Article(id=1200797898486182610, tenantId=1146029695717560320, journalId=1146119989267898375, issueId=1200805346487955826, articleNumber=null, orderNo=null, doi=10.7654/j.issn.2097-1974.20250510, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=research-article, receivedDate=1740153600000, receivedDateStr=2025-02-22, revisedDate=1747238400000, revisedDateStr=2025-05-15, acceptedDate=null, acceptedDateStr=null, onlineDate=1764222128744, onlineDateStr=2025-11-27, pubDate=1761321600000, pubDateStr=2025-10-25, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1764223905265, onlineIssueDateStr=2025-11-27, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=1764222128744, onlineFirstDateStr=2025-11-27, sourceXml=null, magXml=null, createTime=1764222128744, creator=13701087609, updateTime=1764222128744, updator=13701087609, issue=Issue{id=1200805346487955826, tenantId=1146029695717560320, journalId=1146119989267898375, year='2025', volume='48', issue='5', pageStart='1', pageEnd='106', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1764223904486, creator=13701087609, updateTime=1768809576727, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1220039050011005257, tenantId=1146029695717560320, journalId=1146119989267898375, issueId=1200805346487955826, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1220039050011005258, tenantId=1146029695717560320, journalId=1146119989267898375, issueId=1200805346487955826, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=73, endPage=81, ext={EN=ArticleExt(id=1200797898809144029, articleId=1200797898486182610, tenantId=1146029695717560320, journalId=1146119989267898375, language=EN, title=Multi-source Aerodynamic Data Fusion Modeling Based on PINN, columnId=1200797897596990140, journalTitle=Missiles and Space Vehicles, columnName=Aerodynamic Parameter Identification and Application Studies, runingTitle=null, highlight=null, articleAbstract=

Establishing an accurate aerodynamic model is of great significance for analyzing the aerodynamic characteristics of aircraft and designing reliable flight control systems during the aircraft design process. Multi-source data fusion of aerodynamic data from different sources, such as wind tunnel tests and flight tests, is currently a popular method for unsteady aerodynamic modeling by intelligent algorithms. However, traditional fusion algorithms have shortcomings such as high requirements for flight data sources and weak generalization capabilities. Thus an improved intelligent modeling method based on Physics-Informed Neural Networks (PINNs) is proposed to integrate static wind tunnel test data and flight data. Compared to traditional PINNs, the physical loss constraints in improved PINN are reversely constructed to enable feature extraction from different and discrete flight data. The static wind tunnel data are incorporated into both the input and loss function of neural network to construct residual estimates. So the differences between ground and flight aerodynamic data are effectively corrected. The predictive aerodynamic characteristics for different motion forms demonstrate that the improved PINN not only has high aerodynamic prediction accuracy but also exhibits excellent generalization capabilities.

, correspAuthors=null, authorNote=null, correspAuthorsNote=null, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=null, magXml=null, pdfUrl=null, pdf=null, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=null, mapNumber=null, authorCompany=null, fund=null, authors=null, authorsList=Yifeng YANG, Lin SHEN, Enpeng QIU, Zhen CHEN, Suozhu WANG), CN=ArticleExt(id=1200797902172975942, articleId=1200797898486182610, tenantId=1146029695717560320, journalId=1146119989267898375, language=CN, title=基于PINN的多源气动数据融合建模方法, columnId=1200797897802511038, journalTitle=导弹与航天运载技术(中英文), columnName=气动参数辨识及应用研究, runingTitle=null, highlight=null, articleAbstract=

在飞行器设计过程中,建立准确的空气动力模型对分析飞行器气动特性、设计可靠的飞行控制系统具有重要意义。通过智能算法对地面风洞试验数据、飞行试验数据等不同来源的气动数据进行多源数据融合是目前较为热门的非定常气动力建模方法。但传统融合算法存在对飞行数据来源要求高、模型泛化能力弱等不足。基于物理信息神经网络原理,提出了一种改进的静态风洞试验数据与飞行数据智能融合建模方法。通过对传统PINN反向构建物理损失约束,使其具备对多段离散飞行数据进行特征提取的能力。通过在神经网络输入和损失函数中加入稳态气动数据构造残差估计,实现了天地气动数据差异的有效修正。对不同运动形式的气动特性进行预测验证,表明该方法不仅具有较高的气动力预测精度,还具有十分良好的泛化能力。

, correspAuthors=null, authorNote=null, correspAuthorsNote=null, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=YJeyAdPgZ7r+XOqzGqS0YA==, magXml=PM6chXr9PuTPovjNUunpjw==, pdfUrl=null, pdf=Wa/QHEc6Xa1/APAzHApehA==, pdfFileSize=5689613, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=EQkQRl29cfIXGSreMldUnQ==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=/W1JsZY0+Tiez4kJ3bZbmg==, mapNumber=null, authorCompany=null, fund=null, authors=

杨依峰(1990—),男,高级工程师,主要研究方向为飞行器气动设计。

沈 霖(1987—),男,博士,讲师,主要研究方向为非定常空气动力学。

邱恩鹏(1999—),男,硕士研究生,主要研究方向为非定常空气动力学。

陈 臻(1996—),男,博士研究生,主要研究方向为飞行器气动设计。

王锁柱(1984—),男,博士研究生,高级工程师,主要研究方向为飞行器气动设计。

, authorsList=杨依峰, 沈霖, 邱恩鹏, 陈臻, 王锁柱)}, authors=[Author(id=1200805354314527238, tenantId=1146029695717560320, journalId=1146119989267898375, articleId=1200797898486182610, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1200805354440356363, tenantId=1146029695717560320, journalId=1146119989267898375, articleId=1200797898486182610, authorId=1200805354314527238, language=EN, stringName=Yifeng YANG, firstName=Yifeng, middleName=null, lastName=YANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.Beijing Institute of Space Long March Vehicle, Beijing, 100076, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1200805354541019662, tenantId=1146029695717560320, journalId=1146119989267898375, articleId=1200797898486182610, authorId=1200805354314527238, language=CN, stringName=杨依峰, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.北京航天长征飞行器研究所,北京,100076, bio={"content":"

杨依峰(1990—),男,高级工程师,主要研究方向为飞行器气动设计。

"}, bioImg=null, bioContent=

杨依峰(1990—),男,高级工程师,主要研究方向为飞行器气动设计。

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1200805353983177202, tenantId=1146029695717560320, journalId=1146119989267898375, articleId=1200797898486182610, xref=1., ext=[AuthorCompanyExt(id=1200805353991565812, tenantId=1146029695717560320, journalId=1146119989267898375, articleId=1200797898486182610, companyId=1200805353983177202, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.Beijing Institute of Space Long March Vehicle, Beijing, 100076), AuthorCompanyExt(id=1200805354012537333, tenantId=1146029695717560320, journalId=1146119989267898375, articleId=1200797898486182610, companyId=1200805353983177202, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.北京航天长征飞行器研究所,北京,100076)])]), Author(id=1200805354645877266, tenantId=1146029695717560320, journalId=1146119989267898375, articleId=1200797898486182610, 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=1200805354796872216, tenantId=1146029695717560320, journalId=1146119989267898375, articleId=1200797898486182610, authorId=1200805354645877266, language=EN, stringName=Lin SHEN, firstName=Lin, middleName=null, lastName=SHEN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.College of Civil Aviation, Nanjing University of Aeronautics and Astronautics, Nanjing, 210016, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1200805354893341214, tenantId=1146029695717560320, journalId=1146119989267898375, articleId=1200797898486182610, authorId=1200805354645877266, language=CN, stringName=沈霖, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.南京航空航天大学民航学院,南京,210016, bio={"content":"

沈 霖(1987—),男,博士,讲师,主要研究方向为非定常空气动力学。

"}, bioImg=null, bioContent=

沈 霖(1987—),男,博士,讲师,主要研究方向为非定常空气动力学。

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1200805354176115200, tenantId=1146029695717560320, journalId=1146119989267898375, articleId=1200797898486182610, xref=2., ext=[AuthorCompanyExt(id=1200805354192892418, tenantId=1146029695717560320, journalId=1146119989267898375, articleId=1200797898486182610, companyId=1200805354176115200, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.College of Civil Aviation, Nanjing University of Aeronautics and Astronautics, Nanjing, 210016), AuthorCompanyExt(id=1200805354222252547, tenantId=1146029695717560320, journalId=1146119989267898375, articleId=1200797898486182610, companyId=1200805354176115200, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.南京航空航天大学民航学院,南京,210016)])]), Author(id=1200805354989810210, tenantId=1146029695717560320, journalId=1146119989267898375, articleId=1200797898486182610, 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=1200805355103056424, tenantId=1146029695717560320, journalId=1146119989267898375, articleId=1200797898486182610, authorId=1200805354989810210, language=EN, stringName=Enpeng QIU, firstName=Enpeng, middleName=null, lastName=QIU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.College of Civil Aviation, Nanjing University of Aeronautics and Astronautics, Nanjing, 210016, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1200805355191136812, tenantId=1146029695717560320, journalId=1146119989267898375, articleId=1200797898486182610, authorId=1200805354989810210, language=CN, stringName=邱恩鹏, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.南京航空航天大学民航学院,南京,210016, bio={"content":"

邱恩鹏(1999—),男,硕士研究生,主要研究方向为非定常空气动力学。

"}, bioImg=null, bioContent=

邱恩鹏(1999—),男,硕士研究生,主要研究方向为非定常空气动力学。

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1200805354176115200, tenantId=1146029695717560320, journalId=1146119989267898375, articleId=1200797898486182610, xref=2., ext=[AuthorCompanyExt(id=1200805354192892418, tenantId=1146029695717560320, journalId=1146119989267898375, articleId=1200797898486182610, companyId=1200805354176115200, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.College of Civil Aviation, Nanjing University of Aeronautics and Astronautics, Nanjing, 210016), AuthorCompanyExt(id=1200805354222252547, tenantId=1146029695717560320, journalId=1146119989267898375, articleId=1200797898486182610, companyId=1200805354176115200, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.南京航空航天大学民航学院,南京,210016)])]), Author(id=1200805355316965939, tenantId=1146029695717560320, journalId=1146119989267898375, articleId=1200797898486182610, 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=1200805355421823543, tenantId=1146029695717560320, journalId=1146119989267898375, articleId=1200797898486182610, authorId=1200805355316965939, language=EN, stringName=Zhen CHEN, firstName=Zhen, middleName=null, lastName=CHEN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.Beijing Institute of Space Long March Vehicle, Beijing, 100076, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1200805355627344442, tenantId=1146029695717560320, journalId=1146119989267898375, articleId=1200797898486182610, authorId=1200805355316965939, language=CN, stringName=陈臻, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.北京航天长征飞行器研究所,北京,100076, bio={"content":"

陈 臻(1996—),男,博士研究生,主要研究方向为飞行器气动设计。

"}, bioImg=null, bioContent=

陈 臻(1996—),男,博士研究生,主要研究方向为飞行器气动设计。

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1200805353983177202, tenantId=1146029695717560320, journalId=1146119989267898375, articleId=1200797898486182610, xref=1., ext=[AuthorCompanyExt(id=1200805353991565812, tenantId=1146029695717560320, journalId=1146119989267898375, articleId=1200797898486182610, companyId=1200805353983177202, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.Beijing Institute of Space Long March Vehicle, Beijing, 100076), AuthorCompanyExt(id=1200805354012537333, tenantId=1146029695717560320, journalId=1146119989267898375, articleId=1200797898486182610, companyId=1200805353983177202, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.北京航天长征飞行器研究所,北京,100076)])]), Author(id=1200805355786728002, tenantId=1146029695717560320, journalId=1146119989267898375, articleId=1200797898486182610, 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=1200805355874808388, tenantId=1146029695717560320, journalId=1146119989267898375, articleId=1200797898486182610, authorId=1200805355786728002, language=EN, stringName=Suozhu WANG, firstName=Suozhu, middleName=null, lastName=WANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.Beijing Institute of Space Long March Vehicle, Beijing, 100076, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1200805355979665992, tenantId=1146029695717560320, journalId=1146119989267898375, articleId=1200797898486182610, authorId=1200805355786728002, language=CN, stringName=王锁柱, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.北京航天长征飞行器研究所,北京,100076, bio={"content":"

王锁柱(1984—),男,博士研究生,高级工程师,主要研究方向为飞行器气动设计。

"}, bioImg=null, bioContent=

王锁柱(1984—),男,博士研究生,高级工程师,主要研究方向为飞行器气动设计。

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1200805353983177202, tenantId=1146029695717560320, journalId=1146119989267898375, articleId=1200797898486182610, xref=1., ext=[AuthorCompanyExt(id=1200805353991565812, tenantId=1146029695717560320, journalId=1146119989267898375, articleId=1200797898486182610, companyId=1200805353983177202, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.Beijing Institute of Space Long March Vehicle, Beijing, 100076), AuthorCompanyExt(id=1200805354012537333, tenantId=1146029695717560320, journalId=1146119989267898375, articleId=1200797898486182610, companyId=1200805353983177202, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.北京航天长征飞行器研究所,北京,100076)])])], keywords=[Keyword(id=1200805356210352720, tenantId=1146029695717560320, journalId=1146119989267898375, articleId=1200797898486182610, language=EN, orderNo=1, keyword=multi-source data fusion), Keyword(id=1200805356344570451, tenantId=1146029695717560320, journalId=1146119989267898375, articleId=1200797898486182610, language=EN, orderNo=2, keyword=Physics-Informed Neural Networks), Keyword(id=1200805356436845142, tenantId=1146029695717560320, journalId=1146119989267898375, articleId=1200797898486182610, language=EN, orderNo=3, keyword=aerodynamic modeling), Keyword(id=1200805356520731225, tenantId=1146029695717560320, journalId=1146119989267898375, articleId=1200797898486182610, language=CN, orderNo=1, keyword=多源数据融合), Keyword(id=1200805356629783133, tenantId=1146029695717560320, journalId=1146119989267898375, articleId=1200797898486182610, language=CN, orderNo=2, keyword=物理信息神经网络), Keyword(id=1200805356755612257, tenantId=1146029695717560320, journalId=1146119989267898375, articleId=1200797898486182610, language=CN, orderNo=3, keyword=气动力建模)], refs=[Reference(id=1200805360551457442, tenantId=1146029695717560320, journalId=1146119989267898375, articleId=1200797898486182610, doi=null, pmid=null, pmcid=null, year=2020, volume=33, issue=10, pageStart=2499, pageEnd=2509, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=CHEN S, GAO Z, ZHU X, journalName=Chinese Journal of Aeronautics, refType=null, unstructuredReference=CHEN S, GAO Z, ZHU X, et al. Unstable unsteady aerodynamic modeling based on least squares support vector machines with general excitation[J]. Chinese Journal of Aeronautics, 2020, 33(10): 2499-2509., articleTitle=Unstable unsteady aerodynamic modeling based on least squares support vector machines with general excitation, refAbstract=null), Reference(id=1200805360664703655, tenantId=1146029695717560320, journalId=1146119989267898375, articleId=1200797898486182610, doi=null, pmid=null, pmcid=null, year=2018, volume=39, issue=6, pageStart=84, pageEnd=95, url=null, language=null, rfNumber=[2], rfOrder=1, authorNames=郭林亮, 祝明红, 傅澔, journalName=航空学报, refType=null, unstructuredReference=郭林亮, 祝明红, 傅澔, 等. 水平风洞中开展飞机尾旋特性研究的理论分析[J]. 航空学报, 2018, 39(6): 84-95., articleTitle=水平风洞中开展飞机尾旋特性研究的理论分析, refAbstract=null), Reference(id=1200805360773755560, tenantId=1146029695717560320, journalId=1146119989267898375, articleId=1200797898486182610, doi=null, pmid=null, pmcid=null, year=2018, volume=39, issue=6, pageStart=84, pageEnd=95, url=null, language=null, rfNumber=[2], rfOrder=2, authorNames=GUO Linliang, ZHU Minghong, FU Hao, journalName=Acta Aeronauticaet Astronautica Sinica, refType=null, unstructuredReference=GUO Linliang, ZHU Minghong, FU Hao, et al. Theoretical analysis of research on aircraft spin characteristic in horizontal wind tun-nel[J]. Acta Aeronauticaet Astronautica Sinica, 2018, 39(6): 84-95., articleTitle=null, refAbstract=null), Reference(id=1200805360928944811, tenantId=1146029695717560320, journalId=1146119989267898375, articleId=1200797898486182610, doi=null, pmid=null, pmcid=null, year=1995, volume=32, issue=6, pageStart=1407, pageEnd=1409, url=null, language=null, rfNumber=[3], rfOrder=3, authorNames=FREMAUX C M, journalName=Journal of Aircraft, refType=null, unstructuredReference=FREMAUX C M. Estimation of the moment coefficients for dynamically scaled free-spinning wind tunnel model[J]. Journal of Aircraft, 1995, 32(6): 1407-1409., articleTitle=Estimation of the moment coefficients for dynamically scaled free-spinning wind tunnel model, refAbstract=null), Reference(id=1200805361046385328, tenantId=1146029695717560320, journalId=1146119989267898375, articleId=1200797898486182610, doi=null, pmid=null, pmcid=null, year=2003, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[4], rfOrder=4, authorNames=黄灵恩, 潘怡, journalName=null, refType=null, unstructuredReference=黄灵恩, 潘怡. 用逐步回归法辨识飞机模型尾旋时的气动力[C]. 烟台: 中国航空学会飞行力学与飞行试验专业委员会学术交流会, 2003., articleTitle=用逐步回归法辨识飞机模型尾旋时的气动力, refAbstract=null), Reference(id=1200805361151242930, tenantId=1146029695717560320, journalId=1146119989267898375, articleId=1200797898486182610, doi=null, pmid=null, pmcid=null, year=2003, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[4], rfOrder=5, authorNames=HUANG Ling'en, PAN Yi, journalName=null, refType=null, unstructuredReference=HUANG Ling'en, PAN Yi. The aerodynamic forces during the spin of an aircraft model are identified by the stepwise regression me-thod[C]. Yantai: Academic Exchange Conference of the Flight Mechanics and Flight Test Professional Committee of the Chinese Society of Aeronautics and Astronautics, 2003., articleTitle=null, refAbstract=null), Reference(id=1200805361247711922, tenantId=1146029695717560320, journalId=1146119989267898375, articleId=1200797898486182610, doi=null, pmid=null, pmcid=null, year=2016, volume=68, issue=4, pageStart=276, pageEnd=286, url=null, language=null, rfNumber=[5], rfOrder=6, authorNames=KUTTIERI R A, SINHA M, journalName=Journal of Aerospace Sciences and Technologies, refType=null, unstructuredReference=KUTTIERI R A, SINHA M. Neural partial differentiation for parameter estimation of flexible aircraft dynamics[J]. Journal of Aerospace Sciences and Technologies, 2016, 68(4): 276-286., articleTitle=Neural partial differentiation for parameter estimation of flexible aircraft dynamics, refAbstract=null), Reference(id=1200805361386123956, tenantId=1146029695717560320, journalId=1146119989267898375, articleId=1200797898486182610, doi=null, pmid=null, pmcid=null, year=2020, volume=92, issue=6, pageStart=895, pageEnd=907, url=null, language=null, rfNumber=[6], rfOrder=7, authorNames=VERMA H O, PEYADA N K, journalName=Aircraft Engineering and Aerospace Technology, refType=null, unstructuredReference=VERMA H O, PEYADA N K. Aircraft parameter estimation using ELM network[J]. Aircraft Engineering and Aerospace Technology, 2020, 92(6): 895-907., articleTitle=Aircraft parameter estimation using ELM network, refAbstract=null), Reference(id=1200805361461621429, tenantId=1146029695717560320, journalId=1146119989267898375, articleId=1200797898486182610, doi=null, pmid=null, pmcid=null, year=2024, volume=61, issue=1, pageStart=12, pageEnd=null, url=null, language=null, rfNumber=[7], rfOrder=8, authorNames=GRESHAM J L, SIMMONS B M, HOPWOOD J W, journalName=Journal of Aircraft, refType=null, unstructuredReference=GRESHAM J L, SIMMONS B M, HOPWOOD J W, et al. Spin aerodynamic modeling for a fixed-wing aircraft using flight data[J]. Journal of Aircraft, 2024, 61(1): 12., articleTitle=Spin aerodynamic modeling for a fixed-wing aircraft using flight data, refAbstract=null), Reference(id=1200805361633587898, tenantId=1146029695717560320, journalId=1146119989267898375, articleId=1200797898486182610, doi=null, pmid=null, pmcid=null, year=2014, volume=32, issue=6, pageStart=777, pageEnd=782, url=null, language=null, rfNumber=[8], rfOrder=9, authorNames=何开峰, 钱炜祺, 汪清, journalName=空气动力学学报, refType=null, unstructuredReference=何开峰, 钱炜祺, 汪清, 等. 数据融合技术在空气动力学研究中的应用[J]. 空气动力学学报, 2014, 32(6): 777-782., articleTitle=数据融合技术在空气动力学研究中的应用, refAbstract=null), Reference(id=1200805361797165757, tenantId=1146029695717560320, journalId=1146119989267898375, articleId=1200797898486182610, doi=null, pmid=null, pmcid=null, year=2014, volume=32, issue=6, pageStart=777, pageEnd=782, url=null, language=null, rfNumber=[8], rfOrder=10, authorNames=HE Kaifeng, QIAN Weiqi, WANG Qing, journalName=Acta Aerodynamica Sinica, refType=null, unstructuredReference=HE Kaifeng, QIAN Weiqi, WANG Qing, et al. Application of data fusion technique in aerodynamics studies[J]. Acta Aerodynamica Sinica, 2014, 32(6): 777-782., articleTitle=null, refAbstract=null), Reference(id=1200805362946405055, tenantId=1146029695717560320, journalId=1146119989267898375, articleId=1200797898486182610, doi=null, pmid=null, pmcid=null, year=2020, volume=50, issue=6, pageStart=124, pageEnd=128, url=null, language=null, rfNumber=[9], rfOrder=11, authorNames=李瑛, 颜廷龙, journalName=航空计算技术, refType=null, unstructuredReference=李瑛, 颜廷龙. 航空大数据的融合及挖掘技术综述[J]. 航空计算技术, 2020, 50(6): 124-128., articleTitle=航空大数据的融合及挖掘技术综述, refAbstract=null), Reference(id=1200805363160314563, tenantId=1146029695717560320, journalId=1146119989267898375, articleId=1200797898486182610, doi=null, pmid=null, pmcid=null, year=2020, volume=50, issue=6, pageStart=124, pageEnd=128, url=null, language=null, rfNumber=[9], rfOrder=12, authorNames=LI Ying, YAN Tinglong, journalName=Aeronautical Computing Technique, refType=null, unstructuredReference=LI Ying, YAN Tinglong. A survey of fusion and mining technology of aeronautical big data[J]. Aeronautical Computing Technique, 2020, 50(6): 124-128., articleTitle=null, refAbstract=null), Reference(id=1200805363286143684, tenantId=1146029695717560320, journalId=1146119989267898375, articleId=1200797898486182610, doi=null, pmid=null, pmcid=null, year=2022, volume=40, issue=4, pageStart=117, pageEnd=123, url=null, language=null, rfNumber=[10], rfOrder=13, authorNames=邓晨, 陈功, 王文正, journalName=空气动力学学报, refType=null, unstructuredReference=邓晨, 陈功, 王文正, 等. 基于不确定度和气动模型的气动数据融合算法[J]. 空气动力学学报, 2022, 40(4): 117-123., articleTitle=基于不确定度和气动模型的气动数据融合算法, refAbstract=null), Reference(id=1200805363382612678, tenantId=1146029695717560320, journalId=1146119989267898375, articleId=1200797898486182610, doi=null, pmid=null, pmcid=null, year=2022, volume=40, issue=4, pageStart=117, pageEnd=123, url=null, language=null, rfNumber=[10], rfOrder=14, authorNames=DENG Chen, CHEN Gong, WANG Wenzheng, journalName=Acta Aerodynamica Sinica, refType=null, unstructuredReference=DENG Chen, CHEN Gong, WANG Wenzheng, et al. Aerodynamic data fusion algorithms based on aerodynamic model and uncer-tainly[J]. Acta Aerodynamica Sinica, 2022, 40(4): 117-123., articleTitle=null, refAbstract=null), Reference(id=1200805363453915848, tenantId=1146029695717560320, journalId=1146119989267898375, articleId=1200797898486182610, doi=null, pmid=null, pmcid=null, year=2021, volume=42, issue=4, pageStart=26, pageEnd=71, url=null, language=null, rfNumber=[11], rfOrder=15, authorNames=张伟伟, 寇家庆, 刘溢浪, journalName=航空学报, refType=null, unstructuredReference=张伟伟, 寇家庆, 刘溢浪. 智能赋能流体力学展望[J]. 航空学报, 2021, 42(4): 26-71., articleTitle=智能赋能流体力学展望, refAbstract=null), Reference(id=1200805363579744971, tenantId=1146029695717560320, journalId=1146119989267898375, articleId=1200797898486182610, doi=null, pmid=null, pmcid=null, year=2021, volume=42, issue=4, pageStart=26, pageEnd=71, url=null, language=null, rfNumber=[11], rfOrder=16, authorNames=ZHANG Weiwei, KOU Jiaqing, LIU Yilang, journalName=Acta Aeronauticaet Astronautica Sinica, refType=null, unstructuredReference=ZHANG Weiwei, KOU Jiaqing, LIU Yilang. Prospect of artificial intelligence empowered fluid mechanics[J]. Acta Aeronauticaet Astronautica Sinica, 2021, 42(4): 26-71., articleTitle=null, refAbstract=null), Reference(id=1200805363684602574, tenantId=1146029695717560320, journalId=1146119989267898375, articleId=1200797898486182610, doi=null, pmid=null, pmcid=null, year=2019, volume=null, issue=76, pageStart=832, pageEnd=855, url=null, language=null, rfNumber=[12], rfOrder=17, authorNames=KOU J, ZHANG W, journalName=Applied Mathema-tical Modelling, refType=null, unstructuredReference=KOU J, ZHANG W. Multi-fidelity modeling framework for nonlinear unsteady aerodynamics of airfoils[J]. Applied Mathema-tical Modelling, 2019(76): 832-855., articleTitle=Multi-fidelity modeling framework for nonlinear unsteady aerodynamics of airfoils, refAbstract=null), Reference(id=1200805363839791821, tenantId=1146029695717560320, journalId=1146119989267898375, articleId=1200797898486182610, doi=null, pmid=null, pmcid=null, year=2023, volume=41, issue=2, pageStart=12, pageEnd=20, url=null, language=null, rfNumber=[13], rfOrder=18, authorNames=王旭, 宁晨伽, 王文正, journalName=空气动力学学报, refType=null, unstructuredReference=王旭, 宁晨伽, 王文正, 等. 面向飞行试验的多源气动数据智能融合方法[J]. 空气动力学学报, 2023, 41(2): 12-20., articleTitle=面向飞行试验的多源气动数据智能融合方法, refAbstract=null), Reference(id=1200805363953038033, tenantId=1146029695717560320, journalId=1146119989267898375, articleId=1200797898486182610, doi=null, pmid=null, pmcid=null, year=2023, volume=41, issue=2, pageStart=12, pageEnd=20, url=null, language=null, rfNumber=[13], rfOrder=19, authorNames=WANG Xu, NING Chenjia, WANG Wenzheng, journalName=Acta Aerodynamica Sinica, refType=null, unstructuredReference=WANG Xu, NING Chenjia, WANG Wenzheng, et al. Intelligent fusion method of multi-source aerodynamic data for flight tests[J]. Acta Aerodynamica Sinica, 2023, 41(2): 12-20., articleTitle=null, refAbstract=null), Reference(id=1200805364049507024, tenantId=1146029695717560320, journalId=1146119989267898375, articleId=1200797898486182610, doi=null, pmid=null, pmcid=null, year=2020, volume=401, issue=15, pageStart=109020, pageEnd=null, url=null, language=null, rfNumber=[14], rfOrder=20, authorNames=MENG X, CARNIADAKIS G E, journalName=Journal of Computational Physics, refType=null, unstructuredReference=MENG X, CARNIADAKIS G E. A composite neural network that learns from multi-fidelity data: application to function approxi-mation and inverse PDE problems[J]. Journal of Computational Physics, 2020, 401(15): 109020., articleTitle=A composite neural network that learns from multi-fidelity data: application to function approxi-mation and inverse PDE problems, refAbstract=null), Reference(id=1200805364125004497, tenantId=1146029695717560320, journalId=1146119989267898375, articleId=1200797898486182610, doi=null, pmid=null, pmcid=null, year=2022, volume=60, issue=7, pageStart=4413, pageEnd=4427, url=null, language=null, rfNumber=[15], rfOrder=21, authorNames=LI K, KOU J Q, ZHANG W W, journalName=AIAA Journal, refType=null, unstructuredReference=LI K, KOU J Q, ZHANG W W. Deep learning for multifidelity aerodynamic distribution modeling from experimental and simula-tion data[J]. AIAA Journal, 2022, 60(7): 4413-4427., articleTitle=Deep learning for multifidelity aerodynamic distribution modeling from experimental and simula-tion data, refAbstract=null), Reference(id=1200805364234056403, tenantId=1146029695717560320, journalId=1146119989267898375, articleId=1200797898486182610, doi=null, pmid=null, pmcid=null, year=2023, volume=401, issue=3, pageStart=635, pageEnd=638, url=null, language=null, rfNumber=[16], rfOrder=22, authorNames=颜廷龙, 李瑛, 王凤芹, journalName=计算机与数字工程, refType=null, unstructuredReference=颜廷龙, 李瑛, 王凤芹. 基于改进支持度的飞行数据记忆融合滤波算法[J]. 计算机与数字工程, 2023, 401(3): 635-638., articleTitle=基于改进支持度的飞行数据记忆融合滤波算法, refAbstract=null), Reference(id=1200805364406022870, tenantId=1146029695717560320, journalId=1146119989267898375, articleId=1200797898486182610, doi=null, pmid=null, pmcid=null, year=2023, volume=401, issue=3, pageStart=635, pageEnd=638, url=null, language=null, rfNumber=[16], rfOrder=23, authorNames=YAN Tinglong, LI Ying, WANG Fengqin, journalName=Computer & Digital Engineering, refType=null, unstructuredReference=YAN Tinglong, LI Ying, WANG Fengqin. Flight data memory fusion filtering algorithm based on improved support[J]. Computer & Digital Engineering, 2023, 401(3): 635-638., articleTitle=null, refAbstract=null), Reference(id=1200805364527657688, tenantId=1146029695717560320, journalId=1146119989267898375, articleId=1200797898486182610, doi=null, pmid=null, pmcid=null, year=2021, volume=3, issue=6, pageStart=422, pageEnd=440, url=null, language=null, rfNumber=[17], rfOrder=24, authorNames=KARNIADAKIS G E, KEVREKIDIS I G, LU L, journalName=Nature Reviews Physics, refType=null, unstructuredReference=KARNIADAKIS G E, KEVREKIDIS I G, LU L, et al. Physics-informed machine learning[J]. Nature Reviews Physics, 2021, 3(6): 422-440., articleTitle=Physics-informed machine learning, refAbstract=null), Reference(id=1200805364611543771, tenantId=1146029695717560320, journalId=1146119989267898375, articleId=1200797898486182610, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=360, pageStart=112789, pageEnd=null, url=null, language=null, rfNumber=[18], rfOrder=25, authorNames=MAO Z P, JAGTAP A D, KARNIADAKIS G E, journalName=Computer Methods in Applied Mechanics and Engineering, refType=null, unstructuredReference=MAO Z P, JAGTAP A D, KARNIADAKIS G E. Physics-informed neural networks for high-speed flows[J]. Computer Methods in Applied Mechanics and Engineering, 2020(360): 112789., articleTitle=Physics-informed neural networks for high-speed flows, refAbstract=null), Reference(id=1200805364716401373, tenantId=1146029695717560320, journalId=1146119989267898375, articleId=1200797898486182610, doi=null, pmid=null, pmcid=null, year=2021, volume=null, issue=426, pageStart=109951, pageEnd=null, url=null, language=null, rfNumber=[19], rfOrder=26, authorNames=JIN X W, CAI S Z, LI H, journalName=Journal of Computational Physics, refType=null, unstructuredReference=JIN X W, CAI S Z, LI H, et al. NSFnets (Navier-Stokes flow nets): physics-informed neural networks for the incompressible Navier-Stokes equations[J]. Journal of Computational Physics, 2021(426): 109951., articleTitle=NSFnets (Navier-Stokes flow nets): physics-informed neural networks for the incompressible Navier-Stokes equations, refAbstract=null), Reference(id=1200805364825453280, tenantId=1146029695717560320, journalId=1146119989267898375, articleId=1200797898486182610, doi=null, pmid=null, pmcid=null, year=2023, volume=49, issue=15, pageStart=2669, pageEnd=2678, url=null, language=null, rfNumber=[20], rfOrder=27, authorNames=蔺佳哲, 周岭, 武频, journalName=北京航空航天大学学报, refType=null, unstructuredReference=蔺佳哲, 周岭, 武频, 等. 基于PINN 模型的导弹气动特性快速预测技术[J]. 北京航空航天大学学报, 2023, 49(15): 2669-2678., articleTitle=基于PINN 模型的导弹气动特性快速预测技术, refAbstract=null), Reference(id=1200805364942893794, tenantId=1146029695717560320, journalId=1146119989267898375, articleId=1200797898486182610, doi=null, pmid=null, pmcid=null, year=2023, volume=49, issue=15, pageStart=2669, pageEnd=2678, url=null, language=null, rfNumber=[20], rfOrder=28, authorNames=LIN Jiazhe, ZHOU Ling, WU Pin, journalName=Journal of Beijing University of Aeronautics and Astronautics, refType=null, unstructuredReference=LIN JiazheZHOU Ling, WU Pin,et al. Rapid prediction technology of missile aerodynamic characteristics based on PINN model[J]. Journal of Beijing University of Aeronautics and Astronautics, 2023, 49(15): 2669-2678., articleTitle=null, refAbstract=null), Reference(id=1200805365110665957, tenantId=1146029695717560320, journalId=1146119989267898375, articleId=1200797898486182610, doi=null, pmid=null, pmcid=null, year=2023, volume=41, issue=9, pageStart=30, pageEnd=37, url=null, language=null, rfNumber=[21], rfOrder=29, authorNames=付军泉, 钟伯文, 钟运琴, journalName=空气动力学学报, refType=null, unstructuredReference=付军泉, 钟伯文, 钟运琴, 等. 基于物理信息神经网络的飞机气动参数辨识方法[J]. 空气动力学学报, 2023, 41(9): 30-37., articleTitle=基于物理信息神经网络的飞机气动参数辨识方法, refAbstract=null), Reference(id=1200805365265855208, tenantId=1146029695717560320, journalId=1146119989267898375, articleId=1200797898486182610, doi=null, pmid=null, pmcid=null, year=2023, volume=41, issue=9, pageStart=30, pageEnd=37, url=null, language=null, rfNumber=[21], rfOrder=30, authorNames=FU Junquan, ZHONG Bowen, ZHONG Yunqin, journalName=Acta Aerodynamica Sinica, refType=null, unstructuredReference=FU Junquan, ZHONG Bowen, ZHONG Yunqin, et al. A physics informed neural network based method for aircraft aerodynamic parameter identification[J]. Acta Aerodynamica Sinica, 2023, 41(9): 30-37., articleTitle=null, refAbstract=null), Reference(id=1200805365358129898, tenantId=1146029695717560320, journalId=1146119989267898375, articleId=1200797898486182610, doi=null, pmid=null, pmcid=null, year=2024, volume=62, issue=11, pageStart=13, pageEnd=null, url=null, language=null, rfNumber=[22], rfOrder=31, authorNames=NATHANIEL E M, PIYUSH M M, WADE W H, journalName=AIAA Journal, refType=null, unstructuredReference=NATHANIEL E M, PIYUSH M M, WADE W H. Flight dynamic uncertainty quantification modeling using physics-informed neural networks[J]. AIAA Journal, 2024, 62(11): 13., articleTitle=Flight dynamic uncertainty quantification modeling using physics-informed neural networks, refAbstract=null), Reference(id=1200805365509124844, tenantId=1146029695717560320, journalId=1146119989267898375, articleId=1200797898486182610, doi=null, pmid=null, pmcid=null, year=2020, volume=41, issue=6, pageStart=193, pageEnd=210, url=null, language=null, rfNumber=[23], rfOrder=32, authorNames=沈霖, 黄达, 吴根兴, journalName=航空学报, refType=null, unstructuredReference=沈霖, 黄达, 吴根兴, 等. 战斗机大迎角非定常气动力建模[J]. 航空学报, 2020, 41(6): 193-210., articleTitle=战斗机大迎角非定常气动力建模, refAbstract=null), Reference(id=1200805365613982447, tenantId=1146029695717560320, journalId=1146119989267898375, articleId=1200797898486182610, doi=null, pmid=null, pmcid=null, year=2020, volume=41, issue=6, pageStart=193, pageEnd=210, url=null, language=null, rfNumber=[23], rfOrder=33, authorNames=SHEN Lin, HUANG Da, WU Genxing, journalName=Acta Aeronauticaet Astronautica Sinica, refType=null, unstructuredReference=SHEN Lin, HUANG Da, WU Genxing, et al. Unsteady aerodynamic modeling for fighter configuration at high angles of attack[J]. Acta Aeronauticaet Astronautica Sinica, 2020, 41(6): 193-210., articleTitle=null, refAbstract=null)], funds=[Fund(id=1200805360253661851, tenantId=1146029695717560320, journalId=1146119989267898375, articleId=1200797898486182610, awardId=BK20220873, language=CN, fundingSource=江苏省基础研究计划自然科学基金青年基金项目(BK20220873), fundOrder=null, country=null), Fund(id=1200805360329159325, tenantId=1146029695717560320, journalId=1146119989267898375, articleId=1200797898486182610, awardId=CALT2023-13, language=CN, fundingSource=航天一院高校联合创新基金项目(CALT2023-13), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1200805353983177202, tenantId=1146029695717560320, journalId=1146119989267898375, articleId=1200797898486182610, xref=1., ext=[AuthorCompanyExt(id=1200805353991565812, tenantId=1146029695717560320, journalId=1146119989267898375, articleId=1200797898486182610, companyId=1200805353983177202, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.Beijing Institute of Space Long March Vehicle, Beijing, 100076), AuthorCompanyExt(id=1200805354012537333, tenantId=1146029695717560320, journalId=1146119989267898375, articleId=1200797898486182610, companyId=1200805353983177202, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.北京航天长征飞行器研究所,北京,100076)]), AuthorCompany(id=1200805354176115200, tenantId=1146029695717560320, journalId=1146119989267898375, articleId=1200797898486182610, xref=2., ext=[AuthorCompanyExt(id=1200805354192892418, tenantId=1146029695717560320, journalId=1146119989267898375, articleId=1200797898486182610, companyId=1200805354176115200, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.College of Civil Aviation, Nanjing University of Aeronautics and Astronautics, Nanjing, 210016), AuthorCompanyExt(id=1200805354222252547, tenantId=1146029695717560320, journalId=1146119989267898375, articleId=1200797898486182610, companyId=1200805354176115200, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.南京航空航天大学民航学院,南京,210016)])], figs=[ArticleFig(id=1200805356998881898, tenantId=1146029695717560320, journalId=1146119989267898375, articleId=1200797898486182610, language=EN, label=Fig.1, caption=Flowchart of PINN, figureFileSmall=nclhXXvZ/vgShLmlHC0jgg==, figureFileBig=/C1WjqxFMBAZ9HrZJDKufQ==, tableContent=null), ArticleFig(id=1200805357200208491, tenantId=1146029695717560320, journalId=1146119989267898375, articleId=1200797898486182610, language=CN, label=图1, caption=PINN训练流程, figureFileSmall=nclhXXvZ/vgShLmlHC0jgg==, figureFileBig=/C1WjqxFMBAZ9HrZJDKufQ==, tableContent=null), ArticleFig(id=1200805357330231920, tenantId=1146029695717560320, journalId=1146119989267898375, articleId=1200797898486182610, language=EN, label=Fig.2, caption=Flight trajectory constructed by flight simulations, figureFileSmall=whrgKio9wu1va680E4zW0g==, figureFileBig=HbHJ8Zqxje1KmLbhgKnxCw==, tableContent=null), ArticleFig(id=1200805358466888307, tenantId=1146029695717560320, journalId=1146119989267898375, articleId=1200797898486182610, language=CN, label=图2, caption=仿真构造的飞行轨迹, figureFileSmall=whrgKio9wu1va680E4zW0g==, figureFileBig=HbHJ8Zqxje1KmLbhgKnxCw==, tableContent=null), ArticleFig(id=1200805358575940213, tenantId=1146029695717560320, journalId=1146119989267898375, articleId=1200797898486182610, language=EN, label=Fig.3, caption=Multipoint differential angular acceleration, figureFileSmall=vX9rhNK81QTl8S9yx88JyA==, figureFileBig=12HHA3MkDGAF9VNnvN/jPQ==, tableContent=null), ArticleFig(id=1200805358726935163, tenantId=1146029695717560320, journalId=1146119989267898375, articleId=1200797898486182610, language=CN, label=图3, caption=多点差分法求角加速度精度验证, figureFileSmall=vX9rhNK81QTl8S9yx88JyA==, figureFileBig=12HHA3MkDGAF9VNnvN/jPQ==, tableContent=null), ArticleFig(id=1200805358848569983, tenantId=1146029695717560320, journalId=1146119989267898375, articleId=1200797898486182610, language=EN, label=Fig.4, caption=Comparison between PINN and RF for trajectory 11, figureFileSmall=ud6KhyUkUyQDggqNWiIa2w==, figureFileBig=FNyVxUUOtInGvgWw+M5uHg==, tableContent=null), ArticleFig(id=1200805358982787713, tenantId=1146029695717560320, journalId=1146119989267898375, articleId=1200797898486182610, language=CN, label=图4, caption=PINN与随机森林计算轨迹11的气动力对比, figureFileSmall=ud6KhyUkUyQDggqNWiIa2w==, figureFileBig=FNyVxUUOtInGvgWw+M5uHg==, tableContent=null), ArticleFig(id=1200805359091839619, tenantId=1146029695717560320, journalId=1146119989267898375, articleId=1200797898486182610, language=EN, label=Fig.5, caption=α-β curves of sample data, figureFileSmall=lz1EFqXf3BgAoO1HGKfJ+A==, figureFileBig=K4GYL77LCohs81TodngPrQ==, tableContent=null), ArticleFig(id=1200805359255417479, tenantId=1146029695717560320, journalId=1146119989267898375, articleId=1200797898486182610, language=CN, label=图5, caption=样本数据迎角-侧滑角覆盖范围, figureFileSmall=lz1EFqXf3BgAoO1HGKfJ+A==, figureFileBig=K4GYL77LCohs81TodngPrQ==, tableContent=null), ArticleFig(id=1200805359360275079, tenantId=1146029695717560320, journalId=1146119989267898375, articleId=1200797898486182610, language=EN, label=Fig.6, caption=Comparison of static prediction between PINN and RF, figureFileSmall=HGSl8GoOyTpoPKiYwCZr8A==, figureFileBig=xJ19ZlruvDhIb5tdze/gkQ==, tableContent=null), ArticleFig(id=1200805359469326987, tenantId=1146029695717560320, journalId=1146119989267898375, articleId=1200797898486182610, language=CN, label=图6, caption=PINN与随机森林模型计算稳态气动力对比, figureFileSmall=HGSl8GoOyTpoPKiYwCZr8A==, figureFileBig=xJ19ZlruvDhIb5tdze/gkQ==, tableContent=null), ArticleFig(id=1200805359599350414, tenantId=1146029695717560320, journalId=1146119989267898375, articleId=1200797898486182610, language=EN, label=Fig.7, caption=Validation motion of single-degree of freedom, figureFileSmall=AzJJXGAn7AgND5k1X6Nk2A==, figureFileBig=8GyFyxw3a6BKemAMF+b4UA==, tableContent=null), ArticleFig(id=1200805359754539666, tenantId=1146029695717560320, journalId=1146119989267898375, articleId=1200797898486182610, language=CN, label=图7, caption=设计的单自由度验证运动, figureFileSmall=AzJJXGAn7AgND5k1X6Nk2A==, figureFileBig=8GyFyxw3a6BKemAMF+b4UA==, tableContent=null), ArticleFig(id=1200805359884563093, tenantId=1146029695717560320, journalId=1146119989267898375, articleId=1200797898486182610, language=EN, label=Fig.8, caption=Comparison of aerodynamic loads predicted by PINN and RF in pitch oscillation, figureFileSmall=q3xcrVMWsDZutRtMRoANnA==, figureFileBig=Vf0cowiVuC7PSgQ92YrMog==, tableContent=null), ArticleFig(id=1200805360043946647, tenantId=1146029695717560320, journalId=1146119989267898375, articleId=1200797898486182610, language=CN, label=图8, caption=PINN与随机森林模型计算俯仰运动中的气动力对比, figureFileSmall=q3xcrVMWsDZutRtMRoANnA==, figureFileBig=Vf0cowiVuC7PSgQ92YrMog==, tableContent=null)], attaches=null, journal=Journal(id=1146118917132496903, delFlag=0, nameCn=导弹与航天运载技术(中英文), nameEn=Missiles and Space Vehicles, nameHistory1=null, nameHistory2=null, issn=2097-1974, eissn=, cn=10-1807/V, coden=null, periodic=1, language=CN, oaType=否, 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=DdfacUcWE1ibGHaCsbhL8w==, journalPrice=null, startedYear=null, abbrevIsoEn=Miss Space Veh, journalRemark=null, publicationField=null, createdTime=null, updatedTime=1753780023753, createdBy=null, updatedBy=13701087609, firstLetterCn=M, firstLetterEn=M, subjectCode=Engineering, subjectName=工程, subjectCodeEn=Engineering, subjectNameEn=null, picCn=DdfacUcWE1ibGHaCsbhL8w==, picEn=jBog3LY3UHfAAYfYEqIBHg==, jcr=null, cjcr=null, exts=[JournalExt(id=1157000535829205111, language=CN, name=导弹与航天运载技术(中英文), 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=, createdTime=1753780023772, updatedTime=1753780023772, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=null, submissionAuthorUrl=https://journal.ids.fzyun.cn/auth/realms/journal/protocol/openid-connect/auth?client_id=journal-ddht-author&redirect_uri=https%3A%2F%2Fddht.portal.founderss.cn%2Foauth%2Fcallback&response_type=code&scope=phone+openid+email+profile&state=fefa73ea-30bb-4b68, submissionEditorUrl=https://journal.ids.fzyun.cn/auth/realms/journal/protocol/openid-connect/auth?client_id=journal-ddht-author&redirect_uri=https%3A%2F%2Fddht.portal.founderss.cn%2Foauth%2Fcallback&response_type=code&scope=phone+openid+email+profile&state=fefa73ea-30bb-4b68, submissionReviewUrl=https://journal.ids.fzyun.cn/auth/realms/journal/protocol/openid-connect/auth?client_id=journal-ddht-author&redirect_uri=https%3A%2F%2Fddht.portal.founderss.cn%2Foauth%2Fcallback&response_type=code&scope=phone+openid+email+profile&state=fefa73ea-30bb-4b68, submissionCeEditorUrl=https://journal.ids.fzyun.cn/auth/realms/journal/protocol/openid-connect/auth?client_id=journal-ddht-author&redirect_uri=https%3A%2F%2Fddht.portal.founderss.cn%2Foauth%2Fcallback&response_type=code&scope=phone+openid+email+profile&state=fefa73ea-30bb-4b68, submissionAeEditorUrl=https://journal.ids.fzyun.cn/auth/realms/journal/protocol/openid-connect/auth?client_id=journal-ddht-author&redirect_uri=https%3A%2F%2Fddht.portal.founderss.cn%2Foauth%2Fcallback&response_type=code&scope=phone+openid+email+profile&state=fefa73ea-30bb-4b68, option={"copyright":""}), JournalExt(id=1157000535871148152, language=EN, name=Missiles and Space Vehicles, 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=, createdTime=1753780023782, updatedTime=1753780023782, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=null, submissionAuthorUrl=https://journal.ids.fzyun.cn/auth/realms/journal/protocol/openid-connect/auth?client_id=journal-ddht-author&redirect_uri=https%3A%2F%2Fddht.portal.founderss.cn%2Foauth%2Fcallback&response_type=code&scope=phone+openid+email+profile&state=fefa73ea-30bb-4b68, submissionEditorUrl=, submissionReviewUrl=, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1146119989267898375, websiteList=[Website(id=1148243202378817956, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146119989267898375, 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/ddyht/CN, language=CN, createTime=1751692112774, createBy=18614031015, updateTime=1753519037132, updateBy=18614031015, name=导弹与航天运载技术-中文站点, tplId=1146099689490845704, title=导弹与航天运载技术(中英文), delFlag=0, indexPage=/home, props=[WebsiteProps(id=1148620442723704855, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202378817956, code=articleTextType, value=kx, createTime=1751782053881, updateTime=1751782053881, creator=18614031015, updator=18614031015), WebsiteProps(id=1148620442694344724, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202378817956, code=banner, value=null, createTime=1751782053874, updateTime=1751782053874, creator=18614031015, updator=18614031015), WebsiteProps(id=1148620442677567507, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202378817956, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=gfUyzanfTuxQ2yc+L/MeWA==, createTime=1751782053870, updateTime=1751782053870, creator=18614031015, updator=18614031015), WebsiteProps(id=1148620442711121942, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202378817956, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1751782053878, updateTime=1751782053878, creator=18614031015, updator=18614031015), WebsiteProps(id=1148620442706927637, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202378817956, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1751782053877, updateTime=1751782053877, creator=18614031015, updator=18614031015)]), Website(id=1155906039850618895, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146119989267898375, 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/ddyht/EN, language=EN, createTime=1753519075604, createBy=18614031015, updateTime=1753519075604, updateBy=18614031015, name=导弹与航天运载技术-英文站点, tplId=1146101810881728533, title=Missiles and Space Vehicles, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1155907112585777347, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155906039850618895, code=articleTextType, value=kx, createTime=1753519331356, updateTime=1753519331356, creator=18614031015, updator=18614031015), WebsiteProps(id=1155907112556417216, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155906039850618895, code=banner, value=null, createTime=1753519331349, updateTime=1753519331349, creator=18614031015, updator=18614031015), WebsiteProps(id=1155907112552222911, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155906039850618895, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=gfUyzanfTuxQ2yc+L/MeWA==, createTime=1753519331348, updateTime=1753519331348, creator=18614031015, updator=18614031015), WebsiteProps(id=1155907112577388738, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155906039850618895, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1753519331354, updateTime=1753519331354, creator=18614031015, updator=18614031015), WebsiteProps(id=1155907112564805825, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155906039850618895, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1753519331351, updateTime=1753519331351, creator=18614031015, updator=18614031015)])], journalTitle=导弹与航天运载技术(中英文), weixinUrl=null, journalUrl=null, iacademicId=null, status=0, seqNo=null, journalTitleEn=Missiles and Space Vehicles, journalPhotoCn=DdfacUcWE1ibGHaCsbhL8w==, journalPhotoEn=jBog3LY3UHfAAYfYEqIBHg==, journalFirstLetter=M, 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/ddyht/CN/10.7654/j.issn.2097-1974.20250510, detailUrlEn=https://castjournals.cast.org.cn/joweb/ddyht/EN/10.7654/j.issn.2097-1974.20250510, pdfUrlCn=https://castjournals.cast.org.cn/joweb/ddyht/CN/PDF/10.7654/j.issn.2097-1974.20250510, pdfUrlEn=https://castjournals.cast.org.cn/joweb/ddyht/EN/PDF/10.7654/j.issn.2097-1974.20250510, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于PINN的多源气动数据融合建模方法
收藏切换
PDF下载
杨依峰 1 , 沈霖 2 , 邱恩鹏 2 , 陈臻 1 , 王锁柱 1
导弹与航天运载技术(中英文) | 气动参数辨识及应用研究 2025,48(5): 73-81
收起
收藏切换
导弹与航天运载技术(中英文) | 气动参数辨识及应用研究 2025, 48(5): 73-81
基于PINN的多源气动数据融合建模方法
全屏
杨依峰1, 沈霖2, 邱恩鹏2, 陈臻1, 王锁柱1
作者信息
  • 1.北京航天长征飞行器研究所,北京,100076
  • 2.南京航空航天大学民航学院,南京,210016
  • 杨依峰(1990—),男,高级工程师,主要研究方向为飞行器气动设计。

    沈 霖(1987—),男,博士,讲师,主要研究方向为非定常空气动力学。

    邱恩鹏(1999—),男,硕士研究生,主要研究方向为非定常空气动力学。

    陈 臻(1996—),男,博士研究生,主要研究方向为飞行器气动设计。

    王锁柱(1984—),男,博士研究生,高级工程师,主要研究方向为飞行器气动设计。

Multi-source Aerodynamic Data Fusion Modeling Based on PINN
Yifeng YANG1, Lin SHEN2, Enpeng QIU2, Zhen CHEN1, Suozhu WANG1
Affiliations
  • 1.Beijing Institute of Space Long March Vehicle, Beijing, 100076
  • 2.College of Civil Aviation, Nanjing University of Aeronautics and Astronautics, Nanjing, 210016
出版时间: 2025-10-25 doi: 10.7654/j.issn.2097-1974.20250510
文章导航
收藏切换

在飞行器设计过程中,建立准确的空气动力模型对分析飞行器气动特性、设计可靠的飞行控制系统具有重要意义。通过智能算法对地面风洞试验数据、飞行试验数据等不同来源的气动数据进行多源数据融合是目前较为热门的非定常气动力建模方法。但传统融合算法存在对飞行数据来源要求高、模型泛化能力弱等不足。基于物理信息神经网络原理,提出了一种改进的静态风洞试验数据与飞行数据智能融合建模方法。通过对传统PINN反向构建物理损失约束,使其具备对多段离散飞行数据进行特征提取的能力。通过在神经网络输入和损失函数中加入稳态气动数据构造残差估计,实现了天地气动数据差异的有效修正。对不同运动形式的气动特性进行预测验证,表明该方法不仅具有较高的气动力预测精度,还具有十分良好的泛化能力。

多源数据融合  /  物理信息神经网络  /  气动力建模

Establishing an accurate aerodynamic model is of great significance for analyzing the aerodynamic characteristics of aircraft and designing reliable flight control systems during the aircraft design process. Multi-source data fusion of aerodynamic data from different sources, such as wind tunnel tests and flight tests, is currently a popular method for unsteady aerodynamic modeling by intelligent algorithms. However, traditional fusion algorithms have shortcomings such as high requirements for flight data sources and weak generalization capabilities. Thus an improved intelligent modeling method based on Physics-Informed Neural Networks (PINNs) is proposed to integrate static wind tunnel test data and flight data. Compared to traditional PINNs, the physical loss constraints in improved PINN are reversely constructed to enable feature extraction from different and discrete flight data. The static wind tunnel data are incorporated into both the input and loss function of neural network to construct residual estimates. So the differences between ground and flight aerodynamic data are effectively corrected. The predictive aerodynamic characteristics for different motion forms demonstrate that the improved PINN not only has high aerodynamic prediction accuracy but also exhibits excellent generalization capabilities.

multi-source data fusion  /  Physics-Informed Neural Networks  /  aerodynamic modeling
杨依峰, 沈霖, 邱恩鹏, 陈臻, 王锁柱. 基于PINN的多源气动数据融合建模方法. 导弹与航天运载技术(中英文), 2025 , 48 (5) : 73 -81 . DOI: 10.7654/j.issn.2097-1974.20250510
Yifeng YANG, Lin SHEN, Enpeng QIU, Zhen CHEN, Suozhu WANG. Multi-source Aerodynamic Data Fusion Modeling Based on PINN[J]. Missiles and Space Vehicles, 2025 , 48 (5) : 73 -81 . DOI: 10.7654/j.issn.2097-1974.20250510
飞行器非定常动态气动力精确建模是空气动力学、飞行力学领域尚未解决的一大难题1。传统的飞行器气动力模型一般通过数值模拟或风洞试验获得的气动数据建立。数值模拟方法由于N-S方程离散误差、湍流模型误差等原因,很难对飞行器复杂运动过程的流场进行精确求解。而风洞试验由于存在支架干扰、洞壁干扰等影响因素,获得的气动数据与飞机真实环境下的气动力也存在一定差异。因此,近年来国内外不少研究机构开始探索从风洞虚拟飞、模型自由飞试验和真实飞行数据中进行气动参数辨识的相关工作。如郭林亮等2利用三自由度虚拟飞行装置在水平风洞中开展了尾旋模拟并进行了气动力模型的辨识,将其用于飞行仿真,结果与立式风洞试验较为吻合。Fremaux3、黄灵恩等4分别尝试了通过模型自由飞试验进行气动参数辨识的相关研究。此外,Kuttieri等5进行了通过前馈神经网络对飞行数据进行辨识得到动导数和操纵导数的研究。Verma等6研究了使用极限学习机从试飞数据中辨识气动导数的方法。但Gresham等7的研究显示,从不同运动形式的试飞数据辨识得到的气动力模型参数结构和形式可能完全不同,如果强制固定气动力模型结构形式,从一次试飞数据中辨识得到的气动参数对其他类型飞行数据的预测精度极其有限。
为了提高从飞行数据中辨识得到的气动力模型的泛化能力,实现对任意运动状态下气动力的精确预测,学界尝试将地面数据与飞行数据融合,将地面数据作为防止过拟合的约束,将飞行数据作为提高预测精度的基准,以建立较为准确的非定常气动力模型。经典的如加权平均法8、卡尔曼滤波法9、Kriging模型10等。这类方法利用明确的代数算式对不同来源气动数据进行有效融合,原理简单清晰,但是往往难以满足高维、非线性、复杂数据的建模需求。相对而言,人工智能技术可以不依赖物理机制和先验模型实现高维度的非线性精准映射,因此也被认为是解决多源数据融合难题的有效手段11。如Kou等12采用多核神经网络进行了风洞试验数据与CFD计算结果的变精度融合建模方法研究,实现了模型将低精度欧拉结果对于N-S方程数值结果的逼近。王旭等13采用数据挖掘的随机森林方法实现了试飞数据复杂输入参数的特征分析与排序,实现了低精度数值计算结果与高保真度试飞试验数据的有效融合。Meng等14和Li等15分别使用不同结构的神经网络进行了多源数据融合研究,建立了设计空间内高低精度数据的映射关系,提升了模型的泛化能力。颜廷龙等16提出了一种基于改进支持度的记忆融合滤波算法,有效提高了飞行试验数据的稳定性,为多源数据融合技术提供了信源保证。
近年来,随着人工智能技术的不断发展,人们不再满足于传统神经网络纯数据驱动的黑箱形式,基于物理信息神经网络(Physics Informed Neural Network,PINN)的模型开始被各个领域关注。PINN模型最早被用来求解偏微分方程17,其本质上是在神经网络的损失函数中引入物理约束,使训练得到的神经网络预测结果能满足特定的物理规律。在空气动力学领域,PINN被用来求解欧拉方程18、N-S方程19以及进行导弹气动外形特征快速评估20等。此外,付军泉等21将飞机运动微分方程组引入PINN模型损失函数,从飞行数据中辨识得到了气动导数。Nathaniel等22也进行了类似工作,并对辨识得到的气动力模型进行了不确定度的量化。这些PINN在气动参数辨识中的应用都是通过将PINN网络输出的气动力代入飞机运动方程,通过求解运动微分方程组,获得下一时刻点的飞行状态变量,通过与飞行数据共同构造损失函数,使神经网络输出计算的状态参数不断逼近飞行数据。这就要求样本数据必须是时间连贯的,因此目前的这些相关研究都是从一段连续飞行的数据中进行参数辨识。这样一来,获得的气动力模型的泛化能力很难保证。此外,供辨识使用的采样点还必须具有足够的密度,以保证微分方程组的求解精度。
本文在经典PINN模型的基础上,对模型输入和损失函数进行了重新构建。改进后的PINN模型有效实现了地面静态风洞试验数据和飞行数据的智能融合,可以广泛地将不同速域、不同飞行状态、不同试验车次的飞行数据纳入训练样本进行关键特征提取,使训练得到的神经网络具备较高的非定常气动力预测精度,同时具有良好的泛化能力,可以为工程实践提供准确的参考。
传统PINN模型预测气动力后经飞机运动方程采用龙格-库塔法获得下一时间步长的飞行参数,并与试飞经过进行比较,只能使用一段连续的飞行数据作为样本,本项目对PINN网络添加物理约束构造损失函数的过程进行了改进,通过将飞行数据中的飞行参数代入六自由度飞行动力学方程,反向计算气动力并直接与PINN的神经网络输出值(气动力)构建平衡方程,求解物理损失。采用这种方法,不需要样本数据完全连续,可以使用不同运动状态的多段飞行数据作为训练样本,以此最大限度地拓展可能的样本数据来源,同时也可以最大限度地扩大样本数据包含的运动形式范围,大大提高了气动力模型对不同运动形式中气动力的预测能力。
同时,把静态风洞试验结果作为输入变量的一部分加入神经网络的训练过程,将其作为基准约束神经网络预测值的范围,以提高模型的泛化能力。在损失函数中增加模型静态预测输出,与地面试验数据共同构成物理残差,反馈给神经网络进行结构调整,以此实现天地数据差异的修正,使模型具备从稳态数据预测到动态数据预测的频域一致性。相关的PINN网络训练流程如图1所示。
对于通过六自由度运动方程构造物理约束的过程中所需要的飞行参数,角加速度通常无法直接测量获得。因此,首先将传感器采集到的俯仰角速度q、偏航角速度r和滚转角速度p进行多点差分,获得3个自由度上的角加速度。
将获取的加速度、角加速度以及飞行过程欧拉角等状态变量作为边界条件,可以通过六自由度飞行动力学方程对图1中PINN的神经网络结构输出值进行物理约束,使其在边界条件约束的情况下,向气动力标签数据收敛,最终得到可供使用的PINN网络模型。
其中,物理约束表达式为
f1=rVyb-qVzb+(q¯SCx-mgsinθ+T)/m-axf2=pVzb-rVxb+(q¯SCy+mgcosθsinϕ)/m-ayf3=qVxb-pVyb+(q¯SCz+mgcosθcosϕ)/m-azf4=(c1r+c2p)q+q¯Sb(c3Cl+c4Cn)-p˙f5=c5pr-c6(p2-r2)+c7q¯ScbCm-q˙f6=(c8p-c2r)q+q¯Sb(c9Cn+c4Cl)-r˙
式中 f1~f6为6个约束方程的残差即物理损失;VxbVybVzb分别为沿机体坐标系中各轴的分量;q¯为动压;S为参考面积;m为机体质量;θ为俯仰角;ϕ为滚转角;axayaz分别为机体坐标系中的沿各轴的加速度;CxCyCz分别为轴向力系数、侧向力系数和法向力系数;ClCmCn分别为滚转力矩系数、俯仰力矩系数和偏航力矩系数。各轴方向采用新国标坐标系方向。
此外,系数c1~c9分别为
c1=((Iy-Iz)Iz-Ixz2)/(IxIz-Ixz2)c2=((Ix-Iy+Iz)Ixz)/(IxIz-Ixz2)c3=Iz/(IxIz-Ixz2)c4=Ixz/(IxIz-Ixz2)c5=(Iz-Ix)/Iyc6=Ixz/Iyc7=1/Iyc8=((Ix-Iy)Ix+Ixz2)/(IxIz-Ixz2)c9=Ix/(IxIz-Ixz2)
式中 IxIyIz为各方向的惯性矩;Ixz为各方向的惯量积。
通过选用合适的损失函数,可以将物理约束得到的物理损失反向传播至神经网络,并通过迭代将残差收敛至0。本项目中,采用Smooth_L1函数作为损失函数,其表达式如下:
Li=12Ni=2N0.5fi     if  fi1fi-0.5    otherwise  i=1,2,,6
式中 Li为第i个损失函数的误差总和;N为各个特征的数据量;fi即为式(1)中的物理损失。
对于6条物理方程,最终可以获得6个损失函数,为使得6个预测气动力系数同时收敛,采用线性加权叠加的方法,将物理信息神经网络模型的6个损失函数集成为一个总损失函数,并进行误差反向传播:
SLossk=β1L1k+β2L2k+β3L3k+β4L4k+β5L5k+β6L6k
式中 SLossk为第k批次更新数据的总损失;β1~β6分别为6个维度的损失加权值;L1k~L6k分别为6个维度的第k批次更新数据的损失。
对于PINN中的神经网络,可以采用不同形式的结构形式,本文采用3层隐层的全连接BP网络结构。
由于在复杂机动过程中飞机气流角、绕机体旋转角速度、舵偏角度、飞行马赫数等大量参数都与产生的气动力密切相关,大量的参数输入神经网格结构经过隐层节点的进一步放大,在信号前向传播和误差反向传播时极易陷入梯度爆炸或梯度消失,因此必须采取必要的手段,平衡网络中每一层的激活值和梯度值。
本文采用Xavier初始化对该问题进行改善。其核心思想是根据输入层和输出层的节点数量调整权重的标准差,使得神经网络的权重初始化值从均匀分布中采样,且满足下式定义的均匀分布:
W~U-6nin+nout,6nin+nout
式中 W为神经网络的权重;~U为采样点服从均匀分布;ninnout分别为前一层的输入节点数和当前层的输出节点数。通过Xavier初始化,可以使得神经网络结构参数的训练过程更加稳定,同时也能大大加快训练速度。
此外,为了加快损失函数的收敛速度,本项目在神经网络中加入了Adam(Adaptive Moment Estimation)优化器。
该优化器结合了动量法和RMSprop(Root Mean Square Propagation)的优点,能够在训练过程中动态调整学习率,对于处理稀疏梯度和非平稳目标具有很好的适用性,也能帮助模型跳出局部最小值,寻找到更全局的最优解。其优化流程如下:
假设当前参数为θt,损失函数为J(θt),则当前梯度为
gt=θJ(θt)
对梯度的一阶动量(即梯度的指数加权移动平均)进行估计:
mt=β1mt-1+(1-β1)gt
式中 mt为当前一阶动量估计;mt-1为上一时间步的一阶动量估计;β1为一阶动量衰减系数,根据情况可适当调整,此处取值0.9。
进一步对梯度平方的二阶动量进行估计:
vt=β2vt-1+(1-β2)gt2
式中 vt为当前二阶动量估计,表示梯度平方的指数加权平均;vt-1为上一时间步的二阶动量估计;β2为二阶动量的衰减系数,可根据需要进行调整,此处取值为0.999。
为了消除初期动量和梯度平方估计值趋于0的情况,使用Adam优化器对mtvt进行偏差校正,校正公式为
m^t=mt/1-β1t
v^t=vt/1-β2t
式中 m^t为校正后的一阶动量估计;v^t为校正后的二阶动量估计。
根据校正后的动量估计值和梯度平方估计值,进行参数的更新,更新公式为
θt+1=θt-ηv^t+εm^t
针对某典型三代机构型飞行器,前期基于多自由度耦合风洞试验建立了一种高保真度非定常气动力模型23。在此基础上进行飞行仿真模拟试飞试验获得本文气动力融合建模所需要的飞行数据。通过飞行仿真共构造了11条飞行轨迹曲线,均为首先从定直平飞进入,每次飞行平飞迎角各不相同。
开始机动动作后,偏转升降舵、副翼和方向舵使飞机进行一种倾斜角不变(为零)的螺旋机动减速运动。通过操纵舵面相互配合,使迎角、侧滑角以较为接近的相位分别进入正弦振荡。在各次机动中,迎角、侧滑角的振幅也都有所区别,以模拟真实飞行中飞行员反复进行同样机动操纵时存在的操作误差。
在飞行仿真过程中,采用非线性动态逆方法提供舵偏增稳操纵,通过跟踪设定的目标迎角、侧滑角和倾斜角变化规律,由控制系统自动给出3个控制舵面的偏转角度。整个机动过程中的迎角、侧滑角、3个控制面偏转角以及马赫数随时间的变化规律见图2
同时,为了更充分地验证本文提出的PINN方法对非定常气动力的预测效果,只使用图2中的轨迹1~10对智能模型进行训练,轨迹11用于对训练得到的神经网络进行精度校验。在通过飞行仿真输出飞行轨迹时,还额外增加了5%的随机噪声。此外,轨迹4在飞行初期定直平飞阶段人为对舵面偏转量加入了约10%的随机噪声,在闭环作用下,舵面抖动幅值被进一步放大,其轨迹与其他几组样本产生较大差异,作为部分样本数据在某些极端条件下由于传感器误差等原因区间过大时,气动力建模方法能否依然具有较好的鲁棒性和泛化能力的测试依据。
如前文所述,在真实飞行中角加速度通常很难直接测量,因此需要采用多点差分法计算获得,本文采用五点差分法对角速度信号的一阶时间导数进行求解。由于角加速度数据是损失函数构造过程中的重要参数,对损失精度的判读至关重要,因此需要对求取的角加速度精度进行验证。
本文建模使用的样本数据通过飞行仿真获得,因此可以直接输出过程中的角加速度,以校验多点差分法的计算精度。图3给出了轨迹1通过对角速度求导获得的角加速度与仿真程序直接输出值的对比结果,两者几乎完全重合,证明了该方法是可靠的,因此将其直接用于神经网络损失函数的计算是可行的。
根据前文所述的建模原理,使用飞行轨迹1~10对PINN进行训练后,对轨迹11中的气动力进行预测。同时,为了对比PINN的预测效果,还使用了随机森林13(Random Forest,RF)模型进行了相同训练数据的学习,并对轨迹11进行预测。随机森林模型是较经典的多源数据融合方法,此前常被用来进行静态风洞试验数据和飞行数据的智能融合。两种气动力智能融合建模方法对比结果如图4所示。由图4可以看到,无论是PINN模型还是随机森林模型,都能较准确地预测出气动力的变化规律,呈现了较高的预测精度。同时,两种气动力模型的预测结果都存在一些数据波动,特别是气动力量值较小时。相对而言,PINN模型产生的数据波动要小于随机森林模型。
对于上述的数据波动,可能的来源有两种:
a)本文使用的训练样本添加了5%的随机噪声,导致在不同的飞行轨迹中,相同飞行状态下的气动力可能不同,因此在神经网络学习过程中形成不连贯的“跳点”;
b)样本数据均为较大振幅的机动动作,机动过程迎角、侧滑角变化规律如图5所示,曲线大致围成了一个空心环。当预测运动状态位于环上时,神经网络可以给出较理想的输出精度,但当预测运动状态为较小振幅时,虽然状态变量被包裹在环内空心部分,仍属于“内插”,但由于预测状态未被样本数据覆盖到,神经网络会出现明显的过拟合错误。
为了验证上述波动的形成原因,并测试PINN模型的泛化能力,将运动振幅减小,直至定常直线飞行,此时模型输出值即为静态气动力。
图6给出了所有6个气动力和力矩系数静态值随迎角和侧滑角的变化曲线,所有曲线均为侧滑角为5°时,迎角从-10°至15°连续变化时的静态值。
可以看到,虽然随机森林方法在输入中也加入了静态数据作为约束,但只能相对准确地预测出轴向力系数和法向力系数,对于侧向力系数,能大致给出变化趋势,但量值存在较大偏差。而3个力矩系数则无论是量值大小还是变化趋势都出现了明显误差。且由于随机森林模型只是简单地将地面稳态数据作为输入,并未对地面数据与飞行数据做进一步的误差修正融合,因此随机森林模型输出的静态数据呈现出了明显的过拟合波动。
而PINN网络对6个气动力和力矩系数的预测值都能较好地与真实值对应,且由于在神经网络的物理损失结构中有针对性地加入了静态修正,使得PINN网络能同时具备准确预测稳态气动参数和动态气动参数的能力,显示出了良好的泛化能力。
由于不论是PINN模型还是随机森林模型,静态风洞试验数据均作为模型的输入参与神经网络的训练。虽然PINN模型对于静态气动力的预测精度显然要高于随机森林模型,但仍不能充分证明PINN模型对任意形式运动状态下气动力预测的泛化能力。因此,在此基础上进一步设计一个单自由度俯仰运动,使其运动状态介于稳态和样本运动状态之间,相当于轨迹曲线在图5中的横轴零轴上往返移动,迎角和俯仰角速度变化规律如图7所示。
图8分别给出了PINN模型和随机森林模型对该单自由度俯仰运动过程中6个气动力的预测结果。
可以看到,对于3个纵向气动力和力矩,无论是随机森林模型还是PINN网络都能很好地预测出曲线的走势,且轴向力系数和法向力系数的量值也能很好地重合。而对于俯仰力矩系数,由于样本噪声的存在,PINN网络预测结果有轻微的振荡,但总体上在可接受范围内。而随机森林方法则出现了剧烈波动,这不仅跟样本噪声有关,也是随机森林在预测超出样本数据覆盖范围的运动形式中出现明显过拟合现象的具体体现。
对于横航向的3个力和力矩,在计算轨迹时并未考虑纵向和横航向的气动耦合效应,因此在单自由度运动中应都为零。得益于本文提出的PINN方法实现了静、动态数据的高效融合,其网络预测结果完全正确。而随机森林方法虽然在输入变量中加入了静态量,但输出结果出现了明显的过拟合错误,且量值较大,不可忽略。这也说明了以往的智能类建模方法在进行地面数据与飞行数据融合建模时,只是简单地将静态试验数据作为输入量加入到模型中作为稳态约束是远远不够的。
本文在传统物理信息神经网络原理的基础上,提出了一种基于PINN的多源气动数据融合建模方法。分别使用建立的PINN模型对锥形机动、单自由度俯仰运动过程中的气动力以及稳态气动数据进行计算,并与经典的数据融合随机森林方法进行比较,可以得到如下结论:
a)本文提出的PINN方法改进了损失函数构造方式,相比传统PINN方法进行气动参数辨识时需要依靠飞行数据的时间连续性进行损失计算,本文改进的PINN模型可以对不同试验车次的离散飞行数据进行整合训练,不但提高了飞行数据的利用效率,还能依赖不同运动形式的飞行数据提高模型的泛化能力。
b)本文利用PINN网络进行了多源数据融合研究,除了经典智能融合方法中将风洞试验数据作为神经网络的输入外,还在损失函数中构造了稳态数据残差估计,并提供给神经网络进行结构调整,以此实现了天地数据差异的有效修正,大大提高了PINN从稳态数据预测到动态数据预测的频域一致性。
c)通过与经典随机森林方法的对比,本文提出的PINN模型对于不同运动形式中的非定常气动力预测都具有较高的预测精度,且由于多重物理约束的加入,PINN具有更高的泛化能力,对非样本数据运动形式机动过程中气动力也能给出可信的预测结果。
  • 江苏省基础研究计划自然科学基金青年基金项目(BK20220873)
  • 航天一院高校联合创新基金项目(CALT2023-13)
参考文献 引证文献
排序方式:
[1]
CHEN S, GAO Z, ZHU X, et al. Unstable unsteady aerodynamic modeling based on least squares support vector machines with general excitation[J]. Chinese Journal of Aeronautics, 2020, 33(10): 2499-2509.
[2]
郭林亮, 祝明红, 傅澔, 等. 水平风洞中开展飞机尾旋特性研究的理论分析[J]. 航空学报, 2018, 39(6): 84-95.
GUO Linliang, ZHU Minghong, FU Hao, et al. Theoretical analysis of research on aircraft spin characteristic in horizontal wind tun-nel[J]. Acta Aeronauticaet Astronautica Sinica, 2018, 39(6): 84-95.
[3]
FREMAUX C M. Estimation of the moment coefficients for dynamically scaled free-spinning wind tunnel model[J]. Journal of Aircraft, 1995, 32(6): 1407-1409.
[4]
黄灵恩, 潘怡. 用逐步回归法辨识飞机模型尾旋时的气动力[C]. 烟台: 中国航空学会飞行力学与飞行试验专业委员会学术交流会, 2003.
HUANG Ling'en, PAN Yi. The aerodynamic forces during the spin of an aircraft model are identified by the stepwise regression me-thod[C]. Yantai: Academic Exchange Conference of the Flight Mechanics and Flight Test Professional Committee of the Chinese Society of Aeronautics and Astronautics, 2003.
[5]
KUTTIERI R A, SINHA M. Neural partial differentiation for parameter estimation of flexible aircraft dynamics[J]. Journal of Aerospace Sciences and Technologies, 2016, 68(4): 276-286.
[6]
VERMA H O, PEYADA N K. Aircraft parameter estimation using ELM network[J]. Aircraft Engineering and Aerospace Technology, 2020, 92(6): 895-907.
[7]
GRESHAM J L, SIMMONS B M, HOPWOOD J W, et al. Spin aerodynamic modeling for a fixed-wing aircraft using flight data[J]. Journal of Aircraft, 2024, 61(1): 12.
[8]
何开峰, 钱炜祺, 汪清, 等. 数据融合技术在空气动力学研究中的应用[J]. 空气动力学学报, 2014, 32(6): 777-782.
HE Kaifeng, QIAN Weiqi, WANG Qing, et al. Application of data fusion technique in aerodynamics studies[J]. Acta Aerodynamica Sinica, 2014, 32(6): 777-782.
[9]
李瑛, 颜廷龙. 航空大数据的融合及挖掘技术综述[J]. 航空计算技术, 2020, 50(6): 124-128.
LI Ying, YAN Tinglong. A survey of fusion and mining technology of aeronautical big data[J]. Aeronautical Computing Technique, 2020, 50(6): 124-128.
[10]
邓晨, 陈功, 王文正, 等. 基于不确定度和气动模型的气动数据融合算法[J]. 空气动力学学报, 2022, 40(4): 117-123.
DENG Chen, CHEN Gong, WANG Wenzheng, et al. Aerodynamic data fusion algorithms based on aerodynamic model and uncer-tainly[J]. Acta Aerodynamica Sinica, 2022, 40(4): 117-123.
[11]
张伟伟, 寇家庆, 刘溢浪. 智能赋能流体力学展望[J]. 航空学报, 2021, 42(4): 26-71.
ZHANG Weiwei, KOU Jiaqing, LIU Yilang. Prospect of artificial intelligence empowered fluid mechanics[J]. Acta Aeronauticaet Astronautica Sinica, 2021, 42(4): 26-71.
[12]
KOU J, ZHANG W. Multi-fidelity modeling framework for nonlinear unsteady aerodynamics of airfoils[J]. Applied Mathema-tical Modelling, 2019(76): 832-855.
[13]
王旭, 宁晨伽, 王文正, 等. 面向飞行试验的多源气动数据智能融合方法[J]. 空气动力学学报, 2023, 41(2): 12-20.
WANG Xu, NING Chenjia, WANG Wenzheng, et al. Intelligent fusion method of multi-source aerodynamic data for flight tests[J]. Acta Aerodynamica Sinica, 2023, 41(2): 12-20.
[14]
MENG X, CARNIADAKIS G E. A composite neural network that learns from multi-fidelity data: application to function approxi-mation and inverse PDE problems[J]. Journal of Computational Physics, 2020, 401(15): 109020.
[15]
LI K, KOU J Q, ZHANG W W. Deep learning for multifidelity aerodynamic distribution modeling from experimental and simula-tion data[J]. AIAA Journal, 2022, 60(7): 4413-4427.
[16]
颜廷龙, 李瑛, 王凤芹. 基于改进支持度的飞行数据记忆融合滤波算法[J]. 计算机与数字工程, 2023, 401(3): 635-638.
YAN Tinglong, LI Ying, WANG Fengqin. Flight data memory fusion filtering algorithm based on improved support[J]. Computer & Digital Engineering, 2023, 401(3): 635-638.
[17]
KARNIADAKIS G E, KEVREKIDIS I G, LU L, et al. Physics-informed machine learning[J]. Nature Reviews Physics, 2021, 3(6): 422-440.
[18]
MAO Z P, JAGTAP A D, KARNIADAKIS G E. Physics-informed neural networks for high-speed flows[J]. Computer Methods in Applied Mechanics and Engineering, 2020(360): 112789.
[19]
JIN X W, CAI S Z, LI H, et al. NSFnets (Navier-Stokes flow nets): physics-informed neural networks for the incompressible Navier-Stokes equations[J]. Journal of Computational Physics, 2021(426): 109951.
[20]
蔺佳哲, 周岭, 武频, 等. 基于PINN 模型的导弹气动特性快速预测技术[J]. 北京航空航天大学学报, 2023, 49(15): 2669-2678.
LIN JiazheZHOU Ling, WU Pin,et al. Rapid prediction technology of missile aerodynamic characteristics based on PINN model[J]. Journal of Beijing University of Aeronautics and Astronautics, 2023, 49(15): 2669-2678.
[21]
付军泉, 钟伯文, 钟运琴, 等. 基于物理信息神经网络的飞机气动参数辨识方法[J]. 空气动力学学报, 2023, 41(9): 30-37.
FU Junquan, ZHONG Bowen, ZHONG Yunqin, et al. A physics informed neural network based method for aircraft aerodynamic parameter identification[J]. Acta Aerodynamica Sinica, 2023, 41(9): 30-37.
[22]
NATHANIEL E M, PIYUSH M M, WADE W H. Flight dynamic uncertainty quantification modeling using physics-informed neural networks[J]. AIAA Journal, 2024, 62(11): 13.
[23]
沈霖, 黄达, 吴根兴, 等. 战斗机大迎角非定常气动力建模[J]. 航空学报, 2020, 41(6): 193-210.
SHEN Lin, HUANG Da, WU Genxing, et al. Unsteady aerodynamic modeling for fighter configuration at high angles of attack[J]. Acta Aeronauticaet Astronautica Sinica, 2020, 41(6): 193-210.
2025年第48卷第5期
PDF下载
535
251
引用本文
BibTeX
文章信息
doi: 10.7654/j.issn.2097-1974.20250510
  • 接收时间:2025-02-22
  • 首发时间:2025-11-27
  • 出版时间:2025-10-25
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2025-02-22
  • 修回日期:2025-05-15
基金
江苏省基础研究计划自然科学基金青年基金项目(BK20220873)
航天一院高校联合创新基金项目(CALT2023-13)
作者信息
    1.北京航天长征飞行器研究所,北京,100076
    2.南京航空航天大学民航学院,南京,210016
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/ddyht/CN/10.7654/j.issn.2097-1974.20250510
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