Article(id=1243306061613089698, tenantId=1146029695717560320, journalId=1240685776644648972, issueId=1243306060832944396, articleNumber=null, orderNo=null, doi=10.3969/j.issn.1007-7294.2025.03.001, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1726329600000, receivedDateStr=2024-09-15, revisedDate=null, revisedDateStr=null, acceptedDate=null, acceptedDateStr=null, onlineDate=1774356864597, onlineDateStr=2026-03-24, pubDate=1742400000000, pubDateStr=2025-03-20, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1774356864597, onlineIssueDateStr=2026-03-24, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1774356864597, creator=13701087609, updateTime=1774356864597, updator=13701087609, issue=Issue{id=1243306060832944396, tenantId=1146029695717560320, journalId=1240685776644648972, year='2025', volume='29', issue='3', pageStart='337', pageEnd='516', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=0, createTime=1774356864412, creator=13701087609, updateTime=1774357001622, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1243306636396310539, tenantId=1146029695717560320, journalId=1240685776644648972, issueId=1243306060832944396, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1243306636396310540, tenantId=1146029695717560320, journalId=1240685776644648972, issueId=1243306060832944396, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=337, endPage=350, ext={EN=ArticleExt(id=1243306061864747940, articleId=1243306061613089698, tenantId=1146029695717560320, journalId=1240685776644648972, language=EN, title=Rapid prediction of ship motion and load based on GRU neural network, columnId=1241023037940748650, journalTitle=Journal of Ship Mechanics, columnName=Hydrodynamics, runingTitle=null, highlight=null, articleAbstract=

In this paper, a fast prediction model was established for ship motion and load based on Gated Recurrent Neural Networks (GRU). GRU neural network is a concise and efficient recurrent neural network that captures the temporal information of training samples to establish a model for predicting unknown samples. The forecast model consisted of two independent GRU neural networks used to predict ship motion and load respectively. The historical ship pitch and heave data were jointly used as the input of the motion prediction model to predict the ship pitch and heave in the next few seconds. The motion prediction results were used as the input of the load prediction model to achieve the prediction of the vertical bending moment in the midship. The method was validated through model test data, and the results showed that the prediction results at different lead times were in good agreement with the test results in terms of amplitude and phase, verifying the feasibility of the established ship motion and load prediction model.

, 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=Pei-qiao ZHU, Jun DING, Yan-chao GENG, Yi-ming QIANG), CN=ArticleExt(id=1243306075093582248, articleId=1243306061613089698, tenantId=1146029695717560320, journalId=1240685776644648972, language=CN, title=基于GRU模型的船舶运动与载荷快速预报研究, columnId=1241023038087549292, journalTitle=船舶力学, columnName=流体力学, runingTitle=null, highlight=null, articleAbstract=

本文基于门控神经网络(GRU)建立船舶运动与载荷快速预报模型,GRU神经网络是一种简洁高效的循环神经网络,通过捕捉训练样本的时序信息建立模型来预报未知样本。预报模型由两个独立的GRU神经网络组成,分别实现船舶运动与载荷的预报,将船舶纵摇和垂荡历史数据共同作为运动预报模型输入,预报得到未来数秒后的船舶纵摇和垂荡,并将运动预报结果作为载荷预报模型的输入,实现对船舯垂向弯矩的预报。通过模型试验数据对该方法进行验证,结果表明不同超前预报时间的预报结果与试验结果幅值和相位吻合较好,验证了所建立的船舶运动与载荷预报模型的可行性。

, correspAuthors=null, authorNote=null, correspAuthorsNote=
通讯作者,E-mail:
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=M0m0y8OZkW/AoOcAJmC2vQ==, magXml=cMDNz+p1A6eZFZRIkwzeKA==, pdfUrl=null, pdf=jd5ivcuah0ogSrkiltNXKA==, pdfFileSize=3538411, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=SEyDZjSpcYr4C/ZRJSUEpA==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=WrTzmstWYk/ToVWbvELJjw==, mapNumber=null, authorCompany=null, fund=null, authors=

朱沛樵(2000-),男,硕士,通讯作者,E-mail:

丁军(1986-),男,博士,研究员。

, authorsList=朱沛樵, 丁军, 耿彦超, 强以铭)}, authors=[Author(id=1243306075542372796, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=zpq17359991753@163.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1243306075647230403, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, authorId=1243306075542372796, language=EN, stringName=Pei-qiao ZHU, firstName=Pei-qiao, middleName=null, lastName=ZHU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=China Ship Scientific Research Center, Wuxi 214082, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1243306075777253836, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, authorId=1243306075542372796, language=CN, stringName=朱沛樵, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=中国船舶科学研究中心,江苏 无锡 214082, bio={"content":"

朱沛樵(2000-),男,硕士,通讯作者,E-mail:

"}, bioImg=null, bioContent=

朱沛樵(2000-),男,硕士,通讯作者,E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1243306075399766448, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, xref=null, ext=[AuthorCompanyExt(id=1243306075408155057, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, companyId=1243306075399766448, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=China Ship Scientific Research Center, Wuxi 214082, China), AuthorCompanyExt(id=1243306075412349362, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, companyId=1243306075399766448, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=中国船舶科学研究中心,江苏 无锡 214082)])]), Author(id=1243306075882111445, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, 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=1243306076020523484, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, authorId=1243306075882111445, language=EN, stringName=Jun DING, firstName=Jun, middleName=null, lastName=DING, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=China Ship Scientific Research Center, Wuxi 214082, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1243306076108603873, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, authorId=1243306075882111445, language=CN, stringName=丁军, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=中国船舶科学研究中心,江苏 无锡 214082, bio={"content":"

丁军(1986-),男,博士,研究员。

"}, bioImg=null, bioContent=

丁军(1986-),男,博士,研究员。

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1243306075399766448, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, xref=null, ext=[AuthorCompanyExt(id=1243306075408155057, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, companyId=1243306075399766448, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=China Ship Scientific Research Center, Wuxi 214082, China), AuthorCompanyExt(id=1243306075412349362, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, companyId=1243306075399766448, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=中国船舶科学研究中心,江苏 无锡 214082)])]), Author(id=1243306076221850088, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, 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=1243306076339290603, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, authorId=1243306076221850088, language=EN, stringName=Yan-chao GENG, firstName=Yan-chao, middleName=null, lastName=GENG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=China Ship Scientific Research Center, Wuxi 214082, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1243306076427370994, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, authorId=1243306076221850088, language=CN, stringName=耿彦超, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=中国船舶科学研究中心,江苏 无锡 214082, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1243306075399766448, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, xref=null, ext=[AuthorCompanyExt(id=1243306075408155057, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, companyId=1243306075399766448, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=China Ship Scientific Research Center, Wuxi 214082, China), AuthorCompanyExt(id=1243306075412349362, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, companyId=1243306075399766448, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=中国船舶科学研究中心,江苏 无锡 214082)])]), Author(id=1243306076507062776, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1243306076620308993, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, authorId=1243306076507062776, language=EN, stringName=Yi-ming QIANG, firstName=Yi-ming, middleName=null, lastName=QIANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=China Ship Scientific Research Center, Wuxi 214082, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1243306076704195078, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, authorId=1243306076507062776, language=CN, stringName=强以铭, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=中国船舶科学研究中心,江苏 无锡 214082, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1243306075399766448, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, xref=null, ext=[AuthorCompanyExt(id=1243306075408155057, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, companyId=1243306075399766448, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=China Ship Scientific Research Center, Wuxi 214082, China), AuthorCompanyExt(id=1243306075412349362, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, companyId=1243306075399766448, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=中国船舶科学研究中心,江苏 无锡 214082)])])], keywords=[Keyword(id=1243306076821635594, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, language=EN, orderNo=1, keyword=GRU neural network), Keyword(id=1243306076913910289, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, language=EN, orderNo=2, keyword=ship movement), Keyword(id=1243306077018767894, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, language=EN, orderNo=3, keyword=wave load), Keyword(id=1243306077106848282, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, language=CN, orderNo=1, keyword=GRU神经网络), Keyword(id=1243306077203317278, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, language=CN, orderNo=2, keyword=船舶运动), Keyword(id=1243306077299786276, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, language=CN, orderNo=3, keyword=波浪载荷)], refs=[Reference(id=1243306084073587437, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, doi=null, pmid=null, pmcid=null, year=1983, volume=8, issue=1, pageStart=9, pageEnd=20, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=Triantafyllou M S, Bodson M, Athans M, journalName=IEEE Journal of Oceanic Engineering, refType=null, unstructuredReference=Triantafyllou M S, Bodson M, Athans M. Real time estimation of ship motions using Kalman filtering techniques[J]. IEEE Journal of Oceanic Engineering, 1983, 8(1): 9-20., articleTitle=Real time estimation of ship motions using Kalman filtering techniques, refAbstract=null), Reference(id=1243306084182639344, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, doi=null, pmid=null, pmcid=null, year=2003, volume=null, issue=4, pageStart=52, pageEnd=55+60, url=null, language=null, rfNumber=[2], rfOrder=1, authorNames=赵源, 滕大予, journalName=现代防御技术, refType=null, unstructuredReference=赵源,滕大予. 多维AR(p)模型在预报舰船运动中的应用[J]. 现代防御技术2003(4):52-55+60., articleTitle=多维AR(p)模型在预报舰船运动中的应用, refAbstract=null), Reference(id=1243306084258136819, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, doi=null, pmid=null, pmcid=null, year=2003, volume=null, issue=4, pageStart=52, pageEnd=55+60, url=null, language=null, rfNumber=[2], rfOrder=2, authorNames=Zhao Y, Teng D Y, journalName=Modern Defence Technology, refType=null, unstructuredReference=Zhao Y, Teng D Y. Application of multidimensional AR(p) model in forecasting the state of ship movement[J]. Modern Defence Technology, 2003(4): 52-55+60. (in Chinese), articleTitle=Application of multidimensional AR(p) model in forecasting the state of ship movement, refAbstract=null), Reference(id=1243306084329439990, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, doi=null, pmid=null, pmcid=null, year=1988, volume=null, issue=3, pageStart=85, pageEnd=88, url=null, language=null, rfNumber=[3], rfOrder=3, authorNames=虞兰生, 戴遗山, journalName=中国造船, refType=null, unstructuredReference=虞兰生,戴遗山. 船舶运动的自适应预报[J]. 中国造船1988(3):85-88., articleTitle=船舶运动的自适应预报, refAbstract=null), Reference(id=1243306084417520378, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, doi=null, pmid=null, pmcid=null, year=1988, volume=null, issue=3, pageStart=85, pageEnd=88, url=null, language=null, rfNumber=[3], rfOrder=4, authorNames=Yu L S, Dai Y S, journalName=Shipbuilding of China, refType=null, unstructuredReference=Yu L S, Dai Y S. Adaptive prediction of ship motion[J]. Shipbuilding of China, 1988(3): 85-88. (in Chinese), articleTitle=Adaptive prediction of ship motion, refAbstract=null), Reference(id=1243306085919081216, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, doi=null, pmid=null, pmcid=null, year=2005, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[4], rfOrder=5, authorNames=Khan A, Bil C, Marion K E, journalName=null, refType=null, unstructuredReference=Khan A, Bil C, Marion K E. Theory and application of artificial neural networks for the real time prediction of ship motion[C]//9th International Conference on Knowledge-based Intelligent Information and Engineering Systems, 2005., articleTitle=Theory and application of artificial neural networks for the real time prediction of ship motion, refAbstract=null), Reference(id=1243306086019744513, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, doi=null, pmid=null, pmcid=null, year=2013, volume=17, issue=10, pageStart=1147, pageEnd=1152, url=null, language=null, rfNumber=[5], rfOrder=6, authorNames=顾民, 刘长德, 张进丰, journalName=船舶力学, refType=null, unstructuredReference=顾民,刘长德,张进丰. 基于混沌理论与RBF神经网络的船舶运动极短期预报研究[J]. 船舶力学2013, 17(10):1147-1152., articleTitle=基于混沌理论与RBF神经网络的船舶运动极短期预报研究, refAbstract=null), Reference(id=1243306086120407812, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, doi=null, pmid=null, pmcid=null, year=2013, volume=17, issue=10, pageStart=1147, pageEnd=1152, url=null, language=null, rfNumber=[5], rfOrder=7, authorNames=Gu M, Liu C D, Zhang J F, journalName=Journal of Ship Mechanics, refType=null, unstructuredReference=Gu M, Liu C D, Zhang J F. Extreme short-term prediction of ship motion based on chaotic theory and RBF neural network[J]. Journal of Ship Mechanics, 2013, 17(10): 1147-1152. (in Chinese), articleTitle=Extreme short-term prediction of ship motion based on chaotic theory and RBF neural network, refAbstract=null), Reference(id=1243306086263014154, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, doi=null, pmid=null, pmcid=null, year=2012, volume=190-191, issue=null, pageStart=724, pageEnd=728, url=null, language=null, rfNumber=[6], rfOrder=8, authorNames=Wang Y C, Liu F M, Fu H X, journalName=Applied Mechanics and Materials, refType=null, unstructuredReference=Wang Y C, Liu F M, Fu H X. Ship rolling motion prediction based on wavelet neural network[J]. Applied Mechanics and Materials, 2012, 190-191:724-728., articleTitle=Ship rolling motion prediction based on wavelet neural network, refAbstract=null), Reference(id=1243306086363677453, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, doi=null, pmid=null, pmcid=null, year=2019, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[7], rfOrder=9, authorNames=黄柏刚, journalName=null, refType=null, unstructuredReference=黄柏刚. 基于小波神经网络的波浪中船舶运动在线建模与预报研究[D]. 上海:上海交通大学,2019., articleTitle=基于小波神经网络的波浪中船舶运动在线建模与预报研究, refAbstract=null), Reference(id=1243306086569198354, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, doi=null, pmid=null, pmcid=null, year=2019, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[7], rfOrder=10, authorNames=Huang B G, journalName=null, refType=null, unstructuredReference=Huang B G. Online modeling and predicting of ship motions in waves based on wavelet neural network[D]. Shanghai: Shanghai Jiao Tong University, 2019. (in Chinese), articleTitle=Online modeling and predicting of ship motions in waves based on wavelet neural network, refAbstract=null), Reference(id=1243306086686638869, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, doi=null, pmid=null, pmcid=null, year=2021, volume=477, issue=2245, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[8], rfOrder=11, authorNames=del Águila Ferrandis J, Triantafyllou M S, Chryssostomidis C, Karniadakis G E, journalName=Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences, refType=null, unstructuredReference=del Águila Ferrandis J, Triantafyllou M S, Chryssostomidis C, Karniadakis G E. Learning functionals via LSTM neural networks for predicting vessel dynamics in extreme sea states[J]. Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences, 2021, 477(2245): 20190897., articleTitle=Learning functionals via LSTM neural networks for predicting vessel dynamics in extreme sea states, refAbstract=null), Reference(id=1243306086762136343, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, doi=null, pmid=null, pmcid=null, year=2021, volume=25, issue=3, pageStart=299, pageEnd=310, url=null, language=null, rfNumber=[9], rfOrder=12, 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=1243306086871188251, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, doi=null, pmid=null, pmcid=null, year=2021, volume=25, issue=3, pageStart=299, pageEnd=310, url=null, language=null, rfNumber=[9], rfOrder=13, authorNames=Liu C D, Gu Y X, Zhang J F, journalName=Journal of Ship Mechanics, refType=null, unstructuredReference=Liu C D, Gu Y X, Zhang J F. 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. (in Chinese), articleTitle=Extreme short-term prediction of ship motions based on wavelet filter and LSTM neural network, refAbstract=null), Reference(id=1243306086950880031, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, doi=null, pmid=null, pmcid=null, year=2021, volume=9, issue=4, pageStart=387, pageEnd=null, url=null, language=null, rfNumber=[10], rfOrder=14, authorNames=Wang Y C, Wang H, Zou D X, journalName=Journal of Marine Science and Engineering, refType=null, unstructuredReference=Wang Y C, Wang H, Zou D X, et al. Ship roll prediction algorithm based on Bi-LSTM-TPA combined model[J]. Journal of Marine Science and Engineering, 2021, 9(4): 387., articleTitle=Ship roll prediction algorithm based on Bi-LSTM-TPA combined model, refAbstract=null), Reference(id=1243306087122846500, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, doi=null, pmid=null, pmcid=null, year=2022, volume=114, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[11], rfOrder=15, authorNames=Li M W, Xu D Y, Geng J, journalName=Applied Soft Computing, refType=null, unstructuredReference=Li M W, Xu D Y, Geng J, et al. A hybrid approach for forecasting ship motion using CNN-GRU-AM and GCWOA[J]. Applied Soft Computing, 2022, 114:108084., articleTitle=A hybrid approach for forecasting ship motion using CNN-GRU-AM and GCWOA, refAbstract=null), Reference(id=1243306087223509800, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, doi=null, pmid=null, pmcid=null, year=2023, volume=272, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[12], rfOrder=16, authorNames=Zhang B, Wang S, Deng L W, journalName=Ocean Engineering, refType=null, unstructuredReference=Zhang B, Wang S, Deng L W, et al. Ship motion attitude prediction model based on IWOA-TCN-attention[J]. Ocean Engineering, 2023, 272:113911., articleTitle=Ship motion attitude prediction model based on IWOA-TCN-attention, refAbstract=null), Reference(id=1243306087307395882, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, doi=null, pmid=null, pmcid=null, year=2014, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[13], rfOrder=17, authorNames=Chung J, Gulcehre C, Cho K H, Bengio Y, journalName=Arxiv, refType=null, unstructuredReference=Chung J, Gulcehre C, Cho K H, Bengio Y. Empirical evaluation of gated recurrent neural networks on sequence modeling[J]. Eprint Arxiv, 2014:1412.3555., articleTitle=Empirical evaluation of gated recurrent neural networks on sequence modeling, refAbstract=null)], funds=[Fund(id=1243306083960341223, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, awardId=2022YFB3306200, language=CN, fundingSource=国家重点研发计划资助项目(2022YFB3306200), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1243306075399766448, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, xref=null, ext=[AuthorCompanyExt(id=1243306075408155057, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, companyId=1243306075399766448, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=China Ship Scientific Research Center, Wuxi 214082, China), AuthorCompanyExt(id=1243306075412349362, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, companyId=1243306075399766448, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=中国船舶科学研究中心,江苏 无锡 214082)])], figs=[ArticleFig(id=1243306077459169835, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, language=EN, label=Fig.1, caption=GRU unit structure, figureFileSmall=S3KZuul/D1AI8iHVugTKqQ==, figureFileBig=SEyDZjSpcYr4C/ZRJSUEpA==, tableContent=null), ArticleFig(id=1243306077568221745, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, language=CN, label=图1, caption=GRU门控单元结构图, figureFileSmall=S3KZuul/D1AI8iHVugTKqQ==, figureFileBig=SEyDZjSpcYr4C/ZRJSUEpA==, tableContent=null), ArticleFig(id=1243306077761159737, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, language=EN, label=Fig.2, caption=Flowchart of ship motion and load forecasting, figureFileSmall=NJ8n/Gh0d/yEcLM8XjJQfw==, figureFileBig=3o+WoleU/+xygH8aP9dhmQ==, tableContent=null), ArticleFig(id=1243306077849240126, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, language=CN, label=图2, caption=船舶运动与载荷预报流程图, figureFileSmall=NJ8n/Gh0d/yEcLM8XjJQfw==, figureFileBig=3o+WoleU/+xygH8aP9dhmQ==, tableContent=null), ArticleFig(id=1243306077958292036, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, language=EN, label=Fig.3, caption=Variation of prediction errors versus advance prediction time for heave and pitch in Case 1, figureFileSmall=kMon2VGb23WtBbIVOKutWQ==, figureFileBig=H+v+tW9H25TM/8WGaXifyg==, tableContent=null), ArticleFig(id=1243306078063149641, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, language=CN, label=图3, caption=工况1垂荡、纵摇预报误差随超前预报时间变化, figureFileSmall=kMon2VGb23WtBbIVOKutWQ==, figureFileBig=H+v+tW9H25TM/8WGaXifyg==, tableContent=null), ArticleFig(id=1243306078180590157, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, language=EN, label=Fig.4, caption=Variation of prediction errors versus advance prediction time for heave and pitch in Case 2, figureFileSmall=ciAXM45VOEClAtZM2FXyVA==, figureFileBig=fZR3P6qYrV4XOcIrD3E9Tg==, tableContent=null), ArticleFig(id=1243306078272864849, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, language=CN, label=图4, caption=工况2垂荡、纵摇预报误差随超前预报时间变化, figureFileSmall=ciAXM45VOEClAtZM2FXyVA==, figureFileBig=fZR3P6qYrV4XOcIrD3E9Tg==, tableContent=null), ArticleFig(id=1243306078520328791, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, language=EN, label=Fig.5, caption=Variation of prediction errors versus advance prediction time for heave and pitch in Case 3, figureFileSmall=Rqkf5ZvQj+1E+GzRR4JACw==, figureFileBig=a4JIHM17ghlqGvS35r+Mtg==, tableContent=null), ArticleFig(id=1243306078612603482, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, language=CN, label=图5, caption=工况3垂荡、纵摇指标随超前预报时间变化, figureFileSmall=Rqkf5ZvQj+1E+GzRR4JACw==, figureFileBig=a4JIHM17ghlqGvS35r+Mtg==, tableContent=null), ArticleFig(id=1243306078709072476, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, language=EN, label=Fig.6, caption=Comparison of time domain results between two prediction models with 2 s lead time in heave and pitch for Case 2, figureFileSmall=e7vK72RjbaZprVx6lpkzTw==, figureFileBig=XklnVdvrtD7KvcWkHR7ZCA==, tableContent=null), ArticleFig(id=1243306078767792735, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, language=CN, label=图6, caption=两种预报模型垂荡、纵摇超前2 s预报时域结果对比(以工况二为例), figureFileSmall=e7vK72RjbaZprVx6lpkzTw==, figureFileBig=XklnVdvrtD7KvcWkHR7ZCA==, tableContent=null), ArticleFig(id=1243306078851678818, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, language=EN, label=Fig.7, caption=Comparison of time domain results between two prediction models with 10 s lead time in heave and pitch for Case 2, figureFileSmall=jvKzPnBPLOX6oW11WerRIg==, figureFileBig=KA1JxzsTeuJEKR+TP6I1HQ==, tableContent=null), ArticleFig(id=1243306078943953510, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, language=CN, label=图7, caption=两种预报模型垂荡、纵摇超前10 s预报时域结果对比(以工况二为例), figureFileSmall=jvKzPnBPLOX6oW11WerRIg==, figureFileBig=KA1JxzsTeuJEKR+TP6I1HQ==, tableContent=null), ArticleFig(id=1243306079061394027, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, language=EN, label=Fig.8, caption=Variation of prediction errors of three models with advanced prediction time for heave and pitch (Case 2), figureFileSmall=BBrStYdicGTQMFEtnhz14Q==, figureFileBig=BV7+HZt5dbpnx3t545avaA==, tableContent=null), ArticleFig(id=1243306079178834545, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, language=CN, label=图8, caption=三种模型垂荡、纵摇预报误差随超前预报时间变化(以工况二为例), figureFileSmall=BBrStYdicGTQMFEtnhz14Q==, figureFileBig=BV7+HZt5dbpnx3t545avaA==, tableContent=null), ArticleFig(id=1243306079313052279, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, language=EN, label=Fig.9, caption=Comparison of time domain results among three prediction models with 10 s lead time in heave and pitch (Case 2), figureFileSmall=mn9EqjcAbSfSNz4QSts/lA==, figureFileBig=RUQkLZhI7I/AgYXsQ+gJEQ==, tableContent=null), ArticleFig(id=1243306079426298492, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, language=CN, label=图9, caption=三种模型垂荡、纵摇超前预报10 s时域结果对比(以工况二为例), figureFileSmall=mn9EqjcAbSfSNz4QSts/lA==, figureFileBig=RUQkLZhI7I/AgYXsQ+gJEQ==, tableContent=null), ArticleFig(id=1243306079489213055, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, language=EN, label=Fig.10, caption=Variation of prediction results of vertical bending moment in amidships with advance prediction time for Case 1 ~ Case 3, figureFileSmall=VmO5Cgk20N6P5nEVyEoGHQ==, figureFileBig=obxKtw2Vd/xiWgCgPvgD+A==, tableContent=null), ArticleFig(id=1243306079573099139, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, language=CN, label=图10, caption=工况1-3船舯垂向弯矩预报结果随超前预报时间的变化, figureFileSmall=VmO5Cgk20N6P5nEVyEoGHQ==, figureFileBig=obxKtw2Vd/xiWgCgPvgD+A==, tableContent=null), ArticleFig(id=1243306079656985222, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, language=EN, label=Fig.11, caption=Time domain prediction results of vertical bending moment in amidships (Case 2), figureFileSmall=0h7bDXIqSS7tEzBHaOruPA==, figureFileBig=UkEfbLy+vlna8txsgKOW4A==, tableContent=null), ArticleFig(id=1243306079849923211, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, language=CN, label=图11, caption=船舯垂向弯矩时域预报结果(以工况二为例), figureFileSmall=0h7bDXIqSS7tEzBHaOruPA==, figureFileBig=UkEfbLy+vlna8txsgKOW4A==, tableContent=null), ArticleFig(id=1243306079950586511, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, language=EN, label=Fig.12, caption=Schematic diagram of measuring beam layout and keel beam segmentation, figureFileSmall=b51WXJ51oYZaIsjRwLxylQ==, figureFileBig=klOgKJnNGRmuAQgORqgp5A==, tableContent=null), ArticleFig(id=1243306081456341651, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, language=CN, label=图12, caption=测量梁布置与龙骨梁分段示意图, figureFileSmall=b51WXJ51oYZaIsjRwLxylQ==, figureFileBig=klOgKJnNGRmuAQgORqgp5A==, tableContent=null), ArticleFig(id=1243306081527644824, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, language=EN, label=Fig.13, caption=Layout diagram of strain gauges on the measuring beam, figureFileSmall=RG0wuaTQQW/uHMB4L9Q3IA==, figureFileBig=mR0zB/YVr2GoR+8ixRDn+g==, tableContent=null), ArticleFig(id=1243306081628308123, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, language=CN, label=图13, caption=测量梁上应变片布置示意图, figureFileSmall=RG0wuaTQQW/uHMB4L9Q3IA==, figureFileBig=mR0zB/YVr2GoR+8ixRDn+g==, tableContent=null), ArticleFig(id=1243306081812857506, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, language=EN, label=Fig.14, caption=Variation of heave and pitch prediction errors with advanced prediction time, figureFileSmall=a1Jjxjf8q4CdzBVEoyJtrA==, figureFileBig=bUHMKes4amTSpogsfRYenw==, tableContent=null), ArticleFig(id=1243306081938686630, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, language=CN, label=图14, caption=垂荡、纵摇预报误差随超前预报时间变化, figureFileSmall=a1Jjxjf8q4CdzBVEoyJtrA==, figureFileBig=bUHMKes4amTSpogsfRYenw==, tableContent=null), ArticleFig(id=1243306082026767017, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, language=EN, label=Fig.15, caption=Time domain results of 2 s advance prediction for heave and pitch, figureFileSmall=hPRq7i3Ese2lHQKPViveGQ==, figureFileBig=vBhBc2R+8Do3fXYXI0UBuA==, tableContent=null), ArticleFig(id=1243306082119041707, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, language=CN, label=图15, caption=垂荡、纵摇超前预报2 s时域结果, figureFileSmall=hPRq7i3Ese2lHQKPViveGQ==, figureFileBig=vBhBc2R+8Do3fXYXI0UBuA==, tableContent=null), ArticleFig(id=1243306082223899310, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, language=EN, label=Fig.16, caption=Time domain results of 10 s advance prediction for heave and pitch, figureFileSmall=3Y5xQfz5xm7QMrJllfLGYA==, figureFileBig=hQWfNHiB7nIYRc65rcVaqg==, tableContent=null), ArticleFig(id=1243306082337145519, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, language=CN, label=图16, caption=垂荡、纵摇超前预报10s时域结果, figureFileSmall=3Y5xQfz5xm7QMrJllfLGYA==, figureFileBig=hQWfNHiB7nIYRc65rcVaqg==, tableContent=null), ArticleFig(id=1243306082442003122, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, language=EN, label=Fig.17, caption=Prediction error of vertical bending moment in amidships varying with advanced prediction time, figureFileSmall=Ny+P0OdD/oXSasvNs095WA==, figureFileBig=i2+xBwGLKL4YRMRrw8H5Lg==, tableContent=null), ArticleFig(id=1243306082534277815, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, language=CN, label=图17, caption=船舯垂向弯矩预报误差随超前预报时间变化, figureFileSmall=Ny+P0OdD/oXSasvNs095WA==, figureFileBig=i2+xBwGLKL4YRMRrw8H5Lg==, tableContent=null), ArticleFig(id=1243306082630746810, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, language=EN, label=Fig.18, caption=Time domain prediction results of vertical bending moment in amidships, figureFileSmall=DMfaplAraxlpWSmwerSUew==, figureFileBig=dTb5qxW5NEH/cO18ZzXdNA==, tableContent=null), ArticleFig(id=1243306082735604415, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, language=CN, label=图18, caption=船舯垂向弯矩时域预报结果, figureFileSmall=DMfaplAraxlpWSmwerSUew==, figureFileBig=dTb5qxW5NEH/cO18ZzXdNA==, tableContent=null), ArticleFig(id=1243306082857239235, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, language=EN, label=Tab.1, caption=

Ship principal dimensions

, figureFileSmall=null, figureFileBig=null, tableContent=
名称/单位数值
总长LOA/m179.40
型深H/m12.80
设计水线宽B/m20.60
设计吃水T/m6.5
设计排水量∇/t12 200.00
), ArticleFig(id=1243306082949513926, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, language=CN, label=表1, caption=

船舶主尺度

, figureFileSmall=null, figureFileBig=null, tableContent=
名称/单位数值
总长LOA/m179.40
型深H/m12.80
设计水线宽B/m20.60
设计吃水T/m6.5
设计排水量∇/t12 200.00
), ArticleFig(id=1243306083096314570, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, language=EN, label=Tab.2, caption=

Specific working condition parameters

, figureFileSmall=null, figureFileBig=null, tableContent=
工况编号有义波高Hs/m周期Tz/s浪向/°航速V/kn
工况一6618018
工况二96.513510
工况三147.518010
工况四6918010
), ArticleFig(id=1243306083205366477, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, language=CN, label=表2, caption=

具体工况参数

, figureFileSmall=null, figureFileBig=null, tableContent=
工况编号有义波高Hs/m周期Tz/s浪向/°航速V/kn
工况一6618018
工况二96.513510
工况三147.518010
工况四6918010
), ArticleFig(id=1243306083306029776, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, language=EN, label=Tab.3, caption=

Comparison of prediction errors for 10 s lead in heave and pitch with different inputs and outputs in Case 2

, figureFileSmall=null, figureFileBig=null, tableContent=
输入-输出船舶运动MAEMAPER2
单特征Heave0.41450.30430.6046
Pitch0.73610.27360.7899
多特征Heave0.34070.22790.7324
Pitch0.62580.21360.8514
), ArticleFig(id=1243306083410887380, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, language=CN, label=表3, caption=

工况2不同输入输出垂荡、纵摇超前10 s预报误差对比

, figureFileSmall=null, figureFileBig=null, tableContent=
输入-输出船舶运动MAEMAPER2
单特征Heave0.41450.30430.6046
Pitch0.73610.27360.7899
多特征Heave0.34070.22790.7324
Pitch0.62580.21360.8514
), ArticleFig(id=1243306083536716504, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, language=EN, label=Tab.4, caption=

Prediction results of heave for different models in Case 2

, figureFileSmall=null, figureFileBig=null, tableContent=
超前预报时间LSTMGRUTCN-AM
MAEMAPER2MAEMAPER2MAEMAPER2
2 s0.16930.10760.93410.13820.09710.95590.2060.15510.9014
4 s0.19990.13220.9060.19350.12420.91230.32260.22800.7587
6 s0.27430.20910.82370.23060.17560.87880.32930.26220.7493
8 s0.30970.21230.7780.27230.19710.82720.35690.27410.7076
10 s0.37170.23720.68520.34070.22790.73240.38770.27550.6598
), ArticleFig(id=1243306083658351323, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, language=CN, label=表4, caption=

工况2不同模型垂荡预报结果

, figureFileSmall=null, figureFileBig=null, tableContent=
超前预报时间LSTMGRUTCN-AM
MAEMAPER2MAEMAPER2MAEMAPER2
2 s0.16930.10760.93410.13820.09710.95590.2060.15510.9014
4 s0.19990.13220.9060.19350.12420.91230.32260.22800.7587
6 s0.27430.20910.82370.23060.17560.87880.32930.26220.7493
8 s0.30970.21230.7780.27230.19710.82720.35690.27410.7076
10 s0.37170.23720.68520.34070.22790.73240.38770.27550.6598
), ArticleFig(id=1243306083763208927, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, language=EN, label=Tab.5, caption=

Prediction results of pitch for different models in Case 2

, figureFileSmall=null, figureFileBig=null, tableContent=
超前预报时间LSTMGRUTCN-AM
MAEMAPER2MAEMAPER2MAEMAPER2
2 s0.27970.10790.96980.27050.09770.97060.31860.12230.9619
4 s0.3380.12120.95460.28710.11010.96750.42370.15370.9295
6 s0.49890.19830.90320.4440.18030.9250.6060.22240.8612
8 s0.58250.20130.87270.52570.19700.89530.66560.24950.8293
10 s0.69790.21710.8150.62580.21360.85140.68330.26510.8202
), ArticleFig(id=1243306083851289315, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306061613089698, language=CN, label=表5, caption=

不同模型纵摇预报结果

, figureFileSmall=null, figureFileBig=null, tableContent=
超前预报时间LSTMGRUTCN-AM
MAEMAPER2MAEMAPER2MAEMAPER2
2 s0.27970.10790.96980.27050.09770.97060.31860.12230.9619
4 s0.3380.12120.95460.28710.11010.96750.42370.15370.9295
6 s0.49890.19830.90320.4440.18030.9250.6060.22240.8612
8 s0.58250.20130.87270.52570.19700.89530.66560.24950.8293
10 s0.69790.21710.8150.62580.21360.85140.68330.26510.8202
)], attaches=null, journal=Journal(id=1240685663704625163, delFlag=0, nameCn=船舶力学, nameEn=Journal of Ship Mechanics, nameHistory1=null, nameHistory2=null, issn=1007-7294, eissn=null, cn=32-1468/U, coden=null, periodic=0, language=CN, oaType=null, 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=8VABIsgSw5I4HF/4goaIlA==, journalPrice=null, startedYear=null, abbrevIsoEn=Journal of Ship Mechanics, journalRemark=null, publicationField=null, createdTime=1773732113054, updatedTime=1773732336269, createdBy=18614031015, updatedBy=13701087609, firstLetterCn=J, firstLetterEn=J, subjectCode=Engineering, subjectName=null, subjectCodeEn=Engineering, subjectNameEn=null, picCn=8VABIsgSw5I4HF/4goaIlA==, picEn=Ve/8A/FRYceS/z8o7GCJ5g==, jcr=null, cjcr=null, exts=[JournalExt(id=1240686600003318325, language=CN, name=船舶力学, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1773732336283, updatedTime=1773732336283, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=https://cblx.cbpt.cnki.net/EditorD3N/index.aspx?t=1, submissionEditorUrl=https://cblx.cbpt.cnki.net/EditorD3N/index.aspx?t=3, submissionReviewUrl=https://cblx.cbpt.cnki.net/EditorD3N/index.aspx?t=2, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1240686600041067062, language=EN, name=Journal of Ship Mechanics, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1773732336292, updatedTime=1773732336292, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=https://cblx.cbpt.cnki.net/EditorD3N/index.aspx?t=1, submissionEditorUrl=https://cblx.cbpt.cnki.net/EditorD3N/index.aspx?t=3, submissionReviewUrl=https://cblx.cbpt.cnki.net/EditorD3N/index.aspx?t=2, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1240685776644648972, websiteList=[Website(id=1240686760611607145, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1240685776644648972, 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/cblx/CN, language=CN, createTime=1773732374576, createBy=18614031015, updateTime=1773732394922, updateBy=18614031015, name=船舶力学-中文, tplId=1146099689490845704, title=船舶力学, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1240687166741869216, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1240686760611607145, code=articleTextType, value=kx, createTime=1773732471404, updateTime=1773732471404, creator=18614031015, updator=18614031015), WebsiteProps(id=1240687166725091997, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1240686760611607145, code=banner, value=null, createTime=1773732471400, updateTime=1773732471400, creator=18614031015, updator=18614031015), WebsiteProps(id=1240687166758646435, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1240686760611607145, code=grayFlag, value=0, createTime=1773732471408, updateTime=1773732471408, creator=18614031015, updator=18614031015), WebsiteProps(id=1240687166716703388, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1240686760611607145, code=logo, value=https://castjournals.cast.org.cn/joweb/cblx/CN/file/pic?fileId=/ZVjg3ao2vf5wYxw5Kn1Uw==, createTime=1773732471398, updateTime=1773732471398, creator=18614031015, updator=18614031015), WebsiteProps(id=1240687166771229349, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1240686760611607145, code=minRunFlag, value=0, createTime=1773732471411, updateTime=1773732471411, creator=18614031015, updator=18614031015), WebsiteProps(id=1240687166737674911, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1240686760611607145, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/cblx/CN/file/pic, createTime=1773732471403, updateTime=1773732471403, creator=18614031015, updator=18614031015), WebsiteProps(id=1240687166767035044, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1240686760611607145, code=silenceFlag, value=0, createTime=1773732471410, updateTime=1773732471410, creator=18614031015, updator=18614031015), WebsiteProps(id=1240687166729286302, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1240686760611607145, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1773732471401, updateTime=1773732471401, creator=18614031015, updator=18614031015), WebsiteProps(id=1240687166750257825, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1240686760611607145, code=themeColor, value=null, createTime=1773732471406, updateTime=1773732471406, creator=18614031015, updator=18614031015), WebsiteProps(id=1240687166754452130, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1240686760611607145, code=themeStyle, value=null, createTime=1773732471407, updateTime=1773732471407, creator=18614031015, updator=18614031015)]), Website(id=1240686760674521707, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1240685776644648972, 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/cblx/EN, language=EN, createTime=1773732374590, createBy=18614031015, updateTime=1773732413338, updateBy=18614031015, name=船舶力学-英文, tplId=1146101810881728533, title=Journal of Ship Mechanics, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1240687194269078438, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1240686760674521707, code=articleTextType, value=kx, createTime=1773732477967, updateTime=1773732477967, creator=18614031015, updator=18614031015), WebsiteProps(id=1240687194248106915, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1240686760674521707, code=banner, value=null, createTime=1773732477962, updateTime=1773732477962, creator=18614031015, updator=18614031015), WebsiteProps(id=1240687194285855657, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1240686760674521707, code=grayFlag, value=0, createTime=1773732477971, updateTime=1773732477971, creator=18614031015, updator=18614031015), WebsiteProps(id=1240687194239718306, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1240686760674521707, code=logo, value=https://castjournals.cast.org.cn/joweb/cblx/EN/file/pic?fileId=/ZVjg3ao2vf5wYxw5Kn1Uw==, createTime=1773732477960, updateTime=1773732477960, creator=18614031015, updator=18614031015), WebsiteProps(id=1240687194302632875, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1240686760674521707, code=minRunFlag, value=0, createTime=1773732477975, updateTime=1773732477975, creator=18614031015, updator=18614031015), WebsiteProps(id=1240687194260689829, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1240686760674521707, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/cblx/EN/file/pic, createTime=1773732477965, updateTime=1773732477965, creator=18614031015, updator=18614031015), WebsiteProps(id=1240687194294244266, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1240686760674521707, code=silenceFlag, value=0, createTime=1773732477973, updateTime=1773732477973, creator=18614031015, updator=18614031015), WebsiteProps(id=1240687194256495524, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1240686760674521707, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_en_623/, createTime=1773732477964, updateTime=1773732477964, creator=18614031015, updator=18614031015), WebsiteProps(id=1240687194277467047, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1240686760674521707, code=themeColor, value=null, createTime=1773732477969, updateTime=1773732477969, creator=18614031015, updator=18614031015), WebsiteProps(id=1240687194281661352, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1240686760674521707, code=themeStyle, value=null, createTime=1773732477970, updateTime=1773732477970, creator=18614031015, updator=18614031015)])], journalTitle=船舶力学, weixinUrl=null, journalUrl=https://cblx.cbpt.cnki.net/, iacademicId=null, status=1, seqNo=null, journalTitleEn=Journal of Ship Mechanics, journalPhotoCn=8VABIsgSw5I4HF/4goaIlA==, journalPhotoEn=Ve/8A/FRYceS/z8o7GCJ5g==, journalFirstLetter=J, 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=, provinceCode=null, provinceName=null, collectFlag=false), detailUrlCn=https://castjournals.cast.org.cn/joweb/cblx/CN/10.3969/j.issn.1007-7294.2025.03.001, detailUrlEn=https://castjournals.cast.org.cn/joweb/cblx/EN/10.3969/j.issn.1007-7294.2025.03.001, pdfUrlCn=https://castjournals.cast.org.cn/joweb/cblx/CN/PDF/10.3969/j.issn.1007-7294.2025.03.001, pdfUrlEn=https://castjournals.cast.org.cn/joweb/cblx/EN/PDF/10.3969/j.issn.1007-7294.2025.03.001, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于GRU模型的船舶运动与载荷快速预报研究
收藏切换
PDF下载
朱沛樵 , 丁军 , 耿彦超 , 强以铭
船舶力学 | 流体力学 2025,29(3): 337-350
收起
收藏切换
船舶力学 | 流体力学 2025, 29(3): 337-350
基于GRU模型的船舶运动与载荷快速预报研究
全屏
朱沛樵 , 丁军, 耿彦超, 强以铭
作者信息
  • 中国船舶科学研究中心,江苏 无锡 214082
  • 朱沛樵(2000-),男,硕士,通讯作者,E-mail:

    丁军(1986-),男,博士,研究员。

通讯作者:

通讯作者,E-mail:
Rapid prediction of ship motion and load based on GRU neural network
Pei-qiao ZHU , Jun DING, Yan-chao GENG, Yi-ming QIANG
Affiliations
  • China Ship Scientific Research Center, Wuxi 214082, China
出版时间: 2025-03-20 doi: 10.3969/j.issn.1007-7294.2025.03.001
文章导航
收藏切换

本文基于门控神经网络(GRU)建立船舶运动与载荷快速预报模型,GRU神经网络是一种简洁高效的循环神经网络,通过捕捉训练样本的时序信息建立模型来预报未知样本。预报模型由两个独立的GRU神经网络组成,分别实现船舶运动与载荷的预报,将船舶纵摇和垂荡历史数据共同作为运动预报模型输入,预报得到未来数秒后的船舶纵摇和垂荡,并将运动预报结果作为载荷预报模型的输入,实现对船舯垂向弯矩的预报。通过模型试验数据对该方法进行验证,结果表明不同超前预报时间的预报结果与试验结果幅值和相位吻合较好,验证了所建立的船舶运动与载荷预报模型的可行性。

GRU神经网络  /  船舶运动  /  波浪载荷

In this paper, a fast prediction model was established for ship motion and load based on Gated Recurrent Neural Networks (GRU). GRU neural network is a concise and efficient recurrent neural network that captures the temporal information of training samples to establish a model for predicting unknown samples. The forecast model consisted of two independent GRU neural networks used to predict ship motion and load respectively. The historical ship pitch and heave data were jointly used as the input of the motion prediction model to predict the ship pitch and heave in the next few seconds. The motion prediction results were used as the input of the load prediction model to achieve the prediction of the vertical bending moment in the midship. The method was validated through model test data, and the results showed that the prediction results at different lead times were in good agreement with the test results in terms of amplitude and phase, verifying the feasibility of the established ship motion and load prediction model.

GRU neural network  /  ship movement  /  wave load
朱沛樵, 丁军, 耿彦超, 强以铭. 基于GRU模型的船舶运动与载荷快速预报研究. 船舶力学, 2025 , 29 (3) : 337 -350 . DOI: 10.3969/j.issn.1007-7294.2025.03.001
Pei-qiao ZHU, Jun DING, Yan-chao GENG, Yi-ming QIANG. Rapid prediction of ship motion and load based on GRU neural network[J]. Journal of Ship Mechanics, 2025 , 29 (3) : 337 -350 . DOI: 10.3969/j.issn.1007-7294.2025.03.001
船舶在波浪中航行时,其六自由度的摇荡运动会对船舶的航行安全和操纵作业造成极大危害,例如船舶之间的货物运输、舰载机起降、水下航行器回收等海上作业都对船舶的平稳性有着极高的要求。若能够通过技术手段,获取船舶未来十几秒后的运动幅值,进而对船舶运动进行补偿,这对于提高海上作业效率及安全具有重要意义。
国内外对于船舶运动的快速预报已展开了较多研究,最初学者们采用卡尔曼滤波[1]的方法来实现对船舶运动的预报,但是卡尔曼滤波必须知道系统的状态方程,这在实际船舶航行中是难以实现的。因此学者们将目标转移到了基于数据驱动的方法上,最初采用的就是时间序列分析的方法,该方法将船舶历史运动数据或者是艏前波高时历数据作为输入,采用AR(AutoRegressive)[2]模型或者ARMA(AutoRegressive Moving Average)[3]模型实现船舶运动的预报,但是时间序列分析法是一种线性模型,在处理复杂海况下的船舶运动时误差较大。
随着计算机技术的发展,深度学习技术在各个领域得到了广泛应用,在本世纪初,国内外学者应用深度学习的方法对船舶运动快速预报展开了研究。Khan等[4]使用奇异值分解和遗传算法训练神经网络,实现了对五级和六级海况下船舶横摇的预报;顾民等[5]利用相空间重构理论确定神经网络超参数,使用径向基函数网络(RBF)实现对顶浪船舶纵摇的预报;Wang等[6]、黄柏刚[7]使用小波神经网络对船舶横摇进行了预报,取得了比传统全连接网络更好的结果。但是,船舶运动预报是一个较为典型的时间序列预报问题,对于这一类问题,学者们倾向于使用循环神经网络(RNN)来解决,其中典型就是长短时记忆网络(LSTM)和门控神经网络(GRU)。Ferrandis等[8]使用LSTM网络对双体船和DTBM船在一级海况和八级海况下的纵摇和垂荡进行预报,证明了该方法的可行性;刘长德等[9]使用小波滤波和LSTM模型,实现了对船舶纵摇、垂荡和横摇的预报;Wang等[10]使用双向长短期记忆网络与时间自注意力机制相结合(Bi-LSTM-TPA),将船舶海上实测的横摇角、横摇加速度等运动数据作为输入,对船舶的横摇运动进行了预报,结果表明该网络相较于LSTM模型的预报效果有了明显的提升;Li等[11]提出了一种CNN-GRU-AM模型,使用卷积网络(CNN)提取特征,采用门控循环单元(GRU)学习固有时间特征并提取时间特征向量,并使用注意力机制(AM)来控制特征向量对输出的影响。但是LSTM、GRU等循环神经网络无法并行,难以处理大数据集,为了解决这一问题,学者们也尝试使用时间卷积网络(TCN)实现对船舶运动的预报。Zhang等[12]将TCN与注意力机制结合,对船舶的横摇、纵摇、垂荡进行了预报,证明了TCN网络应用于船舶摇荡预报的可行性。
但是,目前的研究大多仅止步于船舶运动预报,而船舶载荷与船舶运动是息息相关的,本文将使用GRU模型来实现船舶纵摇和垂荡的预报,并在此基础上将船舶运动预报的结果作为载荷预报模型的输入,实现船舶船舯垂向弯矩的预报,这对于保证船舶海上航行与作业安全具有重要意义。
门控神经网络GRU是一种特殊的循环神经网络,该模型最早由Chung等[13]于2014年提出,这一模型可以认为是长短时记忆网络LSTM的改进,将LSTM中的“遗忘门”、“输入门”、“输出门”简化为“重置门”和“更新门”,其中重置门用于控制前一时刻隐藏状态信息的保留程度,更新门则用于控制先前隐藏状态信息和当前候选状态信息对当前隐藏状态的影响,其单元结构如图1所示:
GRU单元的状态计算如式(1)-(4)所示,其中htt时刻单元的隐藏状态;Xt为单元t时刻输入,ht为单元的候选隐藏状态;WxrWhr为重置门的两个权重矩阵;WxzWhz为更新门的权重矩阵;WxhWhh为计算候选隐藏状态的权重矩阵;⊗表示矩阵乘法。
式中的σ、tanh为激活函数,计算公式分别如下:
本文将通过两个GRU模型来实现船舶运动与载荷的预报,预报流程如图2所示,首先通过运动预报模型获取未来几秒后的船舶运动幅值,再将预报得到的运动幅值作为载荷预报模型的输入,得到与之相对应的载荷预报结果。
假设原始时间序列为X=[x1x2,···xTa+Te]和M=[M1M2,···MTa+Te],X代表船舶运动时间序列,M代表波浪载荷时间序列,其中[x1x2,···xTa]为训练集,用于模型训练,[xTa+1x2,···xTa+Te]为测试集,用于测试模型性能。为了使神经网络能够学习到船舶历史运动与未来某一时刻运动之间的映射关系,我们需要规定神经网络输入与标签之间的对应关系,记运动预报模型中神经网络输入与标签的映射关系为[],具体如式(7)所示;载荷预报模型中神经网络模型输入与标签的映射关系为[],其中在时间步上保持一致。
式中,q为历史窗口大小,p为超前预报时间。
将得到的训练集与测试集用于运动预报模型的训练和测试后,可以得到船舶运动预报结果,记为[,···,···],将[,···]作为载荷预报模型的训练集,标签为[,···,]。最后将[,···]作为载荷预报模型的输入,即可得到船舯垂向弯矩预报结果[,···,]。
本文所针对目标船舶主尺度信息如表1所示。船舶运动与载荷数据包含了船舶的垂荡、纵摇及相对应的船舯垂向弯矩。具体工况如表2所示,其中工况一至工况三为仿真数据,采用挪威船级社(DNV)研发的SESAM软件获取,该软件基于三维势流理论进行计算,通过导入型线文件和重量文件计算得到仿真数据,数据采样频率为4 Hz,每一工况包含3600 s的船舶纵摇和垂荡。工况四为船模试验数据,通过在中国船舶科学研究中心耐波性水池进行的模型试验获得。分别使用每一工况数据的80%用于模型训练,剩余20%用于测试模型性能。
对于所获取到的原始数据应进行归一化以后,才能用于模型训练,使用式(8)进行数据归一化,其中xi为原始数据,xmaxxmin为序列中的最大值和最小值,为归一化后的数据。
船舶在海上以恒定速度航行,受到流体作用产生六自由度运动,满足刚体运动理论,因此必定适用于牛顿第二定律,其频域运动方程为
式中,ωe为遭遇频率;mij为惯性矩阵;µij为附加质量;λij为阻尼系数;为等效线性化粘性阻尼系数;δ4j为Kronecker符号,它只在两个下标相同时不等于0,分别为船舶所受的Froude-Krylov力和绕射力。通过求解式(9),便可得到船舶六自由度运动位移。
SESAM软件在进行船舶水动力分析时所使用的是三维势流理论中的自由面格林函数法,该方法也被称为边界元法(Boundary element method),其基本思想是利用边界积分方程将计算域内的待求变量与其边界条件联系起来,通过求解边界积分方程获得目标微分方程的解。相较于有限元法等常见的数值积分方法,格林函数法只需对求解域的边界进行离散,降低了计算的维数,因而更加经济高效。软件具体求解过程参考SESAM使用手册。
文中船舶运动与载荷预报使用平均绝对误差(Mean Absolute Error,MAE)、平均绝对百分比误差(Mean Absolute Percentage Error,MAPE)、决定系数(Coefficient of Determination,R2)三个评价指标来衡量模型预报结果的优劣。本文提出的MAPE为传统MAPE的改进,只选择时序信息中偏离平衡点最多的前1/3值进行平均绝对百分比误差的计算,原因在于船舶运动与载荷的时域变化在一个平衡点之间波动,若平衡点为0则会出现许多小值点,这些小值点会直接影响MAPE的计算,导致其无法真实地反映模型的预报结果。在实际工程中,工程人员更关心的是船舶运动与载荷幅值较大时的预报结果,仅对大值进行MAPE的计算也更符合实际需求,因此本文使用改进的MAPE作为模型的评价指标。在这三个指标中,MAE反映预报结果的绝对误差,MAPE反映预报结果中更受关注的大值的相对误差,R2为归一化指标,反映了预报时域曲线与真实时域曲线的相似程度。三个评价指标的计算公式如(10)-(12)所示:
式中,Yi为船舶运动与载荷真实值,yi是船舶运动与载荷预报值,是按偏离平衡点幅值大小降序排列后的船舶运动与载荷真实值,对应的船舶运动与载荷预报值,n为数据个数,为船舶运动与载荷真实值的平均值。
目前船舶运动预报大多是被当作一个完全的自回归问题来处理,即预报纵摇时仅将历史纵摇数据作为模型输入。但是船舶的纵摇和垂荡运动是紧密联系的,本文将船舶纵摇、垂荡历史信息共同作为GRU模型输入,形成一个垂荡-纵摇联合预报的多输入-多输出模型,并将结果与单输入-单输出的GRU模型进行对比。其中GRU模型的隐藏层单元数为64,层数为2层,训练批处理大小为128,历史窗口大小为20 s,优化器选择为Adam(adaptive moment estimation),学习率设置为0.0005,训练次数为100轮,设置2 s、4 s、6 s、8 s、10 s五个不同的超前预报时间。
三个工况不同预报模型预报结果随超前预报时间的变化如图3-5所示,其中实线代表的是船舶的垂荡,虚线代表的是船舶的纵摇;红色曲线代表的多输入-多输出的联合预报模型,蓝色曲线代表的是单输入-单输出预报模型。
结果表明三个工况的纵摇预报结果均优于垂荡,工况二预报结果最差,表3给出了工况二的预报结果对比,其垂荡和纵摇在多输入的情况下,超前10 s的预报决定系数仅为0.7324和0.8514,工况三次之,工况一的预报结果最好,在多输入的情况下,其垂荡和纵摇超前10 s的预报决定系数可达0.931和0.948,并且随着超前预报时间的增大,两个模型对三个工况的纵摇和垂荡预报结果均会出现下降。但是,无论是哪一个超前时间,将纵摇和垂荡共同作为输入的多输入-多输出预报模型均可以得到比单输入-单输出更好的预报结果,工况二的影响最为明显。多输入-多输出的预报方式在超前预报10 s时,垂荡和纵摇决定系数相较于单输入-单输出模式提高了0.1280和0.0615,前1/3大值的平均绝对百分比误差分别下降了7.64%和6.00%,预报精度有了明显提升。工况一影响最小,纵摇和垂荡的决定系数分别提升了0.0027和0.0116。
工况二预报结果最差的主要原因在于,船舶运动预报精度与海况的恶劣程度、浪向角等因素直接相关,并且浪向角对预报精度的影响更加严重,工况二的浪向角为135°时,相较于一、三两个顶浪航行的工况,预报精度就会有明显的下降。工况一的波浪输入较小,且为顶浪航行,因此船舶的纵摇和垂荡变化规律性较强,使用单输入-单输出的预报方式就能得到一个较好的预报结果,因此预报精度提升较小。
图6图7是两种不同输入的预报模型对工况二下,船舶垂荡与纵摇超前预报时间分别为2 s和10 s时的预报结果对比。由图可知,在超前预报时间为2 s时两种模型均可以较好地预报结果,基本未出现相位偏移;在超前预报10 s时,由于超前预报时间增长,两种预报方式在3525 s-3550 s处均出现了较大的相位和幅值偏差,但是多输入-多输出的联合预报模型在极值处的预报结果明显更优。同时,使用联合预报模型还可以减少模型数量,降低了模型训练的工作量,因此将使用多输入-多输出的联合预报模型来展开下一步的工作。
根据上文的研究可以发现,工况二的预报结果是最差的,为了证明GRU模型的优越性,本文以工况二为例,将GRU模型与LSTM、TCN-AM模型进行对比,其中LSTM模型参数与GRU模型保持一致,TCN-AM模型参数与文献[12]保持一致。
图8是工况二三种不同预报模型的评价指标随超前预报时间的变化结果,其中红色曲线代表的是GRU模型,蓝色曲线代表的是TCN-AM模型,黑色曲线代表的是LSTM模型。
表4-5可知,GRU模型相较于LSTM、TCN-AM模型在这三个评价指标下取得了更好的结果,三个不同模型超前预报10 s的时域预报结果对比如图9所示,相较于LSTM和TCN-AM模型,GRU模型的垂荡结果在超前预报时间10 s时的平均绝对误差分别下降了0.031 m和0.047 m,前1/3大值的平均绝对百分比误差分别下降了0.009和0.048,相关系数提升了0.047和0.073;纵摇超前报时间10 s的平均绝对误差MAE分别下降了0.072和0.058,前1/3大值的平均绝对百分比误差分别下降了0.004和0.052,相关系数提升了0.036和0.031。此外,相较于LSTM和TCN-AM模型,GRU模型的结构更加简单,计算量也更小,因此本文最终选用GRU模型作为船舶纵摇和垂荡快速预报模型。
在获得了船舶运动预报结果后,将船舶运动预报得到的超前预报结果作为GRU载荷预报模型的输入,建立船舶垂荡与纵摇幅值和与之在未来同一时刻的船舯垂向弯矩之间的映射关系,从而实现船舯垂向弯矩的超前预报。本文将表2中三个不同工况的船舶纵摇和垂荡超前预报结果作为输入,使用GRU模型,对三个不同工况下船舯垂向弯矩进行预报。其中GRU模型的隐藏层单元数为64,层数为3层,训练批处理大小为128,优化器选择为Adam(adaptive moment estimation),学习率设置为0.001,训练次数为60轮。
图10为三个工况的船舯垂向弯矩预报结果随超前预报时间的变化曲线,随着超前预报时间的增加,船舯垂向弯矩的预报结果也随之变差。以工况二为例,船舯垂向弯矩决定系数由0.918下降为0.701,前1/3大值的平均绝对百分比误差由0.171增大至0.329。图11为不同超前预报时间的船舯垂向弯矩时域预报结果,当输入超前预报时间为2 s的船舶纵摇和垂荡数据时,船舯垂向弯矩的预报结果基本和真实值保持一致,仅在部分极值处出现一定偏差。但当输入超前预报时间为10 s的船舶纵摇和垂荡数据时,船舯垂向弯矩预报结果与真实值出现了较大偏差,在3525-3550 s处相位与极值都出现了较大偏差,这与上文的船舶运动预报中出现的现象保持一致。
出现这一现象的主要原因,是船舯垂向弯矩的预报结果直接受船舶运动预报精度的影响。随着超前预报时间的增加,船舶垂荡和纵摇的预报精度逐渐下降,这直接导致了与之相对应的船舯垂向弯矩预报精度的下降;在工况二中,当超前预报时间达到10 s时,船舶运动预报在3525-3550 s处出现了较大偏差,对于垂荡的预报偏差尤为剧烈,这也是直接导致工况二超前10 s的船舶弯矩预报在3525-3550 s处出现较大的相位和极值偏差的主要原因。
为了验证预报模型在实际应用中的有效性,本文采用某船模试验获得的纵摇、垂荡及船舯垂向弯矩结果进行建模预报。
按照缩尺比1∶40进行模型试验,船舶模型为分段龙骨梁结构的玻璃钢自航船模,共分4段,用测量梁连接,通过在测量梁下表面焊接小钢板作为连接基座,由螺栓与船模木横梁相连接,测量梁布置与龙骨梁分段模型示意图如图12所示。在第5站、10站和15站分段处的测量梁上布置应变片,以测量船体第5站、10站和15站分段处的垂向弯矩、水平弯矩和扭矩,应变片布置可见图13,应变片S1S4沿梁轴纵向粘贴于梁表面,应变片S5S8沿梁轴纵向45度方向粘贴于梁表面,S1S2半桥连接通过标定形成垂向弯矩MvS3S4半桥连接通过标定形成水平弯矩MhS5S8全桥连接通过标定形成扭矩Mt。通过将伺服式浪高仪安装在水池测量小车上,位于模型前约1.5 m处,测量试验时模型遭遇的波浪,波浪时间历程实时记录在微机上。
图14是纵摇、垂荡的三个不同评价指标随超前预报时间变化结果,其中蓝色折线为垂荡,红色折线为纵摇。通过分析可以发现,在该工况下,本文提出的预报模型可以取得很好的预报结果,即使是在超前预报时间达到10 s时,垂荡和纵摇的决定系数指标分别为0.9318、0.9536,垂荡的预报精度相对较低,这与仿真数据训练得到的模型结论一致。并且超前预报时间对于预报精度的影响并不大,超前时间从2 s提升至10 s,垂荡和纵摇的平均绝对误差仅增加了0.0232 m和0.1253°,这主要是因为这是一个顶浪航行工况,预报难度相对较小。
图15图16分别是垂荡和纵摇超前2 s、10 s的预报结果,结果表明,该工况下船舶纵摇和垂荡都可以保持较高的预报精度,预报结果基本未出现相位偏差。
将垂荡和纵摇的预报结果作为载荷预报GRU模型的输入,就可以得到与之对应的船舯垂向弯矩预报结果。图17是船舯垂向弯矩的预报结果随超前预报时间的变化,结果表明,在超前预报时间不大于10 s时,船舯垂向弯矩预报结果在相位上基本不会出现偏差,其决定系数可保持在0.83以上,但在部分极值点处会出现较大的幅值误差,其前1/3大值的MAPE指标在超前预报时间为10 s时,达到了0.2547,存在较大误差。
图18是船舯垂向弯矩超前2 s和10 s的预报结果时域曲线,结果表明,2 s和10 s的预报结果与真实值相位基本保持一致,但是预报结果在极值处与真实值都出现了较大的偏差,在超前预报时间达到10 s时尤为明显。
本文使用GRU神经网络建立了船舶运动与载荷的快速预报模型,通过仿真数据确定预报模型并使用船模试验数据对预报模型性能进行了验证,得到了如下主要结论:
(1)通过不同工况下的船舶运动预报结果与试验数据的对比分析,验证了所建立的多输入-多输出GRU联合预报模型可有效实现船舶运动历史信息与未来时刻运动的非线性映射,在顶浪航行的情况下,垂荡和纵摇在超前预报时间达到10 s时,仍可以保持很高的预报精度。
(2)通过不同工况下船舶船舯垂向弯矩预报结果与试验数据的对比分析,验证了所建立的基于GRU神经网络的载荷预报模型可以有效实现船舶运动与船舯垂向弯矩的非线性映射,其预报精度直接受船舶运动预报精度的影响,在船舶运动预报精度较高的情况下,船舯垂向弯矩可以得到较好的预报结果。
  • 国家重点研发计划资助项目(2022YFB3306200)
参考文献 引证文献
排序方式:
[1]
Triantafyllou M S, Bodson M, Athans M. Real time estimation of ship motions using Kalman filtering techniques[J]. IEEE Journal of Oceanic Engineering, 1983, 8(1): 9-20.
[2]
赵源,滕大予. 多维AR(p)模型在预报舰船运动中的应用[J]. 现代防御技术2003(4):52-55+60.
Zhao Y, Teng D Y. Application of multidimensional AR(p) model in forecasting the state of ship movement[J]. Modern Defence Technology, 2003(4): 52-55+60. (in Chinese)
[3]
虞兰生,戴遗山. 船舶运动的自适应预报[J]. 中国造船1988(3):85-88.
Yu L S, Dai Y S. Adaptive prediction of ship motion[J]. Shipbuilding of China, 1988(3): 85-88. (in Chinese)
[4]
Khan A, Bil C, Marion K E. Theory and application of artificial neural networks for the real time prediction of ship motion[C]//9th International Conference on Knowledge-based Intelligent Information and Engineering Systems, 2005.
[5]
顾民,刘长德,张进丰. 基于混沌理论与RBF神经网络的船舶运动极短期预报研究[J]. 船舶力学2013, 17(10):1147-1152.
Gu M, Liu C D, Zhang J F. Extreme short-term prediction of ship motion based on chaotic theory and RBF neural network[J]. Journal of Ship Mechanics, 2013, 17(10): 1147-1152. (in Chinese)
[6]
Wang Y C, Liu F M, Fu H X. Ship rolling motion prediction based on wavelet neural network[J]. Applied Mechanics and Materials, 2012, 190-191:724-728.
[7]
黄柏刚. 基于小波神经网络的波浪中船舶运动在线建模与预报研究[D]. 上海:上海交通大学,2019.
Huang B G. Online modeling and predicting of ship motions in waves based on wavelet neural network[D]. Shanghai: Shanghai Jiao Tong University, 2019. (in Chinese)
[8]
del Águila Ferrandis J, Triantafyllou M S, Chryssostomidis C, Karniadakis G E. Learning functionals via LSTM neural networks for predicting vessel dynamics in extreme sea states[J]. Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences, 2021, 477(2245): 20190897.
[9]
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 C D, Gu Y X, Zhang J F. 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. (in Chinese)
[10]
Wang Y C, Wang H, Zou D X, et al. Ship roll prediction algorithm based on Bi-LSTM-TPA combined model[J]. Journal of Marine Science and Engineering, 2021, 9(4): 387.
[11]
Li M W, Xu D Y, Geng J, et al. A hybrid approach for forecasting ship motion using CNN-GRU-AM and GCWOA[J]. Applied Soft Computing, 2022, 114:108084.
[12]
Zhang B, Wang S, Deng L W, et al. Ship motion attitude prediction model based on IWOA-TCN-attention[J]. Ocean Engineering, 2023, 272:113911.
[13]
Chung J, Gulcehre C, Cho K H, Bengio Y. Empirical evaluation of gated recurrent neural networks on sequence modeling[J]. Eprint Arxiv, 2014:1412.3555.
2025年第29卷第3期
PDF下载
78
36
引用本文
BibTeX
文章信息
doi: 10.3969/j.issn.1007-7294.2025.03.001
  • 接收时间:2024-09-15
  • 首发时间:2026-03-24
  • 出版时间:2025-03-20
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2024-09-15
基金
国家重点研发计划资助项目(2022YFB3306200)
作者信息
    中国船舶科学研究中心,江苏 无锡 214082

通讯作者:

通讯作者,E-mail:
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/cblx/CN/10.3969/j.issn.1007-7294.2025.03.001
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