Article(id=1241699535194477089, tenantId=1146029695717560320, journalId=1227999626482147330, issueId=1241699531444769296, articleNumber=null, orderNo=null, doi=10.16579/j.issn.1001.9669.2025.04.015, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1695657600000, receivedDateStr=2023-09-26, revisedDate=1698768000000, revisedDateStr=2023-11-01, acceptedDate=null, acceptedDateStr=null, onlineDate=1773973838852, onlineDateStr=2026-03-20, pubDate=1744646400000, pubDateStr=2025-04-15, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1773973838852, onlineIssueDateStr=2026-03-20, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1773973838852, creator=13701087609, updateTime=1773973838852, updator=13701087609, issue=Issue{id=1241699531444769296, tenantId=1146029695717560320, journalId=1227999626482147330, year='2025', volume='47', issue='4', pageStart='1', pageEnd='157', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1773973837957, creator=13701087609, updateTime=1773974092709, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1241700600002433947, tenantId=1146029695717560320, journalId=1227999626482147330, issueId=1241699531444769296, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1241700600006628252, tenantId=1146029695717560320, journalId=1227999626482147330, issueId=1241699531444769296, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=122, endPage=130, ext={EN=ArticleExt(id=1241699535408386600, articleId=1241699535194477089, tenantId=1146029695717560320, journalId=1227999626482147330, language=EN, title=Wing structural design of supersonic civil aircraft based on deep neural network, columnId=1241699532912784251, journalTitle=Journal of Mechanical Strength, columnName=∙Optimization∙Reliability∙, runingTitle=null, highlight=null, articleAbstract=

At present, the research on supersonic civil aircraft wings mainly focuses on the low sonic boom design and supersonic drag reduction technologies. There are relatively few studies on the wing structural design. Therefore, a multi-level optimization method for the wing structural design in the preliminary design stage of supersonic civil aircrafts was proposed. It included the parametric modeling of the wing structural layout, the automatic generation of the finite element model for the structural size optimization, construction and training of a surrogate model for the deep neural network. And the optimization was solved based on the deep neural network. The analysis results show that the proposed optimization strategy could quickly design the wing structure of the supersonic civil aircraft. The deep neural network model has higher prediction accuracy than the traditional surrogate model. Thus, the proposed approach can improve the efficiency of the preliminary design for wing structure.

, correspAuthors=null, authorNote=null, correspAuthorsNote=
WANG Yu, E-mail:
, 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=Fanggan NIU, Wenyuan MA, Chao YANG, Yu WANG, Hailian YIN), CN=ArticleExt(id=1241699541846643393, articleId=1241699535194477089, tenantId=1146029695717560320, journalId=1227999626482147330, language=CN, title=基于深度神经网络的超声速民机机翼结构设计, columnId=1240594158654641051, journalTitle=机械强度, columnName=·优化·可靠性·, runingTitle=null, highlight=null, articleAbstract=

目前对超声速民机机翼的研究主要侧重于低声爆设计技术和超声速减阻技术,针对机翼结构设计的研究相对较少。因此,提出了一种面向超声速民机初步设计阶段机翼结构设计的多级优化方法,包括机翼结构布局参数化建模、结构尺寸优化有限元模型的自动生成、深度神经网络代理模型的搭建与训练,以及基于深度神经网络代理模型进行优化求解。分析结果表明,提出的优化策略能够对超声速民机机翼结构进行良好的快速设计,深度神经网络模型相比于传统代理模型具有更高的预测精度,提高了机翼结构初步设计的效率。

, correspAuthors=null, authorNote=null, correspAuthorsNote=
王宇,女,1981年生,辽宁凌源人,副教授;主要研究方向为飞行器多学科设计与优化、新概念飞行器、变体机翼设计;E-mail:
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=ZWFFBipohbdCsfiNNHgVkQ==, magXml=O9NMlP2D5fJtbOkB0Br5qw==, pdfUrl=null, pdf=6KUrQ6LfrVbtr4MIzdkasg==, pdfFileSize=5438127, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=j/RUGLdEGDSc1Dna0CvAeg==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=os51G+zzSVOxfz+GDajmEA==, mapNumber=null, authorCompany=null, fund=null, authors=

牛芳淦,男,1998年生,安徽六安人,硕士研究生;主要研究方向为飞行器设计与优化;E-mail:

, authorsList=牛芳淦, 马文圆, 杨超, 王宇, 尹海莲)}, authors=[Author(id=1241699543545336533, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=niufanggan@163.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1241699543641805530, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, authorId=1241699543545336533, language=EN, stringName=Fanggan NIU, firstName=Fanggan, middleName=null, lastName=NIU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=Advanced Design Technology of Aircraft National Defense Key Subject Laboratory, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1241699543717303006, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, authorId=1241699543545336533, language=CN, stringName=牛芳淦, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=南京航空航天大学 飞行器设计先进技术国防重点学科实验室,南京 210016, bio={"content":"

牛芳淦,男,1998年生,安徽六安人,硕士研究生;主要研究方向为飞行器设计与优化;E-mail:

"}, bioImg=null, bioContent=

牛芳淦,男,1998年生,安徽六安人,硕士研究生;主要研究方向为飞行器设计与优化;E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1241699542157021895, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, xref=null, ext=[AuthorCompanyExt(id=1241699542182187720, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, companyId=1241699542157021895, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Advanced Design Technology of Aircraft National Defense Key Subject Laboratory, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China), AuthorCompanyExt(id=1241699542198964937, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, companyId=1241699542157021895, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=南京航空航天大学 飞行器设计先进技术国防重点学科实验室,南京 210016)])]), Author(id=1241699543792800483, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, 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=1241699543889269479, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, authorId=1241699543792800483, language=EN, stringName=Wenyuan MA, firstName=Wenyuan, middleName=null, lastName=MA, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=Advanced Design Technology of Aircraft National Defense Key Subject Laboratory, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1241699543981544170, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, authorId=1241699543792800483, language=CN, stringName=马文圆, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=南京航空航天大学 飞行器设计先进技术国防重点学科实验室,南京 210016, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1241699542157021895, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, xref=null, ext=[AuthorCompanyExt(id=1241699542182187720, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, companyId=1241699542157021895, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Advanced Design Technology of Aircraft National Defense Key Subject Laboratory, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China), AuthorCompanyExt(id=1241699542198964937, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, companyId=1241699542157021895, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=南京航空航天大学 飞行器设计先进技术国防重点学科实验室,南京 210016)])]), Author(id=1241699544057041645, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, 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=1241699544166093557, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, authorId=1241699544057041645, language=EN, stringName=Chao YANG, firstName=Chao, middleName=null, lastName=YANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=Advanced Design Technology of Aircraft National Defense Key Subject Laboratory, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1241699544245785337, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, authorId=1241699544057041645, language=CN, stringName=杨超, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=南京航空航天大学 飞行器设计先进技术国防重点学科实验室,南京 210016, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1241699542157021895, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, xref=null, ext=[AuthorCompanyExt(id=1241699542182187720, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, companyId=1241699542157021895, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Advanced Design Technology of Aircraft National Defense Key Subject Laboratory, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China), AuthorCompanyExt(id=1241699542198964937, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, companyId=1241699542157021895, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=南京航空航天大学 飞行器设计先进技术国防重点学科实验室,南京 210016)])]), Author(id=1241699544333865729, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=wangyu@nuaa.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1241699544417751814, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, authorId=1241699544333865729, language=EN, stringName=Yu WANG, firstName=Yu, middleName=null, lastName=WANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=Advanced Design Technology of Aircraft National Defense Key Subject Laboratory, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1241699544610689804, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, authorId=1241699544333865729, language=CN, stringName=王宇, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=南京航空航天大学 飞行器设计先进技术国防重点学科实验室,南京 210016, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1241699542157021895, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, xref=null, ext=[AuthorCompanyExt(id=1241699542182187720, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, companyId=1241699542157021895, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Advanced Design Technology of Aircraft National Defense Key Subject Laboratory, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China), AuthorCompanyExt(id=1241699542198964937, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, companyId=1241699542157021895, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=南京航空航天大学 飞行器设计先进技术国防重点学科实验室,南京 210016)])]), Author(id=1241699544782656275, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, 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=1241699544887513881, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, authorId=1241699544782656275, language=EN, stringName=Hailian YIN, firstName=Hailian, middleName=null, lastName=YIN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=Advanced Design Technology of Aircraft National Defense Key Subject Laboratory, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1241699544983982877, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, authorId=1241699544782656275, language=CN, stringName=尹海莲, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=南京航空航天大学 飞行器设计先进技术国防重点学科实验室,南京 210016, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1241699542157021895, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, xref=null, ext=[AuthorCompanyExt(id=1241699542182187720, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, companyId=1241699542157021895, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Advanced Design Technology of Aircraft National Defense Key Subject Laboratory, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China), AuthorCompanyExt(id=1241699542198964937, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, companyId=1241699542157021895, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=南京航空航天大学 飞行器设计先进技术国防重点学科实验室,南京 210016)])])], keywords=[Keyword(id=1241699545101423396, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, language=EN, orderNo=1, keyword=Supersonic civil aircraft), Keyword(id=1241699545189503786, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, language=EN, orderNo=2, keyword=Parameterization), Keyword(id=1241699545294361392, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, language=EN, orderNo=3, keyword=Deep neural network), Keyword(id=1241699545399219000, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, language=EN, orderNo=4, keyword=Surrogate model), Keyword(id=1241699545495688001, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, language=EN, orderNo=5, keyword=Structural design), Keyword(id=1241699545604739913, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, language=CN, orderNo=1, keyword=超声速民机), Keyword(id=1241699545688626000, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, language=CN, orderNo=2, keyword=参数化), Keyword(id=1241699545785095001, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, language=CN, orderNo=3, keyword=深度神经网络), Keyword(id=1241699545860592479, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, language=CN, orderNo=4, keyword=代理模型), Keyword(id=1241699545936089957, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, language=CN, orderNo=5, keyword=结构设计)], refs=[Reference(id=1241699554400194748, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, doi=null, pmid=null, pmcid=null, year=2007, volume=15, issue=null, pageStart=10355, pageEnd=10378, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=CHUDOBA B, COLEMAN G, ROBERTS K, journalName=null, refType=null, unstructuredReference=CHUDOBA BCOLEMAN GROBERTS K,et al. What price supersonic speed?A design anatomy of supersonic transportation-part 1[C]//45th AIAA Aerospace Sciences Meeting. Reston:AIAA,200715:10355-10378., articleTitle=What price supersonic speed?A design anatomy of supersonic transportation-part 1, refAbstract=null), Reference(id=1241699554488275140, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, doi=null, pmid=null, pmcid=null, year=2004, volume=20, issue=1, pageStart=59, pageEnd=68, url=null, language=null, rfNumber=[2], rfOrder=1, authorNames=CANDEL S, journalName=Journal of Propulsion and Power, refType=null, unstructuredReference=CANDEL S. Concorde and the future of supersonic transport[J].Journal of Propulsion and Power200420(1):59-68., articleTitle=Concorde and the future of supersonic transport, refAbstract=null), Reference(id=1241699554584744138, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, doi=null, pmid=null, pmcid=null, year=2015, volume=null, issue=3, pageStart=99, pageEnd=102, url=null, language=null, rfNumber=[3], rfOrder=2, authorNames=PEIREN G, journalName=Civil Aircraft Design and Research, refType=null, unstructuredReference=PEIREN G. Tu-144 supersonic transport[J]. Civil Aircraft Design and Research2015(3):99-102., articleTitle=Tu-144 supersonic transport, refAbstract=null), Reference(id=1241699554685407442, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, doi=null, pmid=null, pmcid=null, year=2005, volume=null, issue=null, pageStart=866, pageEnd=867, url=null, language=null, rfNumber=[4], rfOrder=3, authorNames=CONWAY E M, journalName=High-speed dreams:NASA and the technopolitics of supersonic transportation,1945-1999, refType=null, unstructuredReference=CONWAY E M. High-speed dreams:NASA and the technopolitics of supersonic transportation,1945-1999[M]. Baltimore:Johns Hopkins University Press,2005:866-867., articleTitle=null, refAbstract=null), Reference(id=1241699554790265050, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[5], rfOrder=4, authorNames=LIEBHARDT B, LÜTJENS K, UENO A, journalName=null, refType=null, unstructuredReference=LIEBHARDT BLÜTJENS KUENO A,et al. JAXA’s S4 supersonic low-boom airliner-a collaborative study on aircraft design,sonic boom simulation,and market prospects[C]//AIAA Aviation 2020 Forum. Reston:AIAA,2020:241349., articleTitle=JAXA’s S4 supersonic low-boom airliner-a collaborative study on aircraft design,sonic boom simulation,and market prospects, refAbstract=null), Reference(id=1241699554911899872, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, doi=null, pmid=null, pmcid=null, year=2019, volume=null, issue=null, pageStart=11, pageEnd=18, url=null, language=null, rfNumber=[6], rfOrder=5, authorNames=MICHAEL B, journalName=null, refType=null, unstructuredReference=MICHAEL B. Conceptual design of a quiet supersonic technology airliner[C]//AIAA Aviation 2019 Forum. Reston:AIAA,2019:11-18., articleTitle=Conceptual design of a quiet supersonic technology airliner, refAbstract=null), Reference(id=1241699555004174564, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[7], rfOrder=6, authorNames=MAGEE T E, SERRANO L, MENDOZA R, journalName=null, refType=null, unstructuredReference=MAGEE T ESERRANO LMENDOZA R,et al. X-59 CFD and wind tunnel data comparisons[C]//AIAA Aviation 2023 Forum.Reston:AIAA,2023:313279., articleTitle=X-59 CFD and wind tunnel data comparisons, refAbstract=null), Reference(id=1241699555104837871, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, doi=null, pmid=null, pmcid=null, year=2023, volume=44, issue=2, pageStart=20, pageEnd=46, url=null, language=null, rfNumber=[8], rfOrder=7, authorNames=丁玉临, 韩忠华, 乔建领, journalName=航空学报, refType=null, unstructuredReference=丁玉临,韩忠华,乔建领,等. 超声速民机总体气动布局设计关键技术研究进展[J]. 航空学报202344(2):20-46., articleTitle=超声速民机总体气动布局设计关键技术研究进展, refAbstract=null), Reference(id=1241699555247444218, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, doi=null, pmid=null, pmcid=null, year=2023, volume=44, issue=2, pageStart=20, pageEnd=46, url=null, language=null, rfNumber=[8], rfOrder=8, authorNames=DING Yulin, HAN Zhonghua, QIAO Jianling, journalName=Acta Aeronautica et Astronautica Sinica, refType=null, unstructuredReference=DING YulinHAN ZhonghuaQIAO Jianling,et al. Research progress in key technologies for conceptual-aerodynamic configuration design of supersonic transport aircraft[J]. Acta Aeronautica et Astronautica Sinica202344(2):20-46.(In Chinese), articleTitle=Research progress in key technologies for conceptual-aerodynamic configuration design of supersonic transport aircraft, refAbstract=null), Reference(id=1241699555356496128, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, doi=null, pmid=null, pmcid=null, year=2022, volume=43, issue=11, pageStart=63, pageEnd=98, url=null, language=null, rfNumber=[9], rfOrder=9, authorNames=袁吉森, 孙爵, 李玲玉, journalName=航空学报, refType=null, unstructuredReference=袁吉森,孙爵,李玲玉,等. 超声速飞机层流布局设计与评估技术进展[J]. 航空学报202243(11):63-98., articleTitle=超声速飞机层流布局设计与评估技术进展, refAbstract=null), Reference(id=1241699555457159432, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, doi=null, pmid=null, pmcid=null, year=2022, volume=43, issue=11, pageStart=63, pageEnd=98, url=null, language=null, rfNumber=[9], rfOrder=10, authorNames=YUAN Jishen, SUN Jue, LI Lingyu, journalName=Acta Aeronautica et Astronautica Sinica, refType=null, unstructuredReference=YUAN JishenSUN JueLI Lingyu,et al. Progress of supersonic aircraft laminar flow layout design and evalution technologies[J].Acta Aeronautica et Astronautica Sinica202243(11):63-98.(In Chinese), articleTitle=Progress of supersonic aircraft laminar flow layout design and evalution technologies, refAbstract=null), Reference(id=1241699556933554446, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[10], rfOrder=11, authorNames=SERAJ S, MARTINS J R R A, journalName=null, refType=null, unstructuredReference=SERAJ SMARTINS J R R A. Aerodynamic shape optimization of a supersonic transport considering low-speed stability[C]//AIAA Sciece and Technology Forum and Exposition,AIAA Sci Tech Forum 2022. Reston:AIAA,2022:270339., articleTitle=Aerodynamic shape optimization of a supersonic transport considering low-speed stability, refAbstract=null), Reference(id=1241699557034217749, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, doi=null, pmid=null, pmcid=null, year=2021, volume=59, issue=10, pageStart=3923, pageEnd=3936, url=null, language=null, rfNumber=[11], rfOrder=12, authorNames=LI W, GEISELHART K, journalName=AIAA Journal, refType=null, unstructuredReference=LI WGEISELHART K. Integration of low-fidelity MDO and CFD-Based redesign of low-boom supersonic transports[J]. AIAA Journal202159(10):3923-3936., articleTitle=Integration of low-fidelity MDO and CFD-Based redesign of low-boom supersonic transports, refAbstract=null), Reference(id=1241699557168435486, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, doi=null, pmid=null, pmcid=null, year=2010, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[12], rfOrder=13, authorNames=ESPINAL D, IM H, LEE B, journalName=null, refType=null, unstructuredReference=ESPINAL DIM HLEE B,et al. Supersonic bi-directional flying wing,Part II:conceptual design of a high speed civil transport[C]//48th AIAA Aerospace Sciences Meeting Including the New Horizons Forum and Aerospace Exposition. Reston:AIAA,2010:82585., articleTitle=Supersonic bi-directional flying wing,Part II:conceptual design of a high speed civil transport, refAbstract=null), Reference(id=1241699557285876009, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, doi=null, pmid=null, pmcid=null, year=2015, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[13], rfOrder=14, authorNames=MELLQUIST E C, BENDIKSEN O O, journalName=null, refType=null, unstructuredReference=MELLQUIST E CBENDIKSEN O O. Analysis of the transonic flutter of supersonic transport wings[C]//56th AIAA/ASCE/AHS/ASC Structures,Structural Dynamics,and Materials Conference 2015. Reston:AIAA,2015:112819., articleTitle=Analysis of the transonic flutter of supersonic transport wings, refAbstract=null), Reference(id=1241699557369762092, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, doi=null, pmid=null, pmcid=null, year=2022, volume=43, issue=2, pageStart=217, pageEnd=226, url=null, language=null, rfNumber=[14], rfOrder=15, authorNames=唐佳栋, 娄斌, 叶尚军, journalName=力学季刊, refType=null, unstructuredReference=唐佳栋,娄斌,叶尚军,等. 基于卷积神经网络和松鼠优化算法的机翼结构混合优化设计[J]. 力学季刊202243(2):217-226., articleTitle=基于卷积神经网络和松鼠优化算法的机翼结构混合优化设计, refAbstract=null), Reference(id=1241699557483008304, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, doi=null, pmid=null, pmcid=null, year=2022, volume=43, issue=2, pageStart=217, pageEnd=226, url=null, language=null, rfNumber=[14], rfOrder=16, authorNames=TANG Jiadong, LOU Bin, YE Shangjun, journalName=Chinese Quarterly of Mechanics, refType=null, unstructuredReference=TANG JiadongLOU BinYE Shangjun,et al. Hybrid optimization design of wing structure based on convolution neural network and squirrel search algorithm[J]. Chinese Quarterly of Mechanics202243(2):217-226.(In Chinese), articleTitle=Hybrid optimization design of wing structure based on convolution neural network and squirrel search algorithm, refAbstract=null), Reference(id=1241699557571088697, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, doi=null, pmid=null, pmcid=null, year=2023, volume=41, issue=7, pageStart=48, pageEnd=55, url=null, language=null, rfNumber=[15], rfOrder=17, authorNames=屈经国, 彭博, 易贤, journalName=空气动力学学报, refType=null, unstructuredReference=屈经国,彭博,易贤,等. 基于深度神经网络的任意翼型结冰预测方法[J]. 空气动力学学报202341(7):48-55., articleTitle=基于深度神经网络的任意翼型结冰预测方法, refAbstract=null), Reference(id=1241699557634003262, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, doi=null, pmid=null, pmcid=null, year=2023, volume=41, issue=7, pageStart=48, pageEnd=55, url=null, language=null, rfNumber=[15], rfOrder=18, authorNames=QU Jingguo, PENG Bo, YI Xian, journalName=Acta Aerodynamica Sinica, refType=null, unstructuredReference=QU JingguoPENG BoYI Xian,et al. Icing prediction method for arbitrary airfoil using deep neural networks[J]. Acta Aerodynamica Sinica202341(7):48-55.(In Chinese), articleTitle=Icing prediction method for arbitrary airfoil using deep neural networks, refAbstract=null), Reference(id=1241699557743055174, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, doi=null, pmid=null, pmcid=null, year=2019, volume=22, issue=1, pageStart=65, pageEnd=78, url=null, language=null, rfNumber=[16], rfOrder=19, authorNames=DENG L, WANG Y Q, LIU Y, journalName=Journal of Visualization, refType=null, unstructuredReference=DENG LWANG Y QLIU Y,et al. A CNN-based vortex identification method[J]. Journal of Visualization201922(1):65-78., articleTitle=A CNN-based vortex identification method, refAbstract=null), Reference(id=1241699557847912784, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, doi=null, pmid=null, pmcid=null, year=2018, volume=41, issue=5, pageStart=1122, pageEnd=1135, url=null, language=null, rfNumber=[17], rfOrder=20, authorNames=SÁNCHEZ-SÁNCHEZ C, IZZO D, journalName=Journal of Guidance,Control,and Dynamics, refType=null, unstructuredReference=SÁNCHEZ-SÁNCHEZ CIZZO D. Real-time optimal control via deep neural networks:study on landing problems[J]. Journal of Guidance,Control,and Dynamics201841(5):1122-1135., articleTitle=Real-time optimal control via deep neural networks:study on landing problems, refAbstract=null), Reference(id=1241699557982130520, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, doi=null, pmid=null, pmcid=null, year=2016, volume=null, issue=null, pageStart=56, pageEnd=57, url=null, language=null, rfNumber=[18], rfOrder=21, authorNames=姚卫星, 顾怡, journalName=飞机结构设计, refType=null, unstructuredReference=姚卫星,顾怡. 飞机结构设计[M]. 北京:国防工业出版社,2016:56-57., articleTitle=null, refAbstract=null), Reference(id=1241699558082793822, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, doi=null, pmid=null, pmcid=null, year=2016, volume=null, issue=null, pageStart=56, pageEnd=57, url=null, language=null, rfNumber=[18], rfOrder=22, authorNames=YAO Weixing, GU Yi, journalName=Aircraft structural design, refType=null, unstructuredReference=YAO WeixingGU Yi. Aircraft structural design[M]. Beijing:National Defense Industry Press,2016:56-57.(In Chinese), articleTitle=null, refAbstract=null), Reference(id=1241699558330257768, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, doi=null, pmid=null, pmcid=null, year=2016, volume=null, issue=null, pageStart=43, pageEnd=44, url=null, language=null, rfNumber=[19], rfOrder=23, authorNames=刘磊, journalName=null, refType=null, unstructuredReference=刘磊. 空天飞机重量估算方法研究[D]. 南京:南京航空航天大学,2016:43-44., articleTitle=空天飞机重量估算方法研究, refAbstract=null), Reference(id=1241699558430921072, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, doi=null, pmid=null, pmcid=null, year=2016, volume=null, issue=null, pageStart=43, pageEnd=44, url=null, language=null, rfNumber=[19], rfOrder=24, authorNames=LIU Lei, journalName=null, refType=null, unstructuredReference=LIU Lei. Research on weight estimation method of aerospace aircraft[D]. Nanjing:Nanjing University of Aeronautics and Astronautics,2016:43-44.(In Chinese), articleTitle=Research on weight estimation method of aerospace aircraft, refAbstract=null), Reference(id=1241699558535778679, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, doi=null, pmid=null, pmcid=null, year=2000, volume=null, issue=null, pageStart=410, pageEnd=420, url=null, language=null, rfNumber=[20], rfOrder=25, authorNames=王宝忠, journalName=飞机设计手册:第十册:结构设计, refType=null, unstructuredReference=王宝忠. 飞机设计手册:第十册:结构设计[M]. 北京:航空工业出版社,2000:410-420., articleTitle=null, refAbstract=null), Reference(id=1241699558632247677, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, doi=null, pmid=null, pmcid=null, year=2000, volume=null, issue=null, pageStart=410, pageEnd=420, url=null, language=null, rfNumber=[20], rfOrder=26, authorNames=WANG Baozhong, journalName=Aircraft design manual:Volume 10:structural design, refType=null, unstructuredReference=WANG Baozhong. Aircraft design manual:Volume 10:structural design[M]. Beijing:Aviation Industry Publishing House,2000:410-420.(In Chinese), articleTitle=null, refAbstract=null), Reference(id=1241699558762271109, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[21], rfOrder=27, authorNames=Microsoft, journalName=null, refType=null, unstructuredReference=Microsoft. Neural network intelligence[EB/OL].(2019-09-01).https://www.microsoft.com/en-us/research/project/neural-networ-k-intelligence/., articleTitle=Neural network intelligence, refAbstract=null), Reference(id=1241699558892294538, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[22], rfOrder=28, authorNames=Google, journalName=null, refType=null, unstructuredReference=Google. TensorFlow:an end-to-end source machine learning platform[EB/OL]. (2019-08-10). https://opensource.google/proj-ects/tensorflow., articleTitle=TensorFlow:an end-to-end source machine learning platform, refAbstract=null), Reference(id=1241699558997152145, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, doi=null, pmid=null, pmcid=null, year=2010, volume=81654, issue=null, pageStart=807, pageEnd=814, url=null, language=null, rfNumber=[23], rfOrder=29, authorNames=NAIR V, HINTON G E, journalName=null, refType=null, unstructuredReference=NAIR VHINTON G E. Rectified linear units improve restricted Boltzmann machines [C]//27th International Conference on Machine Learning ICML 2010,201081654(807-814)., articleTitle=Rectified linear units improve restricted Boltzmann machines, refAbstract=null), Reference(id=1241699559076843926, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, doi=null, pmid=null, pmcid=null, year=1988, volume=38, issue=3, pageStart=301, pageEnd=339, url=null, language=null, rfNumber=[24], rfOrder=30, authorNames=NEWEY W K, journalName=Journal of Econometrics, refType=null, unstructuredReference=NEWEY W K. Adaptive estimation of regression models via moment restrictions[J]. Journal of Econometrics198838(3):301-339., articleTitle=Adaptive estimation of regression models via moment restrictions, refAbstract=null), Reference(id=1241699559160730010, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, doi=null, pmid=null, pmcid=null, year=2021, volume=42, issue=4, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[25], rfOrder=31, authorNames=范周伟, 余雄庆, 王朝, journalName=航空学报, refType=null, unstructuredReference=范周伟,余雄庆,王朝,等. 基于深度神经网络的客机总体设计参数敏感性分析[J]. 航空学报202142(4):524353., articleTitle=基于深度神经网络的客机总体设计参数敏感性分析, refAbstract=null), Reference(id=1241699559265587616, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, doi=null, pmid=null, pmcid=null, year=2021, volume=42, issue=4, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[25], rfOrder=32, authorNames=FAN Zhouwei, YU Xiongqing, WANG Chao, journalName=Acta Aeronautica et Astronautica Sinica, refType=null, unstructuredReference=FAN ZhouweiYU XiongqingWANG Chao,et al. Sensitivity analysis of key design parameters of commercial aircraft using deep neural network[J]. Acta Aeronautica et Astronautica Sinica202142(4):524353.(In Chinese), articleTitle=Sensitivity analysis of key design parameters of commercial aircraft using deep neural network, refAbstract=null), Reference(id=1241699559362056615, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, doi=null, pmid=null, pmcid=null, year=2015, volume=1, issue=119782, pageStart=448, pageEnd=456, url=null, language=null, rfNumber=[26], rfOrder=33, authorNames=LOFFE S, SZEGEDY C, journalName=null, refType=null, unstructuredReference=LOFFE SSZEGEDY C. Batch normalization:accelerating deep network training by reducing internal covariate shift[C]//32nd International Conference on Machine Learning,ICML 2015. 20151:119782(448-456)., articleTitle=Batch normalization:accelerating deep network training by reducing internal covariate shift, refAbstract=null), Reference(id=1241699559483691439, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, doi=null, pmid=null, pmcid=null, year=2019, volume=135, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[27], rfOrder=34, authorNames=BOUHLEL M A, HWANG J T, BARTOLI N, journalName=Advances in Engineering Software, refType=null, unstructuredReference=BOUHLEL M AHWANG J TBARTOLI N,et al. A Python surrogate modeling framework with derivatives[J]. Advances in Engineering Software2019135:102662., articleTitle=A Python surrogate modeling framework with derivatives, refAbstract=null), Reference(id=1241699559626297785, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[28], rfOrder=35, authorNames=GUOFEI9987, journalName=null, refType=null, unstructuredReference=GUOFEI9987. Scikit-Opt[EB/OL].(2023-09-14). https://github.com/guofei9987/scikit-opt., articleTitle=Scikit-Opt, refAbstract=null)], funds=[Fund(id=1241699554081427628, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, awardId=12032011, language=EN, fundingSource=National Natural Science Foundation of China(12032011), fundOrder=null, country=null), Fund(id=1241699554186285236, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, awardId=12032011, language=CN, fundingSource=国家自然科学基金项目(12032011), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1241699542157021895, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, xref=null, ext=[AuthorCompanyExt(id=1241699542182187720, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, companyId=1241699542157021895, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Advanced Design Technology of Aircraft National Defense Key Subject Laboratory, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China), AuthorCompanyExt(id=1241699542198964937, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, companyId=1241699542157021895, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=南京航空航天大学 飞行器设计先进技术国防重点学科实验室,南京 210016)])], figs=[ArticleFig(id=1241699546074501996, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, language=EN, label=Fig. 1, caption=Top view of the half wing, figureFileSmall=ipQ8c2/9ic8NpPy/6ev8YA==, figureFileBig=j/RUGLdEGDSc1Dna0CvAeg==, tableContent=null), ArticleFig(id=1241699546162582387, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, language=CN, label=图1, caption=机翼半模俯视图, figureFileSmall=ipQ8c2/9ic8NpPy/6ev8YA==, figureFileBig=j/RUGLdEGDSc1Dna0CvAeg==, tableContent=null), ArticleFig(id=1241699547852886920, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, language=EN, label=Fig. 2, caption=Structure layout diagram of the wing, figureFileSmall=MjfQz0peW8h637Q0Hx/c9w==, figureFileBig=LDzaRudPym4rLSYnvmOjQA==, tableContent=null), ArticleFig(id=1241699548091962260, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, language=CN, label=图2, caption=机翼结构布置简图, figureFileSmall=MjfQz0peW8h637Q0Hx/c9w==, figureFileBig=LDzaRudPym4rLSYnvmOjQA==, tableContent=null), ArticleFig(id=1241699548205208477, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, language=EN, label=Fig. 3, caption=Structure layouts of different wings, figureFileSmall=5Q37Ffzy0Omd0CYKBqAffg==, figureFileBig=iqgmpsdxRe/8HScyYyti1A==, tableContent=null), ArticleFig(id=1241699548410729383, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, language=CN, label=图3, caption=不同机翼结构布置形式, figureFileSmall=5Q37Ffzy0Omd0CYKBqAffg==, figureFileBig=iqgmpsdxRe/8HScyYyti1A==, tableContent=null), ArticleFig(id=1241699548553335726, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, language=EN, label=Fig. 4, caption=Area division diagram of the wing, figureFileSmall=B3bd0QUuurLOsJBsUHfe/w==, figureFileBig=WHdNptTrqJVRn8QiKIvkeA==, tableContent=null), ArticleFig(id=1241699548687553461, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, language=CN, label=图4, caption=机翼区域划分示意图, figureFileSmall=B3bd0QUuurLOsJBsUHfe/w==, figureFileBig=WHdNptTrqJVRn8QiKIvkeA==, tableContent=null), ArticleFig(id=1241699548846937020, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, language=EN, label=Fig. 5, caption=Finite element modeling process for the size optimization, figureFileSmall=TDecJv7WVR+NMSGxiT3sBQ==, figureFileBig=iMaR9ywTqyITG8NntS84+g==, tableContent=null), ArticleFig(id=1241699548930823106, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, language=CN, label=图5, caption=尺寸优化有限元建模流程, figureFileSmall=TDecJv7WVR+NMSGxiT3sBQ==, figureFileBig=iMaR9ywTqyITG8NntS84+g==, tableContent=null), ArticleFig(id=1241699549069235149, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, language=EN, label=Fig. 6, caption=Strategy of the optimization design, figureFileSmall=u09gIAhP2HM8fKR9Rjfvkg==, figureFileBig=9OjEQ8S1yvKMNUWevIe9dQ==, tableContent=null), ArticleFig(id=1241699549182481364, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, language=CN, label=图6, caption=优化设计策略, figureFileSmall=u09gIAhP2HM8fKR9Rjfvkg==, figureFileBig=9OjEQ8S1yvKMNUWevIe9dQ==, tableContent=null), ArticleFig(id=1241699549299921882, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, language=EN, label=Fig. 7, caption=Convergence process of the size optimization, figureFileSmall=qsyWpe4XO5S8onjqRHXTvA==, figureFileBig=NIvnxDCTUTnRuH/m4yNmcg==, tableContent=null), ArticleFig(id=1241699549417362398, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, language=CN, label=图7, caption=尺寸优化收敛历程, figureFileSmall=qsyWpe4XO5S8onjqRHXTvA==, figureFileBig=NIvnxDCTUTnRuH/m4yNmcg==, tableContent=null), ArticleFig(id=1241699549518025700, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, language=EN, label=Fig. 8, caption=Structure of the deep neural network, figureFileSmall=D2/EVMrfeJuv7aip+69SCg==, figureFileBig=D6Fg+4Fe/xGjA3MJNk9a4A==, tableContent=null), ArticleFig(id=1241699549610300395, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, language=CN, label=图8, caption=深度神经网络结构, figureFileSmall=D2/EVMrfeJuv7aip+69SCg==, figureFileBig=D6Fg+4Fe/xGjA3MJNk9a4A==, tableContent=null), ArticleFig(id=1241699549715158000, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, language=EN, label=Fig. 9, caption=Stress nephogram of the skeleton structure, figureFileSmall=idyB55XvRZYCym/+GQJObg==, figureFileBig=+jvliclSzyzRoic4xBAM0g==, tableContent=null), ArticleFig(id=1241699549807432692, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, language=CN, label=图9, caption=骨架结构应力云图, figureFileSmall=idyB55XvRZYCym/+GQJObg==, figureFileBig=+jvliclSzyzRoic4xBAM0g==, tableContent=null), ArticleFig(id=1241699549908095992, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, language=EN, label=Fig. 10, caption=Stress nephogram of the skin, figureFileSmall=xf3GLxrd2icY7xr794wsqg==, figureFileBig=52xjszkIlJEHpp6pNuVAQA==, tableContent=null), ArticleFig(id=1241699550033925116, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, language=CN, label=图10, caption=蒙皮应力云图, figureFileSmall=xf3GLxrd2icY7xr794wsqg==, figureFileBig=52xjszkIlJEHpp6pNuVAQA==, tableContent=null), ArticleFig(id=1241699550151365633, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, language=EN, label=Fig. 11, caption=Strain nephogram of the skin, figureFileSmall=dDQKPL1SjyFZutOmkA+kfg==, figureFileBig=t3YlP8LhI9eiTUIfw29owQ==, tableContent=null), ArticleFig(id=1241699550260416521, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, language=CN, label=图11, caption=蒙皮应变云图, figureFileSmall=dDQKPL1SjyFZutOmkA+kfg==, figureFileBig=t3YlP8LhI9eiTUIfw29owQ==, tableContent=null), ArticleFig(id=1241699550386245643, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, language=EN, label=Fig. 12, caption=Displacement nephogram of the wing, figureFileSmall=3hpDP5Q1xzAImAT2LPhf4w==, figureFileBig=4UxVvtYfHaaUPWnxQrLqvQ==, tableContent=null), ArticleFig(id=1241699550537240596, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, language=CN, label=图12, caption=机翼位移云图, figureFileSmall=3hpDP5Q1xzAImAT2LPhf4w==, figureFileBig=4UxVvtYfHaaUPWnxQrLqvQ==, tableContent=null), ArticleFig(id=1241699550616932375, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, language=EN, label=Tab. 1, caption=

Wing parameters

, figureFileSmall=null, figureFileBig=null, tableContent=
分段数
Number of sections
展向长度
Spanwise length/mm
内侧弦长
Inner chord length/mm
前缘后掠角
Swept angle of leading edge/(°)
上反角
Anhedral angle/(°)
12 071.535 356.882.40.0
21 737.019 782.178.60.0
35 212.411 157.160.60.0
45 182.56 024.860.65.0
), ArticleFig(id=1241699550705012768, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, language=CN, label=表1, caption=

机翼参数

, figureFileSmall=null, figureFileBig=null, tableContent=
分段数
Number of sections
展向长度
Spanwise length/mm
内侧弦长
Inner chord length/mm
前缘后掠角
Swept angle of leading edge/(°)
上反角
Anhedral angle/(°)
12 071.535 356.882.40.0
21 737.019 782.178.60.0
35 212.411 157.160.60.0
45 182.56 024.860.65.0
), ArticleFig(id=1241699550788898852, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, language=EN, label=Tab. 2, caption=

Main layout parameters of the wing

, figureFileSmall=null, figureFileBig=null, tableContent=
布局参数
Layout parameter
参数简要说明
Brief description of parameters
nWeb1前翼盒腹板个数
Number of leading wing box webs
nWeb2内段1#翼盒腹板个数
Number of inner section 1# wing box webs
nWeb3内段2#翼盒腹板个数
Number of inner section 2# wing box webs
nRib1第1段机翼翼肋数
Rib number of the first section of the wing
nRib2外段1#翼盒翼肋数
Outer section 1# wing box wing rib number
nRib3外段2#翼盒翼肋数
Outer section 2# wing box wing rib number
), ArticleFig(id=1241699550872784938, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, language=CN, label=表2, caption=

机翼主要布局参数

, figureFileSmall=null, figureFileBig=null, tableContent=
布局参数
Layout parameter
参数简要说明
Brief description of parameters
nWeb1前翼盒腹板个数
Number of leading wing box webs
nWeb2内段1#翼盒腹板个数
Number of inner section 1# wing box webs
nWeb3内段2#翼盒腹板个数
Number of inner section 2# wing box webs
nRib1第1段机翼翼肋数
Rib number of the first section of the wing
nRib2外段1#翼盒翼肋数
Outer section 1# wing box wing rib number
nRib3外段2#翼盒翼肋数
Outer section 2# wing box wing rib number
), ArticleFig(id=1241699552416288820, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, language=EN, label=Tab. 3, caption=

Design variables of the structural layout

, figureFileSmall=null, figureFileBig=null, tableContent=
设计变量
Design variable
初始值
Initial value
下限
Lower limit
上限
Upper limit
nWeb19912
nWeb2559
nWeb37712
nRib1113
nRib2447
nRib3447
), ArticleFig(id=1241699552537923644, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, language=CN, label=表3, caption=

结构布局设计变量

, figureFileSmall=null, figureFileBig=null, tableContent=
设计变量
Design variable
初始值
Initial value
下限
Lower limit
上限
Upper limit
nWeb19912
nWeb2559
nWeb37712
nRib1113
nRib2447
nRib3447
), ArticleFig(id=1241699552638586949, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, language=EN, label=Tab. 4, caption=

Performance parameters of metal material

, figureFileSmall=null, figureFileBig=null, tableContent=
材料
Material
弹性模量
Modulus of elasticity/GPa
泊松比
Poisson ratio
密度
Density/(kg/m3)
7075-T671.70.332 800
), ArticleFig(id=1241699552747638859, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, language=CN, label=表4, caption=

金属材料属性参数

, figureFileSmall=null, figureFileBig=null, tableContent=
材料
Material
弹性模量
Modulus of elasticity/GPa
泊松比
Poisson ratio
密度
Density/(kg/m3)
7075-T671.70.332 800
), ArticleFig(id=1241699552877662293, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, language=EN, label=Tab. 5, caption=

Performance parameters of T800 carbon fiber composite material

, figureFileSmall=null, figureFileBig=null, tableContent=
材料MaterialE11/GPaE22/GPaG12/GPaν12ρ/(kg/m3)
T800149.19.655.040.291 600
), ArticleFig(id=1241699552965742683, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, language=CN, label=表5, caption=

T800碳纤维复合材料属性参数

, figureFileSmall=null, figureFileBig=null, tableContent=
材料MaterialE11/GPaE22/GPaG12/GPaν12ρ/(kg/m3)
T800149.19.655.040.291 600
), ArticleFig(id=1241699553074794594, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, language=EN, label=Tab. 6, caption=

Definition of structural size design variables

, figureFileSmall=null, figureFileBig=null, tableContent=
设计变量
Design variable
初始值
Initial value
下限
Lower limit
上限
Upper limit
各段机翼上蒙皮厚度
Thickness of the wing upper skin of each section/mm
12、10、8、4224
各段机翼下蒙皮厚度
Thickness of the wing lower skin of each section/mm
12、10、8、6325
各段机翼腹板厚度
Wing web thickness of each section/mm
8、6、4、21.58
各段机翼肋腹板厚度
Thickness of each section of the wing rib web plate/mm
8、6、4、218
各段机翼腹板缘条横截面积
Cross-sectional area of each section of the wing web flange/mm2
5003002 000
各段机翼肋缘条横截面积
Cross-sectional area of each section of the wing rib flange/mm2
3002001 500
), ArticleFig(id=1241699553171263592, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, language=CN, label=表6, caption=

结构尺寸设计变量定义

, figureFileSmall=null, figureFileBig=null, tableContent=
设计变量
Design variable
初始值
Initial value
下限
Lower limit
上限
Upper limit
各段机翼上蒙皮厚度
Thickness of the wing upper skin of each section/mm
12、10、8、4224
各段机翼下蒙皮厚度
Thickness of the wing lower skin of each section/mm
12、10、8、6325
各段机翼腹板厚度
Wing web thickness of each section/mm
8、6、4、21.58
各段机翼肋腹板厚度
Thickness of each section of the wing rib web plate/mm
8、6、4、218
各段机翼腹板缘条横截面积
Cross-sectional area of each section of the wing web flange/mm2
5003002 000
各段机翼肋缘条横截面积
Cross-sectional area of each section of the wing rib flange/mm2
3002001 500
), ArticleFig(id=1241699553263538289, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, language=EN, label=Tab. 7, caption=

Partial sample points’ data of the layout design

, figureFileSmall=null, figureFileBig=null, tableContent=
样本点
Sample point
nWeb1nWeb2nWeb3nRib1nRib2nRib3
样本点1
Sample 1
1157147
样本点2
Sample 2
1079274
), ArticleFig(id=1241699553360007285, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, language=CN, label=表7, caption=

部分布局设计样本点数据

, figureFileSmall=null, figureFileBig=null, tableContent=
样本点
Sample point
nWeb1nWeb2nWeb3nRib1nRib2nRib3
样本点1
Sample 1
1157147
样本点2
Sample 2
1079274
), ArticleFig(id=1241699553473253502, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, language=EN, label=Tab. 8, caption=

Sampling value of structural layout design variables

, figureFileSmall=null, figureFileBig=null, tableContent=
设计变量Design variable抽取值Extract value
nWeb19、10、12
nWeb25、7、9
nWeb37、9、12
nRib11、3
nRib24、7
nRib34、7
), ArticleFig(id=1241699553561333894, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, language=CN, label=表8, caption=

结构布局设计变量抽样取值

, figureFileSmall=null, figureFileBig=null, tableContent=
设计变量Design variable抽取值Extract value
nWeb19、10、12
nWeb25、7、9
nWeb37、9、12
nRib11、3
nRib24、7
nRib34、7
), ArticleFig(id=1241699553661997197, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, language=EN, label=Tab. 9, caption=

Comparison of prediction accuracy of each surrogate model

, figureFileSmall=null, figureFileBig=null, tableContent=
模型名称Model nameEMRE/%
深度神经网络代理模型
Deep neural network surrogate model
1.81
二次多项式响应面模型
Second-order polynomial response surface model
5.40
六次多项式响应面模型
Six-order polynomial response surface model
4.10
Kriging模型Kriging model2.25
), ArticleFig(id=1241699553754271891, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, language=CN, label=表9, caption=

各代理模型预测精度对比

, figureFileSmall=null, figureFileBig=null, tableContent=
模型名称Model nameEMRE/%
深度神经网络代理模型
Deep neural network surrogate model
1.81
二次多项式响应面模型
Second-order polynomial response surface model
5.40
六次多项式响应面模型
Six-order polynomial response surface model
4.10
Kriging模型Kriging model2.25
), ArticleFig(id=1241699553867518107, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, language=EN, label=Tab. 10, caption=

Comparison of results of structural optimal design points

, figureFileSmall=null, figureFileBig=null, tableContent=
nWeb1nWeb2nWeb3nRib1nRib2nRib3 m/t
9591466.126.14
), ArticleFig(id=1241699553968181411, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241699535194477089, language=CN, label=表10, caption=

结构最优设计点结果对比

, figureFileSmall=null, figureFileBig=null, tableContent=
nWeb1nWeb2nWeb3nRib1nRib2nRib3 m/t
9591466.126.14
)], attaches=null, journal=Journal(id=1227999351742652416, delFlag=0, nameCn=机械强度, nameEn=Journal of Mechanical Strength, nameHistory1=null, nameHistory2=null, issn=1001-9669, eissn=null, cn=41-1134/TH, 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=9ETNXOzwmuGm49pLRqXxWw==, journalPrice=null, startedYear=null, abbrevIsoEn=Journal of Mechanical Strength, journalRemark=null, publicationField=null, createdTime=1770707460585, updatedTime=1770707700588, createdBy=18614031015, updatedBy=13701087609, firstLetterCn=J, firstLetterEn=J, subjectCode=Engineering, subjectName=null, subjectCodeEn=Engineering, subjectNameEn=null, picCn=9ETNXOzwmuGm49pLRqXxWw==, picEn=sS2ogjwdwM8GMbFtuWTIkA==, jcr=null, cjcr=null, exts=[JournalExt(id=1228000358505578506, language=CN, name=机械强度, 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=1770707700611, updatedTime=1770707700611, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=https://journal.ids.fzyun.cn/auth/realms/journal/protocol/openid-connect/auth?client_id=journal-jxqd-author&redirect_uri=https%3A%2F%2Fjxqd.portal.founderss.cn%2Foauth%2Fcallback&response_type=code&scope=phone+openid+email+profile&state=aa1eff81-489d-4951, submissionEditorUrl=https://journal.ids.fzyun.cn/auth/realms/journal/protocol/openid-connect/auth?client_id=journal-portal&redirect_uri=https%3A%2F%2Fjournal.portal.founderss.cn%2Foauth%2Fcallback&response_type=code&scope=phone+openid+email+profile&state=df5d5e38-1d45-4fcd-b, submissionReviewUrl=https://journal.ids.fzyun.cn/auth/realms/journal/protocol/openid-connect/auth?client_id=journal-jxqd-author&redirect_uri=https%3A%2F%2Fjxqd.portal.founderss.cn%2Foauth%2Fcallback&response_type=code&scope=phone+openid+email+profile&state=49f73d27-439e-4d5b, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1228000358551715851, language=EN, name=Journal of Mechanical Strength, 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=1770707700622, updatedTime=1770707700622, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=https://journal.ids.fzyun.cn/auth/realms/journal/protocol/openid-connect/auth?client_id=journal-jxqd-author&redirect_uri=https%3A%2F%2Fjxqd.portal.founderss.cn%2Foauth%2Fcallback&response_type=code&scope=phone+openid+email+profile&state=aa1eff81-489d-4951, submissionEditorUrl=https://journal.ids.fzyun.cn/auth/realms/journal/protocol/openid-connect/auth?client_id=journal-portal&redirect_uri=https%3A%2F%2Fjournal.portal.founderss.cn%2Foauth%2Fcallback&response_type=code&scope=phone+openid+email+profile&state=df5d5e38-1d45-4fcd-b, submissionReviewUrl=https://journal.ids.fzyun.cn/auth/realms/journal/protocol/openid-connect/auth?client_id=journal-jxqd-author&redirect_uri=https%3A%2F%2Fjxqd.portal.founderss.cn%2Foauth%2Fcallback&response_type=code&scope=phone+openid+email+profile&state=49f73d27-439e-4d5b, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1227999626482147330, websiteList=[Website(id=1228000871984853626, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1227999626482147330, 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/jxqd/CN, language=CN, createTime=1770707823034, createBy=18614031015, updateTime=1770707851936, updateBy=18614031015, name=机械强度-中文, tplId=1146099689490845704, title=机械强度, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1228001259580486284, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1228000871984853626, code=articleTextType, value=kx, createTime=1770707915444, updateTime=1770707915444, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001259555320457, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1228000871984853626, code=banner, value=null, createTime=1770707915438, updateTime=1770707915438, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001259605652111, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1228000871984853626, code=grayFlag, value=0, createTime=1770707915450, updateTime=1770707915450, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001259542737544, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1228000871984853626, code=logo, value=https://castjournals.cast.org.cn/joweb/jxqd/CN/file/pic?fileId=wrginrTxTIens2Yn6gXaKA==, createTime=1770707915435, updateTime=1770707915435, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001259622429329, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1228000871984853626, code=minRunFlag, value=0, createTime=1770707915454, updateTime=1770707915454, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001259572097675, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1228000871984853626, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/jxqd/CN/file/pic, createTime=1770707915442, updateTime=1770707915442, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001259614040720, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1228000871984853626, code=silenceFlag, value=0, createTime=1770707915452, updateTime=1770707915452, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001259567903370, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1228000871984853626, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1770707915441, updateTime=1770707915441, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001259588874893, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1228000871984853626, code=themeColor, value=null, createTime=1770707915446, updateTime=1770707915446, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001259597263502, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1228000871984853626, code=themeStyle, value=null, createTime=1770707915448, updateTime=1770707915448, creator=18614031015, updator=18614031015)]), Website(id=1228000872056156796, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1227999626482147330, 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/jxqd/EN, language=EN, createTime=1770707823051, createBy=18614031015, updateTime=1770707871019, updateBy=18614031015, name=机械强度-英文, tplId=1146101810881728533, title=Journal of Mechanical Strength, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1228001314525868694, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1228000872056156796, code=articleTextType, value=kx, createTime=1770707928544, updateTime=1770707928544, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001314504897171, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1228000872056156796, code=banner, value=null, createTime=1770707928539, updateTime=1770707928539, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001314542645913, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1228000872056156796, code=grayFlag, value=0, createTime=1770707928548, updateTime=1770707928548, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001314496508562, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1228000872056156796, code=logo, value=https://castjournals.cast.org.cn/joweb/jxqd/EN/file/pic?fileId=wrginrTxTIens2Yn6gXaKA==, createTime=1770707928537, updateTime=1770707928537, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001314555228827, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1228000872056156796, code=minRunFlag, value=0, createTime=1770707928551, updateTime=1770707928551, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001314517480085, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1228000872056156796, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/jxqd/EN/file/pic, createTime=1770707928542, updateTime=1770707928542, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001314551034522, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1228000872056156796, code=silenceFlag, value=0, createTime=1770707928550, updateTime=1770707928550, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001314513285780, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1228000872056156796, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_en_623/, createTime=1770707928541, updateTime=1770707928541, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001314530062999, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1228000872056156796, code=themeColor, value=null, createTime=1770707928545, updateTime=1770707928545, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001314538451608, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1228000872056156796, code=themeStyle, value=null, createTime=1770707928547, updateTime=1770707928547, creator=18614031015, updator=18614031015)])], journalTitle=机械强度, weixinUrl=null, journalUrl=https://www.jxqd.net.cn/, iacademicId=null, status=1, seqNo=null, journalTitleEn=Journal of Mechanical Strength, journalPhotoCn=9ETNXOzwmuGm49pLRqXxWw==, journalPhotoEn=sS2ogjwdwM8GMbFtuWTIkA==, 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/jxqd/CN/10.16579/j.issn.1001.9669.2025.04.015, detailUrlEn=https://castjournals.cast.org.cn/joweb/jxqd/EN/10.16579/j.issn.1001.9669.2025.04.015, pdfUrlCn=https://castjournals.cast.org.cn/joweb/jxqd/CN/PDF/10.16579/j.issn.1001.9669.2025.04.015, pdfUrlEn=https://castjournals.cast.org.cn/joweb/jxqd/EN/PDF/10.16579/j.issn.1001.9669.2025.04.015, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于深度神经网络的超声速民机机翼结构设计
收藏切换
PDF下载
牛芳淦 , 马文圆 , 杨超 , 王宇 , 尹海莲
机械强度 | ·优化·可靠性· 2025,47(4): 122-130
收起
收藏切换
机械强度 | ·优化·可靠性· 2025, 47(4): 122-130
基于深度神经网络的超声速民机机翼结构设计
全屏
牛芳淦 , 马文圆, 杨超, 王宇 , 尹海莲
作者信息
  • 南京航空航天大学 飞行器设计先进技术国防重点学科实验室,南京 210016
  • 牛芳淦,男,1998年生,安徽六安人,硕士研究生;主要研究方向为飞行器设计与优化;E-mail:

通讯作者:

王宇,女,1981年生,辽宁凌源人,副教授;主要研究方向为飞行器多学科设计与优化、新概念飞行器、变体机翼设计;E-mail:
Wing structural design of supersonic civil aircraft based on deep neural network
Fanggan NIU , Wenyuan MA, Chao YANG, Yu WANG , Hailian YIN
Affiliations
  • Advanced Design Technology of Aircraft National Defense Key Subject Laboratory, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China
出版时间: 2025-04-15 doi: 10.16579/j.issn.1001.9669.2025.04.015
文章导航
收藏切换

目前对超声速民机机翼的研究主要侧重于低声爆设计技术和超声速减阻技术,针对机翼结构设计的研究相对较少。因此,提出了一种面向超声速民机初步设计阶段机翼结构设计的多级优化方法,包括机翼结构布局参数化建模、结构尺寸优化有限元模型的自动生成、深度神经网络代理模型的搭建与训练,以及基于深度神经网络代理模型进行优化求解。分析结果表明,提出的优化策略能够对超声速民机机翼结构进行良好的快速设计,深度神经网络模型相比于传统代理模型具有更高的预测精度,提高了机翼结构初步设计的效率。

超声速民机  /  参数化  /  深度神经网络  /  代理模型  /  结构设计

At present, the research on supersonic civil aircraft wings mainly focuses on the low sonic boom design and supersonic drag reduction technologies. There are relatively few studies on the wing structural design. Therefore, a multi-level optimization method for the wing structural design in the preliminary design stage of supersonic civil aircrafts was proposed. It included the parametric modeling of the wing structural layout, the automatic generation of the finite element model for the structural size optimization, construction and training of a surrogate model for the deep neural network. And the optimization was solved based on the deep neural network. The analysis results show that the proposed optimization strategy could quickly design the wing structure of the supersonic civil aircraft. The deep neural network model has higher prediction accuracy than the traditional surrogate model. Thus, the proposed approach can improve the efficiency of the preliminary design for wing structure.

Supersonic civil aircraft  /  Parameterization  /  Deep neural network  /  Surrogate model  /  Structural design
牛芳淦, 马文圆, 杨超, 王宇, 尹海莲. 基于深度神经网络的超声速民机机翼结构设计. 机械强度, 2025 , 47 (4) : 122 -130 . DOI: 10.16579/j.issn.1001.9669.2025.04.015
Fanggan NIU, Wenyuan MA, Chao YANG, Yu WANG, Hailian YIN. Wing structural design of supersonic civil aircraft based on deep neural network[J]. Journal of Mechanical Strength, 2025 , 47 (4) : 122 -130 . DOI: 10.16579/j.issn.1001.9669.2025.04.015
世界现役民机的主流仍为高亚声速民机,其在远程航线飞行,尤其是在洲际旅行上花费时间过长,这使得其乘坐舒适度以及经济效益大大降低,难以满足未来人们对快速旅行的需求。因此,超声速民机已成为世界民机未来发展的主要方向之一。世界主要航空强国为了抢占世界民机技术的制高点,也一直在加速发展超声速民机[1]
历史上,对超声速民用飞行的研究始终是民航界乃至全人类的追求。20世纪60年代,英法启动了“协和”式[2]研制计划,同一时间,苏联开启了Tu-144[3]研制项目。当时美国的知名航空公司也启动了多个超声速民机型号项目[4]。最终只有“协和”式和Tu-144研制成功并投入运营。但该两种机型自问世以来备受成本效益、环境破坏以及声爆等因素困扰,并未大规模推广使用。进入21世纪后,各研究机构吸取前面研制的教训,新的超声速民机研究计划中许多指标如巡航马赫数、最大起飞质量比前代大幅降低。影响力较大的超声速民机布局方案有日本宇宙航空研究开发机构推出的S4[5]、洛克希德·马丁公司推出的QSTA[6]等。另外,美国国家航空航天局(NASA)研制了一款代号为X-59 QueSST的低声爆验证机,其缩比模型已经进行了低声爆风洞测试,并计划于后续展开飞行试验[7]
近年来随着高精度数值仿真技术、新型飞机设计流程、先进推进技术的飞速发展,各种多学科分析和先进布局理念开始应用于超声速民机机翼设计,对此国内外进行了很多研究。丁玉临等[8]对超声速民机的发展历史以及国内外在超声速民机设计技术上的研究现状和发展趋势进行了阐述和分析。袁吉森等[9]针对各种阻力在超声速巡航状态下产生的影响,分析了超声速层流气动外形设计与优化技术的研究历程与进展。SERAJ等[10]通过参数化进行气动外形优化的方法权衡考虑了超声速机翼在高速和低速条件下的性能和稳定性。 LI等[11]基于计算流体力学(Computational Fluid Dynamics, CFD)建立了多学科设计优化(Multidisciplinary Design Optimization, MDO)框架,用于设计低声爆等多个任务约束的机翼构型。ESPINAL等[12]采用新型超声速双向飞翼概念设计了一款满足低声爆、低波阻和高性能的全新布局形式。MELLQUIST等[13]利用直接欧拉-拉格朗日耦合方法对三维超声速机翼风洞模型进行了气动弹性计算模拟。由上述介绍可以看出,针对大型超声速民机机翼的气动设计及声爆问题的研究较多,但在结构布局优化和质量估算方面的研究相对较少。
目前,随着有限元仿真技术的快速发展,基于有限元的质量估算方法广泛应用于飞机的概念设计过程。然而,机翼结构优化过程中大量的有限元分析会消耗许多时间,不利于工程实践。为了提高优化效率,构造代理模型通常是有效的方法。常见的代理模型包括多项式响应面模型、径向基函数模型以及Kriging模型等。但是,由于多学科及多层次参数在飞机概念设计中的使用,传统代理模型的预测精度已不能满足当前的优化需求。近年来,深度学习技术凭借其优秀的学习预测能力逐渐融入各个学科领域。唐佳栋等[14]利用一维卷积神经网络代理模型,针对大展弦比机翼的结构轻量化进行了优化设计。屈经国等[15]建立了一种基于深度神经网络的预测模型,实现了任意翼型的结冰预测。DENG等[16]构建深度卷积神经网络模型来识别流场中的涡流。 SÁNCHEZ-SÁNCHEZ等[17]通过深度神经网络来驱动部分机载决策系统来获取最佳着陆控制系统设计。
相比于传统代理模型,深度神经网络可以将特征学习和预测学习有机地整合到一个模型中,十分适合应用于多参数、多层次、高复杂度的机翼结构优化问题。本文将采用深度神经网络作为代理模型,对超声速民机机翼的主要结构设计参数进行训练,完成机翼结构布局优化、尺寸优化的工作。
以某型超声速民机机翼概念方案作为研究对象,该客机巡航马赫数为1.6,初始巡航高度为50 000 ft(1 ft=0.305 m),迎角α = 3°,半翼参考面积S =147.5 m2。其几何外形如图1所示。
根据几何模型可将该机翼按展向分为4段,各段基本参数如表1所示。
根据该超声速民机机翼外形特点,可将其分为内外段进行研究。其中,第1、2段划为内段,其根弦长与后掠角较大,展向长度相对较小,并与机身连接,需要将外翼段产生的载荷传递至机身。第3、4段划分为外段,其展向长度较大,与常规后掠翼外形相似,该段产生的弯矩载荷以及剪切载荷会对内翼段造成较大的影响。
由于各段采用的翼型均为高速薄翼型,本文机翼结构形式将采用多腹板式,其结构特点是蒙皮较厚,一般为变厚度蒙皮,并且具有较多的樯和较少的肋,主要由上、下蒙皮承受弯矩。多腹板式机翼对材料有较高的利用率且刚度大,因此较多应用于高速薄翼飞机上[18]。多腹板式机翼腹板的布置形式还可分为等百分比布置以及平行腹板布置[19]
根据该机翼外形特点,其内段直接与机身相接,弦向厚度变化大,展向长度小,并且后缘为平直设计,因此此段可借鉴根弦长度较大的三角翼结构设计方法,采用垂直于弦向的平行腹板布置,该方式具有传力路径短,结构效率高的优点。而外段展向长度占比较大,与传统客机的机翼相似,但其根部弦长又略大,因此该段可采用等百分比腹板布置形式。
机翼结构的布局参数用来描述机翼的结构布置,主要包括翼肋、腹板的相对位置等参数。根据第1.1节所确定的整体布局形式,生成机翼结构简图,如图2所示。
机翼主要布局参数如表2所示。
图2所示,通过前后缘固定腹板位置参数即内外段在其翼段根部、Kink(第1、2段连接处和第3、4段连接处)、尖部的弦向位置百分比可以确定前、后缘固定腹板的位置,需注意的是1#和2#分界腹板也随之确定下来。1#和2#分界腹板将内段中间区域划分为前翼盒、1#翼盒、2#翼盒,nWeb1nWeb2nWeb3分别为内段中间各区域的腹板个数;内段各区域腹板位置参数则为各个腹板距离前一腹板(以前缘为例)的弦向长度。翼肋数确定了内外段所含的翼肋个数,翼肋位置参数主要为相邻两翼肋的间距(内段第2段机翼的翼肋位置参数为1#翼盒的腹板编号数,例如翼肋位置参数为3,代表该翼肋与1#翼盒的第3根腹板相接)。外段中间区域根据第3、4段Kink位置划分为外段1#、2#翼盒,外段腹板数指两区域的腹板个数,而外段腹板位置参数则为外段每个翼盒与前一段翼盒相接的腹板编号数(如外段1#翼盒腹板位置参数为内段2#翼盒相接的腹板编号数)。各区域腹板数、翼肋数未将各翼段根部、尖部、Kink处翼肋及特殊腹板计算入内。
根据对各区域腹板、翼肋个数及占位进行设置,可得到不同的机翼结构布局参数化几何模型,如图3所示。其中5-3-4表示,nWeb1nWeb2nWeb3的数量分别为5、3、4,下同。
结构布局参数对结构设计有着至关重要的作用,结构尺寸参数同样是机翼结构设计的主要参数。尺寸参数是指结构件的尺寸大小(如蒙皮厚度、腹板厚度、梁缘条截面积等)。在对有限元模型进行参数化的过程中,这类参数为主要变量。
为了降低结构尺寸参数的总数量便于后续优化,通常会将机翼分解为不同区域,相同分段相同设计区域内,同类型结构件的尺寸参数或优化参数设置为相同值。
针对上述的多腹板式机翼布局,主要根据固定腹板对机翼进行划分,其次对区域较大的部分根据腹板个数进行再次划分。如图4所示,可根据前后缘固定腹板及特殊腹板对其弦向先划分为几个区域,各区域编号为mij (i = 1~4,j = 1~8),i为机翼段数,j为各段弦向区域,例如,m2,3代表第2段机翼中第3个弦向区域,其中在内段机翼划分中,前翼盒、1#翼盒、2#翼盒跨度较大,根据其中腹板个数再划分出2个子区域(一般将区域内腹板进行平分),外段机翼1#翼盒、2#翼盒同样根据腹板数再划分为2个子区域。同时各段机翼可根据翼肋个数在展向划分为几个区域,各区域编号为npq( p = 1~4,q = 0~3),p为机翼段数,q为各段展向区域。其中内段的两段机翼展向跨度较小,只划分为单独的1个区域,外段的两段机翼根据翼肋数目增加划分为3个子区域。根据上述划分,每个区域编号可通过坐标(mijnpq )来表示。
为了快速生成机翼结构有限元模型,便于后续优化,本文借助HYPERMESH二次开发技术,编写工具命令语言(Tool Command Language, TCL)脚本程序建立结构有限元模型并进行尺寸优化设计与分析,其流程如图5所示。
生成结构尺寸优化模型的流程如下:
1)导入结构几何模型并进行前处理。在HYPERMESH中导入CATIA结构,建模生成模型文件,然后使用其中的Geom模块对所有曲面进行拓扑关系自动判断并切割,便于后续优化分组。
2)有限元网格生成。确定网格尺寸和网格形式,生成面网格和线网格。
3)调整单元法向。对蒙皮、腹板、翼肋等机翼结构件单元的法向进行调整,以满足气动力加载以及载荷传递。
4)定义材料属性。机翼蒙皮主要由复合材料构成,其他结构由金属材料构成。对于复合材料,采用等效刚度法进行定义,通过脚本文件计算出刚度矩阵后分别定义等效板单元所需的薄膜材料、弯曲材料以及耦合材料,其他金属材料则根据其性能数据进行定义。
5)赋予单元属性。蒙皮单元选用等效板单元;对于各分区腹板及翼肋腹板选用壳单元;对于腹板缘条、肋缘条等线元素采用杆单元。
6)载荷加载及边界条件定义。载荷主要由气动载荷、机翼自身质量和燃油质量3部分组成。其中气动载荷使用气动分析软件CART3D计算出压强场,在HYPERMESH中通过映射的方法将压强场加载到结构模型上;机翼自身质量载荷通过质量卡片设置;燃油质量则以分布力的形式加载到指定部件上。由于有限元分析模型为机翼半模,边界条件定义为与机身相接的内段腹板固支。
7)尺寸优化参数定义。定义各分区内设计变量的初始值、上下限;定义各约束变量所需的响应值;定义各约束条件;定义优化目标;定义优化算法及最大迭代步数。
8)分析计算。选择优化分析,并使用HYPERMESH自带的OPTISTRUCT求解器进行优化计算。
采用深度神经网络代理模型的机翼结构优化问题可分为系统级和子系统级二级优化。其中,结构布局优化为系统级优化,其设计变量为各分区的腹板数和翼肋数等;结构尺寸优化为子系统级优化,其优化参数包括各分区内蒙皮和腹板的厚度t,缘条截面积A等。优化目标为机翼半模结构质量最小,约束条件包括静强度、刚度、翼尖挠度等。系统优化设计策略如图6所示,其数学模型表述为
式中,F (x)为优化目标函数,即机翼的结构质量;X1为系统级设计变量,X1 = (N1N2,…);X2为子系统级设计变量,X2 = (tA);分别为各设计变量的上下限;[ σ ]、[ ε ]分别为机翼各结构件所用材料应力和应变的许用值;[ δ ]为结构允许的最大变形量。
1)目标函数。使结构质量最小化。
2)设计变量(布局优化设计变量X1)。根据布局参数设计,选取6个对机翼结构布局起决定作用的参数,分别为内段前翼盒腹板数,内段1#、2#翼盒腹板数,第1段机翼翼肋数,外段1#、2#翼盒翼肋数(上述腹板翼肋数目皆不含特殊腹板及端肋)。参考同类型机翼结构布局的设计经验和飞机结构设计手册来确定该变量。根据统计,大型客机翼肋间距为600~800 mm,桁条间距为100~200 mm[20],对于多腹板式机翼,机翼蒙皮承受了大部分载荷,相同等级的大型客机,蒙皮厚度、翼肋间距、腹板间距可适当增大。因此,本文机翼腹板间距变化范围取600~1 000 mm,肋间距取600~900 mm,最大桁条间距取100 mm。从而确定各设计变量的变化范围和初始值如表3所示。
1)根据结构尺寸优化流程,首先定义机翼各结构件所用的材料。机翼蒙皮选择T800碳纤维复合材料。层合板采用对称铺层方式,各铺层角度占比为0°铺层占50%,±45°铺层占40%,90°铺层占10%。同时为了简化蒙皮-长桁组成的加筋壁板的建模,本文采用等效刚度法对加筋结构建立有限元模型;其余结构选择铝合金7075-T6。各材料的属性分别如表4表5所示。E11为沿纤维轴向模量;E22为沿纤维横向模量;G12为剪切模量;ν12为泊松比;ρ为材料密度。其次,飞行过载系数设置为2.5 gg=9.8 m/s2),安全系数设置为1. 5。
2)目标函数。使机翼结构质量最小。
3)设计变量(尺寸优化设计变量X2)。根据同类型飞机概念设计方案对结构尺寸设计变量进行定义。为方便说明,对上述分区中各段机翼的设计变量进行整合,各设计变量的取值范围和初始值如表6所示。
4)约束条件。蒙皮最大许用拉应变[ ε+] = 4.5 ×10-3;最大许用压应变[ ε-] =-3.3 × 10-3,最大许用切应变[ γ+] = 6 × 10-3;其余金属材料许用应力为[ σ ] =450 MPa;屈曲因子≥1;翼尖挠度≤10%,半展长约为1 494 mm。
5)优化算法采用HYPERMESH中自带的序列二次规划算法。
经过上述的尺寸优化流程,每个设计样本点经过10~20次迭代达到收敛。任意抽取系统级优化中的2个样本点(表7),得到机翼结构尺寸单目标优化迭代过程如图7所示。
对机翼内部结构进行布局和尺寸二级优化,两级总的设计变量众多,如果对优化空间中的每个设计点都生成几何模型和有限元模型并进行尺寸优化会占用大量时间,很不利于工程实际应用。为了提高优化效率,在结构布局优化设计层级抽取样本点执行子系统级尺寸优化,进而构造代理模型,最后基于代理模型完成结构布局优化求解。此优化策略可以在确保精度的同时大幅减少总的计算量。其中代理模型选择深度神经网络代理模型。该模型具有更复杂更深层次的模型结构,其系统性、准确性相较于传统代理模型更高。
由于结构布局设计参数的取值皆为整数且设计变量较多,采用自定义抽样方法,nWeb1nWeb2nWeb3对机翼结构布局影响较大且取值多,所以从该变量取值范围两端和中间共抽取3个数,nRib1nRib2nRib3取值相对较少,从该变量取值范围两端抽取2个数,各变量抽取值如表8所示。
对各设计变量抽取的样本值进行笛卡儿积运算生成结构布局设计参数的样本点数据,然后通过尺寸优化获取每个样本点对应的质量特性。该抽样方法根据本文中的超声速机翼构型而定,能够较好地反映腹板数以及翼肋数对该机翼结构布局的影响,提高代理模型的精度。将抽取的布局设计参数和对应的质量指标作为深度神经网络的数据集。经运算,该数据集有效样本点共140组,其中随机抽取75%样本点作为训练集,其余样本点作为测试集。
根据对布局设计参数特征和质量指标的分析,确定深度神经网络的结构。一般深度神经网络主要由输入层、隐藏层以及输出层构成。本文所使用的深度神经网络如图8所示,输入层为结构布局设计参数,输出层为半翼结构质量参数。
能否合理选择网络隐藏层层数以及各隐藏层神经元的个数,会对模型的训练时间、学习能力产生很大的影响,这些定义模型结构或训练过程的可调参数被称为超参数。理论上来说,层数越深,神经元数量越多,模型的拟合能力越强,但实际上过多的层数和神经元数量可能会带来过拟合的问题,从而无法对训练集外的数据达到很好的预测,而过少的神经元则又会导致欠拟合。因此,本文根据已有的预训练模型和开源调参工具智能神经网络(Neural Network Intelligence,NNI)[21]对该模型部分超参数进行定义。其中设置隐藏层共计6层。为了使模型更快达到训练精度,各层神经元数目随着层数的加深而减少。并且为了提高拟合效率,需要对学习率进行调整,初始学习率设为0.001,衰减率设置为0.000 5;迭代批次数设为5 000次,每批次训练样本点个数为105个。
深度神经网络代理模型采用深度学习平台TensorFlow(2.5.0版本)[22]进行搭建和训练,其隐藏层采用ReLU激活函数[23],式(2)为其数学表达式,同时对单神经元输出层使用线性激活函数。训练模型的损失函数采用均方误差(Mean Squared Error, MSE)函数,其表达式如式(3)所示。优化器采用自适应矩估计优化(Adaptive Moment Estimation, AME)[24],其主要用来训练数据和损失函数来更新网络。
式中,JMSE为代价值;N为样本总数;x为样本数据;y为真实值;aL为预测值。
在对深度神经网络训练前,首先,需要对数据进行标准化处理,将数据的所有特征都映射到同一尺度上,避免数据的某些特征形成主导作用,影响预测精度。同时,划分随机种子,将样本数据打乱,确保训练模型不会受到样本分布规律影响。
在对深度神经网络训练期间,需要监控隐藏层内某些拟合参数如权重等数值的变化[25]。传统的深度神经网络在训练时,随着内部参数的不断更新,中间各个隐藏层输入的数据分布往往会有较大差异,导致神经网络较高隐藏层需要不断地适应低隐藏层的参数更新,进而使得训练变得异常困难,甚至会造成梯度爆炸/消失问题。对每层隐藏层的输入数据进行批标准化(Batch Normalization, BN)处理[26]可以很好地解决这个问题,该技术主要是在每层的激活函数之前简单地对输入数据进行中心化和归一化处理,从而让模型学习到每层输入值的最佳尺度与均值。同时为了避免过拟合,在训练期间使用丢弃法(Dropout Method,DM),随机将某个时期的一部分神经元丢弃,这可以迫使其余神经元具备更好的通用性。最后,在训练时设置误差监视点,保存训练期间的最佳模型作为最终预测模型。
训练完毕的深度神经网络需要验证所得到的模型是否具有泛化性并检验模型的精度,通过对测试集的输入参数进行预测,并与测试集样本点的真实值比较,计算预测结果的平均相对误差(Mean Relative Error, MRE)EMRE来验证深度神经网络模型预测精度,EMRE的计算式如式(4)所示,EMRE的值越小,表明模型的预测能力越强、性能越好。
式中,k为第k个测试集样本点;yk为原优化流程计算出的质量数据;为深度神经网络预测值。
为了进一步检验深度神经网络的学习能力,对深度神经网络代理模型与传统代理模型的预测精度进行了对比,其结果如表9所示。其中传统代理模型选用了多项式响应面模型和Kriging模型,其模型训练流程基于密歇根大学开发的开源工具箱[27]进行编写。可以看出,深度神经网络模型的平均相对误差都小于传统代理模型,在样本预测精度上有了明显的提升。
1)系统级优化方法。系统级优化通过基于深度神经网络代理模型的优化方法进行求解,优化算法选择遗传算法,其具有良好的全局搜索能力,并通过开源工具包Scikit-Opt[28]对其进行编写,具体参数设置为初始种群数量50,代数160,交叉概率和变异概率分别为0.9、0.001。
2)优化结果与分析。基于代理模型优化后取得满足约束的结构质量最小值为6.12 t,最优点各个设计区域腹板数及翼肋数如表10所示。为了校核最优点的预测精度并对照有限元模型结果进行分析,使用最优点布局设计生成几何模型并通过HYPERMESH软件对该模型进行基于有限元分析的尺寸优化。结果显示,通过有限元软件计算真实响应得到的质量结果m为6.14 t,与深度神经网络代理模型得到的结果的相对误差为0.265%,满足工程精度要求。
结构优化最优点的机翼应力、应变和位移云图分别如图9~图12所示。优化结果显示,机翼根部和内外段转折处应力较大,虽然骨架结构的最大应力为423 MPa,仍有一定余量,但机翼的翼尖位移已达到约束上限,此时取得结构质量最小值,并且整体满足约束要求。由图9图11可知,内段前翼盒基本未承受较大载荷,腹板数布置较少,而内段1#翼盒和2#翼盒承受了大部分来自外段的弯矩载荷及剪切载荷,故该两部分盒段的腹板数布置较多,蒙皮厚度的优化结果也较大。综上所述,该优化结果对设计变量利用率较高,且满足结构强度,对后续详细设计具有参考意义。
针对超声速民机机翼结构设计提出了一种有效的多级优化方法。研究结论如下:
1)采用参数化建模的方法实现了超声速客机机翼结构布局/尺寸的快速建模与优化,提高了分析优化效率。
2)根据优化问题定义,构建了深度神经网络代理模型,大幅减少了总计算量。并通过对比其他传统代理模型,验证了该模型的预测精度,证明该模型对本文优化问题更具备适用性。
3)针对该型超声速客机机翼外形特点,设计了包含两种多腹板式机翼布置的结构方案,并定义了布局和尺寸二级优化方法,优化结果具有参考价值。
  • 国家自然科学基金项目(12032011)
参考文献 引证文献
排序方式:
[1]
CHUDOBA BCOLEMAN GROBERTS K,et al. What price supersonic speed?A design anatomy of supersonic transportation-part 1[C]//45th AIAA Aerospace Sciences Meeting. Reston:AIAA,200715:10355-10378.
[2]
CANDEL S. Concorde and the future of supersonic transport[J].Journal of Propulsion and Power200420(1):59-68.
[3]
PEIREN G. Tu-144 supersonic transport[J]. Civil Aircraft Design and Research2015(3):99-102.
[4]
CONWAY E M. High-speed dreams:NASA and the technopolitics of supersonic transportation,1945-1999[M]. Baltimore:Johns Hopkins University Press,2005:866-867.
[5]
LIEBHARDT BLÜTJENS KUENO A,et al. JAXA’s S4 supersonic low-boom airliner-a collaborative study on aircraft design,sonic boom simulation,and market prospects[C]//AIAA Aviation 2020 Forum. Reston:AIAA,2020:241349.
[6]
MICHAEL B. Conceptual design of a quiet supersonic technology airliner[C]//AIAA Aviation 2019 Forum. Reston:AIAA,2019:11-18.
[7]
MAGEE T ESERRANO LMENDOZA R,et al. X-59 CFD and wind tunnel data comparisons[C]//AIAA Aviation 2023 Forum.Reston:AIAA,2023:313279.
[8]
丁玉临,韩忠华,乔建领,等. 超声速民机总体气动布局设计关键技术研究进展[J]. 航空学报202344(2):20-46.
DING YulinHAN ZhonghuaQIAO Jianling,et al. Research progress in key technologies for conceptual-aerodynamic configuration design of supersonic transport aircraft[J]. Acta Aeronautica et Astronautica Sinica202344(2):20-46.(In Chinese)
[9]
袁吉森,孙爵,李玲玉,等. 超声速飞机层流布局设计与评估技术进展[J]. 航空学报202243(11):63-98.
YUAN JishenSUN JueLI Lingyu,et al. Progress of supersonic aircraft laminar flow layout design and evalution technologies[J].Acta Aeronautica et Astronautica Sinica202243(11):63-98.(In Chinese)
[10]
SERAJ SMARTINS J R R A. Aerodynamic shape optimization of a supersonic transport considering low-speed stability[C]//AIAA Sciece and Technology Forum and Exposition,AIAA Sci Tech Forum 2022. Reston:AIAA,2022:270339.
[11]
LI WGEISELHART K. Integration of low-fidelity MDO and CFD-Based redesign of low-boom supersonic transports[J]. AIAA Journal202159(10):3923-3936.
[12]
ESPINAL DIM HLEE B,et al. Supersonic bi-directional flying wing,Part II:conceptual design of a high speed civil transport[C]//48th AIAA Aerospace Sciences Meeting Including the New Horizons Forum and Aerospace Exposition. Reston:AIAA,2010:82585.
[13]
MELLQUIST E CBENDIKSEN O O. Analysis of the transonic flutter of supersonic transport wings[C]//56th AIAA/ASCE/AHS/ASC Structures,Structural Dynamics,and Materials Conference 2015. Reston:AIAA,2015:112819.
[14]
唐佳栋,娄斌,叶尚军,等. 基于卷积神经网络和松鼠优化算法的机翼结构混合优化设计[J]. 力学季刊202243(2):217-226.
TANG JiadongLOU BinYE Shangjun,et al. Hybrid optimization design of wing structure based on convolution neural network and squirrel search algorithm[J]. Chinese Quarterly of Mechanics202243(2):217-226.(In Chinese)
[15]
屈经国,彭博,易贤,等. 基于深度神经网络的任意翼型结冰预测方法[J]. 空气动力学学报202341(7):48-55.
QU JingguoPENG BoYI Xian,et al. Icing prediction method for arbitrary airfoil using deep neural networks[J]. Acta Aerodynamica Sinica202341(7):48-55.(In Chinese)
[16]
DENG LWANG Y QLIU Y,et al. A CNN-based vortex identification method[J]. Journal of Visualization201922(1):65-78.
[17]
SÁNCHEZ-SÁNCHEZ CIZZO D. Real-time optimal control via deep neural networks:study on landing problems[J]. Journal of Guidance,Control,and Dynamics201841(5):1122-1135.
[18]
姚卫星,顾怡. 飞机结构设计[M]. 北京:国防工业出版社,2016:56-57.
YAO WeixingGU Yi. Aircraft structural design[M]. Beijing:National Defense Industry Press,2016:56-57.(In Chinese)
[19]
刘磊. 空天飞机重量估算方法研究[D]. 南京:南京航空航天大学,2016:43-44.
LIU Lei. Research on weight estimation method of aerospace aircraft[D]. Nanjing:Nanjing University of Aeronautics and Astronautics,2016:43-44.(In Chinese)
[20]
王宝忠. 飞机设计手册:第十册:结构设计[M]. 北京:航空工业出版社,2000:410-420.
WANG Baozhong. Aircraft design manual:Volume 10:structural design[M]. Beijing:Aviation Industry Publishing House,2000:410-420.(In Chinese)
[21]
Microsoft. Neural network intelligence[EB/OL].(2019-09-01).https://www.microsoft.com/en-us/research/project/neural-networ-k-intelligence/.
[22]
Google. TensorFlow:an end-to-end source machine learning platform[EB/OL]. (2019-08-10). https://opensource.google/proj-ects/tensorflow.
[23]
NAIR VHINTON G E. Rectified linear units improve restricted Boltzmann machines [C]//27th International Conference on Machine Learning ICML 2010,201081654(807-814).
[24]
NEWEY W K. Adaptive estimation of regression models via moment restrictions[J]. Journal of Econometrics198838(3):301-339.
[25]
范周伟,余雄庆,王朝,等. 基于深度神经网络的客机总体设计参数敏感性分析[J]. 航空学报202142(4):524353.
FAN ZhouweiYU XiongqingWANG Chao,et al. Sensitivity analysis of key design parameters of commercial aircraft using deep neural network[J]. Acta Aeronautica et Astronautica Sinica202142(4):524353.(In Chinese)
[26]
LOFFE SSZEGEDY C. Batch normalization:accelerating deep network training by reducing internal covariate shift[C]//32nd International Conference on Machine Learning,ICML 2015. 20151:119782(448-456).
[27]
BOUHLEL M AHWANG J TBARTOLI N,et al. A Python surrogate modeling framework with derivatives[J]. Advances in Engineering Software2019135:102662.
[28]
GUOFEI9987. Scikit-Opt[EB/OL].(2023-09-14). https://github.com/guofei9987/scikit-opt.
2025年第47卷第4期
PDF下载
84
39
引用本文
BibTeX
文章信息
doi: 10.16579/j.issn.1001.9669.2025.04.015
  • 接收时间:2023-09-26
  • 首发时间:2026-03-20
  • 出版时间:2025-04-15
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2023-09-26
  • 修回日期:2023-11-01
基金
National Natural Science Foundation of China(12032011)
国家自然科学基金项目(12032011)
作者信息
    南京航空航天大学 飞行器设计先进技术国防重点学科实验室,南京 210016

通讯作者:

王宇,女,1981年生,辽宁凌源人,副教授;主要研究方向为飞行器多学科设计与优化、新概念飞行器、变体机翼设计;E-mail:
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/jxqd/CN/10.16579/j.issn.1001.9669.2025.04.015
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