Article(id=1243879757155251195, tenantId=1146029695717560320, journalId=1240685776644648972, issueId=1243879752042398333, articleNumber=null, orderNo=null, doi=10.3969/j.issn.1007-7294.2024.08.004, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1708963200000, receivedDateStr=2024-02-27, revisedDate=null, revisedDateStr=null, acceptedDate=null, acceptedDateStr=null, onlineDate=1774493644273, onlineDateStr=2026-03-26, pubDate=1724083200000, pubDateStr=2024-08-20, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1774493644273, onlineIssueDateStr=2026-03-26, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1774493644273, creator=13701087609, updateTime=1774493644273, updator=13701087609, issue=Issue{id=1243879752042398333, tenantId=1146029695717560320, journalId=1240685776644648972, year='2024', volume='28', issue='8', pageStart='1133', pageEnd='1296', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1774493643055, creator=13701087609, updateTime=1774493947997, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1243881031133147325, tenantId=1146029695717560320, journalId=1240685776644648972, issueId=1243879752042398333, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1243881031133147326, tenantId=1146029695717560320, journalId=1240685776644648972, issueId=1243879752042398333, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=1162, endPage=1174, ext={EN=ArticleExt(id=1243879757541126146, articleId=1243879757155251195, tenantId=1146029695717560320, journalId=1240685776644648972, language=EN, title=A ship hull offset feature cognition and generation method based on conditional deep convolutional generative adversarial networks, columnId=1241023037940748650, journalTitle=Journal of Ship Mechanics, columnName=Hydrodynamics, runingTitle=null, highlight=null, articleAbstract=

The hull form modelling progress in ship design is significantly relied on the parent hull database and the professional designers well trained with CAD software, and it is usually a time and experience costly work. The conditional generation of ship hull with both geometrical and locational features by training an artificial neural network was concerned by this paper. The geometrical feature means the overall shape variety of ship designs like bulbous bow, stern shaft, etc., the locational feature means the shape difference between stern, front and mid-body of ships. Firstly, a conditional deep-convolutional generative adversarial network (CDC-GAN) was constructed to distinguish the geometrical and locational features individually; Secondly, the CDC-GAN was well trained to learn and generate these features with different resolutions and categories, from easy to hard; In the end, the training cost and performance of networks were compared and concluded to prove the capability of CDC-GAN in solving ship hull form generating issues. This paper is based on authors’ previous investigation with regular GAN, and it provides a further exploration about the potential of CDC-GAN in ship design.

, 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=Lin DU, Sheng-zhong LI, Guang-nian LI, Yue-hui SHU, Zi-xiang LIU, Feng ZHAO), CN=ArticleExt(id=1243879762461044863, articleId=1243879757155251195, tenantId=1146029695717560320, journalId=1240685776644648972, language=CN, title=基于深度卷积生成式对抗网络的船型特征认知与条件生成方法, columnId=1241023038087549292, journalTitle=船舶力学, columnName=流体力学, runingTitle=null, highlight=null, articleAbstract=

船体型值与图片一样也是序列相关型数据,所以用于生成图片的神经网络模型也能生成船型数据。由于船舶种类繁多、需求复杂,本文研究重点从船舶水线上下、船艏、舯、艉等区域位置特征,和船舶设计中普遍存在球艏、尾轴、艏部外板升高等全局几何特征的条件生成需求出发,训练条件深度卷积生成式对抗网络模型(Conditional Deep Convolutional Generative Adversarial Networks)来实现两种特征的条件认知与生成。首先,将实现船型区域位置特征与全局几何特征的条件生成作为目标,分别建立条件深度卷积生成式对抗网络模型;然后,针对两类特征设置若干从易到难的不同分割方案和特征种类,使神经网络能够循序渐进地完成条件生成任务;最后,通过对训练过程和生成结果进行对比,初步证明所研究方法用于解决船型特征条件生成问题的可行性。本研究延续了作者之前的研究成果,属于基于计算机视觉技术的船型智能设计方法领域,旨在进一步探索引入人工智能实现船型智能设计的可行性方法。

, correspAuthors=null, authorNote=null, correspAuthorsNote=
通讯作者,E-mail:
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=ATXwg4VRm+0RJP/LMndGzA==, magXml=JwbN2Rw0KxnonfQKeGTutQ==, pdfUrl=null, pdf=Z5XsGuiWxRBxjVIzy5h0NQ==, pdfFileSize=2129289, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=3lldjk6Ekblcu2yF8f8Cvg==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=1N2yOx9WLhfDe0pYFh+2og==, mapNumber=null, authorCompany=null, fund=null, authors=

杜林(1988-),男,博士,副教授

李胜忠(1980-),男,博士,研究员

李广年(1980-),男,博士,教授,通讯作者,E-mail:

舒跃辉(1999-),男,硕士研究生

刘子祥(1990-),男,工程师

赵峰(1964-),男,研究员。

, authorsList=杜林, 李胜忠, 李广年, 舒跃辉, 刘子祥, 赵峰)}, authors=[Author(id=1243879763065024670, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, 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=1243879763165687971, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, authorId=1243879763065024670, language=EN, stringName=Lin DU, firstName=Lin, middleName=null, lastName=DU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.Maritime and Transportation College, Ningbo University, Ningbo 315000, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1243879763232796840, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, authorId=1243879763065024670, language=CN, stringName=杜林, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.宁波大学 海运学院,浙江 宁波 315000, bio={"content":"

杜林(1988-),男,博士,副教授

"}, bioImg=null, bioContent=

杜林(1988-),男,博士,副教授

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1243879762817560717, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, xref=1., ext=[AuthorCompanyExt(id=1243879762830143630, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, companyId=1243879762817560717, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.Maritime and Transportation College, Ningbo University, Ningbo 315000, China), AuthorCompanyExt(id=1243879762838532239, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, companyId=1243879762817560717, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.宁波大学 海运学院,浙江 宁波 315000)])]), Author(id=1243879763312488622, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, 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=1243879763400569011, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, authorId=1243879763312488622, language=EN, stringName=Sheng-zhong LI, firstName=Sheng-zhong, middleName=null, lastName=LI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.China Ship Scientific Research Center, Wuxi 214082, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1243879763518009530, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, authorId=1243879763312488622, language=CN, stringName=李胜忠, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.中国船舶科学研究中心,江苏 无锡 214082, bio={"content":"

李胜忠(1980-),男,博士,研究员

"}, bioImg=null, bioContent=

李胜忠(1980-),男,博士,研究员

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1243879762935001239, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, xref=2., ext=[AuthorCompanyExt(id=1243879762943389848, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, companyId=1243879762935001239, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.China Ship Scientific Research Center, Wuxi 214082, China), AuthorCompanyExt(id=1243879762951778457, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, companyId=1243879762935001239, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.中国船舶科学研究中心,江苏 无锡 214082)])]), Author(id=1243879763643838658, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=liguangnian@nbu.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1243879763794833609, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, authorId=1243879763643838658, language=EN, stringName=Guang-nian LI, firstName=Guang-nian, middleName=null, lastName=LI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.Maritime and Transportation College, Ningbo University, Ningbo 315000, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1243879763924857041, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, authorId=1243879763643838658, language=CN, stringName=李广年, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.宁波大学 海运学院,浙江 宁波 315000, bio={"content":"

李广年(1980-),男,博士,教授,通讯作者,E-mail:

"}, bioImg=null, bioContent=

李广年(1980-),男,博士,教授,通讯作者,E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1243879762817560717, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, xref=1., ext=[AuthorCompanyExt(id=1243879762830143630, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, companyId=1243879762817560717, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.Maritime and Transportation College, Ningbo University, Ningbo 315000, China), AuthorCompanyExt(id=1243879762838532239, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, companyId=1243879762817560717, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.宁波大学 海运学院,浙江 宁波 315000)])]), Author(id=1243879764025520347, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, 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=1243879764126183647, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, authorId=1243879764025520347, language=EN, stringName=Yue-hui SHU, firstName=Yue-hui, middleName=null, lastName=SHU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.Maritime and Transportation College, Ningbo University, Ningbo 315000, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1243879764218458340, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, authorId=1243879764025520347, language=CN, stringName=舒跃辉, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.宁波大学 海运学院,浙江 宁波 315000, bio={"content":"

舒跃辉(1999-),男,硕士研究生

"}, bioImg=null, bioContent=

舒跃辉(1999-),男,硕士研究生

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1243879762817560717, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, xref=1., ext=[AuthorCompanyExt(id=1243879762830143630, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, companyId=1243879762817560717, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.Maritime and Transportation College, Ningbo University, Ningbo 315000, China), AuthorCompanyExt(id=1243879762838532239, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, companyId=1243879762817560717, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.宁波大学 海运学院,浙江 宁波 315000)])]), Author(id=1243879764327510252, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, 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=1243879764453339379, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, authorId=1243879764327510252, language=EN, stringName=Zi-xiang LIU, firstName=Zi-xiang, middleName=null, lastName=LIU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.China Ship Scientific Research Center, Wuxi 214082, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1243879764591751419, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, authorId=1243879764327510252, language=CN, stringName=刘子祥, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.中国船舶科学研究中心,江苏 无锡 214082, bio={"content":"

刘子祥(1990-),男,工程师

"}, bioImg=null, bioContent=

刘子祥(1990-),男,工程师

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1243879762935001239, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, xref=2., ext=[AuthorCompanyExt(id=1243879762943389848, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, companyId=1243879762935001239, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.China Ship Scientific Research Center, Wuxi 214082, China), AuthorCompanyExt(id=1243879762951778457, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, companyId=1243879762935001239, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.中国船舶科学研究中心,江苏 无锡 214082)])]), Author(id=1243879764713386244, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, 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=1243879764805660941, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, authorId=1243879764713386244, language=EN, stringName=Feng ZHAO, firstName=Feng, middleName=null, lastName=ZHAO, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.China Ship Scientific Research Center, Wuxi 214082, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1243879764952461589, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, authorId=1243879764713386244, language=CN, stringName=赵峰, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.中国船舶科学研究中心,江苏 无锡 214082, bio={"content":"

赵峰(1964-),男,研究员。

"}, bioImg=null, bioContent=

赵峰(1964-),男,研究员。

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1243879762935001239, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, xref=2., ext=[AuthorCompanyExt(id=1243879762943389848, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, companyId=1243879762935001239, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.China Ship Scientific Research Center, Wuxi 214082, China), AuthorCompanyExt(id=1243879762951778457, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, companyId=1243879762935001239, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.中国船舶科学研究中心,江苏 无锡 214082)])])], keywords=[Keyword(id=1243879765082485020, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, language=EN, orderNo=1, keyword=ship hull design method), Keyword(id=1243879765199925539, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, language=EN, orderNo=2, keyword=conditional deep-convolutional generative adversarial network), Keyword(id=1243879765283811627, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, language=EN, orderNo=3, keyword=computer vision), Keyword(id=1243879765380280627, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, language=CN, orderNo=1, keyword=船型智能设计), Keyword(id=1243879765464166714, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, language=CN, orderNo=2, keyword=深度卷积生成式对抗网络), Keyword(id=1243879765535469889, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, language=CN, orderNo=3, keyword=计算机视觉)], refs=[Reference(id=1243879769671053830, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, doi=null, pmid=null, pmcid=null, year=2021, volume=62, issue=2, pageStart=275, pageEnd=283, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=赵峰, 陈伟政, 韦喜忠, journalName=中国造船, refType=null, unstructuredReference=赵峰,陈伟政,韦喜忠,. 系统工程在船舶总体性能研发中的实践思考[J]. 中国造船202162(2):275-283., articleTitle=系统工程在船舶总体性能研发中的实践思考, refAbstract=null), Reference(id=1243879769763328522, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, doi=null, pmid=null, pmcid=null, year=2021, volume=62, issue=2, pageStart=275, pageEnd=283, url=null, language=null, rfNumber=[1], rfOrder=1, authorNames=Zhao Feng, Chen Weizheng, Wei Xizhong, journalName=Shipbuilding of China, refType=null, unstructuredReference=Zhao Feng, Chen Weizheng, Wei Xizhong, et al. A system engineering based approach to enhance ship general performance [J]. Shipbuilding of China, 2021, 62(2): 275-283. (in Chinese), articleTitle=A system engineering based approach to enhance ship general performance, refAbstract=null), Reference(id=1243879769872380428, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, doi=null, pmid=null, pmcid=null, year=2021, volume=43, issue=8, pageStart=1, pageEnd=5, url=null, language=null, rfNumber=[2], rfOrder=2, authorNames=李胜忠, 梁川, 赵峰, journalName=舰船科学技术, refType=null, unstructuredReference=李胜忠,梁川,赵峰. 基于MBSE的船型与水动力性能研究设计模式探讨[J]. 舰船科学技术202143(8):1-5., articleTitle=基于MBSE的船型与水动力性能研究设计模式探讨, refAbstract=null), Reference(id=1243879770006598163, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, doi=null, pmid=null, pmcid=null, year=2021, volume=43, issue=8, pageStart=1, pageEnd=5, url=null, language=null, rfNumber=[2], rfOrder=3, authorNames=Li Shengzhong, Liang Chuan, Zhao Feng, journalName=Ship Science and Technology, refType=null, unstructuredReference=Li Shengzhong, Liang Chuan, Zhao Feng. Discussion on the design pattern of hullform and hydrodynamic performance based on MBSE[J]. Ship Science and Technology, 2021, 43(8): 1-5. (in Chinese), articleTitle=Discussion on the design pattern of hullform and hydrodynamic performance based on MBSE, refAbstract=null), Reference(id=1243879770136621593, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, doi=null, pmid=null, pmcid=null, year=2019, volume=47, issue=2, pageStart=128, pageEnd=136, url=null, language=null, rfNumber=[3], rfOrder=4, authorNames=冯佰威, 冯梅, 常海超, 张丽妹, journalName=华南理工大学学报(自然科学版), refType=null, unstructuredReference=冯佰威,冯梅,常海超,张丽妹. 基于径向基插值的曲面变形方法在船型多目标优化中的应用[J]. 华南理工大学学报(自然科学版)201947(2):128-136., articleTitle=基于径向基插值的曲面变形方法在船型多目标优化中的应用, refAbstract=null), Reference(id=1243879770287616545, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, doi=null, pmid=null, pmcid=null, year=2019, volume=47, issue=2, pageStart=128, pageEnd=136, url=null, language=null, rfNumber=[3], rfOrder=5, authorNames=Feng Baiwei, Feng Mei, Chang Haichao, Zhang Limei, journalName=Journal of South China University of Technology (Natural Science), refType=null, unstructuredReference=Feng Baiwei, Feng Mei, Chang Haichao, Zhang Limei. Application of surface deformation method based on radial basis interpolation in multi-objective optimization of ship hull[J]. Journal of South China University of Technology (Natural Science), 2019, 47(2): 128-136. (in Chinese), articleTitle=Application of surface deformation method based on radial basis interpolation in multi-objective optimization of ship hull, refAbstract=null), Reference(id=1243879770405057057, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, doi=null, pmid=null, pmcid=null, year=2006, volume=37, issue=7, pageStart=457, pageEnd=476, url=null, language=null, rfNumber=[4], rfOrder=6, authorNames=Roh M I, Lee K Y, journalName=Advances in Engineering Software, refType=null, unstructuredReference=Roh M I, Lee K Y. An initial hull structural modeling system for computer-aided process planning in shipbuilding[J]. Advances in Engineering Software, 2006, 37(7): 457-476., articleTitle=An initial hull structural modeling system for computer-aided process planning in shipbuilding, refAbstract=null), Reference(id=1243879770501526055, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, doi=null, pmid=null, pmcid=null, year=2021, volume=62, issue=4, pageStart=267, pageEnd=275, url=null, language=null, rfNumber=[5], rfOrder=7, authorNames=刘希洋, 冯君, 孙文愈, journalName=中国造船, refType=null, unstructuredReference=刘希洋,冯君,孙文愈,. 基于生成对抗网络模型的船体型线逆向重构方法研究[J]. 中国造船202162(4):267-275., articleTitle=基于生成对抗网络模型的船体型线逆向重构方法研究, refAbstract=null), Reference(id=1243879770614772265, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, doi=null, pmid=null, pmcid=null, year=2021, volume=62, issue=4, pageStart=267, pageEnd=275, url=null, language=null, rfNumber=[5], rfOrder=8, authorNames=Liu Xiyang, Feng Jun, Sun Wenyu, journalName=Shipbuilding of China, refType=null, unstructuredReference=Liu Xiyang, Feng Jun, Sun Wenyu, et al. Research on method of reverse reconstruction of ship hull lines based on model of generating adversarial network[J]. Shipbuilding of China, 2021, 62(4): 267-275. (in Chinese), articleTitle=Research on method of reverse reconstruction of ship hull lines based on model of generating adversarial network, refAbstract=null), Reference(id=1243879770748989999, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[6], rfOrder=9, authorNames=陈壮, journalName=null, refType=null, unstructuredReference=陈壮. 基于卷积神经网络的内河船舶检测与识别研究[D]. 大连:大连理工大学,2020., articleTitle=基于卷积神经网络的内河船舶检测与识别研究, refAbstract=null), Reference(id=1243879770891596341, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[6], rfOrder=10, authorNames=Chen Zhuang, journalName=null, refType=null, unstructuredReference=Chen Zhuang. Research on inland river ship detection and recognition based on convolutional neural network[D]. Dalian: Dalian University of Technology, 2020. (in Chinese), articleTitle=Research on inland river ship detection and recognition based on convolutional neural network, refAbstract=null), Reference(id=1243879771021619770, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[7], rfOrder=11, authorNames=张杰, journalName=null, refType=null, unstructuredReference=张杰. 基于深度卷积神经网络的船舶识别方法研究[D]. 哈尔滨:哈尔滨工程大学,2020., articleTitle=基于深度卷积神经网络的船舶识别方法研究, refAbstract=null), Reference(id=1243879771151643202, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[7], rfOrder=12, authorNames=Zhang Jie, journalName=null, refType=null, unstructuredReference=Zhang Jie. Research on ship identification method based on depth convolutional neural network[D]. Harbin: Harbin Engineering University, 2020. (in Chinese), articleTitle=Research on ship identification method based on depth convolutional neural network, refAbstract=null), Reference(id=1243879771256500807, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, doi=null, pmid=null, pmcid=null, year=2021, volume=38, issue=1, pageStart=171, pageEnd=178, url=null, language=null, rfNumber=[8], rfOrder=13, authorNames=郭延华, 孙磊, 马世超, 何宏, journalName=计算机应用与软件, refType=null, unstructuredReference=郭延华,孙磊,马世超,何宏. 一种基于极端尺度变化的船舶识别方法研究[J]. 计算机应用与软件202138(1):171-178., articleTitle=一种基于极端尺度变化的船舶识别方法研究, refAbstract=null), Reference(id=1243879771365552716, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, doi=null, pmid=null, pmcid=null, year=2021, volume=38, issue=1, pageStart=171, pageEnd=178, url=null, language=null, rfNumber=[8], rfOrder=14, authorNames=Guo Yanhua, Sun Lei, Ma Shichao, He Hong, journalName=Computer Applications and Software, refType=null, unstructuredReference=Guo Yanhua, Sun Lei, Ma Shichao, He Hong. A boat recognition method based on extreme scale variation[J]. Computer Applications and Software, 2021, 38(1): 171-178. (in Chinese), articleTitle=A boat recognition method based on extreme scale variation, refAbstract=null), Reference(id=1243879771453633105, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, doi=null, pmid=null, pmcid=null, year=2018, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[9], rfOrder=15, authorNames=张彦儒, journalName=null, refType=null, unstructuredReference=张彦儒. NURBS流曲线研究及船体曲面轻量化设计[D]. 大连:大连理工大学,2018., articleTitle=NURBS流曲线研究及船体曲面轻量化设计, refAbstract=null), Reference(id=1243879771566879315, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, doi=null, pmid=null, pmcid=null, year=2018, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[9], rfOrder=16, authorNames=Zhang Yanru, journalName=null, refType=null, unstructuredReference=Zhang Yanru. Research on NURBS stream curve and lightweight design of hull surface[D]. Dalian: Dalian University of Technology, 2018. (in Chinese), articleTitle=Research on NURBS stream curve and lightweight design of hull surface, refAbstract=null), Reference(id=1243879771667542616, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, doi=null, pmid=null, pmcid=null, year=2022, volume=10, issue=4, pageStart=262, pageEnd=null, url=null, language=null, rfNumber=[10], rfOrder=17, authorNames=Ryumin S, Tryaskin V, journalName=Machines, refType=null, unstructuredReference=Ryumin S, Tryaskin V. Computer-aided system for parametric design of ship hull structures—CADS-hull[J]. Machines, 2022, 10(4): 262., articleTitle=Computer-aided system for parametric design of ship hull structures—CADS-hull, refAbstract=null), Reference(id=1243879771780788829, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, doi=null, pmid=null, pmcid=null, year=2017, volume=174, issue=null, pageStart=927, pageEnd=933, url=null, language=null, rfNumber=[11], rfOrder=18, authorNames=Liu F, Chen C, Wu W, journalName=Procedia Engineering, refType=null, unstructuredReference=Liu F, Chen C, Wu W. Research on intelligent design of luxury yacht[J]. Procedia Engineering, 2017, 174: 927-933., articleTitle=Research on intelligent design of luxury yacht, refAbstract=null), Reference(id=1243879771889840736, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, doi=null, pmid=null, pmcid=null, year=2018, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[12], rfOrder=19, authorNames=Papanikolaou A, journalName=A holistic approach to ship design: Optimisation of ship design and operation for life cycle, refType=null, unstructuredReference=Papanikolaou A. A holistic approach to ship design: Optimisation of ship design and operation for life cycle[M]. Springer, 2018., articleTitle=null, refAbstract=null), Reference(id=1243879771990504035, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, doi=null, pmid=null, pmcid=null, year=1998, volume=86, issue=11, pageStart=2278, pageEnd=2324, url=null, language=null, rfNumber=[13], rfOrder=20, authorNames=Lecun Yann, Bottou Leon, Bengio Yoshua, Haffner Patrick, journalName=Proceedings of the IEEE, refType=null, unstructuredReference=Lecun Yann, Bottou Leon, Bengio Yoshua, Haffner Patrick. Gradient-based learning applied to document recognition[J]. Proceedings of the IEEE, 1998, 86(11): 2278-2324., articleTitle=Gradient-based learning applied to document recognition, refAbstract=null), Reference(id=1243879772112138854, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, doi=null, pmid=null, pmcid=null, year=2017, volume=60, issue=6, pageStart=84, pageEnd=90, url=null, language=null, rfNumber=[14], rfOrder=21, authorNames=Krizhevsky A, Sutskever I, Hinton G E, journalName=Communications of the ACM, refType=null, unstructuredReference=Krizhevsky A, Sutskever I, Hinton G E. ImageNet classification with deep convolutional neural networks[J]. Communications of the ACM, 2017, 60(6): 84-90., articleTitle=ImageNet classification with deep convolutional neural networks, refAbstract=null), Reference(id=1243879772204413546, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, doi=null, pmid=null, pmcid=null, year=2014, volume=null, issue=null, pageStart=2672, pageEnd=2680, url=null, language=null, rfNumber=[15], rfOrder=22, authorNames=Goodfellow I J, Pouget-Abadie J, Mirza M, journalName=null, refType=null, unstructuredReference=Goodfellow I J, Pouget-Abadie J, Mirza M, et al. Generative adversarial nets[C]//Proceedings of the 27th International Conference on Neural Information Processing Systems-Volume 2. Montreal, Canada. 2014: 2672-2680., articleTitle=Generative adversarial nets, refAbstract=null), Reference(id=1243879772305076847, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, doi=null, pmid=null, pmcid=null, year=2015, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[16], rfOrder=23, authorNames=Radford A, Metz L, Chintala S, journalName=null, refType=null, unstructuredReference=Radford A, Metz L, Chintala S. Unsupervised representation learning with deep convolutional generative adversarial networks[C]//International Conference on Learning Representations, 2015., articleTitle=Unsupervised representation learning with deep convolutional generative adversarial networks, refAbstract=null), Reference(id=1243879772388962931, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, doi=null, pmid=null, pmcid=null, year=2020, volume=80, issue=C, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[17], rfOrder=24, authorNames=Sun X, Lian Z H, journalName=Computer Aided Geometric Design, refType=null, unstructuredReference=Sun X, Lian Z H. EasyMesh: An efficient method to reconstruct 3D mesh from a single image[J]. Computer Aided Geometric Design, 2020, 80(C): 101862., articleTitle=EasyMesh: An efficient method to reconstruct 3D mesh from a single image, refAbstract=null), Reference(id=1243879772535763577, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, doi=null, pmid=null, pmcid=null, year=2021, volume=55, issue=1, pageStart=153, pageEnd=161, url=null, language=null, rfNumber=[18], rfOrder=25, authorNames=许豪灿, 李基拓, 陆国栋, journalName=浙江大学学报(工学版), refType=null, unstructuredReference=许豪灿,李基拓,陆国栋. 由LeNet-5从单张着装图像重建三维人体[J]. 浙江大学学报(工学版)202155(1):153-161., articleTitle=由LeNet-5从单张着装图像重建三维人体, refAbstract=null), Reference(id=1243879772678369916, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, doi=null, pmid=null, pmcid=null, year=2021, volume=55, issue=1, pageStart=153, pageEnd=161, url=null, language=null, rfNumber=[18], rfOrder=26, authorNames=Xu Haocan, Li Jituo, Lu Guodong, journalName=Journal of Zhejiang University (Engineering Science), refType=null, unstructuredReference=Xu Haocan, Li Jituo, Lu Guodong. Reconstruction of three-dimensional human bodies from single image by LeNet-5[J]. Journal of Zhejiang University (Engineering Science), 2021, 55(1): 153-161. (in Chinese), articleTitle=Reconstruction of three-dimensional human bodies from single image by LeNet-5, refAbstract=null), Reference(id=1243879772737090175, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, doi=null, pmid=null, pmcid=null, year=2022, volume=26, issue=7, pageStart=949, pageEnd=961, url=null, language=null, rfNumber=[19], rfOrder=27, authorNames=杜林, 李广年, 郑彭军, journalName=船舶力学, refType=null, unstructuredReference=杜林,李广年,郑彭军. 船体曲面特征的计算机视觉认知与生成机制研究[J]. 船舶力学202226(7):949-961., articleTitle=船体曲面特征的计算机视觉认知与生成机制研究, refAbstract=null), Reference(id=1243879772820976258, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, doi=null, pmid=null, pmcid=null, year=2022, volume=26, issue=7, pageStart=949, pageEnd=961, url=null, language=null, rfNumber=[19], rfOrder=28, authorNames=Du Lin, Li Guangnian, Zheng Pengjun, journalName=Journal of Ship Mechanics, refType=null, unstructuredReference=Du Lin, Li Guangnian, Zheng Pengjun. Ship hull feature recognition and creation functionality investigation based on computer vision technology[J]. Journal of Ship Mechanics, 2022, 26(7): 949-961. (in Chinese), articleTitle=Ship hull feature recognition and creation functionality investigation based on computer vision technology, refAbstract=null)], funds=[Fund(id=1243879769343898100, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, awardId=11322203, language=CN, fundingSource=船舶总体性能创新研究开放基金资助项目(11322203), fundOrder=null, country=null), Fund(id=1243879769444561403, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, awardId=52201368, language=CN, fundingSource=国家自然科学基金青年科学基金资助项目(52201368), fundOrder=null, country=null), Fund(id=1243879769536836096, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, awardId=D21013, language=CN, fundingSource=高等学校学科创新引智计划项目(D21013), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1243879762817560717, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, xref=1., ext=[AuthorCompanyExt(id=1243879762830143630, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, companyId=1243879762817560717, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.Maritime and Transportation College, Ningbo University, Ningbo 315000, China), AuthorCompanyExt(id=1243879762838532239, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, companyId=1243879762817560717, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.宁波大学 海运学院,浙江 宁波 315000)]), AuthorCompany(id=1243879762935001239, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, xref=2., ext=[AuthorCompanyExt(id=1243879762943389848, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, companyId=1243879762935001239, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.China Ship Scientific Research Center, Wuxi 214082, China), AuthorCompanyExt(id=1243879762951778457, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, companyId=1243879762935001239, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.中国船舶科学研究中心,江苏 无锡 214082)])], figs=[ArticleFig(id=1243879765699047756, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, language=EN, label=Fig.1, caption=Regular process of hull designing and modelling, figureFileSmall=5nDCavPtFr7BysXpbDxLxw==, figureFileBig=3lldjk6Ekblcu2yF8f8Cvg==, tableContent=null), ArticleFig(id=1243879765799711060, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, language=CN, label=图1, caption=常规船型设计与建模流程, figureFileSmall=5nDCavPtFr7BysXpbDxLxw==, figureFileBig=3lldjk6Ekblcu2yF8f8Cvg==, tableContent=null), ArticleFig(id=1243879766080729443, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, language=EN, label=Fig.2, caption=Research content and plan of this paper, figureFileSmall=qKLt2n38BHJo5O1iwgK6VQ==, figureFileBig=P0Q0f/8S40mr7Jwpo/P8IQ==, tableContent=null), ArticleFig(id=1243879766189781351, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, language=CN, label=图2, caption=本文研究内容和技术路线, figureFileSmall=qKLt2n38BHJo5O1iwgK6VQ==, figureFileBig=P0Q0f/8S40mr7Jwpo/P8IQ==, tableContent=null), ArticleFig(id=1243879766269473132, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, language=EN, label=Fig.3, caption=Three dividing methods of local positioning features'conditional generation, figureFileSmall=CncAVpVQsTSq9SarZ91P3A==, figureFileBig=UP+80r0BpO4lQxvAlzK0zQ==, tableContent=null), ArticleFig(id=1243879766357553520, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, language=CN, label=图3, caption=区域位置特征条件生成的3种分割方式, figureFileSmall=CncAVpVQsTSq9SarZ91P3A==, figureFileBig=UP+80r0BpO4lQxvAlzK0zQ==, tableContent=null), ArticleFig(id=1243879766470799730, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, language=EN, label=Fig.4, caption=Three global geometrical features in details (view from starboard), figureFileSmall=RoUBeoDUZ09ceamuX4CjmQ==, figureFileBig=1+eqKa1unY3uzn7CLLS98w==, tableContent=null), ArticleFig(id=1243879766584045942, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, language=CN, label=图4, caption=从船型投影轮廓角度观测的3种全局几何特征, figureFileSmall=RoUBeoDUZ09ceamuX4CjmQ==, figureFileBig=1+eqKa1unY3uzn7CLLS98w==, tableContent=null), ArticleFig(id=1243879766726652285, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, language=EN, label=Fig.5, caption=Relative positions of three geometrical features in this paper, figureFileSmall=1PBWDane9MIVmTIVD1AWCw==, figureFileBig=cKJzq93VgcPygCRyddYSoQ==, tableContent=null), ArticleFig(id=1243879766818926977, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, language=CN, label=图5, caption=3种几何特征船型数据的相对位置, figureFileSmall=1PBWDane9MIVmTIVD1AWCw==, figureFileBig=cKJzq93VgcPygCRyddYSoQ==, tableContent=null), ArticleFig(id=1243879766923784581, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, language=EN, label=Fig.6, caption=Feature maps of eight classic ship hulls in this paper, figureFileSmall=0AZ4C0yXWMfe6aPKnABEeQ==, figureFileBig=ChLvqPLs9n+Wt9k//WQyYg==, tableContent=null), ArticleFig(id=1243879767037030794, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, language=CN, label=图6, caption=八类典型全局几何特征的船型特征图, figureFileSmall=0AZ4C0yXWMfe6aPKnABEeQ==, figureFileBig=ChLvqPLs9n+Wt9k//WQyYg==, tableContent=null), ArticleFig(id=1243879767133499793, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, language=EN, label=Fig.7, caption=Structure of a CDC-GAN network, figureFileSmall=QdL664Orhr4u+2RDS4rjeg==, figureFileBig=UOs07OQwbk8VwLJZMjdvWw==, tableContent=null), ArticleFig(id=1243879767271911828, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, language=CN, label=图7, caption=条件深度卷积生成式对抗网络模型, figureFileSmall=QdL664Orhr4u+2RDS4rjeg==, figureFileBig=UOs07OQwbk8VwLJZMjdvWw==, tableContent=null), ArticleFig(id=1243879767393546650, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, language=EN, label=Fig.8, caption=CDC-GAN training and converging details of local positioning features, figureFileSmall=dcw/LLiFi+2kNrR+/GkhyA==, figureFileBig=835OmBxO1j7uiHVTMGsbRA==, tableContent=null), ArticleFig(id=1243879767506792864, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, language=CN, label=图8, caption=区域位置特征条件生成网络的训练与收敛情况, figureFileSmall=dcw/LLiFi+2kNrR+/GkhyA==, figureFileBig=835OmBxO1j7uiHVTMGsbRA==, tableContent=null), ArticleFig(id=1243879767620039075, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, language=EN, label=Fig.9, caption=Comparison of samples between different cutting strategies, figureFileSmall=dKPhw7IH1uCLYJi33w/gtw==, figureFileBig=MzzXyVA/LT7Tam7ZUeywQw==, tableContent=null), ArticleFig(id=1243879767737479595, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, language=CN, label=图9, caption=不同分割情况下的区域位置生成样本对比, figureFileSmall=dKPhw7IH1uCLYJi33w/gtw==, figureFileBig=MzzXyVA/LT7Tam7ZUeywQw==, tableContent=null), ArticleFig(id=1243879767901057454, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, language=EN, label=Fig.10, caption=Comparison of samples between different cutting strategies due to gradient change, figureFileSmall=8jcdTEqijwnRMC1k6rV3mg==, figureFileBig=TeZQ9zVt1+amqntVQ8kQ+g==, tableContent=null), ArticleFig(id=1243879768031080884, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, language=CN, label=图10, caption=不同分割情况下的生成样本梯度变化对比, figureFileSmall=8jcdTEqijwnRMC1k6rV3mg==, figureFileBig=TeZQ9zVt1+amqntVQ8kQ+g==, tableContent=null), ArticleFig(id=1243879768165298619, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, language=EN, label=Fig.11, caption=CDCGAN training and converging details of global geometrical features, figureFileSmall=fymThUvuRl/lQK1ZF5OYhw==, figureFileBig=MHu0VEsykNbIfeLIIdPUow==, tableContent=null), ArticleFig(id=1243879768261767619, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, language=CN, label=图11, caption=全局几何特征条件生成网络的训练与收敛情况, figureFileSmall=fymThUvuRl/lQK1ZF5OYhw==, figureFileBig=MHu0VEsykNbIfeLIIdPUow==, tableContent=null), ArticleFig(id=1243879768395985353, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, language=EN, label=Fig.12, caption=Output samples from CDC-GAN before and after training, figureFileSmall=ZJRNCVSXUZmzsF7Cey0NfQ==, figureFileBig=ytjav7WNRuTIGwr6oW+ZFw==, tableContent=null), ArticleFig(id=1243879768576340431, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, language=CN, label=图12, caption=条件生成式对抗网络训练前后的输出样本对比, figureFileSmall=ZJRNCVSXUZmzsF7Cey0NfQ==, figureFileBig=ytjav7WNRuTIGwr6oW+ZFw==, tableContent=null), ArticleFig(id=1243879768693780948, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, language=EN, label=Fig.13, caption=Samples from trained CDC and GAN (Four single-feature cases), figureFileSmall=2TTcLrM+4Z4aQcdF/T858A==, figureFileBig=d0qk5JVWNJqqVFn+0sMGJQ==, tableContent=null), ArticleFig(id=1243879768832192986, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, language=CN, label=图13, caption=采用一体式方法的船型几何特征条件生成样本(单一特征情况), figureFileSmall=2TTcLrM+4Z4aQcdF/T858A==, figureFileBig=d0qk5JVWNJqqVFn+0sMGJQ==, tableContent=null), ArticleFig(id=1243879768920273376, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, language=EN, label=Fig.14, caption=Samples from trained CDC-GAN (Four multi-features cases), figureFileSmall=c2dJkwArnZwms83dUUTjHA==, figureFileBig=Ay/gT5ZnEo6ckBXbMHK7aA==, tableContent=null), ArticleFig(id=1243879769025130981, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, language=CN, label=图14, caption=采用一体式方法的船型几何特征条件生成样本(多种特征情况), figureFileSmall=c2dJkwArnZwms83dUUTjHA==, figureFileBig=Ay/gT5ZnEo6ckBXbMHK7aA==, tableContent=null), ArticleFig(id=1243879769121599977, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, language=EN, label=Fig.15, caption=Comparison of samples with different geometrical features, figureFileSmall=JP47yT6dHsvZNWxDS0GMbw==, figureFileBig=uN7Y3ilOAnUJHmBGy8+PqQ==, tableContent=null), ArticleFig(id=1243879769222263277, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243879757155251195, language=CN, label=图15, caption=具有不同几何特征的船型样本对比, figureFileSmall=JP47yT6dHsvZNWxDS0GMbw==, figureFileBig=uN7Y3ilOAnUJHmBGy8+PqQ==, tableContent=null)], 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.1007-7294.2024.08.004, detailUrlEn=https://castjournals.cast.org.cn/joweb/cblx/EN/10.3969/j.issn.1007-7294.2024.08.004, pdfUrlCn=https://castjournals.cast.org.cn/joweb/cblx/CN/PDF/10.3969/j.issn.1007-7294.2024.08.004, pdfUrlEn=https://castjournals.cast.org.cn/joweb/cblx/EN/PDF/10.3969/j.issn.1007-7294.2024.08.004, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于深度卷积生成式对抗网络的船型特征认知与条件生成方法
收藏切换
PDF下载
杜林 1 , 李胜忠 2 , 李广年 1 , 舒跃辉 1 , 刘子祥 2 , 赵峰 2
船舶力学 | 流体力学 2024,28(8): 1162-1174
收起
收藏切换
船舶力学 | 流体力学 2024, 28(8): 1162-1174
基于深度卷积生成式对抗网络的船型特征认知与条件生成方法
全屏
杜林1, 李胜忠2, 李广年1 , 舒跃辉1, 刘子祥2, 赵峰2
作者信息
  • 1.宁波大学 海运学院,浙江 宁波 315000
  • 2.中国船舶科学研究中心,江苏 无锡 214082
  • 杜林(1988-),男,博士,副教授

    李胜忠(1980-),男,博士,研究员

    李广年(1980-),男,博士,教授,通讯作者,E-mail:

    舒跃辉(1999-),男,硕士研究生

    刘子祥(1990-),男,工程师

    赵峰(1964-),男,研究员。

通讯作者:

通讯作者,E-mail:
A ship hull offset feature cognition and generation method based on conditional deep convolutional generative adversarial networks
Lin DU1, Sheng-zhong LI2, Guang-nian LI1 , Yue-hui SHU1, Zi-xiang LIU2, Feng ZHAO2
Affiliations
  • 1.Maritime and Transportation College, Ningbo University, Ningbo 315000, China
  • 2.China Ship Scientific Research Center, Wuxi 214082, China
出版时间: 2024-08-20 doi: 10.3969/j.issn.1007-7294.2024.08.004
文章导航
收藏切换

船体型值与图片一样也是序列相关型数据,所以用于生成图片的神经网络模型也能生成船型数据。由于船舶种类繁多、需求复杂,本文研究重点从船舶水线上下、船艏、舯、艉等区域位置特征,和船舶设计中普遍存在球艏、尾轴、艏部外板升高等全局几何特征的条件生成需求出发,训练条件深度卷积生成式对抗网络模型(Conditional Deep Convolutional Generative Adversarial Networks)来实现两种特征的条件认知与生成。首先,将实现船型区域位置特征与全局几何特征的条件生成作为目标,分别建立条件深度卷积生成式对抗网络模型;然后,针对两类特征设置若干从易到难的不同分割方案和特征种类,使神经网络能够循序渐进地完成条件生成任务;最后,通过对训练过程和生成结果进行对比,初步证明所研究方法用于解决船型特征条件生成问题的可行性。本研究延续了作者之前的研究成果,属于基于计算机视觉技术的船型智能设计方法领域,旨在进一步探索引入人工智能实现船型智能设计的可行性方法。

船型智能设计  /  深度卷积生成式对抗网络  /  计算机视觉

The hull form modelling progress in ship design is significantly relied on the parent hull database and the professional designers well trained with CAD software, and it is usually a time and experience costly work. The conditional generation of ship hull with both geometrical and locational features by training an artificial neural network was concerned by this paper. The geometrical feature means the overall shape variety of ship designs like bulbous bow, stern shaft, etc., the locational feature means the shape difference between stern, front and mid-body of ships. Firstly, a conditional deep-convolutional generative adversarial network (CDC-GAN) was constructed to distinguish the geometrical and locational features individually; Secondly, the CDC-GAN was well trained to learn and generate these features with different resolutions and categories, from easy to hard; In the end, the training cost and performance of networks were compared and concluded to prove the capability of CDC-GAN in solving ship hull form generating issues. This paper is based on authors’ previous investigation with regular GAN, and it provides a further exploration about the potential of CDC-GAN in ship design.

ship hull design method  /  conditional deep-convolutional generative adversarial network  /  computer vision
杜林, 李胜忠, 李广年, 舒跃辉, 刘子祥, 赵峰. 基于深度卷积生成式对抗网络的船型特征认知与条件生成方法. 船舶力学, 2024 , 28 (8) : 1162 -1174 . DOI: 10.3969/j.issn.1007-7294.2024.08.004
Lin DU, Sheng-zhong LI, Guang-nian LI, Yue-hui SHU, Zi-xiang LIU, Feng ZHAO. A ship hull offset feature cognition and generation method based on conditional deep convolutional generative adversarial networks[J]. Journal of Ship Mechanics, 2024 , 28 (8) : 1162 -1174 . DOI: 10.3969/j.issn.1007-7294.2024.08.004
船型设计和建模方法作为连接船舶设计流程和建造流程的中间环节,一直是相关学术研究和实际应用领域内的重点和热点[1]。作为建造阶段的上游环节,船型设计的品质和效率直接影响船舶性能和整个设计与建造过程的顺利完成[3-4]。随着人工智能、计算机视觉等新兴技术在船型设计领域应用研究逐渐受到重视,研究船型设计与建模的新方法,提高设计环节的智能化、信息化、自动化程度成为目前得到较多关注的研究方向[5]
以计算机视觉技术为例,其在船舶目标识别方面的研究已经取得了一些富有开创性的成果:陈壮将含有丰富语义信息的高层特征图与含有丰富空间信息的底层特征图进行融合,加强对小目标船舶的检测能力[6];张杰对YOLOv3算法进行改进,能够在实时检测速度的条件下准确地识别出视觉图像里的船舶类型[7];郭延华等提出一种应用于极小船舶目标识别的单级检测算法[8]。船体型值与图片一样也是序列相关型数据,所以用于船舶目标识别的计算机视觉技术也能用于船型设计,但此方向的应用研究仍在起步阶段。
目前船型设计工具主要采用以非均匀有理B样条(Non-Uniform Rational B-Splines,简称NURBS)为代表的曲面表达式拟合模型[9-10]。此类模型在表达光滑形状方面极具优势,且能够通过调整表达式阶数、控制点位置对曲面形状进行一定范围的调整,在船型优化领域应用广泛。同时,采用此类技术的相关软件平台发展已非常成熟,且在我国船舶行业内占据大量市场份额。有些CAD产品开发公司专门针对船型设计需求,在软件内预制了部分船型文件,有助于提高设计效率,部分解决了三维船型建模需要从零开始的问题。
较为知名的CAD平台包括法国达索公司的CATIA、美国Bentley Software公司的MAXSURF船舶设计系统、荷兰代尔夫特理工大学主导开发的轻量级船体设计软件DELFTSHIP、美国Robert McNeel & Associates公司开发的Rhinoceros 3D、法国达索公司旗下Matra Datavision工作室公布的开源软件FreeCAD和德国FRIENDSHIP SYSTEMS公司开发的CAESES设计和优化平台等。功能丰富的CAD软件虽然大大减轻了手工绘图在船型设计中的负担,特别是三维建模的普遍应用,加速了低效率、高成本尺规作图的淘汰,形成了CAD和CAE的通用接口[12],使得船型优化设计工作能够实现部分自动化[11],显著提高了船型设计的效率和品质,但是仍未能摆脱其对设计者经验和母型船数据的根本依赖。
随着人工智能、计算机视觉等信息科学技术的跨越式发展[13],及其近年来在各个领域内的广泛应用[14],生成模型(generative model)作为一种新的数据构型方法开始逐渐受到重视,ChatGPT和SORA就是生成模型技术成功的实际应用案例。经典生成模型主要包括变分自编码器VAE(Variational Auto-Encoders)和生成式对抗网络GAN(Generative Adversarial Networks)两类[15]。其中,后者被广泛认为更具发展潜力且已逐渐成为生成模型的主流方向[16],不仅在图像生成和三维建模方面都取得了长足的进步[17-18],而且在船型生成上的潜在研究价值也得到了初步验证[19]。在收到设计需求后,常规船型设计模式主要依赖设计者解读设计条件,通过经验判断出目标船型的基础特征,根据特征检索数据库中较为相似的母型船,参照母型船数据在CAD软件中完成建模和模型修正、优化设计等工作。整个流程可以大致分为两个环节,即从无到有的模型建立环节和满足设计要求的模型修正环节,如图1所示。
鉴于常规船型设计与建模流程严重依赖设计师经验和母型数据的问题,本文聚焦船型设计流程中从无到有的模型建立环节,引入在图像生成、三维建模领域已广泛应用的深度卷积条件生成式对抗网络模型(Conditional Deep-Convolutional Generative Adversarial Networks,简称CDC-GAN),探索一种基于计算机视觉和特征学习的船型特征条件生成与建模方法,实现计算机程序能够在不借助人工操作和数据库的情况下,仅需输入目标特征,即可生成具有明显指定特征的区域或全局船型数据,如生成船艏部、艉部水线以下位置的区域船型数据,或生成带有球鼻艏形状的全局船型数据等。
本文延续作者之前的研究内容[19],在初步验证了计算机视觉技术和生成式对抗网络模型在船型特征认知与生成方面的可行性后,进一步将生成任务细化,如图2所示,分别以船型区域位置特征和全局几何特征为对象,通过CDC-GAN来分别学习这两类特征并生成具有指定特征的船型样本。从之前的方法可行性验证,向多种船型特征的指定条件生成方法可行性验证推进,继续探索AIGC(Artificial Intelligent Generative Content,生成式人工智能)技术在船型设计方面潜在的工程实用性。
用于神经网络训练的船型数据集将按照解决两类条件生成任务的问题导向,即船型全局几何特征和区域位置特征的条件生成,分别进行前处理。
针对区域位置特征分类认知问题的前处理方法延续了作者之前的研究内容[19]:首先将每个船型样本网格化,按照船侧方向进行投影,半宽值大则颜色深;然后对投影区域采用3种方式进行分割,即1×4,2×4和2×5,如图3所示。三种分割方式对应4、8、10三种分类的区域位置特征情况,按照此方法分类的船型样本后续将用于训练生成指定区域样本的CDC-GAN,比如指定生成船艏水线以下部分(即要求生成图3(c)中的8、9区域,或图3(b)中的7区域)。
在船型全局几何特征的条件生成中,将引入3种全局几何特征,即艏部外板升高、球鼻艏、尾轴或呆木结构,各特征如图4~5所示,散点部分为STL格式文件节点数据,在经过无量纲化和边缘检测处理后,轮廓线清晰可见。采用栅格化处理船型数据仅用于船型特征识别和生成,由于颗粒度限制导致斜线呈现出一定的阶梯形状属正常现象,此现象会在后处理过程中光顺消除。
将船型样本按照3种特征排列组合,分为8个子类,各子类的典型全局几何形状以三位二进制形式进行编码,即000、001、010、100、011、101、110和111,分别表征对应几何特征的有无。根据样本所具备的几何特征的数量,将其划分为单一特征样本与多种特征样本,如图6所示。
本文将条件生成式对抗网络(Conditional GAN)与深度卷积生成式对抗网络(Deep-Convolutional GAN)相结合,设计一个用于生成指定条件船型数据的深度卷积生成式对抗网络框架CDC-GAN,如图7所示,并基于此模型实现船型区域位置特征和全局几何特征的条件生成。
生成器网络(Generator Network)数据处理流程如下:首先,将一维的标签和种子张量经过反卷积运算后成为两个三维张量,完成第一次数据升维过程中两个张量的尺寸一致;然后,纵向合并两个张量再进行第二次升维,将合并张量纵向信息压缩、长宽方向信息增密,使其扁平化;最后,再经过一次反卷积,将纵向维度压缩到一,长宽方向则按照需要的分辨率进行调整,如果是区域位置特征生成则为32×32,如果是全局几何特征则为64×128,这里以32×32的正方形区域特征为例。
判别器网络(Discriminator)数据处理流程如下:首先,从真实样本中按照分类数量在所有种类中依次抽取1个以二维特征张量存在的样本,将所抽取的样本张量纵向堆叠成为一个三维特征张量,对生成器输出样本进行若干次复制后也堆叠成为一个三维特征张量;然后,将两个三维特征张量进行第一次卷积计算后再进行纵向拼接;最后,对拼接后的三维张量连续进行两次二维卷积计算,最后一次将所有数据坍缩为1个决策张量,这个张量的取值最终决定判别器对目标样本的分类。如果是区域位置特征,则判断目标样本是某一位置处的船型特征区域样本,如果是全局几何特征,则判断目标样本是具有指定几何特征的某一类船型特征全局样本。
需要注意,在研究手写数字的条件生成时曾出现一种现象,输出样本虽看起来像6但输出标签是8,这种标签错但样本对的生成样本称为假阳性样本,对应的还有假阴性(标签样本都错)、真阳性(标签样本都对)、真阴性(标签对样本错)。所以,相比原生GAN,CDC-GAN的判别器不仅要判断生成器样本是否有义,还要判断样本与标签是否匹配正确,这会极大提升训练难度。
本文实现两类条件生成:第一类,神经网络充分训练后能生成具有指定位置特征的船型区域数据样本;第二类,神经网络充分训练后能够生成具有指定几何特征的船型全局几何数据样本。
进行船型区域分割的基础单位是32×32的正方形,1×4则为将船体按照基础单位进行1行4列的划分,其他情况同理。由此可知,1×4方案全局分辨率为32×128,2×4全局分辨率为64×128,2×5全局分辨率为64×160,特征张量中的半宽值被无量纲化至0~1之间。设定3种分割方案的目的是为了测试上一章所设计的CDC-GAN在解决难度逐渐增大的区域分割问题时是否会失效(1×4=4,2×4=8,2×5=10,分区数量增多,分类难度增大)。
这3种分割方案的标签分类生成训练情况如图8所示。由于GAN自身收敛性弱、训练困难的特性,导致损失函数值处于相对高位,但总体数值稳定在1.0~1.5之间,且右侧的判别器准确率情况显示5~10 epoch训练阶段的模型具有较理想的概率(即生成样本的逼真度超过判别器的识别能力)。纵向对比三种分割方案的损失函数变化可以发现,2×4和2×5方案的GD损失函数在训练30个循环后开始出现较大波动,说明逐渐递增的分割数量确实让模型训练变得不稳定,纵向对比鉴别器的样本分类准确率也可以得出相同的结论。但是,由于GAN自身收敛性弱的特点,其训练指标并不能完全反映性能,所以具体样本生成情况还需进一步观测。
不同分割方式下的区域位置生成样本与真实样本对比情况如图9所示。1×4情况下的生成样本艉部明显出现了尾轴结构的特征,且其他区域也具有良好的区域特征,特别是艉部、舯体后部、舯体前部甚至展现出了较为光顺的区域间连接,这在没有区域间约束的分区生成情况下较为罕见。
随着在2×4和2×5情况下船型区域位置数量增多,生成难度增大,网络所提供的生成样本质量出现了些许下降。首先各区域样本开始出现更为明显的噪点,在2×4情况下艉部水线以上部分左侧较为明显,且个别位置的区域样本内部的曲率变化较为模糊,具体表现在2×4的水线上舯体前部和2×5的水线上舯体后部和中部。另一个现象是,相比1×4,在2×4和2×5情况,随着区域细分的增加,样本间的光顺过渡愈发恶劣、问题愈发明显。
为了进一步探索样本空间分布,图10分别对不同分割情况下的样本空间几何特性进行了对比。总体来看,1×4的各个整体侧投影轮廓线能够保持船型的基本全局特征,未出现明显的错位现象。艉部形状从梯形逐渐向三角形过渡,艏部轮廓也从丰满逐渐瘦削。2×4和2×5也呈现出类似的特征,但是其在船舯位置的最大半宽保持不变,而1×4情况则在船舯位置能够观测到较为明显的最大半宽值减小现象。
以上结果初步证明,文中所设计的深度卷积条件生成式对抗网络CDC-GAN,在32×32的区域分辨率下,采用船型曲面的分区生成方法,能够实现1×4、2×4和2×5分区方式的条件生成,即经过充分训练后,仅通过单一网络就能够实现不同区域的生成。同时,相同结构的CDC-GAN在面对3种由易到难的分区条件生成问题时表现略有不同:宏观上看,1×4情况下的各分区间连接明显较为光顺,由于这种情况没有垂向分割,所以整体的曲面连续感较好;2×4和2×5情况下,各分区之间割裂感强烈,对比生成样本梯度变化情况可知,能够通过调节种子数使所有分区的生成样本更加丰满,这种情况下曲面割裂感将得到明显改善。
全局几何特征的条件生成方法是指将船体进行无量纲化处理后,按照其宏观、显性的几何特征对样本进行标签化分类,将样本和对应标签输入神经网络进行充分训练后,网络能够根据指定条件输出具有对应几何特征的船型样本。
需要注意的是,在研究用于生成区域位置特征的CDC-GAN时,只需要输入和输出32×32的区域数据和对应的样本标签即可,而在研究用于生成全局几何特征的CDC-GAN时,却需要一次性输入和输出一个完整的船型样本数据。这代表后者要求神经网络一次性处理更多的数据。所以,与区域位置特征的条件生成问题相比,全局几何特征条件生成问题更复杂、数据体量更庞大、训练难度更大。为了降低网络的学习负担,与之前研究区域位置特征的条件生成问题时一样,本文将分别以难、易两种情况来对全局几何特征的条件进行生成,即单一几何特征情况(特征间互斥)和多种几何特征(特征间相融)。为了输出具有完整、清晰、多样全局几何特征的船型生成样本,本文采用了64×128的全局分辨率。
从损失函数值与判别器准确率两个指标的变化来看,用于全局几何特征条件生成的CDC-GAN的训练情况仍然呈现较明显的波动,如图11所示:单一特征的损失函数值在经历了初期的高位震荡后,保持在2附近持续小幅度波动;多种特征的总体趋势与单一特征存在一定程度的相似性,但其判别器损失值在2附近则持续大幅度波动,这说明多特征训练难度更高,损失值不稳定,在判别器准确率方面也没有显著提升,这在前期研究中出现过。主要是因为GAN较难训练的特性,收敛性是模型训练成功的必要不充分条件,所以还需进一步观测训练过程中的样本品质变化。
在对比训练样本品质变化时,发现品质确实有明显提升,如图12所示。可以看到,虽然在图12(a)Epoch=1时的生成样本效果较差,经过Epoch=60次的训练后,图12(b)生成样本不仅能够表达出明显的单一特征(Class 0~3),同时也能较为清晰地输出具有多种全局几何特征的样本(Class 4~7),即模型在未能较好收敛的情况下,所生成的8类样本仍然呈现出显著的全局几何特征。
为了更清晰地展示样本几何特征与船型细节,将无量纲样本进行简单降噪处理后,将所有船型统一主尺度为:总长120 m,总宽20 m,型深12 m,并输出三维船型,按照单一特征情况和多种特征情况分别进行展示和对比。
在单一特征情况下共生成四种样本,如图13所示,样本a不具有任何特征(编号000),样本b、c、d各自有且仅有一种特征,特征间为互斥关系。与其他样本相比,样本b的球艏特征非常明显,其在艏部水线以下部分出现了清晰可见的球艏几何形状。样本c在艏艉区域的水下部分具有光滑的曲面轮廓线,这表明其不具有球艏和尾轴结构,但其外板上缘出现小幅度但十分明显的升高。样本d的艉部轮廓线相比其他样本非常模糊,可以观察到与其他样本有明显的几何差异。
在多种特征情况下共生成四种样本,如图14所示,样本e同时具有全部3种特征(编号111),样本f、g、h则各具有不同的两种特征组合,各特征间为相容关系。需要注意的是,由于尾轴结构的几何特征在半宽方向上不及其他两类特征明显,再加上三维视图角度因素,使其较难在同一尺度下与其他特征一同被观测到。样本e具有明显的球艏形状、外板升高特征,虽然难以清晰观测到尾轴结构,但其艉部水线以下的轮廓模糊部分能够证明此处在船宽方向有凸起,即尾轴结构。样本f虽然具有相同的尾轴结构和外板升高特征,但是较稳平顺的水线下艏部轮廓证明其没有球艏。样本g的尾轴结构和球艏非常清晰,但平整的外板上缘证明其不具备外板升高特征。样本h虽具有外板升高,但与其他样本完全不同的水线下艉部特征证明它不具备尾轴结构,同时,样本h虽然能够观测到类似球艏的艏部凸起,但表现品质较为一般。
样本h与样本a的多角度对比特写如图15所示。图15(a)中能够较为清晰地看出样本h(右侧)相较样本a(左侧)具有明显的球艏和外板升高特征,两项特征的轮廓线清晰可见;图15(b)的艉部特写中,无尾轴(左侧)较有尾轴(右侧)呈现平直底部轮廓,进一步证明了条件特征生成机制的有效性。
在作者以往的研究内容中,已搭建了用于船体曲面特征生成的对抗网络模型,初步验证了生成式对抗网络在解决船型生成问题上的潜在研究价值[19]。作为延续,本文进一步探索了船型区域位置特征和全局几何特征的条件生成方法,通过引入条件特征张量,将常规生成式对抗网络(GAN)改造成深度卷积条件生成式对抗网络(CDC-GAN),并分别采用分区式和一体式方法验证此模型在生成某船型的不同区域、具有不同全局几何特征的可行性与有效性,经过研究获得以下结论:
(1)采用深度卷积条件生成式对抗网络模型,能实现船型区域位置特征的条件生成,即在32×32的区域分辨率下,按照1×4、2×4、2×5的分割方法,能够在仅训练一个神经网络的情况下根据指定位置标签生成对应区域的船型特征。据观测,同一区域生成样本具有较丰富的几何多样性。
(2)采用深度卷积条件生成式对抗网络模型,能实现全局几何形状特征的条件生成,即在64×128全局分辨率下引入三类几何特征,成功实现单一特征(互斥)和多种特征(相容)的船型样本条件生成。三维几何船型显示本文在脱离常规参数化建模和NURBS曲面情况下,能够初步实现船型样本的条件生成,进一步证明了此方法在船型智能设计方面具有尚待开发的研究潜力。
(3)鉴于生成式对抗网络收敛指标和样本h所呈现的特征并不理想,推断基于现有模型采用一体式方法的船型几何特征条件生成问题已愈发困难。一方面随着特征标签数量增加,条件生成问题将愈发复杂,训练成本也将随之激增,如何提升生成式对抗网络的收敛效率已经逐渐成为进一步亟需解决的关键问题之一;另一方面,样本h并没有体现出明显的球艏特征,这可能代表本文的模型结构已经不能驾驭此类复杂问题,所以如何设计功能更强大的神经网络将成为后续研究的另一个关键问题。
(4)分区式生成方法的区域位置特征条件生成模型体现的样本多样性,和一体式生成方法的全局几何特征条件生成模型体现的曲面有义性,都是船型设计中的关键指标。在作者以往的研究中提及了两种方法的优势和劣势,本文则进一步证明了对两种方法进行融合的重要性。
综上所述,在常规生成式对抗网络的基础上设计了深度卷积条件生成式对抗网络,分别实现了区域位置特征和全局几何特征的条件生成,在进一步证明了生成式对抗网络在船型智能设计方面的潜力之外,还验证了其工程应用的可行性,即根据需求迅速生成指定几何或区域特征的船型数据。作者将针对神经网络结构优化、指定排水量、生成样本光顺等后续问题,继续开展进一步研究。
  • 船舶总体性能创新研究开放基金资助项目(11322203)
  • 国家自然科学基金青年科学基金资助项目(52201368)
  • 高等学校学科创新引智计划项目(D21013)
参考文献 引证文献
排序方式:
[1]
赵峰,陈伟政,韦喜忠,. 系统工程在船舶总体性能研发中的实践思考[J]. 中国造船202162(2):275-283.
Zhao Feng, Chen Weizheng, Wei Xizhong, et al. A system engineering based approach to enhance ship general performance [J]. Shipbuilding of China, 2021, 62(2): 275-283. (in Chinese)
[2]
李胜忠,梁川,赵峰. 基于MBSE的船型与水动力性能研究设计模式探讨[J]. 舰船科学技术202143(8):1-5.
Li Shengzhong, Liang Chuan, Zhao Feng. Discussion on the design pattern of hullform and hydrodynamic performance based on MBSE[J]. Ship Science and Technology, 2021, 43(8): 1-5. (in Chinese)
[3]
冯佰威,冯梅,常海超,张丽妹. 基于径向基插值的曲面变形方法在船型多目标优化中的应用[J]. 华南理工大学学报(自然科学版)201947(2):128-136.
Feng Baiwei, Feng Mei, Chang Haichao, Zhang Limei. Application of surface deformation method based on radial basis interpolation in multi-objective optimization of ship hull[J]. Journal of South China University of Technology (Natural Science), 2019, 47(2): 128-136. (in Chinese)
[4]
Roh M I, Lee K Y. An initial hull structural modeling system for computer-aided process planning in shipbuilding[J]. Advances in Engineering Software, 2006, 37(7): 457-476.
[5]
刘希洋,冯君,孙文愈,. 基于生成对抗网络模型的船体型线逆向重构方法研究[J]. 中国造船202162(4):267-275.
Liu Xiyang, Feng Jun, Sun Wenyu, et al. Research on method of reverse reconstruction of ship hull lines based on model of generating adversarial network[J]. Shipbuilding of China, 2021, 62(4): 267-275. (in Chinese)
[6]
陈壮. 基于卷积神经网络的内河船舶检测与识别研究[D]. 大连:大连理工大学,2020.
Chen Zhuang. Research on inland river ship detection and recognition based on convolutional neural network[D]. Dalian: Dalian University of Technology, 2020. (in Chinese)
[7]
张杰. 基于深度卷积神经网络的船舶识别方法研究[D]. 哈尔滨:哈尔滨工程大学,2020.
Zhang Jie. Research on ship identification method based on depth convolutional neural network[D]. Harbin: Harbin Engineering University, 2020. (in Chinese)
[8]
郭延华,孙磊,马世超,何宏. 一种基于极端尺度变化的船舶识别方法研究[J]. 计算机应用与软件202138(1):171-178.
Guo Yanhua, Sun Lei, Ma Shichao, He Hong. A boat recognition method based on extreme scale variation[J]. Computer Applications and Software, 2021, 38(1): 171-178. (in Chinese)
[9]
张彦儒. NURBS流曲线研究及船体曲面轻量化设计[D]. 大连:大连理工大学,2018.
Zhang Yanru. Research on NURBS stream curve and lightweight design of hull surface[D]. Dalian: Dalian University of Technology, 2018. (in Chinese)
[10]
Ryumin S, Tryaskin V. Computer-aided system for parametric design of ship hull structures—CADS-hull[J]. Machines, 2022, 10(4): 262.
[11]
Liu F, Chen C, Wu W. Research on intelligent design of luxury yacht[J]. Procedia Engineering, 2017, 174: 927-933.
[12]
Papanikolaou A. A holistic approach to ship design: Optimisation of ship design and operation for life cycle[M]. Springer, 2018.
[13]
Lecun Yann, Bottou Leon, Bengio Yoshua, Haffner Patrick. Gradient-based learning applied to document recognition[J]. Proceedings of the IEEE, 1998, 86(11): 2278-2324.
[14]
Krizhevsky A, Sutskever I, Hinton G E. ImageNet classification with deep convolutional neural networks[J]. Communications of the ACM, 2017, 60(6): 84-90.
[15]
Goodfellow I J, Pouget-Abadie J, Mirza M, et al. Generative adversarial nets[C]//Proceedings of the 27th International Conference on Neural Information Processing Systems-Volume 2. Montreal, Canada. 2014: 2672-2680.
[16]
Radford A, Metz L, Chintala S. Unsupervised representation learning with deep convolutional generative adversarial networks[C]//International Conference on Learning Representations, 2015.
[17]
Sun X, Lian Z H. EasyMesh: An efficient method to reconstruct 3D mesh from a single image[J]. Computer Aided Geometric Design, 2020, 80(C): 101862.
[18]
许豪灿,李基拓,陆国栋. 由LeNet-5从单张着装图像重建三维人体[J]. 浙江大学学报(工学版)202155(1):153-161.
Xu Haocan, Li Jituo, Lu Guodong. Reconstruction of three-dimensional human bodies from single image by LeNet-5[J]. Journal of Zhejiang University (Engineering Science), 2021, 55(1): 153-161. (in Chinese)
[19]
杜林,李广年,郑彭军. 船体曲面特征的计算机视觉认知与生成机制研究[J]. 船舶力学202226(7):949-961.
Du Lin, Li Guangnian, Zheng Pengjun. Ship hull feature recognition and creation functionality investigation based on computer vision technology[J]. Journal of Ship Mechanics, 2022, 26(7): 949-961. (in Chinese)
2024年第28卷第8期
PDF下载
86
39
引用本文
BibTeX
文章信息
doi: 10.3969/j.issn.1007-7294.2024.08.004
  • 接收时间:2024-02-27
  • 首发时间:2026-03-26
  • 出版时间:2024-08-20
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2024-02-27
基金
船舶总体性能创新研究开放基金资助项目(11322203)
国家自然科学基金青年科学基金资助项目(52201368)
高等学校学科创新引智计划项目(D21013)
作者信息
    1.宁波大学 海运学院,浙江 宁波 315000
    2.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.1007-7294.2024.08.004
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