol{b}_{\mathrm{c}}\right)$
$ C_{t}=f_{t} C_{t-1}+i_{t} C_{t}$
$ \boldsymbol{o}_{t}=\sigma\left(\boldsymbol{W}_{\mathrm{o}}\left[\boldsymbol{x}_{t}, \boldsymbol{h}_{t-1}\right]+\boldsymbol{b}_{\mathrm{o}}\right)$
$ \boldsymbol{h}_{t}=\boldsymbol{o}_{t} \tanh \boldsymbol{C}_{t}$
式中:ht-1为前一层神经元的输出;xt为输入向量;σ为sigmoid激活函数;WfWc 均为权值系数矩阵;bfbibc为偏置矩阵;Ct-1Ct分别为上一神经元与当前神经元的信息存储状态;Woot的系数矩阵;boot的偏置;ht为当前神经元的输出。
时域卷积网络(TCN)是由Bai等[19]提出的一种针对序列数据建模的深度学习神经网络。TCN是基于传统的一维卷积进行变形,使其成为一种更加适合时间序列预测、分类等任务的神经网络模型。在序列建模任务中,TCN模型通过残差连接和可分离卷积技术降低了梯度爆炸和梯度消失的可能性,同时模型内部可以共享权重,降低了模型的大小。
TCN模型主体由若干个残差模块串联组成,其中每个残差模块中包含2个膨胀因果卷积层、2个权重归一化层、2个激活函数(一般采用ReLU函数)、2个随机丢弃层和1个可选择的1×1卷积层,具体结构如图2所示。
TCN模型的核心为膨胀因果卷积模块,如图2所示。该层会对每个隐藏层的输入数据进行零填充(填充长度=卷积核长度-1),以确保各层输入与输出长度一致。之后根据设定的卷积核大小k和扩张率d对各层输入进行间隔采样和因果卷积。
通过间隔采样,TCN模型减小了在对长序列学习过程中的计算量,并且使得TCN具有指数级的感受野。因果卷积机制确保了未来的数据信息不会在模型训练过程中反向传递回到过去。
数据经过因果卷积后传递至权重归一化层,该层将权重向量w基于其欧氏范数和方向分解为参数向量v和参数标量g,之后通过计算损失函数,使用随机梯度下降(stochastic gradient descent,SGD)等优化方法更新vg
模型内部数据通过权重归一化后进入激活函数层,TCN模型中一般选取ReLU函数作为激活函数。
通过激活函数实现数据关系映射后,为避免模型过拟合,需要通过Dropout层按照一定的概率暂时舍弃一部分数据后更新隐藏层状态。
以NACA TN 2929飞机模型为例进行垂荡、横摇、纵摇三自由度运动时历仿真计算,开展水面目标物极短期运动预报方法研究。表1为NACA TN 2929飞机模型的主尺度信息。
数值仿真通过势流计算求解,基于PM谱(Pierson-Moskowitz spectrum,PM)生成不同海况下波浪仿真数据,结合NACA TN 2929飞机水动力特征对三自由度运动响应进行水动力仿真,最终求解NACA TN 2929飞机三自由度的运动有义值。
基于仿真运动时历数据开展对比分析研究,考虑水上飞机实际运动过程中存在的非线性特征,选取典型的中级5级海况,计算工况如表2所示。仿真数据总时长为36 000 s,时间间隔为0.5 s。其中垂荡、横摇、纵摇运动部分时历仿真结果如图3~图5所示。
在时间序列预测任务中,均方根误差(root mean squared error, RMSE)是最常用的性能指标之一,RMSE代表了实际值与预测值之间的平均误差大小,且对异常值不敏感,能更好地反映预测结果的稳定性和准确性。
为充分衡量模型在不同数据分布特征下的预报性能,基于RMSE计算结果定义了一种正则化的均方根误差(normalized root mean square error, NRMSE)作为相对误差衡量标准。通过同时评估绝对误差与相对误差可以较好地实现不同工况下整体时间序列预测精度评估。
$ \text { RMSE }=\sqrt{\frac{1}{m} \sum_{i=1}^{m}\left(y_{i}^{\text {pred }}-y_{i}^{\text {actu }}\right)^{2}}$
$ \text { NRMSE }=\frac{\sqrt{\frac{1}{m} \sum_{i=1}^{m}\left(y_{i}^{\text {pred }}-y_{i}^{\text {actu }}\right)^{2}}}{H_{\mathrm{s}}}$
式中: y i a c t u y i p r e d分别为每一时刻下的水面目标物的实际运动时历与时序模型预报的时历;m为该时序片段中包含的样本点数;Hs为该段时历的有义值。
分别基于AR模型、LSTM模型与TCN模型对水面目标物的垂荡、纵摇与横摇仿真时历开展预报效果对比分析。根据设定的历史输入步长与预报步长,采用滑动窗口的形式对整段运动时历进行片段分割,分别构建模型训练所需的输入输出矩阵,其中AR模型通过自回归计算实现迭代预报, 阶数p设置为40,相应的计算滑动窗口步长设置为240步,预报步长为40步。LSTM与TCN模型选取仿真数据的前30 000 s作为训练集,后6 000 s作为测试集,输入步长为240步,输出预报步长为40步,即采用历史的120 s运动时历预报未来20 s内的运动时历变化。
图6所示,由垂荡运动的预报结果中可以初步看出AR模型仅在提前预报时长较短(2 s)时,有相对较好的预报精度,随预报时长的增加AR模型的预报效果明显下降;而两种基于神经网络的预报模型能够对该水上飞机提前预报6 s运动进行准确预报。
为进一步探究三种模型的预报差异,对模型在三自由度运动提前预报12 s结果进行对比,如图7所示,在提前预报时长为12 s时,LSTM模型与TCN模型的预报效果明显优于AR模型,AR模型无法对水上飞机的三自由度运动进行准确预报。相对而言LSTM模型与TCN模型的预报时历曲线与实际曲线整体吻合度较好,对于幅值处的特征提取能力,在不同自由度运动的预报结果下,TCN模型预报效果略优于LSTM模型。
通过计算不同预报时长下的RMSE与NRMSE可定量衡量模型的预报性能,考虑到各模型是针对同一组数据开展的预报效果测试,预报时历的数据分布范围相同,因此相对误差NRMSE的变化趋势与绝对误差RMSE的变化趋势保持一致,如图8所示的RMSE计算结果为例展示不同预报时长下三种模型的预报性能,如表3所示以垂荡预报结果为例,展示了不同预报时长下的具体误差的计算结果。
图8表9可以看出,随着预报时间的增长,AR模型的预报误差急剧增大。当提前预报时长在2 s以内,即预报时长较短时,AR模型仅能对NACA TN 2929飞机的垂荡运动给出相对较好的预报效果,对于横摇和纵摇运动预报效果较差,随着预报时长的增加,AR模型的预报误差曲线变化速率明显高于深度学习模型,已不能给出准确的预报结果。
LSTM模型与TCN模型的RMSE变化趋势基本保持一致,在提前预报时长小于3 s时,误差略有增加,在4~20 s提前预报时长范围内误差趋于稳定,预报时历和真实时历曲线吻合度较高。每个提前预报时长下的LSTM模型和TCN模型在不同自由度运动下预报误差仅在较小范围内略有波动。从整体误差分布来看,基于深度学习构建的预报模型的预报性能要优于传统的时序预报模型。
以NACA TN 2929飞机运动仿真数据为例,基于构建的三种水面目标物运动预报模型,对海浪中水上飞机的运动极短期预报方法及适用性开展研究,得出如下结论。
(1) AR模型在三自由度下的预报误差均较大,提前预报时长为12 s时,垂荡、横摇、纵摇对应的均方根误差分别为1.289 m、3.697°、3.900°,预报结果的幅值与相位存在较大差异,预报结果不能满足工程需求。这主要是因为AR模型采用的是迭代预报的方式,时间序列数据间的时序相关性会随着预报时长变长而减小,从而严重影响AR模型的预报效果。
(2) 基于深度学习构建的LSTM和TCN模型的能够实现对NACA TN 2929飞机的垂荡、横摇和纵摇运动十秒级的准确预报,可满足其在极短期内起飞与降落的需求。其中TCN模型的预报性能略优于LSTM模型,在提前预报时长为12 s时,TCN模型预报的垂荡、横摇、纵摇运动对应的均方根误差分别为0.074 m、0.172°、0.256°,预报效果明显优于AR模型,原因是在中高海况下水上飞机的运动时历包含明显的非线性特征,深度学习的时序预报方法具有较强的非线性拟合能力与时序特征提取能力,而AR模型的构建基于线性理论,对于非线性时间序列的预报能力较差。
通过对目前典型的3种时序预报模型进行构建和结果对比,验证了基于神经网络构建的预报模型更适用于水上飞机运动预报算法的研究,可为进一步开展更加精确的水上飞机极短期预报方法的选取提供理论参考价值。
  • 中国科协青年人才托举工程(YESS20220013)
参考文献 引证文献
排序方式:
[1]
胡开业, 南春, 石林飞, 等. 水陆两栖飞机规则波中滑行运动数值仿真研究[J]. 中国造船, 2020, 61(S2): 254-261.
Hu Kaiye, Nan Chun, Shi Linfei, et al. Numerical simulation research on planing motion of amphibious aircraft in regular waves[J]. Shipbuilding of China, 2020, 61(S2): 254-261.
[2]
张永杰, 崔博, 王明振, 等. 水陆两栖飞机着水试验与理论分析方法研究进展[J]. 航空学报, 2023, 44(21): 528665-528665.
Zhang Yongjie, Cui Bo, Wang Mingzhen, et al. Research progress of amphibious aircraft water landing test and theoretical analysis methods[J]. Acta Aeronautica et Astronautica Sinica, 2023, 44(21): 528665-528665.
[3]
张杜文, 李新颖, 吴彬, 等. 水陆两栖飞机全机模型静水滑行水动性能预报[J]. 科学技术与工程, 2024, 24(6): 2581-2589.
Zhang Duwen, Li Xinying, Wu Bin, et al. Hydrodynamic performance prediction of full-aircraft model of amphibious hydroplane[J]. Science Technology and Engineering, 2024, 24(6): 2581-2589.
[4]
胡奇, 吴彬, 王明振, 等. 水陆两栖飞机静水滑行特性仿真分析[C]// 第十一届全国流体力学学术会议论文摘要集. 深圳: 中国力学学会流体力学专业委员会, 2020: 380.
HuQi, WuBin, WangMingzhen, et al. Simulation analysis of hydro static sliding characteristics of amphibious aircraft[C]// Abstracts of the 11th National Conference on Fluid Mechanics. Shenzhen: Chinese Society of Theoretical and Applied Mechanics Fluid Mechanics Professional Committee, 2020: 380.
[5]
胡开业, 石林飞, 周辉, 等. 基于计算流体动力学方法的两栖飞机规则波中运动特性研究[J]. 哈尔滨工程大学学报, 2024, 45(1): 44-52.
Hu Kaiye, Shi Linfei, Zhou Hui, et al. Research on the take-off motion characteristics of amphibious aircraft in regular waves based on the computational fluid dynamics method[J]. Journal of Harbin Engineering University, 2024, 45(1): 44-52.
[6]
黄礼敏. 海浪中非平稳非线性舰船运动在线预报研究[D]. 哈尔滨: 哈尔滨工程大学, 2016.
Huang Limin. On-line prediction of non-stationary and nonlinear ship motions at sea[D]. Harbin: Harbin Engineering University, 2016.
[7]
彭秀艳, 刘长德. 基于格型递归最小二乘算法的船舶运动极短期预报[J]. 船舶力学, 2012, 16(S1): 44-51.
Peng Xiuyan, Liu Changde. Extreme short time prediction of ship motion based on lattice recursive least square[J]. Journal of Ship Mechanics, 2012, 16(S1): 44-51.
[8]
Wang W, Li M. A short-time prediction method of ship motion attitude based on EEMD-LSSVM[J]. International Journal of Science, 2020, 7: 66-74.
[9]
Fu H, Gu Z, Wang Y. Ship pitch prediction based on Bi-ConvLSTM-CA model[J]. Journal of Marine Science and Engineering, 2022, 10(7): 840.
[10]
Wei Y, Chen Z, Zhao C, et al. A time-varying ensemble model for ship motion prediction based on feature selection and clustering methods[J]. Ocean Engineering, 2023, 270. DOI: 10.1016/j.oceaneng.2023.113659.
[11]
Gao N, Hu A, Hou L, et al. Real-time ship motion prediction based on adaptive wavelet transform and dynamic neural network[J]. Ocean Engineering, 2023, 280. DOI: 10.1016/j.oceaneng.2023.114466.
[12]
刘煜城. 基于深度学习的船舶运动极短期预报方法研究[D]. 哈尔滨: 哈尔滨工程大学, 2019.
Liu Yucheng. Research on short-term forecasting method of ship motion based on deep learning[D]. Harbin: Harbin Engineering University, 2019.
[13]
刘长德, 顾宇翔, 张进丰. 基于小波滤波和LSTM神经网络的船舶运动极短期预报研究[J]. 船舶力学, 2021, 25(3): 299-310.
Liu Changde, Gu Yuxiang, Zhang Jinfeng. Extreme short-term prediction of ship motions based on wavelet filter and LSTM neural network[J]. Journal of Ship Mechanics, 2021, 25(3): 299-310.
[14]
易文海, 高志亮. 基于LSTM神经网络的随机横浪中船舶横摇运动极短期预报[J]. 武汉理工大学学报(交通科学与工程版), 2021, 45(6): 1113-1117.
Yi Wenhai, Gao Zhiliang. Very short-term prediction of ship rolling motion in random transverse waves based on LSTM neural network[J]. Journal of Wuhan University of Technology(Transportation Science & Engineering Edition), 2021, 45(6): 1113-1117.
[15]
Hou X, Xia S. Short-term prediction of ship roll motion in waves based on convolutional neural network[J]. Journal of Marine Science and Engineering, 2024, 12(1).DOI: 10.3390/jmse12010102.
[16]
杨冰华. 基于深度学习的船舶运动姿态极短期预报研究[D]. 镇江: 江苏科技大学, 2022.
Yang Binghua. Research on very short-term prediction of ship motion attitude based on deep learning[D]. Zhenjiang: Jiangsu University of Science and Technology, 2022.
[17]
薛兴. 船舶运动极短期预报研究[D]. 大连: 大连海事大学, 2022.
Xue Xing. Research on extreme short-term prediction of ship motions[D]. Dalian: Dalian Maritime University, 2022.
[18]
Y, Duan Y, Kang W, et al. Traffic flow prediction with big data: a deep learning approach[J]. Intelligent Transportation Systems, IEEE Transactionson, 2015, 16(2): 865-873.
[19]
Bai S, Kolter J Z, Koltun V. An empirical evaluation of generic convolutional and recurrent networks for sequence modeling[J]. arXiv preprint arXiv: 1803. 01271, 2018.
2025年第25卷第18期
PDF下载
213
99
引用本文
BibTeX
文章信息
doi: 10.12404/j.issn.1671-1815.2404967
  • 接收时间:2024-07-03
  • 首发时间:2025-12-17
  • 出版时间:2025-06-28
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2024-07-03
  • 修回日期:2025-03-19
基金
中国科协青年人才托举工程(YESS20220013)
作者信息
    1 哈尔滨工程大学青岛创新发展基地, 青岛 266000
    2 空装驻西安地区第五军事代表室, 西安 710000
    3 中航工业西安飞行自动控制研究所, 西安 710076

通讯作者:

* 宫珏(1995—),女,汉族,辽宁庄河人,硕士,工程师。研究方向:系统对准、组合导航及完好性。E-mail:
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/kxjsygc/CN/10.12404/j.issn.1671-1815.2404967
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