Article(id=1149789602862559683, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1149768563956826506, articleNumber=null, orderNo=null, doi=10.12404/j.issn.1671-1815.2405114, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1720368000000, receivedDateStr=2024-07-08, revisedDate=1741363200000, revisedDateStr=2025-03-08, acceptedDate=null, acceptedDateStr=null, onlineDate=1752060803380, onlineDateStr=2025-07-09, pubDate=1749312000000, pubDateStr=2025-06-08, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1752060803380, onlineIssueDateStr=2025-07-09, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1752060803380, creator=13701087609, updateTime=1752060803380, updator=13701087609, issue=Issue{id=1149768563956826506, tenantId=1146029695717560320, journalId=1146123166801305609, year='2025', volume='25', issue='16', pageStart='6587', pageEnd='7021', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=0, createTime=1752055787314, creator=13701087609, updateTime=1768456850262, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1218559607937618069, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1149768563956826506, language=EN, specialIssueTitle=, coverIllustrator=, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1218559607937618070, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1149768563956826506, language=CN, specialIssueTitle=, coverIllustrator=, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=6961, endPage=6969, ext={EN=ArticleExt(id=1149789603126800836, articleId=1149789602862559683, tenantId=1146029695717560320, journalId=1146123166801305609, language=EN, title=Physical Field Inversion Method of Smart Skin Based on BP-IGWO and Distributed Sensors, columnId=1156262731079607234, journalTitle=Science Technology and Engineering, columnName=Papers·Aeronautics and Astronautics, runingTitle=null, highlight=null, articleAbstract=

The smart skin of an aircraft is realized by integrating distributed sensors, actuators, and controllers into the composite skin, thereby enabling it to monitor its own state and detect damages. The physical field inversion algorithm plays a key role in the signal processing of the smart skin. However, due to factors such as the low sensor density, traditional inversion algorithms exhibit limited accuracy. In order to enhance the monitoring precision of the smart skin, a back propagation(BP) neural network-improved grey wolf optimizer(IGWO) inversion algorithm, which combined a BP neural network with an IGWO-optimized Kriging model, was proposed. A prototype of the smart skin was subsequently fabricated, and wind tunnel tests were conducted to validate the proposed algorithm. The results demonstrate that the BP-IGWO inversion algorithm achieves higher accuracy and superior detail representation compared to traditional inversion algorithms, and can better monitor the state of smart skin.

, correspAuthors=Yan-zhi LONG, 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=Yan-zhi LONG, Bo-yu ZHENG, Xin ZHAO, Lu-jun ZHENG, Ren-wen CHEN), CN=ArticleExt(id=1149789620067594928, articleId=1149789602862559683, tenantId=1146029695717560320, journalId=1146123166801305609, language=CN, title=基于BP-IGWO和分布式传感器的智能蒙皮物理场反演方法, columnId=1156262731373208516, journalTitle=科学技术与工程, columnName=论文·航空、航天, runingTitle=null, highlight=null, articleAbstract=

飞行器智能蒙皮通过在飞行器复合材料蒙皮上集成分布式传感器、驱动器和控制器,使其具有监测其本身状态和损伤的能力,其中物理场反演算法是智能蒙皮信号处理中的重要一环。但是由于传感器布置密度小等原因,传统的反演算法精度不高。为了提高智能蒙皮的监测精度,提出一种将反向传播(back propagation,BP)神经网络与改进的灰狼优化算法(improved grey wolf optimizer,IGWO)优化克里金模型融合的BP-IGWO反演算法。制作智能蒙皮原理样件,通过风洞试验对该算法进行验证。结果表明:BP-IGWO反演算法较之传统反演算法具有更高的精度和细节呈现能力,能更好地监测智能蒙皮的状态。

, correspAuthors=龙彦志, authorNote=null, correspAuthorsNote=null, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=bBWx7bcfyvpj7lFSHIvO/Q==, magXml=kAsVSfz/oNiBR+FEclqKfA==, pdfUrl=null, pdf=ARXTWy5TJUC0bIOJFnR8Nw==, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=M2higIVn0yASKHHj+U+5Ng==, mapNumber=null, authorCompany=null, fund=null, authors=

龙彦志(1987—),男,汉族,湖南益阳人,博士研究生,研究方向:大气数据探测技术。E-mail:

, authorsList=龙彦志, 郑博宇, 赵鑫, 郑禄军, 陈仁文)}, authors=[Author(id=1177977294879605453, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=longyz161@qq.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1177977294988657360, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, authorId=1177977294879605453, language=EN, stringName=Yan-zhi LONG, firstName=Yan-zhi, middleName=null, lastName=LONG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1 Aerospace College, Nanjing University of Aeronautics and Astronautics, Nanjing 210000, China
2 Chengdu CAIC Electronics Co. , Ltd. , Chengdu 610091, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1177977295055766225, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, authorId=1177977294879605453, language=CN, stringName=龙彦志, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1 南京航空航天大学航空学院, 南京 210000
2 成都凯天电子股份有限公司, 成都 610091, bio={"content":"

龙彦志(1987—),男,汉族,湖南益阳人,博士研究生,研究方向:大气数据探测技术。E-mail:

"}, bioImg=null, bioContent=

龙彦志(1987—),男,汉族,湖南益阳人,博士研究生,研究方向:大气数据探测技术。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1177977294678278852, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, xref=1, ext=[AuthorCompanyExt(id=1177977294686667461, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, companyId=1177977294678278852, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 Aerospace College, Nanjing University of Aeronautics and Astronautics, Nanjing 210000, China), AuthorCompanyExt(id=1177977294695056070, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, companyId=1177977294678278852, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 南京航空航天大学航空学院, 南京 210000)]), AuthorCompany(id=1177977294774747848, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, xref=2, ext=[AuthorCompanyExt(id=1177977294783136458, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, companyId=1177977294774747848, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 Chengdu CAIC Electronics Co. , Ltd. , Chengdu 610091, China), AuthorCompanyExt(id=1177977294791525066, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, companyId=1177977294774747848, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 成都凯天电子股份有限公司, 成都 610091)])]), Author(id=1177977295148040915, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, 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=1177977295236121301, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, authorId=1177977295148040915, language=EN, stringName=Bo-yu ZHENG, firstName=Bo-yu, middleName=null, lastName=ZHENG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 Aerospace College, Nanjing University of Aeronautics and Astronautics, Nanjing 210000, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1177977295294841558, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, authorId=1177977295148040915, language=CN, stringName=郑博宇, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 南京航空航天大学航空学院, 南京 210000, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1177977294678278852, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, xref=1, ext=[AuthorCompanyExt(id=1177977294686667461, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, companyId=1177977294678278852, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 Aerospace College, Nanjing University of Aeronautics and Astronautics, Nanjing 210000, China), AuthorCompanyExt(id=1177977294695056070, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, companyId=1177977294678278852, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 南京航空航天大学航空学院, 南京 210000)])]), Author(id=1177977295399699160, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, 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=1177977295508751066, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, authorId=1177977295399699160, language=EN, stringName=Xin ZHAO, firstName=Xin, middleName=null, lastName=ZHAO, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2 Chengdu CAIC Electronics Co. , Ltd. , Chengdu 610091, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1177977295580054235, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, authorId=1177977295399699160, language=CN, stringName=赵鑫, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2 成都凯天电子股份有限公司, 成都 610091, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1177977294774747848, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, xref=2, ext=[AuthorCompanyExt(id=1177977294783136458, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, companyId=1177977294774747848, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 Chengdu CAIC Electronics Co. , Ltd. , Chengdu 610091, China), AuthorCompanyExt(id=1177977294791525066, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, companyId=1177977294774747848, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 成都凯天电子股份有限公司, 成都 610091)])]), Author(id=1177977295647163101, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, 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=1177977295726854879, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, authorId=1177977295647163101, language=EN, stringName=Lu-jun ZHENG, firstName=Lu-jun, middleName=null, lastName=ZHENG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 Aerospace College, Nanjing University of Aeronautics and Astronautics, Nanjing 210000, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1177977295789769440, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, authorId=1177977295647163101, language=CN, stringName=郑禄军, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 南京航空航天大学航空学院, 南京 210000, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1177977294678278852, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, xref=1, ext=[AuthorCompanyExt(id=1177977294686667461, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, companyId=1177977294678278852, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 Aerospace College, Nanjing University of Aeronautics and Astronautics, Nanjing 210000, China), AuthorCompanyExt(id=1177977294695056070, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, companyId=1177977294678278852, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 南京航空航天大学航空学院, 南京 210000)])]), Author(id=1177977295856878306, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, 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=1177977295923987172, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, authorId=1177977295856878306, language=EN, stringName=Ren-wen CHEN, firstName=Ren-wen, middleName=null, lastName=CHEN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 Aerospace College, Nanjing University of Aeronautics and Astronautics, Nanjing 210000, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1177977296003678949, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, authorId=1177977295856878306, language=CN, stringName=陈仁文, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 南京航空航天大学航空学院, 南京 210000, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1177977294678278852, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, xref=1, ext=[AuthorCompanyExt(id=1177977294686667461, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, companyId=1177977294678278852, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 Aerospace College, Nanjing University of Aeronautics and Astronautics, Nanjing 210000, China), AuthorCompanyExt(id=1177977294695056070, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, companyId=1177977294678278852, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 南京航空航天大学航空学院, 南京 210000)])])], keywords=[Keyword(id=1177977296121119462, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, language=EN, orderNo=1, keyword=smart skin), Keyword(id=1177977296179839719, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, language=EN, orderNo=2, keyword=physical field inversion technology), Keyword(id=1177977296251142888, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, language=EN, orderNo=3, keyword=neural network), Keyword(id=1177977296309863145, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, language=EN, orderNo=4, keyword=back propagation-improved grey wolf optimizer(BP-IGWO)), Keyword(id=1177977296385360618, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, language=EN, orderNo=5, keyword=Kriging), Keyword(id=1177977296452469483, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, language=CN, orderNo=1, keyword=智能蒙皮), Keyword(id=1177977296515384044, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, language=CN, orderNo=2, keyword=物理场反演), Keyword(id=1177977296578298605, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, language=CN, orderNo=3, keyword=人工神经网络), Keyword(id=1177977296637018862, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, language=CN, orderNo=4, keyword=反向传播神经网络-改进的灰狼优化器(BP-IGWO)), Keyword(id=1177977296708322031, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, language=CN, orderNo=5, keyword=克里金法)], refs=[Reference(id=1177977298717393673, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, doi=null, pmid=null, pmcid=null, year=2022, volume=54, issue=6, pageStart=1732, pageEnd=1740, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=周帅, 肖周芳, 付琳, journalName=力学学报, refType=null, unstructuredReference=周帅, 肖周芳, 付琳, 等. 一类面向高阶精度自适应流动计算的流场插值方法[J]. 力学学报, 2022, 54(6): 1732-1740., articleTitle=一类面向高阶精度自适应流动计算的流场插值方法, refAbstract=null), Reference(id=1177977298822251274, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, doi=null, pmid=null, pmcid=null, year=2022, volume=54, issue=6, pageStart=1732, pageEnd=1740, url=null, language=null, rfNumber=[1], rfOrder=1, authorNames=Zhou Shuai, Xiao Zhoufang, Fu Lin, journalName=Chinese Journal of Theoretical and Applied Mechanics, refType=null, unstructuredReference=Zhou Shuai, Xiao Zhoufang, Fu Lin, et al. Solution interpolation for high-order accurate adaptive flow simulation[J]. Chinese Journal of Theoretical and Applied Mechanics, 2022, 54(6): 1732-1740., articleTitle=Solution interpolation for high-order accurate adaptive flow simulation, refAbstract=null), Reference(id=1177977298885165835, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, doi=null, pmid=null, pmcid=null, year=2022, volume=56, issue=8, pageStart=1690, pageEnd=1699, url=null, language=null, rfNumber=[2], rfOrder=2, authorNames=王振宇, 黄伟奇, 孙健, journalName=原子能科学技术, refType=null, unstructuredReference=王振宇, 黄伟奇, 孙健, 等. 泊松克里金算法在核辐射场重构中的应用研究[J]. 原子能科学技术, 2022, 56(8): 1690-1699., articleTitle=泊松克里金算法在核辐射场重构中的应用研究, refAbstract=null), Reference(id=1177977298964857612, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, doi=null, pmid=null, pmcid=null, year=2022, volume=56, issue=8, pageStart=1690, pageEnd=1699, url=null, language=null, rfNumber=[2], rfOrder=3, authorNames=Wang Zhenyu, Huang Weiqi, Sun Jian, journalName=Atomic Energy Science and Technology, refType=null, unstructuredReference=Wang Zhenyu, Huang Weiqi, Sun Jian, et al. Reconstruction of nuclear radiation dose field using alternative poisson-Kriging algorithm[J]. Atomic Energy Science and Technology, 2022, 56(8): 1690-1699., articleTitle=Reconstruction of nuclear radiation dose field using alternative poisson-Kriging algorithm, refAbstract=null), Reference(id=1177977299031966477, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, doi=null, pmid=null, pmcid=null, year=2022, volume=36, issue=4, pageStart=40, pageEnd=47, url=null, language=null, rfNumber=[3], rfOrder=4, authorNames=许富景, 杜少成, 荆蕊蕊, journalName=电子测量与仪器学报, refType=null, unstructuredReference=许富景, 杜少成, 荆蕊蕊. 基于压缩感知与分段 Hermite 插值的二维温度场重构方法[J]. 电子测量与仪器学报, 2022, 36(4): 40-47., articleTitle=基于压缩感知与分段 Hermite 插值的二维温度场重构方法, refAbstract=null), Reference(id=1177977299094881038, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, doi=null, pmid=null, pmcid=null, year=2022, volume=36, issue=4, pageStart=40, pageEnd=47, url=null, language=null, rfNumber=[3], rfOrder=5, authorNames=Xu Fujing, Du Shaocheng, Jing Ruirui, journalName=Journal of Electronic Measurement and Instrumentation, refType=null, unstructuredReference=Xu Fujing, Du Shaocheng, Jing Ruirui, et al. Two-dimensional temperature field reconstruction method based on compressed sensing and piecewise Hermite interpolation[J]. Journal of Electronic Measurement and Instrumentation, 2022, 36(4): 40-47., articleTitle=Two-dimensional temperature field reconstruction method based on compressed sensing and piecewise Hermite interpolation, refAbstract=null), Reference(id=1177977299153601295, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, doi=null, pmid=null, pmcid=null, year=2021, volume=50, issue=4, pageStart=502, pageEnd=507, url=null, language=null, rfNumber=[4], rfOrder=6, authorNames=张天一, 李文昌, 肖金玉, journalName=电子科技大学学报, refType=null, unstructuredReference=张天一, 李文昌, 肖金玉, 等. 基于稀疏字典学习的 VLSI 温度场重构技术[J]. 电子科技大学学报, 2021, 50(4): 502-507., articleTitle=基于稀疏字典学习的 VLSI 温度场重构技术, refAbstract=null), Reference(id=1177977299220710160, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, doi=null, pmid=null, pmcid=null, year=2021, volume=50, issue=4, pageStart=502, pageEnd=507, url=null, language=null, rfNumber=[4], rfOrder=7, authorNames=Zhang Tianyi, Li Wenchang, Xiao Jinyu, journalName=Journal of University of Electronic Science and Technology of China, refType=null, unstructuredReference=Zhang Tianyi, Li Wenchang, Xiao Jinyu, et al. Thermal field reconstruction for VLSI based on sparse dictionary learning[J]. Journal of University of Electronic Science and Technology of China, 2021, 50(4): 502-507., articleTitle=Thermal field reconstruction for VLSI based on sparse dictionary learning, refAbstract=null), Reference(id=1177977299279430417, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, doi=null, pmid=null, pmcid=null, year=2024, volume=24, issue=28, pageStart=12033, pageEnd=12042, url=null, language=null, rfNumber=[5], rfOrder=8, authorNames=肖友淦, 刘硕, 曹岑, journalName=科学技术与工程, refType=null, unstructuredReference=肖友淦, 刘硕, 曹岑, 等. 基于乘子法的地震波波速和介质密度的多参数稳健反演[J]. 科学技术与工程, 2024, 24(28): 12033-12042., articleTitle=基于乘子法的地震波波速和介质密度的多参数稳健反演, refAbstract=null), Reference(id=1177977299363316498, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, doi=null, pmid=null, pmcid=null, year=2024, volume=24, issue=28, pageStart=12033, pageEnd=12042, url=null, language=null, rfNumber=[5], rfOrder=9, authorNames=Xiao Yougan, Liu Shuo, Cao Cen, journalName=Science Technology and Engineering, refType=null, unstructuredReference=Xiao Yougan, Liu Shuo, Cao Cen, et al. Multi-parameter robust inversion of seismic wave velocity and medium density based on multiplier method[J]. Science Technology and Engineering, 2024, 24(28): 12033-12042., articleTitle=Multi-parameter robust inversion of seismic wave velocity and medium density based on multiplier method, refAbstract=null), Reference(id=1177977299447202579, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, doi=null, pmid=null, pmcid=null, year=2022, volume=22, issue=22, pageStart=9822, pageEnd=9829, url=null, language=null, rfNumber=[6], rfOrder=10, authorNames=陈正林, 何国志, 张劼超, journalName=科学技术与工程, refType=null, unstructuredReference=陈正林, 何国志, 张劼超, 等. 小样本数据下三维地应力反演分析[J]. 科学技术与工程, 2022, 22(22): 9822-9829., articleTitle=小样本数据下三维地应力反演分析, refAbstract=null), Reference(id=1177977299514311444, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, doi=null, pmid=null, pmcid=null, year=2022, volume=22, issue=22, pageStart=9822, pageEnd=9829, url=null, language=null, rfNumber=[6], rfOrder=11, authorNames=Chen Zhenglin, He Guozhi, Zhang Jiechao, journalName=Science Technology and Engineering, refType=null, unstructuredReference=Chen Zhenglin, He Guozhi, Zhang Jiechao, et al. Three dimensional in-situ stress inversion analysis with small sample data[J]. Science Technology and Engineering, 2022, 22(22): 9822-9829., articleTitle=Three dimensional in-situ stress inversion analysis with small sample data, refAbstract=null), Reference(id=1177977299568837397, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, doi=null, pmid=null, pmcid=null, year=2021, volume=21, issue=31, pageStart=13268, pageEnd=13276, url=null, language=null, rfNumber=[7], rfOrder=12, authorNames=韩思旭, 陈小斌, 陈卫营, journalName=科学技术与工程, refType=null, unstructuredReference=韩思旭, 陈小斌, 陈卫营, 等. 基于CUDA架构并行算法的带地形AMT二维反演实现与应用[J]. 科学技术与工程, 2021, 21(31): 13268-13276., articleTitle=基于CUDA架构并行算法的带地形AMT二维反演实现与应用, refAbstract=null), Reference(id=1177977299677889302, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, doi=null, pmid=null, pmcid=null, year=2021, volume=21, issue=31, pageStart=13268, pageEnd=13276, url=null, language=null, rfNumber=[7], rfOrder=13, authorNames=Han Sixu, Chen Xiaobin, Chen Weiying, journalName=Science Technology and Engineering, refType=null, unstructuredReference=Han Sixu, Chen Xiaobin, Chen Weiying, et al. Implementation and application of 2D audio-frequency magnetotelluric method inversion with topography based on compute unified device architecture parallel algorithm[J]. Science Technology and Engineering, 2021, 21(31): 13268-13276., articleTitle=Implementation and application of 2D audio-frequency magnetotelluric method inversion with topography based on compute unified device architecture parallel algorithm, refAbstract=null), Reference(id=1177977299757581079, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, doi=null, pmid=null, pmcid=null, year=2023, volume=23, issue=26, pageStart=11098, pageEnd=11107, url=null, language=null, rfNumber=[8], rfOrder=14, authorNames=李丽丽, 李长伟, 程勃, journalName=科学技术与工程, refType=null, unstructuredReference=李丽丽, 李长伟, 程勃, 等. 基于改进粒子群算法的大地电磁反演[J]. 科学技术与工程, 2023, 23(26): 11098-11107., articleTitle=基于改进粒子群算法的大地电磁反演, refAbstract=null), Reference(id=1177977299833078552, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, doi=null, pmid=null, pmcid=null, year=2023, volume=23, issue=26, pageStart=11098, pageEnd=11107, url=null, language=null, rfNumber=[8], rfOrder=15, authorNames=Li Lili, Li Changwei, Cheng Bo, journalName=Science Technology and Engineering, refType=null, unstructuredReference=Li Lili, Li Changwei, Cheng Bo, et al. Magnetotelluric inversion based on improved particle swarm optimization algorithm[J]. Science Technology and Engineering, 2023, 23(26): 11098-11107., articleTitle=Magnetotelluric inversion based on improved particle swarm optimization algorithm, refAbstract=null), Reference(id=1177977299916964633, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, doi=null, pmid=null, pmcid=null, year=2023, volume=37, issue=6, pageStart=25, pageEnd=33, url=null, language=null, rfNumber=[9], rfOrder=16, authorNames=张昊, 杨雄伟, 李明水, journalName=实验流体力学, refType=null, unstructuredReference=张昊, 杨雄伟, 李明水. 基于双加权 POD 的建筑物风压场重构[J]. 实验流体力学, 2023, 37(6): 25-33., articleTitle=基于双加权 POD 的建筑物风压场重构, refAbstract=null), Reference(id=1177977299992462106, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, doi=null, pmid=null, pmcid=null, year=2023, volume=37, issue=6, pageStart=25, pageEnd=33, url=null, language=null, rfNumber=[9], rfOrder=17, authorNames=Zhang Hao, Yang Xiongwei, Li Mingshui, journalName=Journal of Experiments in Fluid Mechanics, refType=null, unstructuredReference=Zhang Hao, Yang Xiongwei, Li Mingshui, A bi-weighted-POD and its application on wind pressure field[J]. Journal of Experiments in Fluid Mechanics, 2023, 37(6): 25-33., articleTitle=A bi-weighted-POD and its application on wind pressure field, refAbstract=null), Reference(id=1177977300055376667, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, doi=null, pmid=null, pmcid=null, year=2021, volume=597, issue=null, pageStart=126095, pageEnd=null, url=null, language=null, rfNumber=[10], rfOrder=18, authorNames=Lima C H R, Hyun-Han K, Yong-Tak K, journalName=Journal of Hydrology, refType=null, unstructuredReference=Lima C H R, Hyun-Han K, Yong-Tak K. A Bayesian Kriging model applied for spatial downscaling of daily rainfall from GCMs[J]. Journal of Hydrology, 2021, 597: 126095., articleTitle=A Bayesian Kriging model applied for spatial downscaling of daily rainfall from GCMs, refAbstract=null), Reference(id=1177977300122485533, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, doi=null, pmid=null, pmcid=null, year=2020, volume=722, issue=null, pageStart=137290, pageEnd=null, url=null, language=null, rfNumber=[11], rfOrder=19, authorNames=Gribov A, Konstantin K, journalName=Science of the Total Environment, refType=null, unstructuredReference=Gribov A, Konstantin K. Empirical Bayesian Kriging implementation and usage[J]. Science of the Total Environment, 2020, 722: 137290., articleTitle=Empirical Bayesian Kriging implementation and usage, refAbstract=null), Reference(id=1177977300206371614, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=1441, pageEnd=null, url=null, language=null, rfNumber=[12], rfOrder=20, authorNames=Konopatskiy E, Bezditnyi A A B, journalName=Journal of Physics: Conference Series, refType=null, unstructuredReference=Konopatskiy E, Bezditnyi A A B. Geometric modeling of multifactor processes and phenomena by the multidimensional parabolic interpolation method[J]. Journal of Physics: Conference Series, 2020, 1441: DOI: 10.1088/1742-6596/1441/1/012063., articleTitle=Geometric modeling of multifactor processes and phenomena by the multidimensional parabolic interpolation method, refAbstract=null), Reference(id=1177977300307034912, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, doi=null, pmid=null, pmcid=null, year=2019, volume=70, issue=null, pageStart=626, pageEnd=642, url=null, language=null, rfNumber=[13], rfOrder=21, authorNames=Kang K, Qin C, Lee B, journalName=Applied Mathematical Modelling, refType=null, unstructuredReference=Kang K, Qin C, Lee B, et al. Modified screening-based Kriging method with cross validation and application to engineering design[J]. Applied Mathematical Modelling, 2019, 70: 626-642., articleTitle=Modified screening-based Kriging method with cross validation and application to engineering design, refAbstract=null), Reference(id=1177977300369949475, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, doi=null, pmid=null, pmcid=null, year=2023, volume=420, issue=null, pageStart=114788, pageEnd=null, url=null, language=null, rfNumber=[14], rfOrder=22, authorNames=Conti C, López-Ureña S, journalName=Journal of Computational and Applied Mathematics, refType=null, unstructuredReference=Conti C, López-Ureña S. Non-oscillatory butterfly-type interpolation on triangular meshes[J]. Journal of Computational and Applied Mathematics, 2023, 420: 114788., articleTitle=Non-oscillatory butterfly-type interpolation on triangular meshes, refAbstract=null), Reference(id=1177977300445446948, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, doi=null, pmid=null, pmcid=null, year=2022, volume=17, issue=null, pageStart=165, pageEnd=179, url=null, language=null, rfNumber=[15], rfOrder=23, authorNames=Omidi M, Mohsen M, journalName=Journal of the Iranian Statistical Society, refType=null, unstructuredReference=Omidi M, Mohsen M. Spatial interpolation using copula for non-Gaussian modeling of rainfall data[J]. Journal of the Iranian Statistical Society, 2022, 17: 165-179., articleTitle=Spatial interpolation using copula for non-Gaussian modeling of rainfall data, refAbstract=null), Reference(id=1177977300525138726, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, doi=null, pmid=null, pmcid=null, year=2017, volume=605, issue=null, pageStart=276, pageEnd=290, url=null, language=null, rfNumber=[16], rfOrder=24, authorNames=Rizo-Decelis L D, Pardo-Igúzquiza E, Andreo B, journalName=Science of the Total Environment, refType=null, unstructuredReference=Rizo-Decelis L D, Pardo-Igúzquiza E, Andreo B. Spatial prediction of water quality variables along a main river channel, in presence of pollution hotspots[J]. Science of the Total Environment, 2017, 605: 276-290., articleTitle=Spatial prediction of water quality variables along a main river channel, in presence of pollution hotspots, refAbstract=null), Reference(id=1177977300609024808, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, doi=null, pmid=null, pmcid=null, year=2023, volume=263, issue=null, pageStart=125582, pageEnd=null, url=null, language=null, rfNumber=[17], rfOrder=25, authorNames=Gyeongmin K, Jin H, journalName=Energy, refType=null, unstructuredReference=Gyeongmin K, Jin H. A probabilistic approach to potential estimation of renewable energy resources based on augmented spatial interpolation[J]. Energy, 2023, 263: 125582., articleTitle=A probabilistic approach to potential estimation of renewable energy resources based on augmented spatial interpolation, refAbstract=null), Reference(id=1177977300718076714, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, doi=null, pmid=null, pmcid=null, year=2021, volume=21, issue=null, pageStart=25818, pageEnd=25830, url=null, language=null, rfNumber=[18], rfOrder=26, authorNames=Deabes W, Khayyat K M J, journalName=IEEE Sensors, refType=null, unstructuredReference=Deabes W, Khayyat K M J. Image reconstruction in electrical capacitance tomography based on deep neural networks[J]. IEEE Sensors, 2021, 21: 25818-25830., articleTitle=Image reconstruction in electrical capacitance tomography based on deep neural networks, refAbstract=null), Reference(id=1177977300835517228, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, doi=null, pmid=null, pmcid=null, year=2019, volume=null, issue=null, pageStart=1368, pageEnd=null, url=null, language=null, rfNumber=[19], rfOrder=27, authorNames=Belov A M, Denisova A Y, journalName=Journal of Physics: Conference Series, refType=null, unstructuredReference=Belov A M, Denisova A Y. Spatial interpolation methods for spectral-spatial remote sensing image super-resolution algorithm based on gradient descent approach[J]. Journal of Physics: Conference Series, 2019, 1368: DOI: 10.1080/01431161.2019.712233., articleTitle=Spatial interpolation methods for spectral-spatial remote sensing image super-resolution algorithm based on gradient descent approach, refAbstract=null)], funds=[Fund(id=1177977298549621512, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, awardId=2023YFB3209003, language=CN, fundingSource=国家重点研发计划(2023YFB3209003), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1177977294678278852, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, xref=1, ext=[AuthorCompanyExt(id=1177977294686667461, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, companyId=1177977294678278852, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 Aerospace College, Nanjing University of Aeronautics and Astronautics, Nanjing 210000, China), AuthorCompanyExt(id=1177977294695056070, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, companyId=1177977294678278852, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 南京航空航天大学航空学院, 南京 210000)]), AuthorCompany(id=1177977294774747848, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, xref=2, ext=[AuthorCompanyExt(id=1177977294783136458, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, companyId=1177977294774747848, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 Chengdu CAIC Electronics Co. , Ltd. , Chengdu 610091, China), AuthorCompanyExt(id=1177977294791525066, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, companyId=1177977294774747848, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 成都凯天电子股份有限公司, 成都 610091)])], figs=[ArticleFig(id=1177977296880288496, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, language=EN, label=Fig.1, caption=Wing model, figureFileSmall=AKUXUk8M3LK06nrC1lkMDw==, figureFileBig=jIhpOX5a089HQJefJxv2gA==, tableContent=null), ArticleFig(id=1177977296947397361, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, language=CN, label=图1, caption=机翼模型, figureFileSmall=AKUXUk8M3LK06nrC1lkMDw==, figureFileBig=jIhpOX5a089HQJefJxv2gA==, tableContent=null), ArticleFig(id=1177977297014506226, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, language=EN, label=Fig.2, caption=Optimizing Kriging model with improved grey wolf optimizer, figureFileSmall=3439nuGQb+3K8xROt81i7Q==, figureFileBig=VIXfHbbgEa0sCKNk4LGr5Q==, tableContent=null), ArticleFig(id=1177977297064837875, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, language=CN, label=图2, caption=改进灰狼算法优化克里金模型, figureFileSmall=3439nuGQb+3K8xROt81i7Q==, figureFileBig=VIXfHbbgEa0sCKNk4LGr5Q==, tableContent=null), ArticleFig(id=1177977297127752436, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, language=EN, label=Fig.3, caption=Neural network 1 regression effect diagram, figureFileSmall=/WW4ofiIlNH5X3mzeoHQQQ==, figureFileBig=irwmh6ERPEy8fNhE0amGag==, tableContent=null), ArticleFig(id=1177977297190666997, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, language=CN, label=图3, caption=神经网络1回归效果图, figureFileSmall=/WW4ofiIlNH5X3mzeoHQQQ==, figureFileBig=irwmh6ERPEy8fNhE0amGag==, tableContent=null), ArticleFig(id=1177977297240998646, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, language=EN, label=Fig.4, caption=Neural network 2 regression effect diagram, figureFileSmall=gSW39j1REynNh2hudmmapA==, figureFileBig=t/H0svEayTlFDqEwLap70A==, tableContent=null), ArticleFig(id=1177977297299718903, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, language=CN, label=图4, caption=神经网络2回归效果图

Data为输出数据;Fit为数据拟合的线性关系;Y=T为输出值等于目标值时的线性关系;R为Fit与Y=T的相关系数

, figureFileSmall=gSW39j1REynNh2hudmmapA==, figureFileBig=t/H0svEayTlFDqEwLap70A==, tableContent=null), ArticleFig(id=1177977297375216376, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, language=EN, label=Fig.5, caption=BP-IGWO inversion algorithm flowchart, figureFileSmall=t8dIbDzqgdJLpnTmZwmpYw==, figureFileBig=PjOxhICKvZP5qreg1uaLOw==, tableContent=null), ArticleFig(id=1177977297442325241, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, language=CN, label=图5, caption=BP-IGWO反演算法流程图, figureFileSmall=t8dIbDzqgdJLpnTmZwmpYw==, figureFileBig=PjOxhICKvZP5qreg1uaLOw==, tableContent=null), ArticleFig(id=1177977297505239802, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, language=EN, label=Fig.6, caption=Retrieval of pressure field using different algorithms, figureFileSmall=xWwzKD8Hg9tc30UVc8wvow==, figureFileBig=/9gLTkGGTcKjd2UEB0mfnQ==, tableContent=null), ArticleFig(id=1177977297605903099, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, language=CN, label=图6, caption=不同算法的反演气压场, figureFileSmall=xWwzKD8Hg9tc30UVc8wvow==, figureFileBig=/9gLTkGGTcKjd2UEB0mfnQ==, tableContent=null), ArticleFig(id=1177977297693983484, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, language=EN, label=Fig.7, caption=Assemble the internal structure of the sample, figureFileSmall=VzyZsIc0lZDDpoKUjQC8QA==, figureFileBig=HoVCUb4rn/PbZz/PPV3d7Q==, tableContent=null), ArticleFig(id=1177977297752703741, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, language=CN, label=图7, caption=组装样件内部结构, figureFileSmall=VzyZsIc0lZDDpoKUjQC8QA==, figureFileBig=HoVCUb4rn/PbZz/PPV3d7Q==, tableContent=null), ArticleFig(id=1177977297815618302, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, language=EN, label=Fig.8, caption=Experimental site diagram, figureFileSmall=xRz47c0whwX0HW0PDwxkhA==, figureFileBig=NeFR18z5j2AKEEqojm07Gg==, tableContent=null), ArticleFig(id=1177977297899504383, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, language=CN, label=图8, caption=试验现场图, figureFileSmall=xRz47c0whwX0HW0PDwxkhA==, figureFileBig=NeFR18z5j2AKEEqojm07Gg==, tableContent=null), ArticleFig(id=1177977297966613248, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, language=EN, label=Fig.9, caption=Pressure comparison under wind speed of 60 m/s at 0 ° angle of attack and 0 ° sideslip angle, figureFileSmall=pgZyKu0JHVCMi+u9SUwwAQ==, figureFileBig=6FRJkkBrnD/ZXhYLF6SGxA==, tableContent=null), ArticleFig(id=1177977298025333505, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, language=CN, label=图9, caption=0°攻角0°侧滑角60 m/s风速下压力对比, figureFileSmall=pgZyKu0JHVCMi+u9SUwwAQ==, figureFileBig=6FRJkkBrnD/ZXhYLF6SGxA==, tableContent=null), ArticleFig(id=1177977298084053762, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, language=EN, label=Table 1, caption=

Chordwise position of pressure sensor

, figureFileSmall=null, figureFileBig=null, tableContent=
编号 1 2 3 4 5 6
相对弦长位置/% 3 6 15 30 60 97
弦向位置/mm 12 24 60 120 240 388
上翼面位置/mm 21 34 72 132 352 403
下翼面位置/mm 18 31 67 127 247 396
), ArticleFig(id=1177977298146968323, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, language=CN, label=表1, caption=

气压传感器弦向位置

, figureFileSmall=null, figureFileBig=null, tableContent=
编号 1 2 3 4 5 6
相对弦长位置/% 3 6 15 30 60 97
弦向位置/mm 12 24 60 120 240 388
上翼面位置/mm 21 34 72 132 352 403
下翼面位置/mm 18 31 67 127 247 396
), ArticleFig(id=1177977298226660100, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, language=EN, label=Table 2, caption=

Mean square error between inverted pressure field and original pressure field under different operating conditions

, figureFileSmall=null, figureFileBig=null, tableContent=
工况条件 反演气压场与原始气压场均方误差/Pa
攻角/(°) 风速/(m·s-1) 三次样条法 双调和样条法 克里金法 IGWO优化克里金法 BP-IGWO反演算法
-6 30 2.86×103 1.05×104 3.24×103 2.67×103 2.92×106
-6 60 6.3×104 1.66×105 5.25×104 4.32×104 1.83×106
0 30 2.64×103 6.60×103 3.58×103 2.61×103 9.49×105
0 60 4.70×104 1.03×105 5.86×104 4.06×104 9.11×105
6 30 2.74×103 3.43×103 3.84×103 2.50×103 6.30×105
6 60 5.07×104 5.62×104 6.03×104 4.40×104 3.69×105
), ArticleFig(id=1177977298281186053, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, language=CN, label=表2, caption=

不同工况反演气压场与原始气压场均方误差

, figureFileSmall=null, figureFileBig=null, tableContent=
工况条件 反演气压场与原始气压场均方误差/Pa
攻角/(°) 风速/(m·s-1) 三次样条法 双调和样条法 克里金法 IGWO优化克里金法 BP-IGWO反演算法
-6 30 2.86×103 1.05×104 3.24×103 2.67×103 2.92×106
-6 60 6.3×104 1.66×105 5.25×104 4.32×104 1.83×106
0 30 2.64×103 6.60×103 3.58×103 2.61×103 9.49×105
0 60 4.70×104 1.03×105 5.86×104 4.06×104 9.11×105
6 30 2.74×103 3.43×103 3.84×103 2.50×103 6.30×105
6 60 5.07×104 5.62×104 6.03×104 4.40×104 3.69×105
), ArticleFig(id=1177977298344100614, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, language=EN, label=Table 3, caption=

Chordwise position of pressure sensor

, figureFileSmall=null, figureFileBig=null, tableContent=
编号 1 2 3 4 5 6 7 8 9 10 11
相对弦长位置/% 3.0 4.5 6.0 10.5 15.0 22.5 30.0 45.0 60.0 78.5 97.0
弦向位置/mm 12 18 24 42 60 90 120 180 240 314 388
上翼面位置/mm 21 27.5 34 53 72 102 132 242 352 377.5 403
下翼面位置/mm 18 24.5 31 49 67 97 127 187 247 341.5 396
), ArticleFig(id=1177977298423792391, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789602862559683, language=CN, label=表3, caption=

气压传感器弦向位置

, figureFileSmall=null, figureFileBig=null, tableContent=
编号 1 2 3 4 5 6 7 8 9 10 11
相对弦长位置/% 3.0 4.5 6.0 10.5 15.0 22.5 30.0 45.0 60.0 78.5 97.0
弦向位置/mm 12 18 24 42 60 90 120 180 240 314 388
上翼面位置/mm 21 27.5 34 53 72 102 132 242 352 377.5 403
下翼面位置/mm 18 24.5 31 49 67 97 127 187 247 341.5 396
)], attaches=null, journal=Journal(id=1146119176004939786, delFlag=0, nameCn=科学技术与工程, nameEn=Science Technology and Engineering, nameHistory1=null, nameHistory2=null, issn=1671-1815, eissn=, cn=11-4688/T, coden=null, periodic=4, language=CN, oaType=是, ccby=null, superviseOffice=null, ownerOffice=null, pubOffice=null, editorOffice=null, officeType=null, aims=null, clcCode=null, officeProv=null, officeCity=null, officeAddr=null, officeZip=null, officeEmail=null, officePhone=null, editDirector=null, officeDirector=null, officeDirectorPhone=null, officeStaffNum=null, officeEmpNum=null, coverPicUrl=UKU/O7GSka5polgCTkbIIw==, journalPrice=null, startedYear=null, abbrevIsoEn=Sci Technol Eng, journalRemark=null, publicationField=null, createdTime=null, updatedTime=1754445529766, createdBy=null, updatedBy=13701087609, firstLetterCn=S, firstLetterEn=S, subjectCode=Natural Sciences, subjectName=自然科学, subjectCodeEn=Natural Sciences, subjectNameEn=null, picCn=UKU/O7GSka5polgCTkbIIw==, picEn=5hwlULoNwcbj3xUmVi9MAQ==, jcr=null, cjcr=null, exts=[JournalExt(id=1159791870395564357, language=CN, name=科学技术与工程, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=null, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=http://www.stae.com.cn/jsygc/home, createdTime=1754445529793, updatedTime=1754445529793, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=http://www.stae.com.cn/jsygc/site/menus/20090429150146001, submissionAuthorUrl=http://www.stae.com.cn/jsygc/author/login, submissionEditorUrl=http://www.stae.com.cn/jsygc/editor/login, submissionReviewUrl=http://www.stae.com.cn/jsygc/reviewer/login, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1159791870441701702, language=EN, name=Science Technology and Engineering, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=null, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=http://www.stae.com.cn/jsygc/home, createdTime=1754445529804, updatedTime=1754445529804, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=http://www.stae.com.cn/jsygc/author/login, submissionEditorUrl=http://www.stae.com.cn/jsygc/editor/login, submissionReviewUrl=http://www.stae.com.cn/jsygc/reviewer/login, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1146123166801305609, websiteList=[Website(id=1148243202391400884, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146123166801305609, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/kxjsygc/CN, language=CN, createTime=1751692112777, createBy=18614031015, updateTime=1753520965431, updateBy=18614031015, name=科学技术与工程-中文站点, tplId=1146099689490845704, title=科学技术与工程, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1148622798802673703, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=articleTextType, value=kx, createTime=1751782615614, updateTime=1751782615614, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622798781702180, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=banner, value=null, createTime=1751782615609, updateTime=1751782615609, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622798769119267, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=j86gbwi+p0Idkyl5SzIlmQ==, createTime=1751782615606, updateTime=1751782615606, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622798794285094, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1751782615612, updateTime=1751782615612, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622798790090789, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1751782615611, updateTime=1751782615611, creator=18614031015, updator=18614031015)]), Website(id=1155914124811976731, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146123166801305609, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/kxjsygc/EN, language=EN, createTime=1753521003206, createBy=18614031015, updateTime=1753521003206, updateBy=18614031015, name=科学技术与工程-英文站点, tplId=1146101810881728533, title=Science Technology and Engineering, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1155914371227308235, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=articleTextType, value=kx, createTime=1753521061952, updateTime=1753521061952, creator=18614031015, updator=18614031015), WebsiteProps(id=1155914371210531016, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=banner, value=null, createTime=1753521061947, updateTime=1753521061947, creator=18614031015, updator=18614031015), WebsiteProps(id=1155914371202142407, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=j86gbwi+p0Idkyl5SzIlmQ==, createTime=1753521061945, updateTime=1753521061945, creator=18614031015, updator=18614031015), WebsiteProps(id=1155914371223113930, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1753521061950, updateTime=1753521061950, creator=18614031015, updator=18614031015), WebsiteProps(id=1155914371218919625, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1753521061949, updateTime=1753521061949, creator=18614031015, updator=18614031015)])], journalTitle=科学技术与工程, weixinUrl=null, journalUrl=null, iacademicId=null, status=0, seqNo=null, journalTitleEn=Science Technology and Engineering, journalPhotoCn=UKU/O7GSka5polgCTkbIIw==, journalPhotoEn=5hwlULoNwcbj3xUmVi9MAQ==, journalFirstLetter=S, journalRecommend=null, journalNew=null, journalCollection=null, jcrJf=null, cjcrJf=null, jcrJfStr=null, cjcrJfStr=null, submissionFirstDecision=null, sciSubjectClassification=null, casSubjectClassification=null, citeScore=null, totalCitationFrequency=null, icpCode=null, psCode=null, advertisingLicenseCode=null, copyrightInformation=null, country=null, option=null, provinceCode=null, provinceName=null, collectFlag=false), detailUrlCn=https://castjournals.cast.org.cn/joweb/kxjsygc/CN/10.12404/j.issn.1671-1815.2405114, detailUrlEn=https://castjournals.cast.org.cn/joweb/kxjsygc/EN/10.12404/j.issn.1671-1815.2405114, pdfUrlCn=https://castjournals.cast.org.cn/joweb/kxjsygc/CN/PDF/10.12404/j.issn.1671-1815.2405114, pdfUrlEn=https://castjournals.cast.org.cn/joweb/kxjsygc/EN/PDF/10.12404/j.issn.1671-1815.2405114, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于BP-IGWO和分布式传感器的智能蒙皮物理场反演方法
收藏切换
PDF下载
龙彦志 1, 2 , 郑博宇 1 , 赵鑫 2 , 郑禄军 1 , 陈仁文 1
科学技术与工程 | 论文·航空、航天 2025,25(16): 6961-6969
收起
收藏切换
科学技术与工程 | 论文·航空、航天 2025, 25(16): 6961-6969
基于BP-IGWO和分布式传感器的智能蒙皮物理场反演方法
全屏
龙彦志1, 2 , 郑博宇1, 赵鑫2, 郑禄军1, 陈仁文1
作者信息
  • 1 南京航空航天大学航空学院, 南京 210000
  • 2 成都凯天电子股份有限公司, 成都 610091
  • 龙彦志(1987—),男,汉族,湖南益阳人,博士研究生,研究方向:大气数据探测技术。E-mail:

Physical Field Inversion Method of Smart Skin Based on BP-IGWO and Distributed Sensors
Yan-zhi LONG1, 2 , Bo-yu ZHENG1, Xin ZHAO2, Lu-jun ZHENG1, Ren-wen CHEN1
Affiliations
  • 1 Aerospace College, Nanjing University of Aeronautics and Astronautics, Nanjing 210000, China
  • 2 Chengdu CAIC Electronics Co. , Ltd. , Chengdu 610091, China
出版时间: 2025-06-08 doi: 10.12404/j.issn.1671-1815.2405114
文章导航
收藏切换

飞行器智能蒙皮通过在飞行器复合材料蒙皮上集成分布式传感器、驱动器和控制器,使其具有监测其本身状态和损伤的能力,其中物理场反演算法是智能蒙皮信号处理中的重要一环。但是由于传感器布置密度小等原因,传统的反演算法精度不高。为了提高智能蒙皮的监测精度,提出一种将反向传播(back propagation,BP)神经网络与改进的灰狼优化算法(improved grey wolf optimizer,IGWO)优化克里金模型融合的BP-IGWO反演算法。制作智能蒙皮原理样件,通过风洞试验对该算法进行验证。结果表明:BP-IGWO反演算法较之传统反演算法具有更高的精度和细节呈现能力,能更好地监测智能蒙皮的状态。

智能蒙皮  /  物理场反演  /  人工神经网络  /  反向传播神经网络-改进的灰狼优化器(BP-IGWO)  /  克里金法

The smart skin of an aircraft is realized by integrating distributed sensors, actuators, and controllers into the composite skin, thereby enabling it to monitor its own state and detect damages. The physical field inversion algorithm plays a key role in the signal processing of the smart skin. However, due to factors such as the low sensor density, traditional inversion algorithms exhibit limited accuracy. In order to enhance the monitoring precision of the smart skin, a back propagation(BP) neural network-improved grey wolf optimizer(IGWO) inversion algorithm, which combined a BP neural network with an IGWO-optimized Kriging model, was proposed. A prototype of the smart skin was subsequently fabricated, and wind tunnel tests were conducted to validate the proposed algorithm. The results demonstrate that the BP-IGWO inversion algorithm achieves higher accuracy and superior detail representation compared to traditional inversion algorithms, and can better monitor the state of smart skin.

smart skin  /  physical field inversion technology  /  neural network  /  back propagation-improved grey wolf optimizer(BP-IGWO)  /  Kriging
龙彦志, 郑博宇, 赵鑫, 郑禄军, 陈仁文. 基于BP-IGWO和分布式传感器的智能蒙皮物理场反演方法. 科学技术与工程, 2025 , 25 (16) : 6961 -6969 . DOI: 10.12404/j.issn.1671-1815.2405114
Yan-zhi LONG, Bo-yu ZHENG, Xin ZHAO, Lu-jun ZHENG, Ren-wen CHEN. Physical Field Inversion Method of Smart Skin Based on BP-IGWO and Distributed Sensors[J]. Science Technology and Engineering, 2025 , 25 (16) : 6961 -6969 . DOI: 10.12404/j.issn.1671-1815.2405114
智能蒙皮是未来先进飞行器的一项重要技术,它利用集成在飞机柔性蒙皮中的分布式智能材料传感器和驱动器,实现对机翼结构自身状态和环境参数的感知、信息处理和状态评估。利用智能蒙皮中的分布式阵列传感器采集的信息,进行物理场的反演,能够对蒙皮的状态和所受的激励进行全面准确的评估,从而为结构健康监测和自适应控制提供准确的信息。
目前物理场反演方法主要是插值拟合法,根据已知关键点的物理量数值,使用插值拟合算法来推算位置点的物理量数值,具有计算量小,实用性和可移植性高等优点[1]
学者们针对物理场反演算法进行了大量的研究。王振宇等[2]研究了泊松克里金法在核辐射场重构中的应用效果。许富景等[3]提出了一种温度场压缩重构方法,有效降低了二维温度场测试对测试点数量的要求。张天一等[4]针对集成电路芯片内部温度场重构问题,提出了一种 基于稀疏字典学习的温度场重构方法。肖友淦等[5]提出一种基于多尺度策略的多参数乘子法反演框架,将时间域多尺度策略与乘子法相结合,在不降低地震波速反演精度的同时,提高密度的反演精度。陈正林等[6]提出了一种以边界荷载法为基础,结合反向传播(back propagation,BP)神经网络的FLAC3D地应力反演改进方法,实现了小样本数据下的三维地应力反演。韩思旭等[7]提出了一种基于CUDA(compute unified device architecture)架构的并行算法,在灵敏度矩阵计算和反演方程正则化方面耗时更少,加速比最高可达10倍以上。李丽丽等[8]提出了一种改进的优化粒子群算法,有效解决了过早收敛的问题。张昊等[9]将本征正交分解法应用到建筑物风压场重构 中,取得了较高的反演精度。Lima等[10]使用BK (Bayesian Kriging)模型进行低尺度GCM(Galois/counter mode)日降雨量模拟,更好地解决了参数的不确定性。Gribov等[11]提出经验贝叶斯克里格(empirical Bayesian Kriging,EBK)变体,是一种快速可靠的自动和交互式数据插值解决方案,可以用于插值非常大的数据集。Konopatskiy等[12]介绍了一种特殊的多维抛物线插值法,这种方法可以有效地利用多维插值而不是多维逼近来解决建模问题。Kang等[13]提出了一种基于交叉验证误差的基筛选Kriging方法,以减轻动态Kriging算法的计算负担,同时保持其准确性。Conti等[14]提出并分析一种正则三角形网格数据的非振荡内插值细分方案。Omidi等[15]基于两个Max-id copula族的加权几何平均值给出了空间copula函数,然后将提出的copula与蜜蜂算法结合,进行空间插值。Rizo-Decelis等[16]使用 topological kriging法,通过交叉验证选择最佳估计方法。Gyeongmin等[17]使用普通克里金法和蒙特卡洛模拟进行建模,提出了一种基于增强空间插值的概率估计方法。Deabes等[18]提出一种基于长短期记忆深度神经网络模型的电容层析图像重建算法。Belov等[19]研究发现,空间插值方法对重建图像的质量和算法收敛速度有很大的影响。
综上可知,传统的物理量采集方法在采集过程中面临着破坏机翼外形,传感器孤立安装导致的系统复杂,可靠性低等问题。上述反演方法又存在测量点单一,算力要求高等问题。鉴于此,提出一种将BP与改进的灰狼优化算法(improved grey wolf optimizer,IGWO)优化克里金模型相融合的反演算法BP-IGWO,在较少测量点的情况下较好地还原出物理量在机翼蒙皮表面的分布情况。从而对机翼蒙皮的状态和受到的激励进行监测,为结构健康监测和自适应控制提供支持。
采用机翼缩比模型,该缩比模型采用NACA2415翼型,翼展600 mm,弦长400 mm,如图1所示。
以NACA2415翼型作为参照简化机翼模型,建立模型如图1所示。
在无侧滑角的情况下按机翼攻角-10°~20°步进2°,气流速度30~60 m/s步进5 m/s进行仿真;在攻角2°的情况下按机翼侧滑角-10°~10°步进2°,气流速度30~60 m/s步进5 m/s进行仿真。
通过对约200种不同实验工况仿真结果的分析,综合考虑仿真结果与模型整体结构,选取压强变化最明显的6个位置布置6排传感器,位置如表1所示。每排设置4个传感器,沿展向均匀布置。将该24个点作为本文反演算法的24个输入数据。
常规的插值反演算法仅考虑输入数据的局部变化趋势,在实际运用中并不能取得很好的反演效果,因此对反演算法进行改进和优化。
克里金模型是依据协方差函数对随机过程/随机场进行空间建模和预测(插值)的回归算法。在特定的随机过程,克里金法能够给出最优线性无偏估计。
给定d维空间下的 n个样本X={x1,x2,…,xn},其中xIRd,以及对应各点的响应矩阵Y={y1,y2,…,yn},其中yIRm
克里金模型由线性回归模型和随机函数组成,可表示为
Y(x)=f(x)+Z(x)
式(1)中:f(x)为回归函数;Z为均值为0、方差为σ2、相关矩阵为Ψ的高斯随机过程。
克里金模型利用回归函数描述数据的总体趋势,并使用高斯随机过程对残差进行插值。其中回归函数的形式可表示为
f(x)= i = 1 paibi(X)=bT(X)α
式(2)中:ai为系数;bi(X)为基函数,i=1,2,…,p;这里可以将f(x)看作是广义高斯过程Y的均值。
克里金模型的线性回归模型可以用 n×p 维的基函数矩阵F表示,即
F= b 1 ( X 1 ) b 2 ( X 1 ) b p ( X 1 ) b 1 ( X 2 ) b 2 ( X 2 ) b p ( X 2 ) b 1 ( X n ) b 2 ( X n ) b p ( X n )
而高斯随机过程主要由已知点的 n×n 维相关矩阵Ψ来定义。
Ψ= ψ ( X 1 , X 1 ) ψ ( X 1 , X 2 ) ψ ( X 1 , X n ) ψ ( X 2 , X 1 ) ψ ( X 2 , X 2 ) ψ ( X 2 , X n ) ψ ( X n , X 1 ) ψ ( X n , X 2 ) ψ ( X n , X n )
未知点与已知点的相关矩阵r(x)定义为
r(x)=[ψ(X,X1),ψ(X,X2),…,ψ(X,Xn)]
空间插值问题的基本思想是使用空间上所有已知点的数据,通过加权求和的方式来预测未知点的值,克里金模型采用式(6)所示的预测模型。
y ^(X)=cTy
式(6)中: y ^为克里金模型的预测值;y为已知点矩阵;c为要求的系数矩阵。
为了求解系数矩阵,首先需要计算预测模型的误差,计算公式为
$\begin{aligned} \hat{\boldsymbol{y}}(X)-\boldsymbol{y}(X) & =\boldsymbol{c}^{\mathrm{T}} \boldsymbol{y}-\boldsymbol{y}(X) \\ & =\boldsymbol{c}^{\mathrm{T}}(\boldsymbol{F} \boldsymbol{\alpha}+\boldsymbol{Z})-\left[\boldsymbol{b}(X)^{\mathrm{T}} \boldsymbol{\alpha}+\boldsymbol{z}\right] \\ & =\boldsymbol{c}^{\mathrm{T}} \boldsymbol{Z}-\boldsymbol{z}+\left(\boldsymbol{F}^{\mathrm{T}} \boldsymbol{c}\right) \end{aligned}$
式(7)中:Z= [ z 1 , z 2 , , z n ] T为已知点的误差;z为未知点的误差。
为了保证预测模型的无偏性, 要求FTc-b(X)=0。
预测器的均方误差为
$\begin{aligned} \varphi(X) & =E\left\{[\hat{\boldsymbol{y}}(X)-\boldsymbol{y}(x)]^{2}\right\} \\ & =E\left[\left(\boldsymbol{c}^{\mathrm{T}} \boldsymbol{Z}-\boldsymbol{z}\right)^{2}\right] \\ & =\sigma^{2}\left(1+\boldsymbol{c}^{\mathrm{T}} \boldsymbol{\Psi} \boldsymbol{c}-2 \boldsymbol{c}^{\mathrm{T}} \boldsymbol{r}^{\mathrm{T}}\right) \end{aligned}$
同时,克里金模型要保证预测器的最优性,即均方误差最小。结合模型无偏性和最优性的要求,构造拉格朗日函数为
$\begin{aligned} L(\boldsymbol{c}, \boldsymbol{\lambda})= & \sigma^{2}\left(1+\boldsymbol{c}^{\mathrm{T}} \boldsymbol{\Psi} \boldsymbol{c}-2 \boldsymbol{c}^{\mathrm{T}} \boldsymbol{r}^{\mathrm{T}}\right)- \\ & \boldsymbol{\lambda}^{\mathrm{T}}\left(\boldsymbol{F}^{\mathrm{T}} \boldsymbol{c}-\boldsymbol{b}\right) \end{aligned}$
式(9)中:λ为拉格朗日算子。
拉格朗日函数分别对cλ求导,得
$\frac{\mathrm{d} L}{\mathrm{~d} \boldsymbol{c}}=2 \sigma^{2}\left(\boldsymbol{\Psi} \boldsymbol{c}-\boldsymbol{r}^{\mathrm{T}}\right)-\boldsymbol{F} \boldsymbol{\lambda}$
$\frac{\mathrm{d} L}{\mathrm{~d} \boldsymbol{c}}=\boldsymbol{F}^{\mathrm{T}} \boldsymbol{c}-\boldsymbol{b}$
根据最优性的一阶必要条件,可得
$\left(\begin{array}{cc} \boldsymbol{\Psi} & \boldsymbol{F} \\ \boldsymbol{F}^{\mathrm{T}} & \mathbf{0} \end{array}\right)\binom{\boldsymbol{c}}{\boldsymbol{\lambda}}=\binom{\boldsymbol{r}^{\mathrm{T}}}{\boldsymbol{b}}$
式(12)中: λ ^=- λ 2 σ 2,求解式(12)可得
$\left\{\begin{array}{l} \hat{\boldsymbol{\lambda}}=\left(\boldsymbol{F}^{\mathrm{T}} \boldsymbol{\Psi}^{-1} \boldsymbol{F}\right)^{-1}\left(\boldsymbol{F}^{\mathrm{T}} \boldsymbol{\Psi}^{-1} \boldsymbol{R}^{\mathrm{T}}-\boldsymbol{b}\right) \\ \boldsymbol{c}=\boldsymbol{\Psi}^{-1}\left(\boldsymbol{r}^{\mathrm{T}}-\boldsymbol{F} \hat{\boldsymbol{\lambda}}\right) \end{array}\right.$
此时将 λ ^c 代入,可得
$\begin{aligned} \hat{\boldsymbol{y}}(X)= & \left(\boldsymbol{r}^{\mathrm{T}}-\boldsymbol{F} \hat{\boldsymbol{\lambda}}\right)^{\mathrm{T}} \boldsymbol{\Psi}^{-1} \boldsymbol{y} \\ = & \boldsymbol{r}^{\mathrm{T}} \boldsymbol{\Psi}^{-1} \boldsymbol{y}-\left(\boldsymbol{F}^{\mathrm{T}} \boldsymbol{\Psi}^{-1} \boldsymbol{R}^{\mathrm{T}}-\right. \\ & \boldsymbol{b})^{\mathrm{T}}\left(\boldsymbol{F}^{\mathrm{T}} \boldsymbol{\Psi}^{-1} \boldsymbol{F}\right)^{-1} \boldsymbol{F}^{\mathrm{T}} \boldsymbol{\Psi}^{-1} \boldsymbol{y} \end{aligned}$
α*= ( F T Ψ - 1 F ) - 1FTΨ-1y,式(14)可以化简为
$\begin{aligned} \hat{\boldsymbol{y}}(X) & =\boldsymbol{r}^{\mathrm{T}} \boldsymbol{\Psi}^{-1} \boldsymbol{y}-\left(\boldsymbol{F}^{\mathrm{T}} \boldsymbol{\Psi}^{-1} \boldsymbol{R}^{\mathrm{T}}-\boldsymbol{b}\right)^{\mathrm{T}} \boldsymbol{\alpha}^{*} \\ & =\boldsymbol{b}^{\mathrm{T}} \boldsymbol{\alpha}^{*}+\boldsymbol{r} \boldsymbol{\Psi}^{-1}\left(\boldsymbol{y}-\boldsymbol{F} \boldsymbol{\alpha}^{*}\right) \end{aligned}$
又令γ*=Ψ-1(y-*), 最终可得克里金模型的预测均值,可表示为
$\hat{\boldsymbol{y}}(X)=\boldsymbol{b}^{\mathrm{T}} \boldsymbol{\alpha}^{*}+\boldsymbol{r} \boldsymbol{\gamma}^{*}$
灰狼优化算法(grey wolf optimizer, GWO)是一种新型智能优化算法。该算法按照社会地位由高到低把狼群范围定义为αβδω 4种阶层。狼群的捕猎过程由αβδ引导ω前往有希望的区域。改进灰狼算法在灰狼算法的基础上,引入基于维度学习的搜索策略,在更新位置时考虑灰狼算法搜索策略产生的候选者,并选取其中的最优解。
克里金模型首先需要选择相关函数模型。选用效果最好的高斯模型作为克里金法的相关函数。考虑到气压场在xy两个维度上可能具有不同的相关性,对两个不同的维度分别建立相关函数,有θ1θ2两个超参数。首先需要确定目标函数和参数范围,目标函数定义为
lnL=- n 2lnσ2- 1 2ln Ψ
式(17)中:σ2为过程方差;Ψ为相关矩阵。
改进灰狼算法优化的目标就是目标函数值最小。
选取灰狼种群数量N为20,最大迭代次数Maxiter为60,这里需要优化两个参数,所以设置IGWO中的维度数D为2。
改进灰狼算法优化克里金模型的流程如图2所示。
BP神经网络是一种按照误差反向传播进行训练的多层前馈网络,其训练主要包括信号前向传递和误差逆向反馈两个过程, 基于梯度下降法使实际输出结果和期望输出结果的误差均方差达到最小值。
三层的神经网络可以实现对任意有限闭区间的映射逼近。三层BP神经网络也是目前在超声信号分类领域常用的网络结构。因此,设计三层的BP神经网络。
根据经验公式计算得到,两个神经网络的结构分别为6输入24输出和4输入10输出,选择ReLU函数作为激活函数。针对物理场反演算法在边缘位置反演效果较差的问题,使用仿真数据训练的BP神经网络补充缺失的数据点。通过仿真得到189组不同工况下的气压仿真数据,这些数据中包含气压在模型表面的分布规律。利用BP神经网络提取出这些变化趋势,通过回归的方式把试验数据扩展成一个规模更大的数据点集。最后把这些数据点作为IGWO优化克里金法的输入,得到更符合理论趋势的反演气压场。
直接将24个数据点作为神经网络的输入得到扩展数据点集的方式理论上能够还原出整个气压场的变化规律,但是在实验过程中训练时间长,并且得到的模型容易过拟合,因此使用两个BP神经网络分别对两个方向上的气压场进行训练。
第1个神经网络的输入是仿真数据弦向上的6个数据点,由于气压场在弦向上变化更加明显,所以网络输出为6个数据点沿线上对应的24个数据点。第2个神经网络的输入是仿真数据展向上的4个数据点,输出的是对应的10个数据点。为了增大训练样本,并同时考虑实验误差,把原始仿真数据加上高斯噪声以后与原始数据一起训练,两个神经网络的隐含层节点数使用经验公式确定,训练结果可视化为模型回归效果图,如图3图4所示。对于一个理想的拟合,数据应该沿着45°角下降,网络输出和目标应该相等,即数据点无限接近目标直线。
神经网络训练完成后,首先将弦向上4组试验气压数据输入第1个神经网络,实现了弦向上6个数据点向24个数据点的扩展。然后使用扩展后的数据按照展向分成24组,分别输入第二个神经网络,实现展向上4个数据点向10个数据点的扩展。最后将得到的扩展后的10×24个气压数据点输入IGWO优化克里金模型中,得到最终的反演气压场,流程如图5所示。
为了观察不同算法的反演效果,选取仿真值进行分析对比,这里选取攻角为6°,风速60 m/s工况对三次样条法、双调和样条法、克里金法、IGWO优化克里金法和BP-IGWO反演算法进行分析。反演得到的气压场如图6所示。
对比以上反演气压场与原始气压场,可以发现三次样条插值法反演的气压场过渡平滑,前缘部分气压分布与原始气压场十分相似,但是后缘由于传感器数量较少,与原始气压场差别较大。双调和样条插值法虽然自动对输入数据区域外的点进行插值补齐,但是该方法反演的气 压场前缘位置围绕输入数据点形成4个中心,与原始气压场变化趋势不符,并且外插点的误差较大。IGWO 优化克里金法反演的气压场相比于克里金法优化了前缘的变化趋势,并且保留了后缘部分的拟合精度,而BP-IGWO算法在 IGWO 优化克里金模型的基础上增加了机翼前缘部分的细节,并且后缘部分更加平滑。结合1.2节中仿真得到的气压场,可以初步判断 BP-IGWO反演算法具有更好的气压场反演效果。为了进一步评估气压场的反演效果,计算不同工况下试验数据反演气压场与仿真气压场的均方误差,如表2所示。
表2中数据可以看出,由于风速较高的情况下气压场分布比较复杂,所以相较于低流速气压场,高流速气压场整体误差较大。在低流速情况下,三次样条法与IGWO优化克里金法所得的反演气压场均方误差比较接近,优于双调和样条法和普通克里金法。总体而言, IGWO优化克里金法结合了克里金法的优点,反演精度相较于克里金法得到了明显提升,相比与三次样条法,双调和样条法和普通克里金法,均方误差分别降低了19.8%、60%、25%。而BP-IGWO反演算法在不同工况下的反演精度均优于 IGWO 优化 克里金模型,均方误差相较于 IGWO 优化克里金模型又降低了 20.6%,具有明显的优势。
综上可知,所提出的 BP 神经网络与 IGWO 优化克里金模型组合反演算法能够补齐缺失的边 缘数据点,大幅度提高反演精度。
为了验证BP-IGWO反演算法的可行性,在前文得到的传感器阵列布局基础上,增加更多的压力传感器。传感器展向均匀布置9个传感器,弦向布局如表3所示。
根据上述布局设计和制作传感器阵列原理样件,能够完成对机翼表面气动压力进行测量。通过将算法选取的传感器点位,得到的数据进行反演,并将反演得到的结果与其余传感器测量的压力值进行对比,验证BP-IGWO算法在实际应用场景下的可用性。制作组装后的样机内部结构如图7所示。
样机的风洞试验在南京航空航天大学NH-2风洞进行,该风洞为全钢结构闭口回流风洞,全长140 m,这种风洞利用效率高、受外接干扰少,试验段宽3 m,高2.5 m,最大风速能够达到90 m/s。
试验设备如图8所示,包括机翼模型,模型支架,柔性传感器阵列,数据处理采集模块和上位机。
试验共采集到154组数据,每组数据均采集1 min。由于采集的物理量都为稳态量,即保持风速和机翼姿态不变的情况下采集数据,因此进行数据处理时对每组数据做时间上的平均,并将得到的平均值列成一行,得到每个传感器在当前工况下的输出。
随后将这些数据进行整理排序,分为变攻角状态下112组数据和变迎角状态下42组数据。变攻角状态将攻角从-10°递增到20°,按2°的间隔分成16种攻角状态,在每一个攻角下流速从30 m/s开始递增到60 m/s,按照5 m/s的间隔设置速度,,得到共112数据;同样的,变侧滑角状态下,攻角保持0°,侧滑角从0°递增到10°,按2°间隔,速度同样从30 m/s开始递增到60 m/s。
在实验结束后对这些数据进行了整理和处理,结果表明反演得到的压力值压力在空间上的分布和它们随工况变化的趋势与试验测量得到的压力值差距很小。
由于数据量过大,以下为选取的0°攻角0°侧滑角60 m/s风速工况下反演数据与实验数据的对比,误差基数取最大实验值与最小实验值之差,如图9所示。
经计算可得,所有工况下反演所得气压场与仿真所得气压场的平均误差为5.53%。可见BP-IGWO算法反演得到的气压场能够较好地反映机翼表面的气压分布情况。
以流体力学仿真数据为基础,设计传感器布局,后针对传统插值反演算法整体效果差,插值精度低的问题,对物理场反演算法进行研究,提出BP神经网络与IGWO优化克里金组合反演算法,得到以下结论。
(1)该算法在克里金模型的基础上使用改进灰狼算法优化了相关模型参数,并使用仿真数据训练的BP神经网络对试验数据进行扩充,反演效果明显优于传统反演算法。
(2)制作智能蒙皮样件,对物理场反演效果进行风洞实验,经测试对比,平均误差明显降低,整体反演效果良好。
  • 国家重点研发计划(2023YFB3209003)
参考文献 引证文献
排序方式:
[1]
周帅, 肖周芳, 付琳, 等. 一类面向高阶精度自适应流动计算的流场插值方法[J]. 力学学报, 2022, 54(6): 1732-1740.
Zhou Shuai, Xiao Zhoufang, Fu Lin, et al. Solution interpolation for high-order accurate adaptive flow simulation[J]. Chinese Journal of Theoretical and Applied Mechanics, 2022, 54(6): 1732-1740.
[2]
王振宇, 黄伟奇, 孙健, 等. 泊松克里金算法在核辐射场重构中的应用研究[J]. 原子能科学技术, 2022, 56(8): 1690-1699.
Wang Zhenyu, Huang Weiqi, Sun Jian, et al. Reconstruction of nuclear radiation dose field using alternative poisson-Kriging algorithm[J]. Atomic Energy Science and Technology, 2022, 56(8): 1690-1699.
[3]
许富景, 杜少成, 荆蕊蕊. 基于压缩感知与分段 Hermite 插值的二维温度场重构方法[J]. 电子测量与仪器学报, 2022, 36(4): 40-47.
Xu Fujing, Du Shaocheng, Jing Ruirui, et al. Two-dimensional temperature field reconstruction method based on compressed sensing and piecewise Hermite interpolation[J]. Journal of Electronic Measurement and Instrumentation, 2022, 36(4): 40-47.
[4]
张天一, 李文昌, 肖金玉, 等. 基于稀疏字典学习的 VLSI 温度场重构技术[J]. 电子科技大学学报, 2021, 50(4): 502-507.
Zhang Tianyi, Li Wenchang, Xiao Jinyu, et al. Thermal field reconstruction for VLSI based on sparse dictionary learning[J]. Journal of University of Electronic Science and Technology of China, 2021, 50(4): 502-507.
[5]
肖友淦, 刘硕, 曹岑, 等. 基于乘子法的地震波波速和介质密度的多参数稳健反演[J]. 科学技术与工程, 2024, 24(28): 12033-12042.
Xiao Yougan, Liu Shuo, Cao Cen, et al. Multi-parameter robust inversion of seismic wave velocity and medium density based on multiplier method[J]. Science Technology and Engineering, 2024, 24(28): 12033-12042.
[6]
陈正林, 何国志, 张劼超, 等. 小样本数据下三维地应力反演分析[J]. 科学技术与工程, 2022, 22(22): 9822-9829.
Chen Zhenglin, He Guozhi, Zhang Jiechao, et al. Three dimensional in-situ stress inversion analysis with small sample data[J]. Science Technology and Engineering, 2022, 22(22): 9822-9829.
[7]
韩思旭, 陈小斌, 陈卫营, 等. 基于CUDA架构并行算法的带地形AMT二维反演实现与应用[J]. 科学技术与工程, 2021, 21(31): 13268-13276.
Han Sixu, Chen Xiaobin, Chen Weiying, et al. Implementation and application of 2D audio-frequency magnetotelluric method inversion with topography based on compute unified device architecture parallel algorithm[J]. Science Technology and Engineering, 2021, 21(31): 13268-13276.
[8]
李丽丽, 李长伟, 程勃, 等. 基于改进粒子群算法的大地电磁反演[J]. 科学技术与工程, 2023, 23(26): 11098-11107.
Li Lili, Li Changwei, Cheng Bo, et al. Magnetotelluric inversion based on improved particle swarm optimization algorithm[J]. Science Technology and Engineering, 2023, 23(26): 11098-11107.
[9]
张昊, 杨雄伟, 李明水. 基于双加权 POD 的建筑物风压场重构[J]. 实验流体力学, 2023, 37(6): 25-33.
Zhang Hao, Yang Xiongwei, Li Mingshui, A bi-weighted-POD and its application on wind pressure field[J]. Journal of Experiments in Fluid Mechanics, 2023, 37(6): 25-33.
[10]
Lima C H R, Hyun-Han K, Yong-Tak K. A Bayesian Kriging model applied for spatial downscaling of daily rainfall from GCMs[J]. Journal of Hydrology, 2021, 597: 126095.
[11]
Gribov A, Konstantin K. Empirical Bayesian Kriging implementation and usage[J]. Science of the Total Environment, 2020, 722: 137290.
[12]
Konopatskiy E, Bezditnyi A A B. Geometric modeling of multifactor processes and phenomena by the multidimensional parabolic interpolation method[J]. Journal of Physics: Conference Series, 2020, 1441: DOI: 10.1088/1742-6596/1441/1/012063.
[13]
Kang K, Qin C, Lee B, et al. Modified screening-based Kriging method with cross validation and application to engineering design[J]. Applied Mathematical Modelling, 2019, 70: 626-642.
[14]
Conti C, López-Ureña S. Non-oscillatory butterfly-type interpolation on triangular meshes[J]. Journal of Computational and Applied Mathematics, 2023, 420: 114788.
[15]
Omidi M, Mohsen M. Spatial interpolation using copula for non-Gaussian modeling of rainfall data[J]. Journal of the Iranian Statistical Society, 2022, 17: 165-179.
[16]
Rizo-Decelis L D, Pardo-Igúzquiza E, Andreo B. Spatial prediction of water quality variables along a main river channel, in presence of pollution hotspots[J]. Science of the Total Environment, 2017, 605: 276-290.
[17]
Gyeongmin K, Jin H. A probabilistic approach to potential estimation of renewable energy resources based on augmented spatial interpolation[J]. Energy, 2023, 263: 125582.
[18]
Deabes W, Khayyat K M J. Image reconstruction in electrical capacitance tomography based on deep neural networks[J]. IEEE Sensors, 2021, 21: 25818-25830.
[19]
Belov A M, Denisova A Y. Spatial interpolation methods for spectral-spatial remote sensing image super-resolution algorithm based on gradient descent approach[J]. Journal of Physics: Conference Series, 2019, 1368: DOI: 10.1080/01431161.2019.712233.
2025年第25卷第16期
PDF下载
522
196
引用本文
BibTeX
文章信息
doi: 10.12404/j.issn.1671-1815.2405114
  • 接收时间:2024-07-08
  • 首发时间:2025-07-09
  • 出版时间:2025-06-08
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2024-07-08
  • 修回日期:2025-03-08
基金
国家重点研发计划(2023YFB3209003)
作者信息
    1 南京航空航天大学航空学院, 南京 210000
    2 成都凯天电子股份有限公司, 成都 610091
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/kxjsygc/CN/10.12404/j.issn.1671-1815.2405114
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