Article(id=1325149885359599853, tenantId=1146029695717560320, journalId=1255847867265597444, issueId=1325146207672214104, articleNumber=null, orderNo=null, doi=10.11858/gywlxb.20251287, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=research-article, receivedDate=1766937600000, receivedDateStr=2025-12-29, revisedDate=1770912000000, revisedDateStr=2026-02-13, acceptedDate=null, acceptedDateStr=null, onlineDate=1793869952763, onlineDateStr=2026-11-05, pubDate=1783180800000, pubDateStr=2026-07-05, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1793869952763, onlineIssueDateStr=2026-11-05, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1793869952763, creator=13701087609, updateTime=1793869952763, updator=13701087609, issue=Issue{id=1325146207672214104, tenantId=1146029695717560320, journalId=1255847867265597444, year='2026', volume='40', issue='7', pageStart='070101-1', pageEnd='070114-14', issueExtLink='null', onlineDate='null', pubDate='1783180800000', pubDateStr='2026-07-05', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=0, createTime=1793869075935, creator='13701087609', updateTime=1793870526447, updator='13701087609', preIssue=null, nextIssue=null, articleTotal=null, ext={EN=IssueExt(id=1325152292009279913, tenantId=1146029695717560320, journalId=1255847867265597444, issueId=1325146207672214104, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1325152292009279914, tenantId=1146029695717560320, journalId=1255847867265597444, issueId=1325146207672214104, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null, downloadFileDto=null}, startPage=070111-1, endPage=070111-17, ext={EN=ArticleExt(id=1325149890334044400, articleId=1325149885359599853, tenantId=1146029695717560320, journalId=1255847867265597444, language=EN, title=Impact Response and Design Optimization of Triangular Corrugated Sandwich Beams: A Machine Learning Approach, columnId=1325146208670458457, journalTitle=Chinese Journal of High Pressure Physics, columnName=Mechanical Behavior of Lightweight Composite Protective Materials and Structures, runingTitle=null, highlight=null, articleAbstract=

To enhance the prediction accuracy of low-velocity impact performance and improve the structural design efficiency of triangular corrugated sandwich beams, this paper proposes a machine learning modeling and optimization process for the impact response of sandwich beams based on a hard-parameter-sharing multi-task learning (MTL) framework. A sample dataset is generated using finite element models, and the rationality of the models is validated against existing experimental results. Subsequently, an MTL model is trained to simultaneously predict the structural specific energy absorption (SEA), the maximum deflection of the top panel, and the initial peak load. The results show that the MTL model optimized via Bayesian optimization demonstrates strong predictive performance under a 50 J impact energy condition. The predictions align well with the finite element simulation results, with the coefficient of determination R2 for all output variables in the test set exceeding 0.989, thereby validating the effectiveness and reliability of the model in response prediction and engineering optimization analysis. Parameter sensitivity analysis reveals that the core cell count and core wall thickness have the most significant influence on structural stiffness, followed by the top panel thickness, while the bottom panel thickness has a relatively minor impact. Moreover, the core wall thickness exhibits a certain saturation threshold in terms of performance enhancement. In combination with the non-dominated sorting genetic algorithm Ⅱ (NSGA-Ⅱ), multi-objective optimization analysis are conducted focusing on deformation characteristics, energy absorption performance, and comprehensive performance, and yields optimal parameter configurations that meet different engineering design requirements for sandwich beams.

, authors=Dong LI, Xiaobin ZHANG, Zhifang LIU, Jianyin LEI, authorsList=Dong LI, Xiaobin ZHANG, Zhifang LIU, Jianyin LEI, authorCompany=null, correspAuthors=Zhifang LIU, authorNote=null, correspAuthorsNote=null, copyrightStatement=Copyright © 2026 Chinese Journal of High Pressure Physics. All rights reserved., 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, fund=null), CN=ArticleExt(id=1325149967538598188, articleId=1325149885359599853, tenantId=1146029695717560320, journalId=1255847867265597444, language=CN, title=基于机器学习的三角形波纹夹芯梁的冲击响应与设计优化, columnId=1325146208871785051, journalTitle=高压物理学报, columnName=轻质复合防护材料与结构的力学行为, runingTitle=null, highlight=null, articleAbstract=

为提高三角形波纹夹芯梁在低速冲击下的性能预测精度与结构设计效率,基于硬参数共享的多任务学习(multi task learning, MTL)框架,构建了一种面向夹芯梁冲击响应的机器学习建模与优化流程。基于有限元模型生成样本数据集,并参考已有实验结果对模型合理性进行校核。在此基础上训练MTL模型,实现了对结构比吸能、上面板最大挠度及初始峰值载荷的同步预测。结果表明,经贝叶斯优化后的MTL模型在50 J冲击能量下表现出较好的预测性能,预测结果与有限元模拟结果吻合较好,测试集中各输出量的决定系数均达到0.989以上,验证了该模型在响应预测与工程优化分析中的有效性和可靠性。参数敏感性分析表明:芯层胞元数量和芯层壁厚对结构刚度的影响最显著,其次为上面板厚度,而下面板厚度的影响相对较小;芯层壁厚在性能提升方面存在一定的饱和阈值。结合非支配排序遗传算法Ⅱ(NSGA-Ⅱ),分别对变形特性、吸能性能及综合性能开展多目标优化分析,获得了满足不同工程设计需求的夹芯梁最优参数构型。

, authors=李栋, 张晓斌, 刘志芳, 雷建银, authorsList=李栋, 张晓斌, 刘志芳, 雷建银, authorCompany=null, correspAuthors=刘志芳, authorNote=

李 栋(2000-),男,硕士研究生,主要从事冲击动力学研究. E-mail:

, correspAuthorsNote=
刘志芳(1971-),女,博士,教授,主要从事冲击动力学研究. E-mail:
, copyrightStatement=版权所有©《高压物理学报》编辑部 2026, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=UcxdrvzDCPrvq1xhqpGLHQ==, magXml=4C5vxgoHnxsLPIMww8d4kQ==, pdfUrl=null, pdf=0g88uJmTu6dHBBXCpRYW0w==, pdfFileSize=10206176, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=Dg52IZO35WtDd6WyEvbrzQ==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=DhEvpfqmr5J86QKG8+A2Lg==, mapNumber=null, fund=null)}, authors=[Author(id=1325149973007970611, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=1255379997@qq.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1325149973804888373, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, authorId=1325149973007970611, language=EN, stringName=Dong LI, firstName=Dong, middleName=null, lastName=LI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=School of Aerospace Engineering, Taiyuan University of Technology, Taiyuan 030024, Shanxi, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1325149974626971958, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, authorId=1325149973007970611, language=CN, stringName=李栋, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=太原理工大学航空航天学院, 山西 太原 030024, bio={"content":"

李 栋(2000-),男,硕士研究生,主要从事冲击动力学研究. E-mail:

"}, bioImg=null, bioContent=

李 栋(2000-),男,硕士研究生,主要从事冲击动力学研究. E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1325149971779039533, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, xref=null, ext=[AuthorCompanyExt(id=1325149972114583854, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, companyId=1325149971779039533, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Aerospace Engineering, Taiyuan University of Technology, Taiyuan 030024, Shanxi, China), AuthorCompanyExt(id=1325149972143943983, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, companyId=1325149971779039533, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=太原理工大学航空航天学院, 山西 太原 030024)])]), Author(id=1325149976359219513, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, 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=1325149977164525884, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, authorId=1325149976359219513, language=EN, stringName=Xiaobin ZHANG, firstName=Xiaobin, middleName=null, lastName=ZHANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=School of Aerospace Engineering, Taiyuan University of Technology, Taiyuan 030024, Shanxi, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1325149978473148734, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, authorId=1325149976359219513, language=CN, stringName=张晓斌, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=太原理工大学航空航天学院, 山西 太原 030024, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1325149971779039533, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, xref=null, ext=[AuthorCompanyExt(id=1325149972114583854, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, companyId=1325149971779039533, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Aerospace Engineering, Taiyuan University of Technology, Taiyuan 030024, Shanxi, China), AuthorCompanyExt(id=1325149972143943983, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, companyId=1325149971779039533, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=太原理工大学航空航天学院, 山西 太原 030024)])]), Author(id=1325149980557717824, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=liuzhifang@tyut.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1325149981421744450, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, authorId=1325149980557717824, language=EN, stringName=Zhifang LIU, firstName=Zhifang, middleName=null, lastName=LIU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=School of Aerospace Engineering, Taiyuan University of Technology, Taiyuan 030024, Shanxi, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1325149982675841347, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, authorId=1325149980557717824, language=CN, stringName=刘志芳, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=太原理工大学航空航天学院, 山西 太原 030024, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1325149971779039533, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, xref=null, ext=[AuthorCompanyExt(id=1325149972114583854, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, companyId=1325149971779039533, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Aerospace Engineering, Taiyuan University of Technology, Taiyuan 030024, Shanxi, China), AuthorCompanyExt(id=1325149972143943983, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, companyId=1325149971779039533, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=太原理工大学航空航天学院, 山西 太原 030024)])]), Author(id=1325149983502119237, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, 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=1325149985154675015, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, authorId=1325149983502119237, language=EN, stringName=Jianyin LEI, firstName=Jianyin, middleName=null, lastName=LEI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=School of Aerospace Engineering, Taiyuan University of Technology, Taiyuan 030024, Shanxi, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1325149986853368138, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, authorId=1325149983502119237, language=CN, stringName=雷建银, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=太原理工大学航空航天学院, 山西 太原 030024, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1325149971779039533, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, xref=null, ext=[AuthorCompanyExt(id=1325149972114583854, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, companyId=1325149971779039533, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Aerospace Engineering, Taiyuan University of Technology, Taiyuan 030024, Shanxi, China), AuthorCompanyExt(id=1325149972143943983, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, companyId=1325149971779039533, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=太原理工大学航空航天学院, 山西 太原 030024)])])], keywords=[Keyword(id=1325149988489146700, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, language=EN, orderNo=1, keyword=machine learning), Keyword(id=1325149989822935374, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, language=EN, orderNo=2, keyword=corrugated sandwich beam), Keyword(id=1325149990586298703, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, language=EN, orderNo=3, keyword=impact response), Keyword(id=1325149991404187984, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, language=EN, orderNo=4, keyword=performance prediction), Keyword(id=1325149992314351953, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, language=EN, orderNo=5, keyword=structural optimization), Keyword(id=1325149993971102035, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, language=CN, orderNo=1, keyword=机器学习), Keyword(id=1325149994856100181, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, language=CN, orderNo=2, keyword=波纹夹芯梁), Keyword(id=1325149995644629334, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, language=CN, orderNo=3, keyword=冲击响应), Keyword(id=1325149996512850264, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, language=CN, orderNo=4, keyword=性能预测), Keyword(id=1325149998983295321, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, language=CN, orderNo=5, keyword=结构优化)], refs=[Reference(id=1325150043858153887, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=null, journalName=null, refType=null, unstructuredReference=ZHANG D J, ZHAO Z Y, DU S F, et al. Dynamic response of ultralight all-metallic sandwich panel with 3D tube cellular core to shallow-buried explosives [J]. Science China Technological Sciences, 2021, 64(7): 1371–1388., articleTitle=null, refAbstract=null), Reference(id=1325150044277584288, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[2], rfOrder=1, authorNames=null, journalName=null, refType=null, unstructuredReference=LE V T, HA N S, GOO N S. Advanced sandwich structures for thermal protection systems in hypersonic vehicles: a review [J]. Composites Part B: Engineering, 2021, 226: 109301., articleTitle=null, refAbstract=null), Reference(id=1325150044768317857, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[3], rfOrder=2, authorNames=null, journalName=null, refType=null, unstructuredReference=WANG J F, SHI C Y, YANG N, et al. Strength, stiffness, and panel peeling strength of carbon fiber-reinforced composite sandwich structures with aluminum honeycomb cores for vehicle body [J]. Composite Structures, 2018, 184: 1189–1196., articleTitle=null, refAbstract=null), Reference(id=1325150045519098274, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[4], rfOrder=3, authorNames=null, journalName=null, refType=null, unstructuredReference=CHAHARDOLI S, ATTAR A A, GHORBANHOSSEINI S, et al. Investigation of the bending and crushing for the light-weight structures used in vehicle’s radiator [J]. Mechanics Based Design of Structures and Machines, 2023, 51(8): 4491–4507., articleTitle=null, refAbstract=null), Reference(id=1325150045607178659, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[5], rfOrder=4, authorNames=null, journalName=null, refType=null, unstructuredReference=SHU C F, ZHAO S Y, HOU S J. Crashworthiness analysis of two-layered corrugated sandwich panels under crushing loading [J]. Thin-Walled Structures, 2018, 133: 42–51., articleTitle=null, refAbstract=null), Reference(id=1325150046366347684, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[6], rfOrder=5, authorNames=null, journalName=null, refType=null, unstructuredReference=LIU K, ZONG S, LI Y, et al. Structural response of the U-type corrugated core sandwich panel used in ship structures under the lateral quasi-static compression load [J]. Marine Structures, 2022, 84: 103198., articleTitle=null, refAbstract=null), Reference(id=1325150048056652197, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[7], rfOrder=6, authorNames=null, journalName=null, refType=null, unstructuredReference=RUBINO V, DESHPANDE V S, FLECK N A. The dynamic response of end-clamped sandwich beams with a Y-frame or corrugated core [J]. International Journal of Impact Engineering, 2008, 35(8): 829–844., articleTitle=null, refAbstract=null), Reference(id=1325150048497054118, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[8], rfOrder=7, authorNames=null, journalName=null, refType=null, unstructuredReference=RUBINO V, DESHPANDE V S, FLECK N A. The three-point bending of Y-frame and corrugated core sandwich beams [J]. International Journal of Mechanical Sciences, 2010, 52(3): 485–494., articleTitle=null, refAbstract=null), Reference(id=1325150048895512999, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[9], rfOrder=8, authorNames=null, journalName=null, refType=null, unstructuredReference=ST-PIERRE L, DESHPANDE V S, FLECK N A. The low velocity impact response of sandwich beams with a corrugated core or a Y-frame core [J]. International Journal of Mechanical Sciences, 2015, 91: 71–80., articleTitle=null, refAbstract=null), Reference(id=1325150049289777577, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[10], rfOrder=9, authorNames=null, journalName=null, refType=null, unstructuredReference=XIA F K, YU T X, DURANDET Y, et al. Triangular corrugated sandwich panels under longitudinal bending [J]. Thin-Walled Structures, 2021, 169: 108359., articleTitle=null, refAbstract=null), Reference(id=1325150049377857962, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[11], rfOrder=10, authorNames=null, journalName=null, refType=null, unstructuredReference=LIU J Z, LI S, GUO J C, et al. Machine learning (ML) based models for predicting the ultimate bending moment resistance of high strength steel welded I-section beam under bending [J]. Thin-Walled Structures, 2023, 191: 111051., articleTitle=null, refAbstract=null), Reference(id=1325150049734373803, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[12], rfOrder=11, authorNames=null, journalName=null, refType=null, unstructuredReference=FORD E, MANEPARAMBIL K, KUMAR A, et al. Transfer (machine) learning approaches coupled with target data augmentation to predict the mechanical properties of concrete [J]. Machine Learning with Applications, 2022, 8: 100271., articleTitle=null, refAbstract=null), Reference(id=1325150049822454188, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[13], rfOrder=12, authorNames=null, journalName=null, refType=null, unstructuredReference=YANG L, LIN H, WEI L C, et al. Application of a novel machine learning model for the prediction and optimization of anti-blast performance of sandwich honeycomb blast walls [J]. Ocean Engineering, 2024, 312: 119217., articleTitle=null, refAbstract=null), Reference(id=1325150050246078893, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[14], rfOrder=13, authorNames=null, journalName=null, refType=null, unstructuredReference=FANG X, SHEN H S, WANG H. Three-point bending behaviors of sandwich beams with data-driven 3D auxetic lattice core based on deep learning [J]. Composite Structures, 2025, 354: 118751., articleTitle=null, refAbstract=null), Reference(id=1325150050569040302, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[15], rfOrder=14, authorNames=null, journalName=null, refType=null, unstructuredReference=ANDIKA, SANTOSA S P, WIDAGDO D, et al. Design and multi-objective optimization of auxetic sandwich panels for blastworthy structures using machine learning method [J]. Applied Sciences, 2024, 14(23): 10831., articleTitle=null, refAbstract=null), Reference(id=1325150052234178991, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[16], rfOrder=15, authorNames=null, journalName=null, refType=null, unstructuredReference=QIU W J, LIU K, ZONG S, et al. An optimisation method for anti-blast performance of corrugated sandwich plate structure based on neural network and sparrow search algorithm [J]. Ships and Offshore Structures, 2024, 19(8): 1028–1043., articleTitle=null, refAbstract=null), Reference(id=1325150052653609392, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[17], rfOrder=16, authorNames=null, journalName=null, refType=null, unstructuredReference=TEIMOURI A, ALINIA M, KAMARIAN S, et al. Design optimization of additively manufactured sandwich beams through experimentation, machine learning, and imperialist competitive algorithm [J]. Journal of Engineering Design, 2024, 35(3): 320–337., articleTitle=null, refAbstract=null), Reference(id=1325150052741689777, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[18], rfOrder=17, authorNames=null, journalName=null, refType=null, unstructuredReference=MCKAY M D, BECKMAN R J, CONOVER W J. A comparison of three methods for selecting values of input variables in the analysis of output from a computer code [J]. Technometrics, 1979, 21(2): 239–245., articleTitle=null, refAbstract=null), Reference(id=1325150053081428402, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[19], rfOrder=18, authorNames=null, journalName=null, refType=null, unstructuredReference=CARUANA R. Multitask learning [J]. Machine Learning, 1997, 28(1): 41–75., articleTitle=null, refAbstract=null), Reference(id=1325150053156925875, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[20], rfOrder=19, authorNames=null, journalName=null, refType=null, unstructuredReference=SNOEK J, LAROCHELLE H, ADAMS R P. Practical bayesian optimization of machine learning algorithms [C]//Proceedings of the 26th International Conference on Neural Information Processing Systems. Lake Tahoe: Curran Associates Inc., 2012: 2951–2959., articleTitle=null, refAbstract=null), Reference(id=1325150053555384756, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[21], rfOrder=20, authorNames=null, journalName=null, refType=null, unstructuredReference=DEB K, PRATAP A, AGARWAL S, et al. A fast and elitist multiobjective genetic algorithm: NSGA-Ⅱ [J]. IEEE Transactions on Evolutionary Computation, 2002, 6(2): 182–197., articleTitle=null, refAbstract=null), Reference(id=1325150053618299317, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[22], rfOrder=21, authorNames=null, journalName=null, refType=null, unstructuredReference=JING L, SU X Y, CHEN D, et al. Experimental and numerical study of sandwich beams with layered-gradient foam cores under low-velocity impact [J]. Thin-Walled Structures, 2019, 135: 227–244., articleTitle=null, refAbstract=null), Reference(id=1325150053685408182, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[23], rfOrder=22, authorNames=null, journalName=null, refType=null, unstructuredReference=LIU Z S, YU Y Y, YANG Z, et al. Dynamic experimental studies of A6N01S-T5 aluminum alloy material and structure for high-speed trains [J]. Acta Mechanica Sinica, 2019, 35(4): 763–772., articleTitle=null, refAbstract=null), Reference(id=1325150053995786679, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[24], rfOrder=23, authorNames=null, journalName=null, refType=null, unstructuredReference=YU Z H, LIU K, ZHOU X F, et al. Low-velocity impact response of aluminum alloy corrugated sandwich beams used for high-speed trains [J]. Thin-Walled Structures, 2023, 183: 110375., articleTitle=null, refAbstract=null), Reference(id=1325150054343913912, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[25], rfOrder=24, authorNames=null, journalName=null, refType=null, unstructuredReference=荣吉利, 王圣龙, 陈子超, 等. 水下爆炸冲击载荷下波纹夹芯板动态响应及结构优化设计 [J]. 北京理工大学学报, 2024, 44(7): 679–691., articleTitle=null, refAbstract=null), Reference(id=1325150054742372793, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[25], rfOrder=25, authorNames=null, journalName=null, refType=null, unstructuredReference=RONG J L, WANG S L, CHEN Z C, et al. Dynamic response and structural optimal design of corrugated sandwich panel subjected to underwater explosion impact loads [J]. Transactions of Beijing Institute of Technology, 2024, 44(7): 679–691., articleTitle=null, refAbstract=null), Reference(id=1325150054851424698, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[26], rfOrder=26, authorNames=null, journalName=null, refType=null, unstructuredReference=卢传浩, 周宇琦, 曹勇, 等. 新型梯度连续可控夹层板抗冲击性能研究及优化 [J]. 力学学报, 2024, 56(6): 1713–1726., articleTitle=null, refAbstract=null), Reference(id=1325150056596255163, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[26], rfOrder=27, authorNames=null, journalName=null, refType=null, unstructuredReference=LU C H, ZHOU Y Q, CAO Y, et al. Research and optimization of impact resistance of novel gradient continuous controllable sandwich panels [J]. Chinese Journal of Theoretical and Applied Mechanics, 2024, 56(6): 1713–1726., articleTitle=null, refAbstract=null)], funds=null, companyList=[AuthorCompany(id=1325149971779039533, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, xref=null, ext=[AuthorCompanyExt(id=1325149972114583854, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, companyId=1325149971779039533, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Aerospace Engineering, Taiyuan University of Technology, Taiyuan 030024, Shanxi, China), AuthorCompanyExt(id=1325149972143943983, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, companyId=1325149971779039533, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=太原理工大学航空航天学院, 山西 太原 030024)])], figs=[ArticleFig(id=1325149999859904858, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, language=EN, label=Fig. 1, caption=Research framework, figureFileSmall=t2Op0RihURXNj6Rono5J2Q==, figureFileBig=Dg52IZO35WtDd6WyEvbrzQ==, tableContent=null), ArticleFig(id=1325150000669405531, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, language=CN, label=图1, caption=研究框架, figureFileSmall=t2Op0RihURXNj6Rono5J2Q==, figureFileBig=Dg52IZO35WtDd6WyEvbrzQ==, tableContent=null), ArticleFig(id=1325150003999682910, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, language=EN, label=Fig. 2, caption=Schematic diagram of the corrugated sandwich beam structure, figureFileSmall=RlRkC158/geNc/uUG/2LBw==, figureFileBig=mqm9i7f9RX7RXIQUtZanxw==, tableContent=null), ArticleFig(id=1325150004846932319, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, language=CN, label=图2, caption=波纹夹芯梁的结构示意图, figureFileSmall=RlRkC158/geNc/uUG/2LBw==, figureFileBig=mqm9i7f9RX7RXIQUtZanxw==, tableContent=null), ArticleFig(id=1325150005270557025, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, language=EN, label=Fig. 3, caption=Schematic diagram of an MTL model with hard parameter sharing, figureFileSmall=ROAxHjRo6+kJjWJCqNEuSg==, figureFileBig=l4aVTAHNMgtmCPU9XiU6hg==, tableContent=null), ArticleFig(id=1325150005773873507, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, language=CN, label=图3, caption=硬参数共享的多任务学习模型示意图, figureFileSmall=ROAxHjRo6+kJjWJCqNEuSg==, figureFileBig=l4aVTAHNMgtmCPU9XiU6hg==, tableContent=null), ArticleFig(id=1325150008193986918, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, language=EN, label=Fig. 4, caption=Finite element model of the corrugated sandwich beam, figureFileSmall=BnSkEXQkyW2rn2TMrGm4Ng==, figureFileBig=fkHkAzkLKDOFaHmTTyntog==, tableContent=null), ArticleFig(id=1325150008621805927, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, language=CN, label=图4, caption=波纹夹芯梁的有限元模型, figureFileSmall=BnSkEXQkyW2rn2TMrGm4Ng==, figureFileBig=fkHkAzkLKDOFaHmTTyntog==, tableContent=null), ArticleFig(id=1325150009880097128, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, language=EN, label=Fig. 5, caption=Validation of model effectiveness, figureFileSmall=QjRF/9ohytCqB+dlviK4zw==, figureFileBig=x0E/tAfC3lNal82JUTnTlg==, tableContent=null), ArticleFig(id=1325150010333081961, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, language=CN, label=图5, caption=模型有效性验证, figureFileSmall=QjRF/9ohytCqB+dlviK4zw==, figureFileBig=x0E/tAfC3lNal82JUTnTlg==, tableContent=null), ArticleFig(id=1325150011998220651, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, language=EN, label=Fig. 6, caption=Projection distribution of LHS samples in the parameter space, figureFileSmall=E633Kt2U+JkkSDvod5tUSw==, figureFileBig=a5NsWXp2PQFT0Z8RRiPMJA==, tableContent=null), ArticleFig(id=1325150012891607404, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, language=CN, label=图6, caption=LHS样本在参数空间中的投影分布, figureFileSmall=E633Kt2U+JkkSDvod5tUSw==, figureFileBig=a5NsWXp2PQFT0Z8RRiPMJA==, tableContent=null), ArticleFig(id=1325150013646582125, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, language=EN, label=Fig. 7, caption=Stability verification and performance comparison through repeated training-testing of models, figureFileSmall=mX5PAzzy38vKsWnX5e8aUw==, figureFileBig=GPLVlHbvwwzgtrdTiiRC1w==, tableContent=null), ArticleFig(id=1325150014472860014, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, language=CN, label=图7, caption=模型重复训练-测试的稳定性验证与性能对比, figureFileSmall=mX5PAzzy38vKsWnX5e8aUw==, figureFileBig=GPLVlHbvwwzgtrdTiiRC1w==, tableContent=null), ArticleFig(id=1325150016570012016, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, language=EN, label=Fig. 8, caption=Regression analysis for test samples, figureFileSmall=rnF/Va6UEJfSpPaIbXMCaQ==, figureFileBig=mHOVy+nkd0lXLaIMNkG6bQ==, tableContent=null), ArticleFig(id=1325150017077522802, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, language=CN, label=图8, caption=测试样本的回归分析, figureFileSmall=rnF/Va6UEJfSpPaIbXMCaQ==, figureFileBig=mHOVy+nkd0lXLaIMNkG6bQ==, tableContent=null), ArticleFig(id=1325150017861857651, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, language=EN, label=Fig. 9, caption=Influence of the core unit cell count on the impact structural response of sandwich beams, figureFileSmall=JS7pn4OQF6sYsnda+SVY3g==, figureFileBig=b08YlXhR+6P890D/HW7FMA==, tableContent=null), ArticleFig(id=1325150018717495668, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, language=CN, label=图9, caption=胞元数量对夹芯梁冲击结构响应的影响, figureFileSmall=JS7pn4OQF6sYsnda+SVY3g==, figureFileBig=b08YlXhR+6P890D/HW7FMA==, tableContent=null), ArticleFig(id=1325150021208912247, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, language=EN, label=Fig. 10, caption=Influence of the core unit cell count on the deformation mode of sandwich beams, figureFileSmall=YLMaEc3e64sTt9lo+fLDsA==, figureFileBig=12Tm/fjUTKRKZO7JG7d9SA==, tableContent=null), ArticleFig(id=1325150021691257208, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, language=CN, label=图10, caption=胞元数量对夹芯梁变形模式的影响, figureFileSmall=YLMaEc3e64sTt9lo+fLDsA==, figureFileBig=12Tm/fjUTKRKZO7JG7d9SA==, tableContent=null), ArticleFig(id=1325150022056161657, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, language=EN, label=Fig. 11, caption=Influence of top plate thickness on the impact structural response of sandwich beams, figureFileSmall=FR54HXRc2fbt/LUnSQLiTw==, figureFileBig=ZYtCDFnl3oOxR1dEyVAL7g==, tableContent=null), ArticleFig(id=1325150022920188282, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, language=CN, label=图11, caption=上面板厚度对夹芯梁冲击结构响应的影响, figureFileSmall=FR54HXRc2fbt/LUnSQLiTw==, figureFileBig=ZYtCDFnl3oOxR1dEyVAL7g==, tableContent=null), ArticleFig(id=1325150022999880060, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, language=EN, label=Fig. 12, caption=Influence of top plate thickness on the deformation mode of sandwich beams, figureFileSmall=LUlwAQO31N/E9AOa+L8iiQ==, figureFileBig=ge5RX9CdqrRNerWD6xYnnA==, tableContent=null), ArticleFig(id=1325150023364784510, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, language=CN, label=图12, caption=上面板厚度对夹芯梁变形模式的影响, figureFileSmall=LUlwAQO31N/E9AOa+L8iiQ==, figureFileBig=ge5RX9CdqrRNerWD6xYnnA==, tableContent=null), ArticleFig(id=1325150023767437695, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, language=EN, label=Fig. 13, caption=Influence of web thickness of the core on the impact structural response of sandwich beams, figureFileSmall=3Pem+uV8jQMx/ET5Xk7qrw==, figureFileBig=HywBwAH861D5Nz2uBmQ59A==, tableContent=null), ArticleFig(id=1325150025415799169, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, language=CN, label=图13, caption=芯层壁厚对夹芯梁冲击结构响应的影响, figureFileSmall=3Pem+uV8jQMx/ET5Xk7qrw==, figureFileBig=HywBwAH861D5Nz2uBmQ59A==, tableContent=null), ArticleFig(id=1325150025852006786, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, language=EN, label=Fig. 14, caption=Influence of web thickness of the core on the deformation mode of sandwich beams, figureFileSmall=UFQCfx8uV6EYoq6f9lsZhQ==, figureFileBig=xUsy6ifO85TU54Ku6TAvaA==, tableContent=null), ArticleFig(id=1325150026237882755, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, language=CN, label=图14, caption=芯层厚度对夹芯梁变形模式的影响, figureFileSmall=UFQCfx8uV6EYoq6f9lsZhQ==, figureFileBig=xUsy6ifO85TU54Ku6TAvaA==, tableContent=null), ArticleFig(id=1325150026309185924, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, language=EN, label=Fig. 15, caption=Influence of bottom plate thickness on the impact structural response of sandwich beams, figureFileSmall=liJ2u3rDoIwKs8ARkn+8zw==, figureFileBig=Qo3f/CaRHCS2tLWKbMpgKg==, tableContent=null), ArticleFig(id=1325150026653118853, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, language=CN, label=图15, caption=下面板厚度对夹芯梁冲击结构响应的影响, figureFileSmall=liJ2u3rDoIwKs8ARkn+8zw==, figureFileBig=Qo3f/CaRHCS2tLWKbMpgKg==, tableContent=null), ArticleFig(id=1325150026749587847, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, language=EN, label=Fig. 16, caption=Influence of bottom plate thickness on the deformation mode of sandwich beams, figureFileSmall=kY5+rNRRyocc98jBLHY38w==, figureFileBig=OqX2NhaM5ylmrqvX1lxfgQ==, tableContent=null), ArticleFig(id=1325150027475202440, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, language=CN, label=图16, caption=下面板厚度对夹芯梁变形模式的影响, figureFileSmall=kY5+rNRRyocc98jBLHY38w==, figureFileBig=OqX2NhaM5ylmrqvX1lxfgQ==, tableContent=null), ArticleFig(id=1325150027584254345, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, language=EN, label=Fig. 17, caption=Pareto optimal solution set for deformation optimization, figureFileSmall=nmMq5lTcNYWWWZpdnVh0jw==, figureFileBig=uPQUsTc1hEi4Y2idPnfyYQ==, tableContent=null), ArticleFig(id=1325150027995296138, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, language=CN, label=图17, caption=变形优化的Pareto解集, figureFileSmall=nmMq5lTcNYWWWZpdnVh0jw==, figureFileBig=uPQUsTc1hEi4Y2idPnfyYQ==, tableContent=null), ArticleFig(id=1325150028074987915, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, language=EN, label=Fig. 18, caption=Pareto iteration plot for energy absorption optimization, figureFileSmall=R1U3FVO3SIdasn49J2yGew==, figureFileBig=coEef56bYM++kyTRFBViIg==, tableContent=null), ArticleFig(id=1325150030046310796, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, language=CN, label=图18, caption=吸能优化的Pareto迭代图, figureFileSmall=R1U3FVO3SIdasn49J2yGew==, figureFileBig=coEef56bYM++kyTRFBViIg==, tableContent=null), ArticleFig(id=1325150030448963981, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, language=EN, label=Fig. 19, caption=Pareto optimal solution set for energy absorption and deformation optimization, figureFileSmall=ZuGQ000sY4HbhqDxLH4X9g==, figureFileBig=P2dxBw38icyW+Lp4cILfmA==, tableContent=null), ArticleFig(id=1325150031002612110, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, language=CN, label=图19, caption=吸能与变形优化的Pareto解集, figureFileSmall=ZuGQ000sY4HbhqDxLH4X9g==, figureFileBig=P2dxBw38icyW+Lp4cILfmA==, tableContent=null), ArticleFig(id=1325150031329767823, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, language=EN, label=Fig. 20, caption=Error between prediction and finite element simulation results, figureFileSmall=Yz3RIzY7Js0niRC0EIVN3A==, figureFileBig=QFOD99xFwZm/LQCYf+gYjQ==, tableContent=null), ArticleFig(id=1325150031761781136, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, language=CN, label=图20, caption=预测结果与有限元模拟结果之间的误差, figureFileSmall=Yz3RIzY7Js0niRC0EIVN3A==, figureFileBig=QFOD99xFwZm/LQCYf+gYjQ==, tableContent=null), ArticleFig(id=1325150032508367249, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, language=EN, label=Table 1, caption=Material parameters of the corrugated sandwich beam[23], figureFileSmall=null, figureFileBig=null, tableContent=
MaterialDensity/(g·cm−3)Young’s modulus/GPaYield stress/MPaPoisson’s ratio
A6N01S-T52.769181.910.33
), ArticleFig(id=1325150033414336914, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, language=CN, label=表1, caption=

波纹夹芯梁的材料参数[23]

, figureFileSmall=null, figureFileBig=null, tableContent=
MaterialDensity/(g·cm−3)Young’s modulus/GPaYield stress/MPaPoisson’s ratio
A6N01S-T52.769181.910.33
), ArticleFig(id=1325150034299335059, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, language=EN, label=Table 2, caption=Comparison of experimental and finite element simulation results for impact response at non-nodal positions, figureFileSmall=null, figureFileBig=null, tableContent=
Ei/JExperimental resultSimulation resultMean relativeerror/%
Esa/(J·g−1)δmax/mmFmax/kNEsa/(J·g−1)δmax/mmFmax/kN
300.20111.565.310.20811.845.432.72
500.29015.066.650.29214.936.781.17
900.53020.389.050.52219.819.262.21
), ArticleFig(id=1325150035452768660, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, language=CN, label=表2, caption=

非节点位置冲击下实验与有限元模拟冲击响应结果对比

, figureFileSmall=null, figureFileBig=null, tableContent=
Ei/JExperimental resultSimulation resultMean relativeerror/%
Esa/(J·g−1)δmax/mmFmax/kNEsa/(J·g−1)δmax/mmFmax/kN
300.20111.565.310.20811.845.432.72
500.29015.066.650.29214.936.781.17
900.53020.389.050.52219.819.262.21
), ArticleFig(id=1325150035909947797, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, language=EN, label=Table 3, caption=Value range of input features, figureFileSmall=null, figureFileBig=null, tableContent=
nt1/mmtc/mmt2/mmρc/(g·cm−3)
2, 4, 61.6−2.40.8−1.61.6−2.40.064−0.276
), ArticleFig(id=1325150036702671254, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, language=CN, label=表3, caption=

输入特征的取值范围

, figureFileSmall=null, figureFileBig=null, tableContent=
nt1/mmtc/mmt2/mmρc/(g·cm−3)
2, 4, 61.6−2.40.8−1.61.6−2.40.064−0.276
), ArticleFig(id=1325150037168238999, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, language=EN, label=Table 4, caption=Performance comparison between SVR and MTL models, figureFileSmall=null, figureFileBig=null, tableContent=
ModelOutputR²MAERMSEtt/stp/s
SVREsa0.95410.00760.01010.100.10
δmax0.98110.31650.4015
Fmax0.96260.35930.4690
MTLEsa0.98680.00480.00592.180.10
δmax0.99370.20370.2791
Fmax0.98690.23850.3124
), ArticleFig(id=1325150038879515032, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, language=CN, label=表4, caption=

SVR与MTL模型的性能对比

, figureFileSmall=null, figureFileBig=null, tableContent=
ModelOutputR²MAERMSEtt/stp/s
SVREsa0.95410.00760.01010.100.10
δmax0.98110.31650.4015
Fmax0.96260.35930.4690
MTLEsa0.98680.00480.00592.180.10
δmax0.99370.20370.2791
Fmax0.98690.23850.3124
), ArticleFig(id=1325150039332499865, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, language=EN, label=Table 5, caption=Comparison of deformation optimization results with those of the control group, figureFileSmall=null, figureFileBig=null, tableContent=
Methodnt1/mmtc/mmt2/mmMTLSimulation
δmax/mmFmax/kNδmax/mmFmax/kN
Knee point62.41.01.611.565.3811.645.23
Control group22.01.82.015.066.65
), ArticleFig(id=1325150039726764442, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, language=CN, label=表5, caption=

变形优化结果与对照组的比较

, figureFileSmall=null, figureFileBig=null, tableContent=
Methodnt1/mmtc/mmt2/mmMTLSimulation
δmax/mmFmax/kNδmax/mmFmax/kN
Knee point62.41.01.611.565.3811.645.23
Control group22.01.82.015.066.65
), ArticleFig(id=1325150040506904987, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, language=EN, label=Table 6, caption=Comparison of energy absorption optimization results with those of the control group, figureFileSmall=null, figureFileBig=null, tableContent=
Methodnt1/mmtc/mmt2/mmMTLSimulation
Esa/(J·g−1)Fmax/kNEsa/(J·g−1)Fmax/kN
Knee point21.60.81.60.3952.570.3882.68
Control group22.01.82.00.2976.65
), ArticleFig(id=1325150040922141084, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, language=CN, label=表6, caption=

吸能优化结果与对照组的比较

, figureFileSmall=null, figureFileBig=null, tableContent=
Methodnt1/mmtc/mmt2/mmMTLSimulation
Esa/(J·g−1)Fmax/kNEsa/(J·g−1)Fmax/kN
Knee point21.60.81.60.3952.570.3882.68
Control group22.01.82.00.2976.65
), ArticleFig(id=1325150041341571485, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, language=EN, label=Table 7, caption=Comparison of energy absorption and deformation optimization results with those of the control group, figureFileSmall=null, figureFileBig=null, tableContent=
Methodnt1/mmtc/mmt2/mmMTLSimulation
Esa/(J·g−1)δmax/mmFmax/kNEsa/(J·g−1)δmax/mmFmax/kN
Knee point42.30.91.60.31114.114.710.30414.214.66
Control group22.01.82.00.29715.066.65
), ArticleFig(id=1325150041740030366, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, language=CN, label=表7, caption=

吸能及变形优化结果与对照组的比较

, figureFileSmall=null, figureFileBig=null, tableContent=
Methodnt1/mmtc/mmt2/mmMTLSimulation
Esa/(J·g−1)δmax/mmFmax/kNEsa/(J·g−1)δmax/mmFmax/kN
Knee point42.30.91.60.31114.114.710.30414.214.66
Control group22.01.82.00.29715.066.65
)], attaches=null, journal=Journal(id=1255846718311514113, delFlag=0, nameCn=高压物理学报, nameEn=Chinese Journal of High Pressure Physics, nameHistory1=null, nameHistory2=null, issn=1000-5773, eissn=null, cn=51-1147/O4, coden=null, periodic=0, language=CN, oaType=null, ccby=null, superviseOffice=null, ownerOffice=null, pubOffice=null, editorOffice=null, officeType=null, aims=null, clcCode=null, officeProv=null, officeCity=null, officeAddr=null, officeZip=null, officeEmail=null, officePhone=null, editDirector=null, officeDirector=null, officeDirectorPhone=null, officeStaffNum=null, officeEmpNum=null, coverPicUrl=KWePOcsfwWv2cMGG6VIsRw==, journalPrice=null, startedYear=null, abbrevIsoEn=Chinese Journal of High Pressure Physics, journalRemark=null, publicationField=null, createdTime=1777346790154, updatedTime=1788952099200, createdBy=18614031015, updatedBy=13041195026, firstLetterCn=G, firstLetterEn=G, subjectCode=Science, subjectName=null, subjectCodeEn=Science, subjectNameEn=null, picCn=KWePOcsfwWv2cMGG6VIsRw==, picEn=yfL33fksqTlch2QW39glNg==, jcr=null, cjcr=null, exts=[JournalExt(id=1304522912573182860, language=CN, name=高压物理学报, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1788952099221, updatedTime=1788952099221, createdBy=13041195026, updatedBy=13041195026, submissionGuidelinesUrl=, submissionAuthorUrl=https://gywlxbauthor.manuscriptcloud.com/, submissionEditorUrl=https://gywlxbeditor.manuscriptcloud.com/, submissionReviewUrl=https://gywlxbauthor.manuscriptcloud.com/, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1304522912619320205, language=EN, name=Chinese Journal of High Pressure Physics, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1788952099232, updatedTime=1788952099232, createdBy=13041195026, updatedBy=13041195026, submissionGuidelinesUrl=, submissionAuthorUrl=https://gywlxbauthor.manuscriptcloud.com/, submissionEditorUrl=https://gywlxbeditor.manuscriptcloud.com/, submissionReviewUrl=https://gywlxbauthor.manuscriptcloud.com/, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1255847867265597444, websiteList=[Website(id=1255847989789208939, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1255847867265597444, 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/gywlxb/CN, language=CN, createTime=1777347093294, createBy=18614031015, updateTime=1777347319285, updateBy=18614031015, name=高压物理学报-中文, tplId=1146099689490845704, title=高压物理学报, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1255849119986364878, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1255847989789208939, code=articleTextType, value=kx, createTime=1777347362753, updateTime=1777347362753, creator=18614031015, updator=18614031015), WebsiteProps(id=1255849119952810443, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1255847989789208939, code=banner, value=null, createTime=1777347362745, updateTime=1777347362745, creator=18614031015, updator=18614031015), WebsiteProps(id=1255849120045085137, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1255847989789208939, code=grayFlag, value=0, createTime=1777347362767, updateTime=1777347362767, creator=18614031015, updator=18614031015), WebsiteProps(id=1255849119944421834, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1255847989789208939, code=logo, value=https://castjournals.cast.org.cn/joweb/gywlxb/CN/file/pic?fileId=5J9nsSD+WX0mc+nIBFk2Hg==, createTime=1777347362743, updateTime=1777347362743, creator=18614031015, updator=18614031015), WebsiteProps(id=1255849120368046547, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1255847989789208939, code=minRunFlag, value=0, createTime=1777347362844, updateTime=1777347362844, creator=18614031015, updator=18614031015), WebsiteProps(id=1255849119973781965, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1255847989789208939, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/gywlxb/CN/file/pic, createTime=1777347362750, updateTime=1777347362750, creator=18614031015, updator=18614031015), WebsiteProps(id=1255849120347075026, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1255847989789208939, code=silenceFlag, value=0, createTime=1777347362839, updateTime=1777347362839, creator=18614031015, updator=18614031015), WebsiteProps(id=1255849119965393356, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1255847989789208939, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1777347362748, updateTime=1777347362748, creator=18614031015, updator=18614031015), WebsiteProps(id=1255849120007336399, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1255847989789208939, code=themeColor, value=null, createTime=1777347362758, updateTime=1777347362758, creator=18614031015, updator=18614031015), WebsiteProps(id=1255849120019919312, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1255847989789208939, code=themeStyle, value=null, createTime=1777347362761, updateTime=1777347362761, creator=18614031015, updator=18614031015)]), Website(id=1255847989940203908, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1255847867265597444, 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/gywlxb/EN, language=EN, createTime=1777347093329, createBy=18614031015, updateTime=1777347316256, updateBy=18614031015, name=高压物理学报-英文, tplId=1146101810881728533, title=Chinese Journal of High Pressure Physics, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1255849089909010882, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1255847989940203908, code=articleTextType, value=kx, createTime=1777347355582, updateTime=1777347355582, creator=18614031015, updator=18614031015), WebsiteProps(id=1255849089871262143, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1255847989940203908, code=banner, value=null, createTime=1777347355573, updateTime=1777347355573, creator=18614031015, updator=18614031015), WebsiteProps(id=1255849089934176709, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1255847989940203908, code=grayFlag, value=0, createTime=1777347355588, updateTime=1777347355588, creator=18614031015, updator=18614031015), WebsiteProps(id=1255849089858679230, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1255847989940203908, code=logo, value=https://castjournals.cast.org.cn/joweb/gywlxb/EN/file/pic?fileId=5J9nsSD+WX0mc+nIBFk2Hg==, createTime=1777347355570, updateTime=1777347355570, creator=18614031015, updator=18614031015), WebsiteProps(id=1255849089950953927, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1255847989940203908, code=minRunFlag, value=0, createTime=1777347355592, updateTime=1777347355592, creator=18614031015, updator=18614031015), WebsiteProps(id=1255849089888039361, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1255847989940203908, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/gywlxb/EN/file/pic, createTime=1777347355577, updateTime=1777347355577, creator=18614031015, updator=18614031015), WebsiteProps(id=1255849089942565318, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1255847989940203908, code=silenceFlag, value=0, createTime=1777347355590, updateTime=1777347355590, creator=18614031015, updator=18614031015), WebsiteProps(id=1255849089879650752, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1255847989940203908, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_en_623/, createTime=1777347355575, updateTime=1777347355575, creator=18614031015, updator=18614031015), WebsiteProps(id=1255849089917399491, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1255847989940203908, code=themeColor, value=null, createTime=1777347355584, updateTime=1777347355584, creator=18614031015, updator=18614031015), WebsiteProps(id=1255849089925788100, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1255847989940203908, code=themeStyle, value=null, createTime=1777347355586, updateTime=1777347355586, creator=18614031015, updator=18614031015)])], journalTitle=高压物理学报, weixinUrl=null, journalUrl=https://www.gywlxb.cn, iacademicId=null, status=1, seqNo=null, journalTitleEn=Chinese Journal of High Pressure Physics, journalPhotoCn=KWePOcsfwWv2cMGG6VIsRw==, journalPhotoEn=yfL33fksqTlch2QW39glNg==, journalFirstLetter=G, journalRecommend=null, journalNew=null, journalCollection=null, jcrJf=null, cjcrJf=null, jcrJfStr=null, cjcrJfStr=null, submissionFirstDecision=null, sciSubjectClassification=null, casSubjectClassification=null, citeScore=null, totalCitationFrequency=null, icpCode=null, psCode=null, advertisingLicenseCode=null, copyrightInformation=null, country=null, option=, provinceCode=null, provinceName=null, collectFlag=false, interPubPlatform=, interPubPlatformUrl=null), detailUrlCn=https://castjournals.cast.org.cn/joweb/gywlxb/CN/10.11858/gywlxb.20251287, detailUrlEn=https://castjournals.cast.org.cn/joweb/gywlxb/EN/10.11858/gywlxb.20251287, pdfUrlCn=https://castjournals.cast.org.cn/joweb/gywlxb/CN/PDF/10.11858/gywlxb.20251287, pdfUrlEn=https://castjournals.cast.org.cn/joweb/gywlxb/EN/PDF/10.11858/gywlxb.20251287, aliStartDate=0, aliEndDate=0, collectionFlag=false, citedCount=null, citedUrl=null, previewStatus=0, delFlag=0, hasFullText=1, orderTime=1783180800000, fullTextJson=null, articleText=null, reference=null)
收藏切换
基于机器学习的三角形波纹夹芯梁的冲击响应与设计优化
收藏切换
PDF下载
李栋 , 张晓斌 , 刘志芳 , 雷建银
高压物理学报 | 轻质复合防护材料与结构的力学行为 2026,40(7): 070111-1-070111-17
收起
收藏切换
高压物理学报 |轻质复合防护材料与结构的力学行为 2026 , 40 (7) : 070111-1 -070111-17
基于机器学习的三角形波纹夹芯梁的冲击响应与设计优化
全屏
[Author(id=1325149973007970611, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=1255379997@qq.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1325149973804888373, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, authorId=1325149973007970611, language=EN, stringName=Dong LI, firstName=Dong, middleName=null, lastName=LI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=School of Aerospace Engineering, Taiyuan University of Technology, Taiyuan 030024, Shanxi, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1325149974626971958, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, authorId=1325149973007970611, language=CN, stringName=李栋, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=太原理工大学航空航天学院, 山西 太原 030024, bio={"content":"

李 栋(2000-),男,硕士研究生,主要从事冲击动力学研究. E-mail:

"}, bioImg=null, bioContent=

李 栋(2000-),男,硕士研究生,主要从事冲击动力学研究. E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1325149971779039533, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, xref=null, ext=[AuthorCompanyExt(id=1325149972114583854, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, companyId=1325149971779039533, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Aerospace Engineering, Taiyuan University of Technology, Taiyuan 030024, Shanxi, China), AuthorCompanyExt(id=1325149972143943983, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, companyId=1325149971779039533, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=太原理工大学航空航天学院, 山西 太原 030024)])]), Author(id=1325149976359219513, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, 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=1325149977164525884, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, authorId=1325149976359219513, language=EN, stringName=Xiaobin ZHANG, firstName=Xiaobin, middleName=null, lastName=ZHANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=School of Aerospace Engineering, Taiyuan University of Technology, Taiyuan 030024, Shanxi, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1325149978473148734, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, authorId=1325149976359219513, language=CN, stringName=张晓斌, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=太原理工大学航空航天学院, 山西 太原 030024, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1325149971779039533, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, xref=null, ext=[AuthorCompanyExt(id=1325149972114583854, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, companyId=1325149971779039533, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Aerospace Engineering, Taiyuan University of Technology, Taiyuan 030024, Shanxi, China), AuthorCompanyExt(id=1325149972143943983, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, companyId=1325149971779039533, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=太原理工大学航空航天学院, 山西 太原 030024)])]), Author(id=1325149980557717824, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=liuzhifang@tyut.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1325149981421744450, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, authorId=1325149980557717824, language=EN, stringName=Zhifang LIU, firstName=Zhifang, middleName=null, lastName=LIU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=School of Aerospace Engineering, Taiyuan University of Technology, Taiyuan 030024, Shanxi, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1325149982675841347, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, authorId=1325149980557717824, language=CN, stringName=刘志芳, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=太原理工大学航空航天学院, 山西 太原 030024, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1325149971779039533, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, xref=null, ext=[AuthorCompanyExt(id=1325149972114583854, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, companyId=1325149971779039533, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Aerospace Engineering, Taiyuan University of Technology, Taiyuan 030024, Shanxi, China), AuthorCompanyExt(id=1325149972143943983, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, companyId=1325149971779039533, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=太原理工大学航空航天学院, 山西 太原 030024)])]), Author(id=1325149983502119237, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, 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=1325149985154675015, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, authorId=1325149983502119237, language=EN, stringName=Jianyin LEI, firstName=Jianyin, middleName=null, lastName=LEI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=School of Aerospace Engineering, Taiyuan University of Technology, Taiyuan 030024, Shanxi, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1325149986853368138, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, authorId=1325149983502119237, language=CN, stringName=雷建银, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=太原理工大学航空航天学院, 山西 太原 030024, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1325149971779039533, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, xref=null, ext=[AuthorCompanyExt(id=1325149972114583854, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, companyId=1325149971779039533, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Aerospace Engineering, Taiyuan University of Technology, Taiyuan 030024, Shanxi, China), AuthorCompanyExt(id=1325149972143943983, tenantId=1146029695717560320, journalId=1255847867265597444, articleId=1325149885359599853, companyId=1325149971779039533, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=太原理工大学航空航天学院, 山西 太原 030024)])])]
李栋 , 张晓斌, 刘志芳 , 雷建银
作者信息
  • 太原理工大学航空航天学院, 山西 太原 030024
通讯作者:
刘志芳(1971-),女,博士,教授,主要从事冲击动力学研究. E-mail:
作者简介:

李 栋(2000-),男,硕士研究生,主要从事冲击动力学研究. E-mail:

Impact Response and Design Optimization of Triangular Corrugated Sandwich Beams: A Machine Learning Approach
Dong LI , Xiaobin ZHANG, Zhifang LIU , Jianyin LEI
Affiliations
  • School of Aerospace Engineering, Taiyuan University of Technology, Taiyuan 030024, Shanxi, China
出版时间: 2026-07-05 doi: 10.11858/gywlxb.20251287
文章导航
收藏切换

为提高三角形波纹夹芯梁在低速冲击下的性能预测精度与结构设计效率,基于硬参数共享的多任务学习(multi task learning, MTL)框架,构建了一种面向夹芯梁冲击响应的机器学习建模与优化流程。基于有限元模型生成样本数据集,并参考已有实验结果对模型合理性进行校核。在此基础上训练MTL模型,实现了对结构比吸能、上面板最大挠度及初始峰值载荷的同步预测。结果表明,经贝叶斯优化后的MTL模型在50 J冲击能量下表现出较好的预测性能,预测结果与有限元模拟结果吻合较好,测试集中各输出量的决定系数均达到0.989以上,验证了该模型在响应预测与工程优化分析中的有效性和可靠性。参数敏感性分析表明:芯层胞元数量和芯层壁厚对结构刚度的影响最显著,其次为上面板厚度,而下面板厚度的影响相对较小;芯层壁厚在性能提升方面存在一定的饱和阈值。结合非支配排序遗传算法Ⅱ(NSGA-Ⅱ),分别对变形特性、吸能性能及综合性能开展多目标优化分析,获得了满足不同工程设计需求的夹芯梁最优参数构型。

机器学习  /  波纹夹芯梁  /  冲击响应  /  性能预测  /  结构优化

To enhance the prediction accuracy of low-velocity impact performance and improve the structural design efficiency of triangular corrugated sandwich beams, this paper proposes a machine learning modeling and optimization process for the impact response of sandwich beams based on a hard-parameter-sharing multi-task learning (MTL) framework. A sample dataset is generated using finite element models, and the rationality of the models is validated against existing experimental results. Subsequently, an MTL model is trained to simultaneously predict the structural specific energy absorption (SEA), the maximum deflection of the top panel, and the initial peak load. The results show that the MTL model optimized via Bayesian optimization demonstrates strong predictive performance under a 50 J impact energy condition. The predictions align well with the finite element simulation results, with the coefficient of determination R2 for all output variables in the test set exceeding 0.989, thereby validating the effectiveness and reliability of the model in response prediction and engineering optimization analysis. Parameter sensitivity analysis reveals that the core cell count and core wall thickness have the most significant influence on structural stiffness, followed by the top panel thickness, while the bottom panel thickness has a relatively minor impact. Moreover, the core wall thickness exhibits a certain saturation threshold in terms of performance enhancement. In combination with the non-dominated sorting genetic algorithm Ⅱ (NSGA-Ⅱ), multi-objective optimization analysis are conducted focusing on deformation characteristics, energy absorption performance, and comprehensive performance, and yields optimal parameter configurations that meet different engineering design requirements for sandwich beams.

machine learning  /  corrugated sandwich beam  /  impact response  /  performance prediction  /  structural optimization
李栋, 张晓斌, 刘志芳, 雷建银. 基于机器学习的三角形波纹夹芯梁的冲击响应与设计优化. 高压物理学报, 2026 , 40 (7) : 070111-1 -070111-17 . DOI: 10.11858/gywlxb.20251287
Dong LI, Xiaobin ZHANG, Zhifang LIU, Jianyin LEI. Impact Response and Design Optimization of Triangular Corrugated Sandwich Beams: A Machine Learning Approach[J]. Chinese Journal of High Pressure Physics, 2026 , 40 (7) : 070111-1 -070111-17 . DOI: 10.11858/gywlxb.20251287
夹芯梁由上、下面板和中间芯层组成,因其具有比刚度高、抗冲击性能优异和吸能能力强等优点,在航空航天、交通运输及国防军工等领域得到了广泛应用[1–2]。近年来,随着轻量化与安全性要求的提升,该类结构在高速列车和汽车等地面交通装备中的应用越来越多[3–4]。这是因为夹芯结构能够在减轻车体重量的同时提高吸能效率,从而增强车辆的结构安全性,符合未来高性能交通装备的发展趋势。
波纹夹芯梁作为典型的夹芯结构形式之一,因其独特的几何特性和优异的力学性能而受到广泛关注[5–6]。学者们通过实验和有限元模拟等方法,对波纹夹芯结构在动态载荷下的力学响应进行了系统研究。例如:Rubino等[7–8]研究了芯层方向和边界条件对船用波纹夹芯梁力学性能的影响,结果表明,与同质量整体梁相比,纵向芯层夹芯梁具有更优异的抗冲击性能,其中,芯层压痕是主要的失效模式,边界条件通过改变面板变形形式显著影响整体响应;St-Pierre等[9]对波纹夹芯梁的动态与准静态力学行为进行了对比研究,验证了准静态模型在低速冲击下的适用性;Xia等[10]结合实验、数值模拟与理论分析,系统研究了铝合金波纹夹芯梁在纵向弯曲工况下的力学响应,指出芯层几何参数对结构变形模式、峰值载荷及比吸能具有显著影响。
在工程研究与结构设计领域,传统实验测试与有限元数值模拟虽能较为准确地描述结构的响应规律,但其计算成本较高,在涉及多参数、多工况的迭代优化设计中,效率问题更为突出。基于代理模型的机器学习方法展现出了显著优势。该方法从已有数据中学习输入参数与结构响应之间的复杂关系,可以实现性能快速预测的同时,辅助完成从性能要求反推设计参数的逆向探索,显著提升设计效率[11–12]。在单任务学习(single-task learning, STL)框架下,神经网络、Kriging、支持向量回归(support vector regression, SVR)及LightGBM等模型已被用于结构响应预测,并与智能优化算法相结合,开展参数反演与结构优化设计。相关研究表明,该类方法能够在一定范围内实现结构性能的快速评估,代表性工作包括:Yang等[13]通过改进人工电场算法优化人工神经网络模型,实现了蜂窝夹芯防爆墙抗爆性能的预测与优化;Fang等[14]利用深度学习完成负泊松比点阵夹芯梁的逆向设计,并通过三点弯曲实验与有限元模拟验证了其优异性能;Andika等[15]结合有限元数据与机器学习,对4种负泊松比夹芯板构型进行了性能优化,结果表明,胞元厚度是影响抗爆性能的关键参数;Qiu等[16]将神经网络与麻雀搜索算法相结合,确定了船用波纹夹芯板的最优抗爆结构尺寸;Teimouri等[17]基于实验数据训练双深度神经网络模型,实现了夹芯梁力学性能与结构质量的联合预测与优化。
现有的多数代理模型研究通常针对单一性能指标分别建立预测模型,或在不同响应之间采用独立建模方法,难以描述结构多响应之间的内在相关性。对于波纹夹芯梁在低速冲击作用下的动力响应问题,比吸能、峰值载荷及变形特征等指标在物理机理上具有明显的相关性,采用独立的单任务代理模型往往需要分别建模与调参,在多目标优化过程中也可能引入预测不一致的问题。同时,针对波纹夹芯梁低速冲击响应的快速预测与多目标优化研究仍相对有限,且多数研究是在节点位置施加载荷,该加载方式有利于发挥结构整体刚度,与工程实际中冲击位置随机、载荷可能作用于节点间面板区域的情况存在一定差异。
基于上述研究背景,本研究选取2个相邻节点之间的中心位置作为冲击加载点,重点分析该不利工况下波纹芯层夹芯梁的非线性动力响应,在此基础上,引入基于硬参数共享的多任务学习(multi-task learning, MTL)模型架构,对比吸能、峰值载荷及变形响应等多个关键性能指标进行联合建模与预测。本工作的重点在于评估MTL框架在波纹夹芯梁低速冲击响应预测与工程优化中的适用性,探讨其在降低多响应代理建模复杂度及提升多目标优化一致性方面的潜在优势,从而为夹芯结构抗冲击性能的工程化设计提供一种可行的建模与优化思路。
所提出的波纹夹芯结构冲击响应预测方法和分析流程的总体研究框架如图1所示。
第1步:建立夹芯梁的有限元模型,并验证其有效性;然后,确定输入特征范围,采用拉丁超立方抽样(Latin hypercube sampling, LHS)方法在该范围内生成样本数据;利用编写的ABAQUS脚本对样本进行有限元模拟,获得波纹夹芯梁在低速冲击下的结构响应;最后,将所得的原始数据在[0, 1]区间内进行归一化预处理,作为机器学习模型的输入和输出样本。
第2步:构建机器学习模型,并使用预处理后的数据对模型进行训练与测试。采用MTL框架,通过贝叶斯优化算法确定模型的最优超参数,以确保训练后的MTL模型能够在保证预测精度的同时,具有较高的预测效率。
第3步:对MTL模型得到的冲击响应预测结果进行性能分析,并基于非支配排序遗传算法Ⅱ(non-dominated sorting genetic algorithm Ⅱ, NSGA-Ⅱ)开展结构参数优化,获得抗冲击性能最优的夹芯梁设计方案。
夹芯梁由上、下面板及中间的三角形波纹芯层组成,具体的几何构型和尺寸如图2所示。梁的总长度L=310 mm,宽度B=40 mm,胞元长度l=100 mm。上、下面板的厚度t1=t2=2 mm,芯层壁厚tc=1.8 mm,芯层高度Hc=46 mm。三角形波纹芯层倾斜板与下面板的夹角θ=46°。夹芯梁两端通过螺栓固定连接,螺栓直径d=12 mm。
LHS[18]是一种从多元参数分布中近似随机抽样的分层技术,能够在保证样本覆盖均匀性的同时,有效减少实现高预测精度所需的训练样本数量。在波纹夹芯梁的冲击响应研究中,主要影响因素包括:芯层胞元数量n、上面板厚度t1、芯层壁厚tc、下面板厚度t2。根据各参数的取值范围,利用LHS生成具有代表性的样本。然后,采用编写的ABAQUS脚本对这些样本进行有限元模拟,提取对应的结构响应数据,构建机器学习模型所需的数据集。
相比于单任务学习,MTL[19]能够在多个相关任务间共享从输入数据中提取的特征信息,从而提高模型的学习效率和泛化能力。该方法通过在不同任务间共享部分参数,减少了模型总参数数量,降低了过拟合风险,并提升了整体的预测稳定性。
本研究采用硬参数共享(hard parameter sharing, HPS)的MTL架构,该模型主要由输入层、共享层、私有层和输出层组成。各层神经元通过激活函数、权值和阈值相互连接,实现多目标响应的联合预测。模型结构如图3所示。
为提高网络训练的非线性拟合能力和收敛速度,模型采用ReLU(rectified linear unit)函数作为激活函数
$ \text{ReLU}(x)=\max (0,x) $
在模型训练过程中,为衡量模型输出与目标输出之间的逼近精度,采用神经网络的均方误差(mean square error, MSE)作为优化目标函数,其表达式如下
$ {\delta }_{\mathrm{MSE}}=\sum \limits_{m=1}^{M}\left[{K}_{m}\frac{1}{N}\sum \limits_{i=1}^{N}{\left(y_{i}^{(m)}-\hat{y}_{i}^{(m)}\right)}^{2}\right] $
式中:δMSE为MSE,M为任务总数,N为样本数量,Km为第m个任务的权重系数;$ y_{i}^{\left(m\right)} $和$ \hat{y}_{i}^{(m)} $分别为第i个样本在第m个任务中的真实值和预测值。本研究中,各任务权重K1∶K2∶K3=1∶1 ∶1。
为获得MTL模型的最优超参数组合,本研究采用贝叶斯优化(Bayesian optimization)[20]对模型进行自动化调参。该方法通过构建高斯过程(Gaussian process, GP)代理模型对目标函数进行建模,并依据预测的不确定性自适应地选择新的采样点,从而以较少的评估次数高效搜索全局最优解。高斯过程的一般定义形式为
$ f(x)\sim {\cal{GP}}(g(x), k(x,x')) $
式中:g(x)为均值函数,通常简化为常数或零函数,即g(x)=0;$ k(x,{x}^{\prime}) $为协方差函数(核函数),用于度量样本点x与$ {x}^{\prime} $之间的相关性。常用的核函数为平方指数核函数(squared exponential kernel),其表达式如下
$ k(x,{x}^{\prime})={\sigma }^{2}\exp \left(-\frac{\| x-{x}^{\prime}{\| }^{2}}{2{b}^{2}}\right) $
式中:σ2为控制方差,b为长度尺度参数。
NNSGA-Ⅱ是一种基于Pareto最优理论的多目标优化遗传算法[21],具有收敛速度快、全局搜索能力强和解集分布均匀等优点。在本研究中:首先,通过训练完成的MTL模型生成初始父代种群;然后,利用快速非支配排序对任意2个个体xi与xj进行比较,以实现解集的分层排序,并通过计算拥挤度距离衡量个体在目标空间的分布密度;在每一代进化过程中,算法依次执行选择、交叉和变异操作,以生成子代种群;接着,使用精英保留策略,将父代与子代种群合并后,按照非支配层级和拥挤距离进行筛选,最终保留最优个体群。通过不断迭代,可获得一组均匀分布且互不支配的最优解,即Pareto前沿(Pareto front)。
任意2个个体xi与xj之间的快速非支配排序可表示为
$ {\boldsymbol{x}}_{i}\prec {\boldsymbol{x}}_{j}\Leftrightarrow \begin{cases}\forall q\in [1,Q] &\;\;\; {f}_{q}({\boldsymbol{x}}_{i})\leqslant {f}_{q}({\boldsymbol{x}}_{j})\\\exists p\in [1,Q] &\;\;\; {f}_{p}({\boldsymbol{x}}_{i}) \lt {f}_{p}({\boldsymbol{x}}_{j})\end{cases} $
式中:若个体xi在所有目标上均不劣于个体xj,并且在至少1个目标上严格优于xj时,称个体xi支配个体xj;Q为目标函数的总数。
拥挤度的表达式为
$ {d}_{i}=\sum \limits_{q=1}^{Q}\frac{\left| f_{q}^{(i+1)}-f_{q}^{(i-1)}\right| }{f_{q}^{\max }-f_{q}^{\min }} $
式中:$ f_{q}^{(i+1)} $和$ f_{q}^{(i-1)} $分别为第q个目标上个体i相邻2个解的目标函数值;$ f_{q}^{\max } $和$ f_{q}^{\min } $分别为当前种群在第q个目标上的最大值和最小值。对于边界个体(极端解),其拥挤度设为无穷大,以确保其在选择过程中被优先保留。
夹芯梁的有限元模型如图4所示。模型中,夹具、螺栓及落锤均定义为刚体。夹芯梁通过2个M12螺栓固定在夹具盖板与底座之间,并施加预紧力,以模拟两端全固定边界条件。夹芯梁的上下面板、螺栓和夹具均采用减缩积分六面体单元(C3D8R),芯层采用减缩积分四边形壳单元(S4R)。夹芯梁和落锤的单元尺寸均为1 mm,夹具部分的单元尺寸为2 mm。
冲击载荷由直径为20 mm、质量为9.239 kg、冲击速度为v的落锤施加于夹芯梁上面板中心位置,该位置为夹芯梁最薄弱的部位。芯层与上下板之间通过ABAQUS中的壳-实体耦合(shell-to-solid coupling)约束进行连接,以保证界面处位移的连续性及载荷的有效传递。落锤与夹芯梁上面板之间定义为面-面接触,摩擦系数取0.16[22]。除上述接触外,其余各部件之间的相互作用采用通用接触定义。夹芯梁的有效长度λ=200 mm。
夹芯梁的上下面板与芯层均由A6N01S-T5铝合金材料制成,其主要材料参数如表1[23]所示。材料的本构关系采用Cowper-Symonds动力学模型描述,即
$ {\sigma }_{\mathrm{y}}=\left[1+{\left(\frac{\dot{\varepsilon }}{C}\right)}^{\tfrac{1}{{P}_{\mathrm{t}}}}\right]{\sigma }_{0} $
式中:$ {\sigma }_{\mathrm{y}} $为动态屈服应力,$ {\sigma }_{0} $为静态屈服应力,$ \dot{\varepsilon } $为应变率,C和Pt为材料常数。对于铝合金材料,通常取C=3257.69 s−1,Pt=1.95。
为验证模型的可靠性,将模拟结果与文献[24]中的实验结果进行对比。当冲击能量Ei为30、50和90 J时,对应的冲击速度v分别为2.55、3.29和4.42 m/s。图5显示了50 J冲击下非节点位置的变形模式及不同冲击能量下非节点和节点位置的力-位移曲线对比。结果表明:在节点位置冲击时,结构刚度较高,力-位移曲线迅速达到峰值,随后芯层的屈曲刚度下降;在非节点位置冲击时,面板弯曲主导变形,整体刚度较低,峰值载荷较小,且力-位移曲线平稳。考虑到实际冲击位置的随机性,本研究选择非节点位置进行后续分析与优化。表2列出了模拟得到的非节点位置的比吸能(specific energy absorption, SEA)Esa、上面板最大挠度δmax及峰值载荷Fmax,与实验结果较为一致,表明有限元模型能够较好地反映夹芯梁的冲击响应特性,可用于后续参数分析与结构优化研究。
在有限元分析中,采用Cowper-Symonds本构模型描述铝合金材料的应变率敏感性,但未显式考虑波纹芯层可能发生的局部屈曲或薄壁失效。局部屈曲会改变能量耗散路径,从而影响SEA的预测精度。因此,基于整体结构响应计算的SEA可能在极薄芯层或不利加载条件下偏保守。
在本研究中,芯层高度Hc=46 mm,冲击能量Ei=50 J。选取胞元数量n、上面板厚度t1、芯层壁厚tc以及下面板厚度t2作为输入特征。为进一步降低模型训练过程中的误差,额外引入芯层相对密度ρc作为输入参数,其计算公式为
$ {\rho }_{\text{c}}=\frac{2{t}_{\text{c}}}{l\sin \theta }\rho $
式中:ρ为材料密度,三角形波纹芯层倾斜板与下面板的夹角$ \theta =\arctan (2H_{\rm c}/l) $。参数取值范围见表3。
输出特征包括夹芯梁的比吸能Esa、上面板的最大挠度δmax以及初始峰值载荷Fmax。Esa的计算公式为
$ {E}_{\mathrm{sa}}=\frac{{E}_{\mathrm{p}}}{m} $
式中:Ep为结构的总吸能,可通过载荷-位移曲线积分获得;m为结构的总质量。
由于在低速冲击条件下,夹芯梁下面板的变形较小,故选取上面板的最大挠度δmax作为主要分析指标,以更准确地反映结构的变形特征。
使用针对离散参数的LHS变体生成共400组样本,并采用有限元模拟得到结果,抽样结果的样本分布如图6所示。随机抽取其中320组样本用于模型训练,其余80组用于模型检验。
根据第1.4节所述方法建立MTL模型,通过贝叶斯优化获得最优模型结构,其中:共享层设置为1层,包含64个神经元;私有层同样为1层,每个任务包含32个神经元。同时,为了防止过拟合,设置早停次数为20。采用第2.2节获得的数据集进行模型训练与测试。在测试集上,输出结果的决定系数R2、平均绝对误差(mean absolute error, MAE)δMAE与均方根误差(root mean square error, RMSE)δRMSE用于评估模型预测性能,其计算公式分别为
$ {R}^{2}=1-\frac{\displaystyle\sum \limits_{i=1}^{N}{({{y}_{i}}-{{\hat{y}}_{i}})}^{2}}{\displaystyle\sum \limits_{i=1}^{N}{({{y}_{i}}-\overline{y})}^{2}} $
$ \delta_{\text{MAE}}=\frac{1}{N}\sum\limits_{i=1}^N|y_i-\hat{y}_i| $
$ \delta_{\text{RMSE}}=\sqrt{\frac{1}{N}\sum \limits_{i=1}^{N}{({{y}_{i}}-{{\hat{y}}_{i}})}^{2}} $
式中:$ {y}_{i} $为第i个样本的实际值,$ {\hat{y}}_{i} $为第i个样本的预测值,$ \overline{y} $为实际值的平均值,N为样本数。R2越接近1,δMAE和δRMSE越接近零,则模型性能越好。
为验证MTL模型的性能,本研究将其与SVR模型进行对比分析。图7给出了2类模型在10次随机数据划分下的预测结果统计差异,并给出了各输出指标95%的置信区间。结果表明,置信区间宽度均小于0.012,说明2种模型均具有良好的重复性。
表4汇总了2种模型的平均评价指标及总训练时间tt与总预测时间tp。可以看出:SVR模型的结构相对简单,训练速度较快,但各输出指标的平均R2较低,且MAE和RMSE较高,拟合能力有限;而MTL模型虽然训练时间较长,但在拟合精度方面表现得更优异,能够更准确地预测夹芯梁的多项响应指标。
在10个MTL模型中,选择综合性能最优的模型用于后续分析与优化。图8给出了该模型的预测结果与有限元模拟结果的回归关系。结果表明,测试集上输出指标Esa、δmax和Fmax的R2分别为0.9895、0.9948和0.9897,均接近1,MAE和RMSE均接近零。上述结果表明,MTL模型在预测夹芯梁冲击响应方面具有较高的精度和较好的拟合能力。
基于训练完成的MTL模型,分析芯层几何参数对波纹夹芯梁冲击响应特性的影响。选取芯层胞元数量n、上面板厚度t1、芯层壁厚tc以及下面板厚度t2作为主要变量,研究其对Esa、δmax及Fmax的影响规律。
在保持t1=2 mm、tc=1.2 mm、t2=2 mm不变的条件下,利用MTL模型预测芯层胞元数量n(取2、4、6)对波纹夹芯梁冲击结构响应的影响规律。图9(a)给出了δmax和Fmax随n变化的预测结果。可以看出,随着n的增加,δmax呈下降趋势,而Fmax则升高。这主要是由于胞元数量增多导致芯层胞元间距减小,倾斜角增大,从而使芯层密度和整体刚度提高。结构的变形模式由整体弯曲逐渐转变为局部凹陷,如图10所示(U为位移)。刚度的增加限制了上面板的整体弯曲变形,导致δmax减小,同时Fmax增大。
图9(b)给出了夹芯梁的Esa随n变化的预测结果以及各组成部分吸能占比。结果表明,上面板和芯层是主要吸能区域。整体总吸能Ep随n的增加而升高,但Esa却呈下降趋势。这是因为,随着n的增加,结构的变形更趋于局部化,而结构质量的增加幅度超过了吸能能力的提升。上面板吸能占比随着n的增加先减小后增大,芯层和下面板的吸能占比则呈先增大后减小的变化规律。如图10(a)和图10(c)所示,当n=2时,芯层的支撑能力较弱,载荷主要集中在上面板,导致上面板的吸能占比较高;而n=6时,芯层的支撑能力增强,塑性变形减小,上面板的吸能占比再次上升。综上可知,随着n的增加,夹芯梁的能量分配逐渐趋于优化,其中n=4时,各部分吸能较为均衡,结构的综合性能较优。
在保持n=4、tc=1.2 mm、t2=2 mm不变的条件下,利用MTL模型分析上面板厚度t1(范围为1.6~2.4 mm)对波纹夹芯梁冲击结构响应的影响规律。
图11(a)给出了δmax和Fmax随t1变化的预测结果。可见,随着t1的增大,δmax呈逐渐下降趋势,而Fmax则持续增大。这是由于t1增大导致上面板的弯曲刚度提高,从而增强了其抵抗变形的能力,导致整体变形量减小,如图12所示。
图11(b)给出了Esa随t1变化的预测结果以及不同t1下各组成部分的吸能占比变化规律。可以看出,随着t1的增大,结构的Ep随之增大。然而,由于结构质量的增长幅度更为显著,导致Esa呈下降趋势。上面板的吸能占比随t1的增加呈先降低后升高的变化规律,而芯层和下面板的吸能占比则表现为先升高后降低。具体而言,当t1较小时,上面板的刚度较低,冲击点附近区域发生显著的塑性变形,导致能量主要集中在上面板局部消耗,传递至芯层和下面板的能量较少[25],如图12(a)所示。随着t1的增大,上面板的塑性变形减弱,更多冲击能量传递至芯层和下面板,使整体结构的能量吸收更均匀。当t1进一步增大并超过一定阈值后,上面板的刚度显著提升,再次成为主要的能量吸收部件,其吸能占比随之上升。
在保持n=4、t1=2 mm、t2=2 mm不变的条件下,利用MTL模型研究芯层壁厚tc(范围为0.8~1.6 mm)对波纹夹芯梁冲击结构响应的影响规律。
图13(a)给出了δmax和Fmax随tc变化的预测结果。结果表明,δmax随tc的增大先逐渐减小后趋于稳定,Fmax随tc增大先增大后趋于稳定。这是由于tc增加使得芯层密度和整体刚度升高,支撑能力增强,从而限制了上面板的变形,致使δmax降低,Fmax增大,如图14(a)和图14(b)所示。当tc=1.6 mm时,芯层塑性变形已不显著,变形模式基本稳定,进一步增加tc对δmax和Fmax的影响不显著,如图14(c)所示。
图13(b)给出了Esa随tc变化的预测结果以及夹芯梁各组成部分的吸能占比随tc的变化规律。随着tc的增大,结构的Ep上升,但Esa下降。具体而言,上面板的吸能占比随tc增大先下降后上升,芯层的吸能占比呈持续下降趋势,下面板的吸能占比先上升后下降。当tc=0.8 mm时,芯层支撑刚度较低,发生大范围塑性变形,吸收的能量较多,而传递给下面板的能量较少,导致下面板吸能占比低。当tc=1.2 mm时,芯层的塑性变形减小,吸收能量减少;随着tc继续增大,芯层的塑性变形进一步减小,芯层的吸能占比持续下降,而下面板的吸能占比先升高后下降。
在保持n=4、t1=2 mm、tc=1.2 mm不变的条件下,利用MTL模型研究下面板厚度t2(范围为1.6~2.4 mm)对波纹夹芯梁冲击结构响应的影响规律。
图15(a)给出了δmax和Fmax随t2变化的预测曲线。随着t2的增加,δmax和Fmax基本保持不变,表明t2对δmax和Fmax的影响很小。图15(b)给出了Esa随t2变化的预测曲线以及夹芯梁各组成部分的吸能占比随t2的变化。随着t2的增大,夹芯梁的Ep升高,但Esa下降。具体表现为,上面板的吸能占比下降,而芯层和下面板的吸能占比升高。这是由于下面板厚度增加导致其抗弯刚度增强,从而提高了抵抗变形能力,芯层压缩变形更加充分,如图16所示。在这种情况下,芯层仍能有效传递能量,同时下面板吸收的能量增多,因此,芯层和下面板的吸能占比呈上升趋势。
MTL模型作为一种高效的替代模型,可用于波纹夹芯梁结构的参数优化设计。为便于描述,可将训练得到的MTL模型表示为代理函数形式
$ [\overline{{E}_{\mathrm{sa}}},\overline{{\delta }_{\text{max}}},\overline{{F}_{\text{max}}}]={f}_{\mathrm{MTL}}(\overline{n},\overline{{t}_{1}},\overline{{t}_{\mathrm{c}}},\overline{{t}_{2}}) $
其中
$\begin{array}{c}\overline{n}=\dfrac{n-\min (n)}{\max (n)-\min (n)},\;\;\;\;\;\;\;\;\overline{{t}_{1}}=\dfrac{{t}_{1}-\min ({t}_{1})}{\max ({t}_{1})-\min ({t}_{1})},\\\overline{{t}_{\mathrm{c}}}=\dfrac{{t}_{\rm c}-\min ({t}_{\rm c})}{\max ({t}_{\rm c})-\min ({t}_{\rm c})},\;\;\;\;\;\;\;\;\overline{{t}_{2}}=\dfrac{{t}_{2}-\min ({t}_{2})}{\max ({t}_{2})-\min ({t}_{2})},\\\overline{{E}_{\mathrm{sa}}}=\dfrac{E_{\mathrm{sa}}^{-1}}{\max (E_{\mathrm{sa}}^{-1})},\;\;\;\;\;\;\;\;\overline{{\delta }_{\text{max}}}=\dfrac{{\delta }_{\max }}{\max ({\delta }_{\max })},\;\;\;\;\;\;\;\;\overline{{F}_{\text{max}}}=\dfrac{{F}_{\max }}{\max ({F}_{\max })}\end{array}$
NSGA-Ⅱ算法的参数设置如下:种群规模为200,交叉概率为0.9,变异概率为0.1,最大迭代代数为100。为获得综合性能最优解,采用最小距离选择法(the minimum distance selection method, TMDSM)确定距离理想最优解(utopia point)最近的综合最优解(knee point),其数学表达式[26]为
$ {D}_{\min }={\left[{\left(\frac{\overline{{E}_{\mathrm{sa}}}(x)}{\min (\overline{{E}_{\mathrm{sa}}}(x))}-1\right)}^{2}+{\left(\frac{\overline{{\delta }_{\text{max}}}(x)}{\min (\overline{{\delta }_{\text{max}}}(x))}-1\right)}^{2}+{\left(\frac{\overline{{F}_{\text{max}}}(x)}{\min (\overline{{F}_{\text{max}}}(x))}-1\right)}^{2}\right]}^{1/2} $
式中:$ \overline{{E}_{\mathrm{sa}}}(x) $、$ \overline{{\delta }_{\text{max}}}(x) $、$ \overline{{F}_{\text{max}}}(x) $分别为解x对应的比吸能、上面板最大挠度及初始峰值载荷。
为优化夹芯梁的变形性能,选取δmax和Fmax作为优化目标函数,对夹芯梁的结构进行优化。选取n、t1、tc和t2为决策变量,优化模型可写为
$\begin{array}{c} \min (\overline{{\delta }_{\text{max}}},\overline{{F}_{\text{max}}})={f}_{\mathrm{MTL}}(\overline{n},\overline{{t}_{1}},\overline{{t}_{\mathrm{c}}},\overline{{t}_{2}})\\\text{s.t.} \colon 0 \lt \overline{{\delta }_{\text{max}}},\overline{{F}_{\text{max}}},\overline{n},\overline{{t}_{1}},\overline{{t}_{\mathrm{c}}},\overline{{t}_{2}}\leqslant 1 \end{array}$
利用NSGA-Ⅱ算法对上述模型进行求解,获得的Pareto前沿如图17所示。该解集由100个相互非支配的最优解组成。从图17可以看出,δmax与Fmax存在明显的竞争关系:当结构变形减小时,峰值载荷呈上升趋势。
通过TMDSM方法确定的Pareto最优解对应的结构参数为:n=6,t1=2.4 mm,tc=1.0 mm,t2=1.6 mm,与原始结构参数的对比如表5所示。相较于对照组,优化后的δmax降低了22.71%,Fmax降低了21.35%。优化结果表明,较大的n可缩短胞元间距,提高芯层密度和刚度;较大的t1可增强结构的抗弯能力,从而有效抑制整体变形;较小的tc有助于降低Fmax;较小的t2则可减少结构总质量。这些参数的协调配置使夹芯梁在变形控制与载荷响应之间实现更优平衡。
为提高夹芯梁的吸能性能,以夹芯梁Esa和Fmax作为优化目标,对波纹夹芯梁的几何结构参数进行优化。选取n、t1、tc和t2为决策变量,建立的多目标优化模型可写为
$\begin{array}{c} \min (\overline{{E}_{\mathrm{sa}}},\overline{{F}_{\text{max}}})={f}_{\mathrm{MTL}}(\overline{n},\overline{{t}_{1}},\overline{{t}_{\mathrm{c}}},\overline{{t}_{2}}) \\\text{s.t.} \colon 0 \lt \overline{{E}_{\mathrm{sa}}},\overline{{F}_{\text{max}}},\overline{n},\overline{{t}_{1}},\overline{{t}_{\mathrm{c}}},\overline{{t}_{2}}\leqslant 1 \end{array} $
利用NSGA-Ⅱ算法对上述模型进行求解。结果表明,Esa和Fmax不存在显著的冲突关系,因此,Pareto解集迅速收敛至单一最优点。为了直观地展示优化过程,采用迭代历史图描绘Pareto解的收敛情况,其中迭代次数调整为50,如图18所示。可见,算法在第6次迭代时即收敛至最优解,表明优化过程稳定且高效。
通过TMDSM方法确定的最优解对应的结构参数为:n=2,t1=1.6 mm,tc=0.8 mm,t2=1.6 mm,与原始结构的对比如表6所示。相较于对照组,优化后结构的Esa提高了30.64%,而Fmax降低了59.70%,表现出显著的吸能性能提升和冲击响应优化效果。
根据第3节的分析可知,随着几何参数的增大,夹芯梁质量的增长速度超过吸能的提升幅度。因此,减小几何参数尺寸使结构整体刚度降低,有助于显著降低初始峰值载荷。综上,采用较小尺寸几何参数配置的夹芯梁在吸能效率与载荷控制方面表现最优。
为提高夹芯梁的综合性能,以Esa、δmax、Fmax作为多目标优化指标,对波纹夹芯梁的几何结构参数进行优化。选取n、t1、tc和t2为决策变量,优化模型可表示为
$\begin{array}{c}\min (\overline{{E}_{\mathrm{sa}}},\overline{{\delta }_{\text{max}}},\overline{{F}_{\text{max}}})={f}_{\mathrm{MTL}}(\overline{n},\overline{{t}_{1}},\overline{{t}_{\mathrm{c}}},\overline{{t}_{2}}) \\\text{s.t.} \colon 0 \lt \overline{{E}_{\mathrm{sa}}},\overline{{\delta }_{\text{max}}},\overline{{F}_{\text{max}}},\overline{n},\overline{{t}_{1}},\overline{{t}_{\mathrm{c}}},\overline{{t}_{2}}\leqslant 1\end{array}$
利用NSGA-Ⅱ算法求解该多目标优化问题,得到的Pareto前沿如图19所示,由100个相互非支配的最优解组成。
通过TMDSM方法选取的综合最优解对应的几何参数为:n=4,t1=2.3 mm,tc=0.9 mm,t2=1.6 mm,与原始结构的对比如表7所示。优化后结构的Esa提高了2.36%,δmax降低了5.64%,Fmax降低了29.92%。分析结果表明,当同时优化Esa、δmax和Fmax 3个目标时,由于目标之间存在竞争关系,Pareto前沿表明各性能提升空间有限,任何一项性能的显著提升都会以牺牲其他指标为代价。因此,在综合优化过程中采取折中策略,使各几何参数取中间值,或在Pareto解的引导下形成折中设计方案。该方案未追求单项性能极值,而是在相互竞争的指标间实现性能的平衡优化。
为排除MTL预测值与有限元仿真结果偶然吻合的可能性,对优化结果进行了可靠性验证。图20给出了各指标预测值与模拟值的相对误差及绝对误差,可以看出,所有指标的相对误差均未超过5%。此外,采用Wilcoxon符号秩检验对3项优化指标进行统计显著性分析。该检验的零假设为MTL预测值与有限元仿真值之间无显著差异,P>0.05表明在0.05显著性水平下不能拒绝原假设,即两者不存在统计显著差异。结果显示,Esa、δmax和Fmax的平均相对误差分别为2.05%、0.70%、2.68%,均在3%以内,P分别为0.50、0.50、0.75,均大于0.05,说明预测值与仿真值之间不存在统计显著差异,可以排除结果偶然性的影响。
本研究基于硬参数共享的MTL框架,构建了一种预测低速冲击载荷作用下夹芯梁结构响应的机器学习建模与优化流程。采用ABAQUS对夹芯梁冲击过程进行数值建模与批量仿真,所得数据用于模型训练与验证。结果表明,该MTL模型在预测精度与计算效率方面均表现稳定,可作为有限元分析的有效补充,用于夹芯梁冲击响应的快速预测评估。在此基础上,系统分析了几何参数对冲击响应的影响规律,并将模型应用于工程优化研究,得到如下主要结论。
(1) 经贝叶斯优化后的MTL模型在所研究的50 J冲击工况下能够同时实现多指标预测,其预测结果与有限元模拟结果保持较好的一致性,测试集中各输出量的R2均达到0.989以上,表明该模型不仅在预测精度方面表现良好,也可以作为有限元分析的辅助工具,用于响应预测与工程优化分析。
(2) 参数敏感性分析结果表明,随着芯层胞元数量n、上面板厚度t1、芯层壁厚tc及下面板厚度t2的增大,比吸能Esa均呈下降趋势。n和tc是影响上面板最大挠度δmax与初始峰值载荷Fmax的主要因素,且tc存在性能饱和阈值;t1的影响居中,而t2的作用相对较小。
(3) 多目标优化结果表明,不同设计目标对应不同的最优几何参数组合。当优化目标为控制结构变形并降低峰值载荷时,较大的n和t1以及较小的tc和t2更为有利;而当优化目标为提高比吸能并降低初始峰值载荷时,整体较小的几何参数配置更具优势。
本研究基于机器学习对夹芯梁冲击响应及优化设计进行了预测。后续工作将重点针对两方面内容进行深入研究:一是引入材料非线性与损伤演化机制,以提升模型在复杂载荷条件下的适用性;二是扩展至多种芯层结构及多尺度夹芯体系的优化设计,并探索与实时监测系统相结合,实现夹芯结构冲击响应的在线预测与自适应优化,为轻量化与高性能结构设计提供支撑。

参考文献 引证文献
排序方式:
[1]
ZHANG D J, ZHAO Z Y, DU S F, et al. Dynamic response of ultralight all-metallic sandwich panel with 3D tube cellular core to shallow-buried explosives [J]. Science China Technological Sciences, 2021, 64(7): 1371–1388.
[2]
LE V T, HA N S, GOO N S. Advanced sandwich structures for thermal protection systems in hypersonic vehicles: a review [J]. Composites Part B: Engineering, 2021, 226: 109301.
[3]
WANG J F, SHI C Y, YANG N, et al. Strength, stiffness, and panel peeling strength of carbon fiber-reinforced composite sandwich structures with aluminum honeycomb cores for vehicle body [J]. Composite Structures, 2018, 184: 1189–1196.
[4]
CHAHARDOLI S, ATTAR A A, GHORBANHOSSEINI S, et al. Investigation of the bending and crushing for the light-weight structures used in vehicle’s radiator [J]. Mechanics Based Design of Structures and Machines, 2023, 51(8): 4491–4507.
[5]
SHU C F, ZHAO S Y, HOU S J. Crashworthiness analysis of two-layered corrugated sandwich panels under crushing loading [J]. Thin-Walled Structures, 2018, 133: 42–51.
[6]
LIU K, ZONG S, LI Y, et al. Structural response of the U-type corrugated core sandwich panel used in ship structures under the lateral quasi-static compression load [J]. Marine Structures, 2022, 84: 103198.
[7]
RUBINO V, DESHPANDE V S, FLECK N A. The dynamic response of end-clamped sandwich beams with a Y-frame or corrugated core [J]. International Journal of Impact Engineering, 2008, 35(8): 829–844.
[8]
RUBINO V, DESHPANDE V S, FLECK N A. The three-point bending of Y-frame and corrugated core sandwich beams [J]. International Journal of Mechanical Sciences, 2010, 52(3): 485–494.
[9]
ST-PIERRE L, DESHPANDE V S, FLECK N A. The low velocity impact response of sandwich beams with a corrugated core or a Y-frame core [J]. International Journal of Mechanical Sciences, 2015, 91: 71–80.
[10]
XIA F K, YU T X, DURANDET Y, et al. Triangular corrugated sandwich panels under longitudinal bending [J]. Thin-Walled Structures, 2021, 169: 108359.
[11]
LIU J Z, LI S, GUO J C, et al. Machine learning (ML) based models for predicting the ultimate bending moment resistance of high strength steel welded I-section beam under bending [J]. Thin-Walled Structures, 2023, 191: 111051.
[12]
FORD E, MANEPARAMBIL K, KUMAR A, et al. Transfer (machine) learning approaches coupled with target data augmentation to predict the mechanical properties of concrete [J]. Machine Learning with Applications, 2022, 8: 100271.
[13]
YANG L, LIN H, WEI L C, et al. Application of a novel machine learning model for the prediction and optimization of anti-blast performance of sandwich honeycomb blast walls [J]. Ocean Engineering, 2024, 312: 119217.
[14]
FANG X, SHEN H S, WANG H. Three-point bending behaviors of sandwich beams with data-driven 3D auxetic lattice core based on deep learning [J]. Composite Structures, 2025, 354: 118751.
[15]
ANDIKA, SANTOSA S P, WIDAGDO D, et al. Design and multi-objective optimization of auxetic sandwich panels for blastworthy structures using machine learning method [J]. Applied Sciences, 2024, 14(23): 10831.
[16]
QIU W J, LIU K, ZONG S, et al. An optimisation method for anti-blast performance of corrugated sandwich plate structure based on neural network and sparrow search algorithm [J]. Ships and Offshore Structures, 2024, 19(8): 1028–1043.
[17]
TEIMOURI A, ALINIA M, KAMARIAN S, et al. Design optimization of additively manufactured sandwich beams through experimentation, machine learning, and imperialist competitive algorithm [J]. Journal of Engineering Design, 2024, 35(3): 320–337.
[18]
MCKAY M D, BECKMAN R J, CONOVER W J. A comparison of three methods for selecting values of input variables in the analysis of output from a computer code [J]. Technometrics, 1979, 21(2): 239–245.
[19]
CARUANA R. Multitask learning [J]. Machine Learning, 1997, 28(1): 41–75.
[20]
SNOEK J, LAROCHELLE H, ADAMS R P. Practical bayesian optimization of machine learning algorithms [C]//Proceedings of the 26th International Conference on Neural Information Processing Systems. Lake Tahoe: Curran Associates Inc., 2012: 2951–2959.
[21]
DEB K, PRATAP A, AGARWAL S, et al. A fast and elitist multiobjective genetic algorithm: NSGA-Ⅱ [J]. IEEE Transactions on Evolutionary Computation, 2002, 6(2): 182–197.
[22]
JING L, SU X Y, CHEN D, et al. Experimental and numerical study of sandwich beams with layered-gradient foam cores under low-velocity impact [J]. Thin-Walled Structures, 2019, 135: 227–244.
[23]
LIU Z S, YU Y Y, YANG Z, et al. Dynamic experimental studies of A6N01S-T5 aluminum alloy material and structure for high-speed trains [J]. Acta Mechanica Sinica, 2019, 35(4): 763–772.
[24]
YU Z H, LIU K, ZHOU X F, et al. Low-velocity impact response of aluminum alloy corrugated sandwich beams used for high-speed trains [J]. Thin-Walled Structures, 2023, 183: 110375.
[25]
荣吉利, 王圣龙, 陈子超, 等. 水下爆炸冲击载荷下波纹夹芯板动态响应及结构优化设计 [J]. 北京理工大学学报, 2024, 44(7): 679–691.
RONG J L, WANG S L, CHEN Z C, et al. Dynamic response and structural optimal design of corrugated sandwich panel subjected to underwater explosion impact loads [J]. Transactions of Beijing Institute of Technology, 2024, 44(7): 679–691.
[26]
卢传浩, 周宇琦, 曹勇, 等. 新型梯度连续可控夹层板抗冲击性能研究及优化 [J]. 力学学报, 2024, 56(6): 1713–1726.
LU C H, ZHOU Y Q, CAO Y, et al. Research and optimization of impact resistance of novel gradient continuous controllable sandwich panels [J]. Chinese Journal of Theoretical and Applied Mechanics, 2024, 56(6): 1713–1726.
2026年第40卷第7期
PDF下载
5
2
引用本文
BibTeX
文章信息
doi: 10.11858/gywlxb.20251287
  • 接收时间:2025-12-29
  • 首发时间:2026-11-05
  • 出版时间:2026-07-05
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2025-12-29
  • 修回日期:2026-02-13
基金
作者信息
    太原理工大学航空航天学院, 山西 太原 030024

通讯作者:

刘志芳(1971-),女,博士,教授,主要从事冲击动力学研究. E-mail:
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/gywlxb/CN/10.11858/gywlxb.20251287
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
科
Family
属数
Number of
genus
种数
Number of
species
占总种数比例
Percentage of
total species (%)
属
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