Article(id=1243306062825238809, tenantId=1146029695717560320, journalId=1240685776644648972, issueId=1243306060832944396, articleNumber=null, orderNo=null, doi=10.3969/j.issn.1007-7294.2025.03.005, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1727193600000, receivedDateStr=2024-09-25, revisedDate=null, revisedDateStr=null, acceptedDate=null, acceptedDateStr=null, onlineDate=1774356864887, onlineDateStr=2026-03-24, pubDate=1742400000000, pubDateStr=2025-03-20, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1774356864887, onlineIssueDateStr=2026-03-24, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1774356864887, creator=13701087609, updateTime=1774356864887, 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=388, endPage=399, ext={EN=ArticleExt(id=1243306063500521768, articleId=1243306062825238809, tenantId=1146029695717560320, journalId=1240685776644648972, language=EN, title=Predictions of wave height and pressure induced by liquid sloshing based on neural network, columnId=1241023037940748650, journalTitle=Journal of Ship Mechanics, columnName=Hydrodynamics, runingTitle=null, highlight=null, articleAbstract=

Numerical modelling based on Navier-Stokes equations and model experiment for studying liquid sloshing have the limits of low computational efficiency and high economic cost. Therefore, to predict the hydrodynamic pressure and wave height, the time-histories to numerical and experimental results were reconstructed in this paper through the neural network model. The total numerical and experimental pressures and free surface elevations were taken as training samples, and CNN, RNN and LSTM with strong repretational ability were used to reproduce the sloshing responses. The internal structural parameters of the neural network were systematically adjusted, besides, the errors and correlations between the predicted and actual values were analyzed. The results show that the error is lower than 4% and the correlations of both RNN and LSTM reach 0.88, which is in general superior to CNN, and that LSTM is optimal in predicting the long sequence data. Overall, three surrogate models can well predict the sloshing wave height and pressure, and are promising in the study of liquid sloshing.

, 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=Xin JIN, Yu-sheng WANG, Fu-gui ZHANG, Jian CHEN, Deng-song LI, Chang-yuan FAN, Ming-ming LIU), CN=ArticleExt(id=1243306068403663320, articleId=1243306062825238809, tenantId=1146029695717560320, journalId=1240685776644648972, language=CN, title=基于神经网络的流体晃荡波高和压强的预测研究, columnId=1241023038087549292, journalTitle=船舶力学, columnName=流体力学, runingTitle=null, highlight=null, articleAbstract=

基于Navier-Stokes方程的数值模型和物理模型实验研究流体晃荡现象存在计算效率低和经济成本高的不足。为此,本文通过构建神经网络模型对数值和实验结果进行时序重构,预测流体晃荡的压强和波高。以数值和实验的总压强和自由表面高程数据作为训练样本,将神经网络中表征能力强的CNN、RNN、LSTM用于重演流体晃荡响应的时间演化过程。在模型训练过程中,系统地调节神经网络的内部结构参数,分析预测结果与实际值之间的误差和相关性。结果表明,RNN和LSTM的重构误差低于4%,相关性达到0.88,整体优于CNN;LSTM的整体性能最佳,可以作为预测长序列数据的首选。整体来讲,三种代理模型均可以较好地复现流体晃荡的波高和压强,在流体晃荡研究方面具有良好的应用前景。

, correspAuthors=null, authorNote=null, correspAuthorsNote=
通讯作者,E-mail:
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=fb1HHNbprQ5+YgvJUBM7Zw==, magXml=rFtZTgIqkQ15pgt3i7xSPw==, pdfUrl=null, pdf=gpxhOhW6n2/D2KUiciZyJw==, pdfFileSize=1957717, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=OXBBRDvd405E0KfKApwODQ==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=qHOdutLwWEQpzNjAaGeDjg==, mapNumber=null, authorCompany=null, fund=null, authors=

金鑫(1988-),男,博士,副教授

刘名名(1986-),男,博士,研究员,通讯作者,E-mail:

, authorsList=金鑫, 王宇圣, 张福贵, 陈健, 李登松, 樊昌元, 刘名名)}, authors=[Author(id=1243306069246718476, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, orderNo=0, 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=1243306069355770387, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, authorId=1243306069246718476, language=EN, stringName=Xin JIN, firstName=Xin, middleName=null, lastName=JIN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.College of Electronic Engineering, Chengdu University of Information Technology, Chengdu 610225, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1243306069439656472, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, authorId=1243306069246718476, language=CN, stringName=金鑫, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.成都信息工程大学 电子工程学院,成都 610225, bio={"content":"

金鑫(1988-),男,博士,副教授

"}, bioImg=null, bioContent=

金鑫(1988-),男,博士,副教授

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1243306068697264616, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, xref=1., ext=[AuthorCompanyExt(id=1243306068709847530, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, companyId=1243306068697264616, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.College of Electronic Engineering, Chengdu University of Information Technology, Chengdu 610225, China), AuthorCompanyExt(id=1243306068718236139, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, companyId=1243306068697264616, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.成都信息工程大学 电子工程学院,成都 610225)])]), Author(id=1243306069536125470, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, 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=1243306069666148901, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, authorId=1243306069536125470, language=EN, stringName=Yu-sheng WANG, firstName=Yu-sheng, middleName=null, lastName=WANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.College of Electronic Engineering, Chengdu University of Information Technology, Chengdu 610225, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1243306069766812202, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, authorId=1243306069536125470, language=CN, stringName=王宇圣, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.成都信息工程大学 电子工程学院,成都 610225, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1243306068697264616, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, xref=1., ext=[AuthorCompanyExt(id=1243306068709847530, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, companyId=1243306068697264616, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.College of Electronic Engineering, Chengdu University of Information Technology, Chengdu 610225, China), AuthorCompanyExt(id=1243306068718236139, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, companyId=1243306068697264616, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.成都信息工程大学 电子工程学院,成都 610225)])]), Author(id=1243306069859086896, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, 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=1243306069955555894, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, authorId=1243306069859086896, language=EN, stringName=Fu-gui ZHANG, firstName=Fu-gui, middleName=null, lastName=ZHANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.College of Electronic Engineering, Chengdu University of Information Technology, Chengdu 610225, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1243306070047830590, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, authorId=1243306069859086896, language=CN, stringName=张福贵, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.成都信息工程大学 电子工程学院,成都 610225, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1243306068697264616, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, xref=1., ext=[AuthorCompanyExt(id=1243306068709847530, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, companyId=1243306068697264616, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.College of Electronic Engineering, Chengdu University of Information Technology, Chengdu 610225, China), AuthorCompanyExt(id=1243306068718236139, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, companyId=1243306068697264616, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.成都信息工程大学 电子工程学院,成都 610225)])]), Author(id=1243306070165271111, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, 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=1243306070291100237, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, authorId=1243306070165271111, language=EN, stringName=Jian CHEN, firstName=Jian, middleName=null, lastName=CHEN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.PowerChina Hebei Electric Power Engineering Co., Ltd., Shijiazhuang 050031, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1243306070374986322, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, authorId=1243306070165271111, language=CN, stringName=陈健, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.中国电建集团 河北省电力勘测设计研究院有限公司,石家庄 050031, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1243306068823093744, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, xref=2., ext=[AuthorCompanyExt(id=1243306068831482354, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, companyId=1243306068823093744, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.PowerChina Hebei Electric Power Engineering Co., Ltd., Shijiazhuang 050031, China), AuthorCompanyExt(id=1243306068860842484, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, companyId=1243306068823093744, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.中国电建集团 河北省电力勘测设计研究院有限公司,石家庄 050031)])]), Author(id=1243306070790222425, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, orderNo=4, 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=1243306070882497119, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, authorId=1243306070790222425, language=EN, stringName=Deng-song LI, firstName=Deng-song, middleName=null, lastName=LI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3.School of Automation, Chengdu University of Information Technology, Chengdu 610225, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1243306070983160421, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, authorId=1243306070790222425, language=CN, stringName=李登松, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3.成都信息工程大学 自动化学院,成都 610225, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1243306068953117177, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, xref=3., ext=[AuthorCompanyExt(id=1243306068961505786, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, companyId=1243306068953117177, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3.School of Automation, Chengdu University of Information Technology, Chengdu 610225, China), AuthorCompanyExt(id=1243306068965700091, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, companyId=1243306068953117177, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3.成都信息工程大学 自动化学院,成都 610225)])]), Author(id=1243306071138349676, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, orderNo=5, 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=1243306071259984503, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, authorId=1243306071138349676, language=EN, stringName=Chang-yuan FAN, firstName=Chang-yuan, middleName=null, lastName=FAN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.College of Electronic Engineering, Chengdu University of Information Technology, Chengdu 610225, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1243306071364842114, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, authorId=1243306071138349676, language=CN, stringName=樊昌元, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.成都信息工程大学 电子工程学院,成都 610225, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1243306068697264616, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, xref=1., ext=[AuthorCompanyExt(id=1243306068709847530, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, companyId=1243306068697264616, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.College of Electronic Engineering, Chengdu University of Information Technology, Chengdu 610225, China), AuthorCompanyExt(id=1243306068718236139, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, companyId=1243306068697264616, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.成都信息工程大学 电子工程学院,成都 610225)])]), Author(id=1243306071444533900, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, orderNo=6, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=liumingming_dlut@163.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1243306071549391507, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, authorId=1243306071444533900, language=EN, stringName=Ming-ming LIU, firstName=Ming-ming, middleName=null, lastName=LIU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=4, address=4.School of Architecture and Engineering, Liaocheng University, Liaocheng 252000, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1243306071666832026, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, authorId=1243306071444533900, language=CN, stringName=刘名名, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=4, address=4.聊城大学 建筑工程学院,山东 聊城 252000, bio={"content":"

刘名名(1986-),男,博士,研究员,通讯作者,E-mail:

"}, bioImg=null, bioContent=

刘名名(1986-),男,博士,研究员,通讯作者,E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1243306069091529216, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, xref=4., ext=[AuthorCompanyExt(id=1243306069129277955, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, companyId=1243306069091529216, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=4.School of Architecture and Engineering, Liaocheng University, Liaocheng 252000, China), AuthorCompanyExt(id=1243306069137666564, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, companyId=1243306069091529216, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=4.聊城大学 建筑工程学院,山东 聊城 252000)])])], keywords=[Keyword(id=1243306071805244065, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, language=EN, orderNo=1, keyword=liquid sloshing), Keyword(id=1243306071910101672, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, language=EN, orderNo=2, keyword=neural network), Keyword(id=1243306071998182061, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, language=EN, orderNo=3, keyword=numerical simulation), Keyword(id=1243306072090456758, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, language=EN, orderNo=4, keyword=prediction), Keyword(id=1243306072216285883, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, language=CN, orderNo=1, keyword=流体晃荡), Keyword(id=1243306072295977663, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, language=CN, orderNo=2, keyword=神经网络), Keyword(id=1243306072384058054, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, language=CN, orderNo=3, keyword=数值模拟), Keyword(id=1243306072476332747, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, language=CN, orderNo=4, keyword=预测)], refs=[Reference(id=1243306076754523022, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, doi=null, pmid=null, pmcid=null, year=2022, volume=138, issue=null, pageStart=280, pageEnd=300, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=Tao K D, Zhou X Q, Ren H L, journalName=Engineering Analysis with Boundary Elements, refType=null, unstructuredReference=Tao K D, Zhou X Q, Ren H L. The application of an advanced coupled SPH-BEM algorithm to 2D fluid sloshing simulation[J]. Engineering Analysis with Boundary Elements, 2022, 138:280-300., articleTitle=The application of an advanced coupled SPH-BEM algorithm to 2D fluid sloshing simulation, refAbstract=null), Reference(id=1243306076834214805, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, doi=null, pmid=null, pmcid=null, year=2022, volume=127, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[2], rfOrder=1, authorNames=Saltari F, Pizzoli M, Gambioli F, journalName=Aerospace Science and Technology, refType=null, unstructuredReference=Saltari F, Pizzoli M, Gambioli F, et al. Sloshing reduced-order model based on neural networks for aeroelastic analyses[J]. Aerospace Science and Technology, 2022, 127:107708., articleTitle=Sloshing reduced-order model based on neural networks for aeroelastic analyses, refAbstract=null), Reference(id=1243306076905517974, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, doi=null, pmid=null, pmcid=null, year=2021, volume=null, issue=22, pageStart=139, pageEnd=141, url=null, language=null, rfNumber=[3], rfOrder=2, authorNames=朱奎松, 赵英涛, 曹丽, journalName=当代化工研究, refType=null, unstructuredReference=朱奎松,赵英涛,曹丽,. 计算流体力学数值计算在化工原理实践课程教学中的应用[J]. 当代化工研究2021(22):139-141., articleTitle=计算流体力学数值计算在化工原理实践课程教学中的应用, refAbstract=null), Reference(id=1243306077010375577, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, doi=null, pmid=null, pmcid=null, year=2021, volume=null, issue=22, pageStart=139, pageEnd=141, url=null, language=null, rfNumber=[3], rfOrder=3, authorNames=Zhu Q S, Zhao Y T, Cao L, journalName=Modern Chemical Research, refType=null, unstructuredReference=Zhu Q S, Zhao Y T, Cao L, et al. Application of computational fluid dynamics numerical calculation in the teaching of chemical engineering principle practice course[J]. Modern Chemical Research, 2021(22): 139-141., articleTitle=Application of computational fluid dynamics numerical calculation in the teaching of chemical engineering principle practice course, refAbstract=null), Reference(id=1243306077098455964, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, doi=null, pmid=null, pmcid=null, year=2012, volume=16, issue=7, pageStart=750, pageEnd=758, url=null, language=null, rfNumber=[4], rfOrder=4, authorNames=李裕龙, 朱仁传, 缪国平, journalName=船舶力学, refType=null, unstructuredReference=李裕龙,朱仁传,缪国平,. 基于OpenFOAM的船舶与液舱流体晃荡在波浪中时域耦合运动的数值模拟[J]. 船舶力学2012, 16(7):750-758., articleTitle=基于OpenFOAM的船舶与液舱流体晃荡在波浪中时域耦合运动的数值模拟, refAbstract=null), Reference(id=1243306077199119265, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, doi=null, pmid=null, pmcid=null, year=2012, volume=16, issue=7, pageStart=750, pageEnd=758, url=null, language=null, rfNumber=[4], rfOrder=5, authorNames=Li Y L, Zhu R C, Miu G P, journalName=Journal of Ship Mechanics, refType=null, unstructuredReference=Li Y L, Zhu R C, Miu G P, et al. Simulation of ship motions coupled with tank sloshing in time domain based on OpenFOAM[J]. Journal of Ship Mechanics, 2012, 16(7): 750-758., articleTitle=Simulation of ship motions coupled with tank sloshing in time domain based on OpenFOAM, refAbstract=null), Reference(id=1243306077299782565, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, doi=null, pmid=null, pmcid=null, year=2019, volume=192, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[5], rfOrder=6, authorNames=Xue M A, Chen Y C, Zheng J H, journalName=Ocean Engineering, refType=null, unstructuredReference=Xue M A, Chen Y C, Zheng J H, et al. Fluid dynamics analysis of sloshing pressure distribution in storage vessels of different shapes[J]. Ocean Engineering, 2019, 192:106582., articleTitle=Fluid dynamics analysis of sloshing pressure distribution in storage vessels of different shapes, refAbstract=null), Reference(id=1243306077404640172, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, doi=null, pmid=null, pmcid=null, year=2023, volume=18, issue=2, pageStart=143, pageEnd=156, url=null, language=null, rfNumber=[6], rfOrder=7, authorNames=Takami T, Ma C, journalName=Ships and Offshore Structures, refType=null, unstructuredReference=Takami T, Ma C. Surrogate model approach for stochastic prediction of sloshing-induced pressure based on SPH with FORM[J]. Ships and Offshore Structures, 2023, 18(2): 143-156., articleTitle=Surrogate model approach for stochastic prediction of sloshing-induced pressure based on SPH with FORM, refAbstract=null), Reference(id=1243306077543052210, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, doi=null, pmid=null, pmcid=null, year=2020, volume=32, issue=12, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[7], rfOrder=8, authorNames=Peng J Z, Chen S H, Aubry N, journalName=Physics of Fluids, refType=null, unstructuredReference=Peng J Z, Chen S H, Aubry N, et al. Time-variant prediction of flow over an airfoil using deep neural network[J]. Physics of Fluids, 2020, 32(12): 123602., articleTitle=Time-variant prediction of flow over an airfoil using deep neural network, refAbstract=null), Reference(id=1243306077626938296, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, doi=null, pmid=null, pmcid=null, year=2022, volume=7, issue=2, pageStart=56, pageEnd=null, url=null, language=null, rfNumber=[8], rfOrder=9, authorNames=Huang Y, Zhang Z Y, Zhang X, journalName=Fluids, refType=null, unstructuredReference=Huang Y, Zhang Z Y, Zhang X, et al. A direct-forcing immersed boundary method for incompressible flows based on physics-informed neural network[J]. Fluids, 2022, 7(2): 56., articleTitle=A direct-forcing immersed boundary method for incompressible flows based on physics-informed neural network, refAbstract=null), Reference(id=1243306077740184507, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, doi=null, pmid=null, pmcid=null, year=2022, volume=32, issue=4, pageStart=394, pageEnd=401, url=null, language=null, rfNumber=[9], rfOrder=10, authorNames=Liu Q, Feng X Y, Tang T N, journalName=International Journal of Offshore and Polar Engineering, refType=null, unstructuredReference=Liu Q, Feng X Y, Tang T N. A machine learning model for wave prediction based on support vector machine[J]. International Journal of Offshore and Polar Engineering, 2022, 32(4): 394-401., articleTitle=A machine learning model for wave prediction based on support vector machine, refAbstract=null), Reference(id=1243306077815681983, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, doi=null, pmid=null, pmcid=null, year=2021, volume=166, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[10], rfOrder=11, authorNames=Ye Z T, Shi F Y, Zhao X Z, journalName=Coastal Engineering, refType=null, unstructuredReference=Ye Z T, Shi F Y, Zhao X Z, et al. A data-driven approach to modeling subgrid-scale shallow marsh hydrodynamics[J]. Coastal Engineering, 2021, 166:103856., articleTitle=A data-driven approach to modeling subgrid-scale shallow marsh hydrodynamics, refAbstract=null), Reference(id=1243306077895373763, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, doi=null, pmid=null, pmcid=null, year=2023, volume=270, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[11], rfOrder=12, authorNames=Guo C, Cui S A, Zeng G, journalName=Ocean Engineering, refType=null, unstructuredReference=Guo C, Cui S A, Zeng G, et al. Vehicle stochastic response prediction of sea-crossing railway bridges under correlated wind and wave via machine learning[J]. Ocean Engineering, 2023, 270:113714., articleTitle=Vehicle stochastic response prediction of sea-crossing railway bridges under correlated wind and wave via machine learning, refAbstract=null), Reference(id=1243306077987648456, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, doi=null, pmid=null, pmcid=null, year=2021, volume=466, issue=null, pageStart=1, pageEnd=15, url=null, language=null, rfNumber=[12], rfOrder=13, authorNames=Zhang C P, Li S, Ye M, journalName=Neurocomputing, refType=null, unstructuredReference=Zhang C P, Li S, Ye M, et al. Learning various length dependence by dual recurrent neural networks[J]. Neurocomputing, 2021, 466:1-15., articleTitle=Learning various length dependence by dual recurrent neural networks, refAbstract=null), Reference(id=1243306078079923148, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, doi=null, pmid=null, pmcid=null, year=2022, volume=36, issue=3, pageStart=118, pageEnd=126, url=null, language=null, rfNumber=[13], rfOrder=14, authorNames=韩仁坤, 刘子扬, 钱炜祺, journalName=实验流体力学, refType=null, unstructuredReference=韩仁坤,刘子扬,钱炜祺,. 基于深度神经网络的流场时空重构方法[J]. 实验流体力学2022, 36(3):118-126., articleTitle=基于深度神经网络的流场时空重构方法, refAbstract=null), Reference(id=1243306078172197839, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, doi=null, pmid=null, pmcid=null, year=2022, volume=36, issue=3, pageStart=118, pageEnd=126, url=null, language=null, rfNumber=[13], rfOrder=15, authorNames=Han R K, Liu Z Y, Qian W Q, journalName=Journal of Experiments in Fluid Mechanics, refType=null, unstructuredReference=Han R K, Liu Z Y, Qian W Q, et al. Spatio-temporal reconstruction method of flow field based on deep neural network[J]. Journal of Experiments in Fluid Mechanics, 2022, 36(3): 118-126. (in Chinese), articleTitle=Spatio-temporal reconstruction method of flow field based on deep neural network, refAbstract=null), Reference(id=1243306078272861141, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, doi=null, pmid=null, pmcid=null, year=2019, volume=37, issue=3, pageStart=462, pageEnd=469, url=null, language=null, rfNumber=[14], rfOrder=16, authorNames=惠心雨, 袁泽龙, 白俊强, journalName=空气动力学学报, refType=null, unstructuredReference=惠心雨,袁泽龙,白俊强,. 基于深度学习的非定常周期性流动预测方法[J]. 空气动力学学报2019, 37(3):462-469., articleTitle=基于深度学习的非定常周期性流动预测方法, refAbstract=null), Reference(id=1243306078507742170, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, doi=null, pmid=null, pmcid=null, year=2019, volume=37, issue=3, pageStart=462, pageEnd=469, url=null, language=null, rfNumber=[14], rfOrder=17, authorNames=Hui X Y, Yuan Z L, Bai J Q, journalName=Acta Aerodynamica Sinica, refType=null, unstructuredReference=Hui X Y, Yuan Z L, Bai J Q, et al. A method of unsteady periodic flow field prediction based on the deep learning[J]. Acta Aerodynamica Sinica, 2019, 37(3): 462-469. (in Chinese), articleTitle=A method of unsteady periodic flow field prediction based on the deep learning, refAbstract=null), Reference(id=1243306078608405467, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, doi=null, pmid=null, pmcid=null, year=2020, volume=882, issue=null, pageStart=A13, pageEnd=null, url=null, language=null, rfNumber=[15], rfOrder=18, authorNames=Murata T, Fukami K, Fukagata K, journalName=Journal of Fluid Mechanics, refType=null, unstructuredReference=Murata T, Fukami K, Fukagata K. Nonlinear mode decomposition with convolutional neural networks for fluid dynamics[J]. Journal of Fluid Mechanics, 2020, 882:A13., articleTitle=Nonlinear mode decomposition with convolutional neural networks for fluid dynamics, refAbstract=null), Reference(id=1243306078704874467, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, doi=null, pmid=null, pmcid=null, year=2022, volume=390, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[16], rfOrder=19, authorNames=Liu Y, Hu R, Kraus A, journalName=Nuclear Engineering and Design, refType=null, unstructuredReference=Liu Y, Hu R, Kraus A, et al. Data-driven modeling of coarse mesh turbulence for reactor transient analysis using convolutional recurrent neural networks[J]. Nuclear Engineering and Design, 2022, 390:111716., articleTitle=Data-driven modeling of coarse mesh turbulence for reactor transient analysis using convolutional recurrent neural networks, refAbstract=null), Reference(id=1243306078788760550, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, doi=null, pmid=null, pmcid=null, year=2022, volume=262, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[17], rfOrder=20, authorNames=Meng Z F, Chen Z, Khoo B C, journalName=Ocean Engineering, refType=null, unstructuredReference=Meng Z F, Chen Z, Khoo B C, et al. Long-time prediction of sea wave trains by LSTM machine learning method[J]. Ocean Engineering, 2022, 262:112213., articleTitle=Long-time prediction of sea wave trains by LSTM machine learning method, refAbstract=null), Reference(id=1243306078914589672, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, doi=null, pmid=null, pmcid=null, year=2023, volume=20, issue=4, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[18], rfOrder=21, authorNames=Puffay C, Vanthornhout J, Gillis M, journalName=Journal of Neural Engineering, refType=null, unstructuredReference=Puffay C, Vanthornhout J, Gillis M, et al. Robust neural tracking of linguistic speech representations using a convolutional neural network[J]. Journal of Neural Engineering, 2023, 20(4): 046040., articleTitle=Robust neural tracking of linguistic speech representations using a convolutional neural network, refAbstract=null), Reference(id=1243306079061390319, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, doi=null, pmid=null, pmcid=null, year=2023, volume=154, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[19], rfOrder=22, authorNames=Luan X L, Huang Z L, journalName=International Journal of Non-Linear Mechanics, refType=null, unstructuredReference=Luan X L, Huang Z L. Stationary random response evaluation of nonlinear oscillators with Preisach hysteresis discretized by RNN model[J]. International Journal of Non-Linear Mechanics, 2023, 154:104449., articleTitle=Stationary random response evaluation of nonlinear oscillators with Preisach hysteresis discretized by RNN model, refAbstract=null), Reference(id=1243306079170442228, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, doi=null, pmid=null, pmcid=null, year=2023, volume=134, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[20], rfOrder=23, authorNames=Kumar B, Yadav N, journalName=Applied Soft Computing, refType=null, unstructuredReference=Kumar B, Yadav N. A novel hybrid model combining βSARMA and LSTM for time series forecasting[J]. Applied Soft Computing, 2023, 134:110019., articleTitle=A novel hybrid model combining βSARMA and LSTM for time series forecasting, refAbstract=null), Reference(id=1243306079304659961, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, doi=null, pmid=null, pmcid=null, year=2020, volume=34, issue=4, pageStart=367, pageEnd=383, url=null, language=null, rfNumber=[21], rfOrder=24, authorNames=Hasegawa K, Fukami K, Murata T, journalName=Theoretical and Computational Fluid Dynamics, refType=null, unstructuredReference=Hasegawa K, Fukami K, Murata T, et al. Machine-learning-based reduced-order modeling for unsteady flows around bluff bodies of various shapes[J]. Theoretical and Computational Fluid Dynamics, 2020, 34(4): 367-383., articleTitle=Machine-learning-based reduced-order modeling for unsteady flows around bluff bodies of various shapes, refAbstract=null), Reference(id=1243306079426294783, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, doi=null, pmid=null, pmcid=null, year=2022, volume=2022, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[22], rfOrder=25, authorNames=Chegini H G, Zarepour G, journalName=Geofluids, refType=null, unstructuredReference=Chegini H G, Zarepour G. Numerical study of rectangular tank with sloshing fluid and simulation of the model using a machine learning method[J]. Geofluids, 2022, 2022:4121956., articleTitle=Numerical study of rectangular tank with sloshing fluid and simulation of the model using a machine learning method, refAbstract=null), Reference(id=1243306079505985536, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, doi=null, pmid=null, pmcid=null, year=2022, volume=10, issue=10, pageStart=1375, pageEnd=null, url=null, language=null, rfNumber=[23], rfOrder=26, authorNames=Xie C, Liu X D, Man T H, journalName=Journal of Marine Science and Engineering, refType=null, unstructuredReference=Xie C, Liu X D, Man T H, et al. PWPNet: A deep learning framework for real-time prediction of significant wave height distribution in a port[J]. Journal of Marine Science and Engineering, 2022, 10(10): 1375., articleTitle=PWPNet: A deep learning framework for real-time prediction of significant wave height distribution in a port, refAbstract=null), Reference(id=1243306079619231748, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, doi=null, pmid=null, pmcid=null, year=2019, volume=50, issue=2, pageStart=1937, pageEnd=1949, url=null, language=null, rfNumber=[24], rfOrder=27, authorNames=Aurelio Y S, Almeida G M, Castro C L, journalName=Neural Processing Letters, refType=null, unstructuredReference=Aurelio Y S, Almeida G M, Castro C L, et al. Learning from imbalanced data sets with weighted cross-entropy function[J]. Neural Processing Letters, 2019, 50(2): 1937-1949., articleTitle=Learning from imbalanced data sets with weighted cross-entropy function, refAbstract=null), Reference(id=1243306079749255178, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, doi=null, pmid=null, pmcid=null, year=2019, volume=188, issue=null, pageStart=564, pageEnd=577, url=null, language=null, rfNumber=[25], rfOrder=28, authorNames=Moslemi M, Farzin A, Kianoush M R, journalName=Engineering Structures, refType=null, unstructuredReference=Moslemi M, Farzin A, Kianoush M R. Nonlinear sloshing response of liquid-filled rectangular concrete tanks under seismic excitation[J]. Engineering Structures, 2019, 188:564-577., articleTitle=Nonlinear sloshing response of liquid-filled rectangular concrete tanks under seismic excitation, refAbstract=null), Reference(id=1243306079891861519, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, doi=null, pmid=null, pmcid=null, year=2021, volume=49, issue=8, pageStart=1637, pageEnd=1641, url=null, language=null, rfNumber=[26], rfOrder=29, authorNames=吴婷婷, 许晓东, 吴云龙, journalName=计算机与数字工程, refType=null, unstructuredReference=吴婷婷,许晓东,吴云龙. 卷积神经网络中SPReLU激活函数的优化研究[J]. 计算机与数字工程2021, 49(8):1637-1641., articleTitle=卷积神经网络中SPReLU激活函数的优化研究, refAbstract=null), Reference(id=1243306081439559700, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, doi=null, pmid=null, pmcid=null, year=2021, volume=49, issue=8, pageStart=1637, pageEnd=1641, url=null, language=null, rfNumber=[26], rfOrder=30, authorNames=Wu T T, Xu X D, Wu Y L, journalName=Computer & Digital Engineering, refType=null, unstructuredReference=Wu T T, Xu X D, Wu Y L. Research on optimization of SPReLU activation function in convolutional neural network[J]. Computer & Digital Engineering, 2021, 49(8): 1637-1641. (in Chinese), articleTitle=Research on optimization of SPReLU activation function in convolutional neural network, refAbstract=null), Reference(id=1243306081536028698, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, doi=null, pmid=null, pmcid=null, year=2022, volume=3, issue=2, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[27], rfOrder=31, authorNames=NIiroomand M P, Morgan J W R, Cafolla C T, journalName=Machine Learning: Science and Technology, refType=null, unstructuredReference=NIiroomand M P, Morgan J W R, Cafolla C T, et al. On the capacity and superposition of minima in neural network loss function landscapes[J]. Machine Learning: Science and Technology, 2022, 3(2): 025004., articleTitle=On the capacity and superposition of minima in neural network loss function landscapes, refAbstract=null), Reference(id=1243306081653469214, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, doi=null, pmid=null, pmcid=null, year=2019, volume=192, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[28], rfOrder=32, authorNames=Xue M A, Chen Y, Zheng J, journalName=Ocean Engineering, refType=null, unstructuredReference=Xue M A, Chen Y, Zheng J, et al. Fluid dynamics analysis of sloshing pressure distribution in storage vessels of different shapes[J]. Ocean Engineering, 2019, 192:106582., articleTitle=Fluid dynamics analysis of sloshing pressure distribution in storage vessels of different shapes, refAbstract=null), Reference(id=1243306081808658465, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, doi=null, pmid=null, pmcid=null, year=2021, volume=143, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[29], rfOrder=33, authorNames=Jin X, Xue M A, Lin P Z, journalName=Soil Dynamics and Earthquake Engineering, refType=null, unstructuredReference=Jin X, Xue M A, Lin P Z. Numerical modeling and formulation of the runup of seismically-induced surge waves in idealized reservoirs[J]. Soil Dynamics and Earthquake Engineering, 2021, 143:106625., articleTitle=Numerical modeling and formulation of the runup of seismically-induced surge waves in idealized reservoirs, refAbstract=null), Reference(id=1243306081909321769, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, doi=null, pmid=null, pmcid=null, year=2009, volume=40, issue=6, pageStart=1636, pageEnd=1641, url=null, language=null, rfNumber=[30], rfOrder=34, authorNames=陈先来, 杨路明, journalName=中南大学学报(自然科学版), refType=null, unstructuredReference=陈先来,杨路明. 基于均矢量相似性的机器学习样本集划分[J]. 中南大学学报(自然科学版)2009, 40(6):1636-1641., articleTitle=基于均矢量相似性的机器学习样本集划分, refAbstract=null), Reference(id=1243306082001596461, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, doi=null, pmid=null, pmcid=null, year=2009, volume=40, issue=6, pageStart=1636, pageEnd=1641, url=null, language=null, rfNumber=[30], rfOrder=35, authorNames=Chen X L, Yang L M, journalName=Journal of Central South University (Science and Technology), refType=null, unstructuredReference=Chen X L, Yang L M. Partitioning machine learning sample set using similarity to mean vector[J]. Journal of Central South University (Science and Technology), 2009, 40(6): 1636-1641. (in Chinese), articleTitle=Partitioning machine learning sample set using similarity to mean vector, refAbstract=null)], funds=[Fund(id=1243306076129571696, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, awardId=2022YFS0541; 2024YFHZ0173, language=CN, fundingSource=四川省科技厅重点研发计划项目(2022YFS0541; 2024YFHZ0173), fundOrder=null, country=null), Fund(id=1243306076217652086, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, awardId=2022NSFSC0976; 2022NSFSC1066, language=CN, fundingSource=四川省自然科学基金青年项目(2022NSFSC0976; 2022NSFSC1066), fundOrder=null, country=null), Fund(id=1243306076335092601, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, awardId=2023YFQ0111, language=CN, fundingSource=四川省区域创新合作基金项目(2023YFQ0111), fundOrder=null, country=null), Fund(id=1243306076452533118, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, awardId=52109096, language=CN, fundingSource=国家自然科学基金青年项目(52109096), fundOrder=null, country=null), Fund(id=1243306076532224901, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, awardId=230806521252005, language=CN, fundingSource=教育部产学合作协同育人项目(230806521252005), fundOrder=null, country=null), Fund(id=1243306076611916681, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, awardId=2019QZKK0104, language=CN, fundingSource=科技部第二次青藏高原科学考察-极端天气气候事件与灾害风险(2019QZKK0104), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1243306068697264616, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, xref=1., ext=[AuthorCompanyExt(id=1243306068709847530, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, companyId=1243306068697264616, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.College of Electronic Engineering, Chengdu University of Information Technology, Chengdu 610225, China), AuthorCompanyExt(id=1243306068718236139, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, companyId=1243306068697264616, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.成都信息工程大学 电子工程学院,成都 610225)]), AuthorCompany(id=1243306068823093744, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, xref=2., ext=[AuthorCompanyExt(id=1243306068831482354, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, companyId=1243306068823093744, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.PowerChina Hebei Electric Power Engineering Co., Ltd., Shijiazhuang 050031, China), AuthorCompanyExt(id=1243306068860842484, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, companyId=1243306068823093744, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.中国电建集团 河北省电力勘测设计研究院有限公司,石家庄 050031)]), AuthorCompany(id=1243306068953117177, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, xref=3., ext=[AuthorCompanyExt(id=1243306068961505786, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, companyId=1243306068953117177, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3.School of Automation, Chengdu University of Information Technology, Chengdu 610225, China), AuthorCompanyExt(id=1243306068965700091, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, companyId=1243306068953117177, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3.成都信息工程大学 自动化学院,成都 610225)]), AuthorCompany(id=1243306069091529216, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, xref=4., ext=[AuthorCompanyExt(id=1243306069129277955, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, companyId=1243306069091529216, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=4.School of Architecture and Engineering, Liaocheng University, Liaocheng 252000, China), AuthorCompanyExt(id=1243306069137666564, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, companyId=1243306069091529216, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=4.聊城大学 建筑工程学院,山东 聊城 252000)])], figs=[ArticleFig(id=1243306072635716311, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, language=EN, label=Fig.1, caption=Flow diagram of neural network, figureFileSmall=wm7IHSAsqd10rnODbskUQQ==, figureFileBig=OXBBRDvd405E0KfKApwODQ==, tableContent=null), ArticleFig(id=1243306072744768224, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, language=CN, label=图1, caption=神经网络模型的流程图, figureFileSmall=wm7IHSAsqd10rnODbskUQQ==, figureFileBig=OXBBRDvd405E0KfKApwODQ==, tableContent=null), ArticleFig(id=1243306072967066351, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, language=EN, label=Fig.2, caption=Flow diagram of LSTM, figureFileSmall=BGMx4Ush6s58jhuE+8RDCg==, figureFileBig=8PWgfuhj50U9QvwLk0PnSg==, tableContent=null), ArticleFig(id=1243306073088701171, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, language=CN, label=图2, caption=LSTM的流程图, figureFileSmall=BGMx4Ush6s58jhuE+8RDCg==, figureFileBig=8PWgfuhj50U9QvwLk0PnSg==, tableContent=null), ArticleFig(id=1243306073189364473, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, language=EN, label=Fig.3, caption=Comparisons of time histories between numerical and experimental results, figureFileSmall=vRHVtA3OjwvpCOJ+m/2/KQ==, figureFileBig=ov+DEGAl1evuipBCumPRSw==, tableContent=null), ArticleFig(id=1243306073319387903, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, language=CN, label=图3, caption=数值结果[29]和实验结果[28]的时程比较, figureFileSmall=vRHVtA3OjwvpCOJ+m/2/KQ==, figureFileBig=ov+DEGAl1evuipBCumPRSw==, tableContent=null), ArticleFig(id=1243306073428439811, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, language=EN, label=Fig.4, caption=Comparisons of time histories between actual and predicted values from three neural network models in the training set, figureFileSmall=4JKS/95yKpEkX1kR4Qxw8A==, figureFileBig=4BpQckHAMsY9H3MKRIZr6A==, tableContent=null), ArticleFig(id=1243306073575240455, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, language=CN, label=图4, caption=训练集中三种神经网络模型预测结果与实际值的时程比较, figureFileSmall=4JKS/95yKpEkX1kR4Qxw8A==, figureFileBig=4BpQckHAMsY9H3MKRIZr6A==, tableContent=null), ArticleFig(id=1243306073730429712, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, language=EN, label=Fig.5, caption=Comparisons of time histories between actual and predicted values from three neural network models in the test set, figureFileSmall=dSXhRTRhC5h7xO3qAjqlug==, figureFileBig=roEg3XyJN8NigVfAfEqLQA==, tableContent=null), ArticleFig(id=1243306073839481626, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, language=CN, label=图5, caption=测试集中三种神经网络模型预测结果与实际值的时程比较, figureFileSmall=dSXhRTRhC5h7xO3qAjqlug==, figureFileBig=roEg3XyJN8NigVfAfEqLQA==, tableContent=null), ArticleFig(id=1243306073940144929, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, language=EN, label=Fig.6, caption=Rendezvous results between actual and predicted values from three neural network models in the training set, figureFileSmall=+WMcfOmfz/9454J1z4briA==, figureFileBig=RUOeALLLGt4YWDhpR1nCMg==, tableContent=null), ArticleFig(id=1243306074057585445, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, language=CN, label=图6, caption=训练集中三种神经网络模型预测结果与实际值的交会结果, figureFileSmall=+WMcfOmfz/9454J1z4briA==, figureFileBig=RUOeALLLGt4YWDhpR1nCMg==, tableContent=null), ArticleFig(id=1243306074296660779, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, language=EN, label=Fig.7, caption=Rendezvous results between actual and predicted values from three neural network models in the test set, figureFileSmall=9v5A8aHM6inmKLsmBxeBrg==, figureFileBig=S6mpwhulhOxu26ylQE1bxw==, tableContent=null), ArticleFig(id=1243306074489598770, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, language=CN, label=图7, caption=测试集中三种神经网络模型预测结果与实际值的交会结果, figureFileSmall=9v5A8aHM6inmKLsmBxeBrg==, figureFileBig=S6mpwhulhOxu26ylQE1bxw==, tableContent=null), ArticleFig(id=1243306074611233590, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, language=EN, label=Fig.8, caption=Time histories, figureFileSmall=P5ajsvdzN8CzoBbwiLPQoA==, figureFileBig=7vHpmj2bIgvaItK2DdZwjQ==, tableContent=null), ArticleFig(id=1243306074850308922, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, language=CN, label=图8, caption=时间历程, figureFileSmall=P5ajsvdzN8CzoBbwiLPQoA==, figureFileBig=7vHpmj2bIgvaItK2DdZwjQ==, tableContent=null), ArticleFig(id=1243306075080995648, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, language=EN, label=Fig.9, caption=Rendezvous results between actual and predicted values from three neural network models, figureFileSmall=Zj95te/D3n/T6+FAu2mK3Q==, figureFileBig=5hGE4zihhxfEY5YE2lQSvw==, tableContent=null), ArticleFig(id=1243306075265545031, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, language=CN, label=图9, caption=三种神经网络模型预测结果与实际值的交会结果, figureFileSmall=Zj95te/D3n/T6+FAu2mK3Q==, figureFileBig=5hGE4zihhxfEY5YE2lQSvw==, tableContent=null), ArticleFig(id=1243306075454288719, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, language=EN, label=Tab.1, caption=

Hyper-parameters of neural network

, figureFileSmall=null, figureFileBig=null, tableContent=
参数名值或类型
损失函数均方误差函数
优化器Adam
训练轮数50
批处理大小16(实验数据)或32(数值结果)
梯度下降0.2
), ArticleFig(id=1243306075559146325, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, language=CN, label=表1, caption=

神经网络超参数

, figureFileSmall=null, figureFileBig=null, tableContent=
参数名值或类型
损失函数均方误差函数
优化器Adam
训练轮数50
批处理大小16(实验数据)或32(数值结果)
梯度下降0.2
), ArticleFig(id=1243306075655615322, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, language=EN, label=Tab.2, caption=

Root mean square error between the predicted and actual values in training/test set

, figureFileSmall=null, figureFileBig=null, tableContent=
样本集类型CNN模型RNN模型LSTM模型
数值总压强0.0130/0.01310.0122/0.01010.0102/0.0071
实验总压强0.0334/0.02310.0371/0.02470.0373/0.0256
数值自由表面高程0.0011/0.00190.0009/0.00090.0007/0.0009
实验自由表面高程0.0028/0.00400.0028/0.00430.0028/0.0043
), ArticleFig(id=1243306075781444448, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, language=CN, label=表2, caption=

训练集/测试集的预测结果与实际值的均方根误差

, figureFileSmall=null, figureFileBig=null, tableContent=
样本集类型CNN模型RNN模型LSTM模型
数值总压强0.0130/0.01310.0122/0.01010.0102/0.0071
实验总压强0.0334/0.02310.0371/0.02470.0373/0.0256
数值自由表面高程0.0011/0.00190.0009/0.00090.0007/0.0009
实验自由表面高程0.0028/0.00400.0028/0.00430.0028/0.0043
), ArticleFig(id=1243306075865330532, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, language=EN, label=Tab.3, caption=

Goodness-of-fit between predicted and actual values in training/test set

, figureFileSmall=null, figureFileBig=null, tableContent=
样本集类型CNN模型RNN模型LSTM模型
数值总压强0.990 09/0.994 550.991 32/0.996 800.993 88/0.998 39
实验总压强0.909 10/0.974 350.887 52/0.970 660.886 64/0.968 53
数值自由表面高程0.994 85/0.992 780.996 48/0.998 510.997 65/0.998 48
实验自由表面高程0.961 79/0.949 040.960 63/0.942 930.961 18/0.941 08
), ArticleFig(id=1243306075986965352, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306062825238809, language=CN, label=表3, caption=

训练集/测试集的预测结果与实际值的拟合优度

, figureFileSmall=null, figureFileBig=null, tableContent=
样本集类型CNN模型RNN模型LSTM模型
数值总压强0.990 09/0.994 550.991 32/0.996 800.993 88/0.998 39
实验总压强0.909 10/0.974 350.887 52/0.970 660.886 64/0.968 53
数值自由表面高程0.994 85/0.992 780.996 48/0.998 510.997 65/0.998 48
实验自由表面高程0.961 79/0.949 040.960 63/0.942 930.961 18/0.941 08
)], 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.1007-7294.2025.03.005, detailUrlEn=https://castjournals.cast.org.cn/joweb/cblx/EN/10.3969/j.issn.1007-7294.2025.03.005, pdfUrlCn=https://castjournals.cast.org.cn/joweb/cblx/CN/PDF/10.3969/j.issn.1007-7294.2025.03.005, pdfUrlEn=https://castjournals.cast.org.cn/joweb/cblx/EN/PDF/10.3969/j.issn.1007-7294.2025.03.005, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于神经网络的流体晃荡波高和压强的预测研究
收藏切换
PDF下载
金鑫 1 , 王宇圣 1 , 张福贵 1 , 陈健 2 , 李登松 3 , 樊昌元 1 , 刘名名 4
船舶力学 | 流体力学 2025,29(3): 388-399
收起
收藏切换
船舶力学 | 流体力学 2025, 29(3): 388-399
基于神经网络的流体晃荡波高和压强的预测研究
全屏
金鑫1, 王宇圣1, 张福贵1, 陈健2, 李登松3, 樊昌元1, 刘名名4
作者信息
  • 1.成都信息工程大学 电子工程学院,成都 610225
  • 2.中国电建集团 河北省电力勘测设计研究院有限公司,石家庄 050031
  • 3.成都信息工程大学 自动化学院,成都 610225
  • 4.聊城大学 建筑工程学院,山东 聊城 252000
  • 金鑫(1988-),男,博士,副教授

    刘名名(1986-),男,博士,研究员,通讯作者,E-mail:

通讯作者:

通讯作者,E-mail:
Predictions of wave height and pressure induced by liquid sloshing based on neural network
Xin JIN1, Yu-sheng WANG1, Fu-gui ZHANG1, Jian CHEN2, Deng-song LI3, Chang-yuan FAN1, Ming-ming LIU4
Affiliations
  • 1.College of Electronic Engineering, Chengdu University of Information Technology, Chengdu 610225, China
  • 2.PowerChina Hebei Electric Power Engineering Co., Ltd., Shijiazhuang 050031, China
  • 3.School of Automation, Chengdu University of Information Technology, Chengdu 610225, China
  • 4.School of Architecture and Engineering, Liaocheng University, Liaocheng 252000, China
出版时间: 2025-03-20 doi: 10.3969/j.issn.1007-7294.2025.03.005
文章导航
收藏切换

基于Navier-Stokes方程的数值模型和物理模型实验研究流体晃荡现象存在计算效率低和经济成本高的不足。为此,本文通过构建神经网络模型对数值和实验结果进行时序重构,预测流体晃荡的压强和波高。以数值和实验的总压强和自由表面高程数据作为训练样本,将神经网络中表征能力强的CNN、RNN、LSTM用于重演流体晃荡响应的时间演化过程。在模型训练过程中,系统地调节神经网络的内部结构参数,分析预测结果与实际值之间的误差和相关性。结果表明,RNN和LSTM的重构误差低于4%,相关性达到0.88,整体优于CNN;LSTM的整体性能最佳,可以作为预测长序列数据的首选。整体来讲,三种代理模型均可以较好地复现流体晃荡的波高和压强,在流体晃荡研究方面具有良好的应用前景。

流体晃荡  /  神经网络  /  数值模拟  /  预测

Numerical modelling based on Navier-Stokes equations and model experiment for studying liquid sloshing have the limits of low computational efficiency and high economic cost. Therefore, to predict the hydrodynamic pressure and wave height, the time-histories to numerical and experimental results were reconstructed in this paper through the neural network model. The total numerical and experimental pressures and free surface elevations were taken as training samples, and CNN, RNN and LSTM with strong repretational ability were used to reproduce the sloshing responses. The internal structural parameters of the neural network were systematically adjusted, besides, the errors and correlations between the predicted and actual values were analyzed. The results show that the error is lower than 4% and the correlations of both RNN and LSTM reach 0.88, which is in general superior to CNN, and that LSTM is optimal in predicting the long sequence data. Overall, three surrogate models can well predict the sloshing wave height and pressure, and are promising in the study of liquid sloshing.

liquid sloshing  /  neural network  /  numerical simulation  /  prediction
金鑫, 王宇圣, 张福贵, 陈健, 李登松, 樊昌元, 刘名名. 基于神经网络的流体晃荡波高和压强的预测研究. 船舶力学, 2025 , 29 (3) : 388 -399 . DOI: 10.3969/j.issn.1007-7294.2025.03.005
Xin JIN, Yu-sheng WANG, Fu-gui ZHANG, Jian CHEN, Deng-song LI, Chang-yuan FAN, Ming-ming LIU. Predictions of wave height and pressure induced by liquid sloshing based on neural network[J]. Journal of Ship Mechanics, 2025 , 29 (3) : 388 -399 . DOI: 10.3969/j.issn.1007-7294.2025.03.005
流体晃荡作为流体力学的一个重要分支,与人类生活和工业生产息息相关,在海洋工程、航空航天、化工材料等领域具有重要的作用[1-3]。近年来,基于非线性势流理论和Navier-Stokes方程的数值模型广泛用于流体晃荡的研究。李裕龙等[4]基于非线性势流理论的数值模型,研究三舱内液体晃荡对船体运动的影响。Xue等[5]采用OpenFoam模拟了水平激励下不同形状储罐内流体的晃荡模式,并分析了流体载荷的频域特性。Takami等[6]基于光滑粒子流体力学(SPH)预测了矩形储罐做不规则旋转运动时流体的极限压力。尽管上述数值手段可以准确地分析流体晃荡现象,但也存在不足,例如其计算较为耗时,通常要数小时甚至几天[7],且涉及复杂的离散网格和边界条件等问题[8]。因此,使用替代方法在短时间内重构流体晃荡的基本特征十分必要。
随着人工智能(AI)的兴起,基于机器学习(ML)建立代理模型是最有效的替代方法之一。近年来,代理模型如支持向量机(SVM)[9]、随机森林(RF)[10]、人工神经网络(ANN)[11]等已逐步应用于流体力学研究。ANN是近年来较为流行的模型,其基于人脑思维,可以从大量复杂、非线性和非平稳性的时间序列中学习到隐藏的规律,给予研究人员前瞻性信息[12]。为了准确地预测流体的运动规律,选取的神经网络模型及其结构参数因场景不同而异。卷积神经网络(CNN)、循环神经网络(RNN)和长短期记忆网络(LSTM)是三种常用的神经网络模型,与其它神经网络模型相比,具有局部表征能力强和权值共享(参数数量减少降低了训练难度)等优势[13-14]。Peng等[7]设计了一种降阶模型,将CNN作为编码器,反卷积神经网络(DCNN)作为解码器(重建由CNN编码器提取到的特征信息),实现了对流场的快速预测,为非定常流动问题研究提供了新思路。Murata等[15]将CNN和自编码器(AE)相结合,构造了一种新的神经网络模型用于流场重建,结果表明,该模型比传统正交分解(POD)模式提取流场特征的能力更强。Liu等[16]将CNN和LSTM相结合,开发了一种神经网络结构,对流场的瞬时状态进行了训练和优化,可有效地预测湍流粘度场。Meng等[17]使用LSTM模型对规则波、不规则波和真实海浪波高的长期演化趋势进行了精确的预测,并通过改变输入长度进一步提高了预测的精度。
为了预测流体晃荡的压强和波高,本文采用CNN、RNN和LSTM三种神经网络模型重现总压强和自由表面高程的时序演变过程。结果表明:CNN、RNN、LSTM三种神经网络模型的均方根误差小于4%,拟合优度普遍大于0.88,说明上述模型均可以有效提取到总压强和自由表面高程的时程信息,能够精准地预测流体晃荡压强和波高的时序信息。
本文将神经网络模型的建立分为样本集划分、模型结构搭建、模型编译和模型训练四个部分,如图1所示。
具体步骤如下:
(1)按照一定比例将输入样本划分为训练集和测试集;
(2)构建由适当数量的输入层、隐藏层和输出层组成的神经网络结构,并在每层网络中设置合适的神经元个数和激活函数;
(3)选择适当的优化器和损失函数对模型进行编译;
(4)设置适当的迭代次数和批处理大小对模型进行训练。
CNN、RNN、LSTM是ANN中具有代表性的三种模型,其特点分别是:CNN可以高效地提取数据的局部特征,最大限度地规避过拟合问题;RNN源于CNN,引入了时间联结功能,即神经元输入的顺序将影响训练的结果;LSTM是RNN的一种衍生模型,避免了神经网络层数多、结构繁琐引起的梯度消失或爆炸现象。虽然上述模型在多个领域已有应用[18-20],但在流体晃荡方面的研究效果仍未可知。基于此,本文采用上述三种模型预测流体的晃荡压强和波高,并对它们的预测效果进行了讨论。鉴于三种模型的原理基本一致,下面以LSTM为例,其流程如图2所示。
LSTM的运算分为忘记、选择记忆和输出三个阶段。忘记阶段对上一节点传递的输入信息进行选择性忘记,以ft作为忘记门控,控制Ct−1将获得的信息进行保留或忘记;选择记忆阶段将输入信息进行选择性记忆,其门控信号由it控制,通过归一化并整合新输入信息得到新的状态Ct;输出阶段决定当前状态的输出对象,具体方法是将门控信号ot与缩放过的Ct进行卷积,得到一个步长的输出。以上计算如式(1)~(6)所示[21]
式中,[ht−1Xt]表示两个向量的连接,WfWiWcWobfbibcbo分别表示四个状态的权重和偏差。
在搭建神经网络之前,将已知数据按照一定比例划分为训练集和测试集两部分。训练集用于更新模型的参数,测试集用于评价模型的泛化能力。由于不同数据在数值上差异可能很大,量纲也不一致,直接取值对模型参数的优化非常不利。因此,为了提高模型训练的速度和精度,将训练数据进行归一化处理,如式(7)所示:
式中,XmaxXmin分别表示训练集中数据的最大值和最小值,Xi为当前数值,XnXi的规一化值[22]。经过归一化后,所有数据都在0和1之间。采用均方根误差(RMSE)和拟合优度(R2)来衡量预测的精确度,分别如式(8)和式(9)所示[23]
式中,n为样本数量,ri是第i个样本的真实值,pi是第i个样本的预测值,是所有真实样本的平均值,是所有样本预测结果的平均值。
建立和编译神经网络模型时,选择合适的反向传播算法、激活函数和损失函数至关重要。其中,激活函数在建立CNN模型时设置,反向传播算法和损失函数在编译三种模型时设置。尽管这些参量的设置在前人的研究中有所体现,但未有关于不同应用场景的通用设置。此外,文中未提及的一些参量,如训练轮数、批处理大小等,也需要根据不同的物理现象灵活调试,找到最佳值。
反向传播算法(BP)的原理是通过逐层求偏导优化先前神经元的权重[24]。利用现代编程软件,可以在优化器(Optimizer)中设置反向传播算法的类型。常用的BP类型有随机梯度下降法(SGD)、动量法(Adam)等。与传统的随机梯度下降法相比,Adam可以为参数设计独立的自适应性学习率,适合应用于非稳态目标,解决大规模数据和参数的优化问题。因此,本文采用Adam优化算法。
激活函数(Activation)借助误差梯度调节神经元的权重和偏差,用于拟合神经网络模型的非线性(不规则性)特征[25]。ReLU作为卷积层中常用的激活函数,将输出结果进行非线性映射,其数学表达式[26]
该函数的值域为正实数,且斜率始终为1,使得神经网络有了稀疏特性,可以解决梯度消失的问题。
损失函数(Loss)用来衡量预测值和真实值之间的差异。对于回归问题,常用的损失函数是均方误差函数[27],其数学表达式为
式中,p表示真实值的分布,q表示预测值的分布。
本文采用Xue等[28](2019)的实验数据和Jin等[29](2021)的数值模拟结果作为输入样本。实验数据的采样间隔为0.06 s,数值模拟结果的采样间隔为0.01 s。数值和实验得到的流体晃荡总压强和自由表面高程的时程比较关系如图3所示。
可以看出,除了图3(a)的初始段(前1.5 s,归结于实验仪器突然启动带来的干扰)和极值点处(实验采样频率相对较低,遗漏部分极值),数值结果和实验数据较为吻合。
本文使用Python中的Keras库完成CNN、RNN、LSTM模型的构建。三种模型均由1个输入层、3个隐藏层和1个输出层组成,每个隐藏层的神经元个数为128。在CNN中,采用一维卷积,卷积层的内核大小设为3,池化层的池大小和跨度均设置为3,激活函数选择ReLU。在RNN和LSTM中,将数值结果和实验数据样本的输入步长分别设为50和10。最后设置与神经网络模型编译和训练有关的超参数,原理如下:
(1)损失函数:根据研究问题的类型进行确定。本文对流体晃荡压强和波高的时序重构属于回归问题,因此选用均方误差函数。
(2)优化器:根据数据的特点进行确定。针对流体晃荡波高和压强数据规模庞大和不规则的特点,本文选用Adam优化器以更好地优化参数。
(3)训练轮数:根据损失函数的变化进行确定。三种模型在训练轮数超过50后,损失函数均不再有明显变化的趋势,此时停止迭代不再训练,最终将训练轮数设定为50。
(4)批处理大小:根据数据量进行确定。通常情况下,数据量越大,批处理大小的值越大。基于以上原理,本文将数值和实验数据的批处理大小分别设为32和16。
(5)梯度下降:为防止出现过拟合现象而设定。其原理是每经过一层神经网络,模型丢弃部分数据。一般而言,每层丢弃数据的比例为0.2。基于以上原则,本文将该参数设置为0.2。
综上所述,神经网络超参数的设置如表1所示。
基于样本集划分理论[30],选取了三种不同比例的训练样本,分别为70%、80%和90%。对比发现,当样本比例为90%时,模型的预测效果最佳。因此,选取前90%的数据作为训练样本,剩余的10%数据作为测试样本。图4图5分别展示了训练集(部分)和测试集中CNN、RNN、LSTM三种模型预测结果与实际值的时程比较关系。
图4图5可以看出,三种模型得到的时程数据与真实结果较为接近,预测效果整体较好,但在局部存在一定的差异(如图4(b)的10.2 s至10.6 s和图5(d)的28.8 s至29 s,数据在该时段的波动较强,预测效果相对较差),这与波浪的非线性特性紧密相关。一般来说,波浪的非线性越强,神经网络模型的预测精度相应降低[17]。例如,三种模型对极值点的预测效果较其它位置差,这是因为波浪在此刻变化最剧烈,非线性最强。此外,RNN和LSTM模型对极值点的预测效果较CNN更佳(如图5(a)和(c)所示),说明在重构非线性数据方面,RNN和LSTM模型的性能优于CNN模型。鉴于图4图5不能直观地量化预测效果,下面将通过误差分析进行细致描述。
表2列举了训练集和测试集中不同样本预测结果与实际值的均方根误差。可以得出:对于所有样本,三种模型的均方根误差均不显著,说明三者的解算结果均能较好地接近真实数据。在训练集和测试集中,三种模型的均方根误差相近,说明通过对样本的训练,神经网络已经提取到充足的信息,可以根据学习到的规律比较精确地拟合训练集之外的样本。对于同一样本中的训练集或测试集,三种模型的均方根误差没有明显的差异。因此在满足精度的前提下,为了提高计算效率,可以优先采用CNN模型。
下面具体分析不同样本的均方根误差。对于实验结果,三种模型的均方根误差十分接近。对于数值结果(其样本容量大于实验结果),RNN和LSTM模型的均方根误差普遍小于CNN模型,主要归结于RNN和LSTM模型适合处理有长期依赖关系的数据,而CNN模型没有“记忆”效应。因此,当处理数据量较大的序列时,如果对预测精度要求高,可以优先使用RNN或LSTM模型。此外,在同一模型中,数值和实验的自由表面高程的均方根误差总是小于数值和实验的总压强,这也与流体晃荡的非线性特性密切相关。在自由表面高程和总压强的时程曲线中,总压强关于平衡位置的不对称性较自由表面高程更为明显,属于典型的非线性特性。因此,自由表面高程(非线性较弱)的预测效果好于总压强(非线性较强)是合理的。
综合上述结果可以推断,三种代理模型的预测效果优异,均可应用于流体晃荡研究;对于线性特性较强或容量较小的样本集,三种模型的预测结果基本无差异;对于非线性较强或大容量样本集,RNN和LSTM模型比CNN模型的预测精度更高。在实际应用中,可根据不同情况选择对应的代理模型。
图6图7分别展现了训练集和测试集中,CNN、RNN和LSTM预测结果与实际值的交会结果。可以看出:大部分数据点都集中在理想线附近,说明预测结果与实际值的相关性良好。此外,图6(c)图7(c)中的数据点与理想线最为接近,且CNN模型数据点偏离理想线的程度略大于RNN和LSTM模型,表明对于数值的自由表面高程,预测结果与实际值的相关性是所有样本中最佳的,且RNN和LSTM模型的拟合效果优于CNN模型,主要是因为该样本满足非线性特性显著和容量大的双重特点,根据3.1节的分析,其预测效果优异是合理的。
对比图6图7不难发现:图6中数值和实验总压强的相关性均低于数值和实验的自由表面高程,而图7中数值和实验总压强的相关性高于数值和实验的自由表面高程。从3.1节得知,总压强在平衡位置的不对称性比自由表面高程更强,非线性特征更为突出,理论上预测的精度更高,而图6呈现的规律恰好印证了这一结论。尽管图7不能印证上述结论,但不能说明理论推演的失效。潜在原因是测试集的样本量远小于训练集,不足以体现普遍存在的规律。
为了证明这一规律的普遍性,下面补充一个样本案例进行说明。我们通过Fluent仿真了塔巴斯地震激励(图8(a))下长度为20 m、水深为12 m的一个液舱内的流体晃荡问题,激发的自由表面高程如图8(b)所示。可以发现,该样本的非线性,即波峰和波谷的非对称性,明显强于上述的自由表面高程样本。CNN、RNN、LSTM三种神经网络模型中的参数设置与前文保持一致。三种模型对训练集和测试集的预测结果与实际值的交会结果分别如图9所示。
图9可以看出,RNN和LSTM的预测效果明显优于CNN,再一次证明了对于非线性较强的数据序列,RNN和LSTM模型的重构能力强于CNN。将此样本与上述的数值自由表面高程样本的预测结果进行比较,可以发现此样本数据点偏离理想线的程度更大。以上结果表明,数据的非线性会显著地影响模型的预测效果。一般而言,非线性越强,模型的预测性能越差。
本文还通过拟合优度对预测结果与实际值的相关性进行了量化,三种模型的拟合优度如表3所示。从表中可知,所有样本的拟合优度均在0.88以上,表明预测结果与实际值的拟合特性较强。尤其是数值结果的拟合优度均超过了0.99,这主要归结于:随着训练样本量的逐步增大,神经网络提取到的信息越全面,模型预测的精准性进一步提高,可以从数值结果的相关结论印证(其拟合优度近似于1且高于实验结果)。此外,对于数值结果,RNN和LSTM模型的拟合优度大于CNN模型,即相关性强于CNN模型,而对于实验结果则不一定出现此规律。上述讨论结果再次印证了RNN和LSTM模型在预测长序列数据的准确度方面较CNN模型更佳。
本文实现了基于CNN、RNN和LSTM三种神经网络模型对流体晃荡的总压强和自由表面高程的准确预测。研究结果表明:
(1)神经网络模型具有预测非线性复杂数据序列的潜力。本文采用的神经网络模型均能精准地捕捉流体晃荡时波高和压强的主要特征,尽管预测值和真实值存在一定的偏差,但误差整体较小,证明了神经网络模型在流体晃荡预测方面的实用性。
(2)样本量对模型预测的准确度有一定影响。对于大容量的数值样本集,RNN和LSTM模型的误差小于CNN模型,相关性强于CNN模型,优于样本量较小的实验样本集,凸显了RNN和LSTM模型具有一定记忆功能的优越性。
(3)样本的非线性特性是影响预测精度的重要因素之一。对于数值和实验的总压强,三种模型的均方根误差均大于0.005,反观数值和实验的自由表面高程,其均方根误差均小于0.005。本文中总压强时程曲线的非线性特性比自由表面高程更强,因此预测结果与实际值的偏离程度相对较大。
(4)基于神经网络模型对流体晃荡的波高和压强的时序重构技术,其花费和预测时间远小于传统的数值模型和模型实验,有望用于快速准确地研究真实的流体晃荡现象。下一步工作将着重探究神经网络结构参数对预测结果的影响以及如何提高预测的精确度。
  • 四川省科技厅重点研发计划项目(2022YFS0541; 2024YFHZ0173)
  • 四川省自然科学基金青年项目(2022NSFSC0976; 2022NSFSC1066)
  • 四川省区域创新合作基金项目(2023YFQ0111)
  • 国家自然科学基金青年项目(52109096)
  • 教育部产学合作协同育人项目(230806521252005)
  • 科技部第二次青藏高原科学考察-极端天气气候事件与灾害风险(2019QZKK0104)
参考文献 引证文献
排序方式:
[1]
Tao K D, Zhou X Q, Ren H L. The application of an advanced coupled SPH-BEM algorithm to 2D fluid sloshing simulation[J]. Engineering Analysis with Boundary Elements, 2022, 138:280-300.
[2]
Saltari F, Pizzoli M, Gambioli F, et al. Sloshing reduced-order model based on neural networks for aeroelastic analyses[J]. Aerospace Science and Technology, 2022, 127:107708.
[3]
朱奎松,赵英涛,曹丽,. 计算流体力学数值计算在化工原理实践课程教学中的应用[J]. 当代化工研究2021(22):139-141.
Zhu Q S, Zhao Y T, Cao L, et al. Application of computational fluid dynamics numerical calculation in the teaching of chemical engineering principle practice course[J]. Modern Chemical Research, 2021(22): 139-141.
[4]
李裕龙,朱仁传,缪国平,. 基于OpenFOAM的船舶与液舱流体晃荡在波浪中时域耦合运动的数值模拟[J]. 船舶力学2012, 16(7):750-758.
Li Y L, Zhu R C, Miu G P, et al. Simulation of ship motions coupled with tank sloshing in time domain based on OpenFOAM[J]. Journal of Ship Mechanics, 2012, 16(7): 750-758.
[5]
Xue M A, Chen Y C, Zheng J H, et al. Fluid dynamics analysis of sloshing pressure distribution in storage vessels of different shapes[J]. Ocean Engineering, 2019, 192:106582.
[6]
Takami T, Ma C. Surrogate model approach for stochastic prediction of sloshing-induced pressure based on SPH with FORM[J]. Ships and Offshore Structures, 2023, 18(2): 143-156.
[7]
Peng J Z, Chen S H, Aubry N, et al. Time-variant prediction of flow over an airfoil using deep neural network[J]. Physics of Fluids, 2020, 32(12): 123602.
[8]
Huang Y, Zhang Z Y, Zhang X, et al. A direct-forcing immersed boundary method for incompressible flows based on physics-informed neural network[J]. Fluids, 2022, 7(2): 56.
[9]
Liu Q, Feng X Y, Tang T N. A machine learning model for wave prediction based on support vector machine[J]. International Journal of Offshore and Polar Engineering, 2022, 32(4): 394-401.
[10]
Ye Z T, Shi F Y, Zhao X Z, et al. A data-driven approach to modeling subgrid-scale shallow marsh hydrodynamics[J]. Coastal Engineering, 2021, 166:103856.
[11]
Guo C, Cui S A, Zeng G, et al. Vehicle stochastic response prediction of sea-crossing railway bridges under correlated wind and wave via machine learning[J]. Ocean Engineering, 2023, 270:113714.
[12]
Zhang C P, Li S, Ye M, et al. Learning various length dependence by dual recurrent neural networks[J]. Neurocomputing, 2021, 466:1-15.
[13]
韩仁坤,刘子扬,钱炜祺,. 基于深度神经网络的流场时空重构方法[J]. 实验流体力学2022, 36(3):118-126.
Han R K, Liu Z Y, Qian W Q, et al. Spatio-temporal reconstruction method of flow field based on deep neural network[J]. Journal of Experiments in Fluid Mechanics, 2022, 36(3): 118-126. (in Chinese)
[14]
惠心雨,袁泽龙,白俊强,. 基于深度学习的非定常周期性流动预测方法[J]. 空气动力学学报2019, 37(3):462-469.
Hui X Y, Yuan Z L, Bai J Q, et al. A method of unsteady periodic flow field prediction based on the deep learning[J]. Acta Aerodynamica Sinica, 2019, 37(3): 462-469. (in Chinese)
[15]
Murata T, Fukami K, Fukagata K. Nonlinear mode decomposition with convolutional neural networks for fluid dynamics[J]. Journal of Fluid Mechanics, 2020, 882:A13.
[16]
Liu Y, Hu R, Kraus A, et al. Data-driven modeling of coarse mesh turbulence for reactor transient analysis using convolutional recurrent neural networks[J]. Nuclear Engineering and Design, 2022, 390:111716.
[17]
Meng Z F, Chen Z, Khoo B C, et al. Long-time prediction of sea wave trains by LSTM machine learning method[J]. Ocean Engineering, 2022, 262:112213.
[18]
Puffay C, Vanthornhout J, Gillis M, et al. Robust neural tracking of linguistic speech representations using a convolutional neural network[J]. Journal of Neural Engineering, 2023, 20(4): 046040.
[19]
Luan X L, Huang Z L. Stationary random response evaluation of nonlinear oscillators with Preisach hysteresis discretized by RNN model[J]. International Journal of Non-Linear Mechanics, 2023, 154:104449.
[20]
Kumar B, Yadav N. A novel hybrid model combining βSARMA and LSTM for time series forecasting[J]. Applied Soft Computing, 2023, 134:110019.
[21]
Hasegawa K, Fukami K, Murata T, et al. Machine-learning-based reduced-order modeling for unsteady flows around bluff bodies of various shapes[J]. Theoretical and Computational Fluid Dynamics, 2020, 34(4): 367-383.
[22]
Chegini H G, Zarepour G. Numerical study of rectangular tank with sloshing fluid and simulation of the model using a machine learning method[J]. Geofluids, 2022, 2022:4121956.
[23]
Xie C, Liu X D, Man T H, et al. PWPNet: A deep learning framework for real-time prediction of significant wave height distribution in a port[J]. Journal of Marine Science and Engineering, 2022, 10(10): 1375.
[24]
Aurelio Y S, Almeida G M, Castro C L, et al. Learning from imbalanced data sets with weighted cross-entropy function[J]. Neural Processing Letters, 2019, 50(2): 1937-1949.
[25]
Moslemi M, Farzin A, Kianoush M R. Nonlinear sloshing response of liquid-filled rectangular concrete tanks under seismic excitation[J]. Engineering Structures, 2019, 188:564-577.
[26]
吴婷婷,许晓东,吴云龙. 卷积神经网络中SPReLU激活函数的优化研究[J]. 计算机与数字工程2021, 49(8):1637-1641.
Wu T T, Xu X D, Wu Y L. Research on optimization of SPReLU activation function in convolutional neural network[J]. Computer & Digital Engineering, 2021, 49(8): 1637-1641. (in Chinese)
[27]
NIiroomand M P, Morgan J W R, Cafolla C T, et al. On the capacity and superposition of minima in neural network loss function landscapes[J]. Machine Learning: Science and Technology, 2022, 3(2): 025004.
[28]
Xue M A, Chen Y, Zheng J, et al. Fluid dynamics analysis of sloshing pressure distribution in storage vessels of different shapes[J]. Ocean Engineering, 2019, 192:106582.
[29]
Jin X, Xue M A, Lin P Z. Numerical modeling and formulation of the runup of seismically-induced surge waves in idealized reservoirs[J]. Soil Dynamics and Earthquake Engineering, 2021, 143:106625.
[30]
陈先来,杨路明. 基于均矢量相似性的机器学习样本集划分[J]. 中南大学学报(自然科学版)2009, 40(6):1636-1641.
Chen X L, Yang L M. Partitioning machine learning sample set using similarity to mean vector[J]. Journal of Central South University (Science and Technology), 2009, 40(6): 1636-1641. (in Chinese)
2025年第29卷第3期
PDF下载
63
29
引用本文
BibTeX
文章信息
doi: 10.3969/j.issn.1007-7294.2025.03.005
  • 接收时间:2024-09-25
  • 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:2024-09-25
基金
四川省科技厅重点研发计划项目(2022YFS0541; 2024YFHZ0173)
四川省自然科学基金青年项目(2022NSFSC0976; 2022NSFSC1066)
四川省区域创新合作基金项目(2023YFQ0111)
国家自然科学基金青年项目(52109096)
教育部产学合作协同育人项目(230806521252005)
科技部第二次青藏高原科学考察-极端天气气候事件与灾害风险(2019QZKK0104)
作者信息
    1.成都信息工程大学 电子工程学院,成都 610225
    2.中国电建集团 河北省电力勘测设计研究院有限公司,石家庄 050031
    3.成都信息工程大学 自动化学院,成都 610225
    4.聊城大学 建筑工程学院,山东 聊城 252000

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.1007-7294.2025.03.005
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