Article(id=1241831203842621709, tenantId=1146029695717560320, journalId=1241755870837649424, issueId=1241831200843699167, articleNumber=null, orderNo=null, doi=10.19636/j.cnki.cjsm42-1250/o3.2025.032, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1759161600000, receivedDateStr=2025-09-30, revisedDate=null, revisedDateStr=null, acceptedDate=null, acceptedDateStr=null, onlineDate=1774005231103, onlineDateStr=2026-03-20, pubDate=1761494400000, pubDateStr=2025-10-27, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1774005231103, onlineIssueDateStr=2026-03-20, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1774005231103, creator=13701087609, updateTime=1774005231103, updator=13701087609, issue=Issue{id=1241831200843699167, tenantId=1146029695717560320, journalId=1241755870837649424, year='2025', volume='46', issue='5', pageStart='571', pageEnd='706', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=1, specialIssue=null, createTime=1774005230388, creator=13701087609, updateTime=1774005316875, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1241831563734881184, tenantId=1146029695717560320, journalId=1241755870837649424, issueId=1241831200843699167, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1241831563739075489, tenantId=1146029695717560320, journalId=1241755870837649424, issueId=1241831200843699167, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=571, endPage=588, ext={EN=ArticleExt(id=1241831205390319887, articleId=1241831203842621709, tenantId=1146029695717560320, journalId=1241755870837649424, language=EN, title=A Data-Physics Hybrid Approach for Multiaxial Fatigue Life Prediction of Ti-6Al-4V Alloy, columnId=1241831201674171363, journalTitle=Chinese Journal of Solid Mechanics, columnName=Research Papers, runingTitle=null, highlight=null, articleAbstract=

With the increasing deployment of additively manufactured Ti-6Al-4V in aerospace and other high-performance structural applications, reliable prediction of fatigue life under complex multiaxial loading has become essential for safe design and lifecycle management. However, conventional data-driven approaches often lack predictive accuracy and physical consistency on small datasets and non-proportional multiaxial stress states, limiting their generalizability and interpretability. To address these limitations, this work computes the Mises equivalent stress directly from experimental loading histories and incorporates a Basquin-model-based theoretical fatigue life as prior physics knowledge. Building on this prior, we propose a residual connection-based physics-informed neural network (PI-Res) that learns only the datadriven residual relative to the theoretical life, thereby merging mechanistic fidelity with statistical adaptability. Using laser powder bed fusion (L-PBF) Ti-6Al-4V as the case material, we conduct a systematic comparison against representative purely data-driven baselines—artificial neural networks, random forests, and support vector regression—as well as three canonical data-physics fusion strategies: physics-informed feature engineering, physics-informed loss functions, and physics-informed residual connections. Across multiaxial loading scenarios and distinct life regimes, the PI-Res framework consistently demonstrates superior predictive accuracy alongside stronger adherence to physical trends implied by the stress-life relationship. Moreover, by anchoring the learning process to a mechanistic prior and delegating only the unexplained variance to the network, PI-Res improves robustness under data scarcity and enhances interpretability of model behavior. These findings indicate that residual-style injection of domain knowledge offers a principled pathway to reconcile small-sample constraints with mechanistic coherence in fatigue modeling. Practically, the proposed approach provides a reliable tool to support fatigue life assessment, design margins, and maintenance scheduling for additively manufactured components. Theoretically, it illustrates a transferable physics-data fusion paradigm that can be extended to other material systems and generalized multiaxial fatigue problems where integrating prior physics with flexible learners is crucial.

, correspAuthors=Yu'e Ma, authorNote=null, correspAuthorsNote=null, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=null, magXml=null, pdfUrl=null, pdf=null, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=null, mapNumber=null, authorCompany=null, fund=null, authors=null, authorsList=Xingyue Sun, Yunyu Liu, Yu'e Ma, Weihong Zhang), CN=ArticleExt(id=1241831211295900019, articleId=1241831203842621709, tenantId=1146029695717560320, journalId=1241755870837649424, language=CN, title=基于数据-物理融合驱动方法的Ti6Al4V多轴疲劳寿命预测研究, columnId=1241831201896469478, journalTitle=固体力学学报, columnName=研究论文, runingTitle=null, highlight=null, articleAbstract=

随着增材制造Ti-6Al-4V合金在航空航天与高性能结构领域的广泛应用,其在复杂载荷条件下的疲劳性能研究愈发重要. 针对传统数据驱动方法在小样本和多轴加载条件下存在预测精度不足与物理一致性欠缺的问题,本文以实验载荷计算Mises等效应力为基础,结合Basquin模型获得理论寿命作为先验,提出了一种基于残差连接的物理信息融合神经网络(PI-Res). 以激光粉末床融合(L-PBF)Ti-6Al-4V材料为研究对象,对比了人工神经网络、随机森林与支持向量回归等多种数据驱动方法性能,以及三种典型的数据-物理融合策略(物理信息特征工程、物理信息损失函数和物理信息残差连接). 结果表明,PI-Res模型在多轴加载条件下展现出更优的预测精度和物理一致性,能够兼顾不同寿命区间的适应性. 该研究为构建兼具可靠性与可解释性的疲劳寿命预测模型提供了新的思路与参考.

, correspAuthors=马玉娥, authorNote=null, correspAuthorsNote=
**E-mail:.
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=FZNhIBkjh47cQdrqXEkUnA==, magXml=MFNbXgHg+R6bZ1GkDhBVAA==, pdfUrl=null, pdf=E+o25jzje8rBskfBXO/fjg==, pdfFileSize=6974522, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=hIvnzOGDKUls7ZDrS1gtKQ==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=s27FS3+nXYpBigpu4dWo9A==, mapNumber=null, authorCompany=null, fund=null, authors=null, authorsList=孙兴悦, 刘耘宇, 马玉娥, 张卫红)}, authors=[Author(id=1241831211815993735, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1241831211937628555, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, authorId=1241831211815993735, language=EN, stringName=Xingyue Sun, firstName=Xingyue, middleName=null, lastName=Sun, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1School of Aeronautics, Northwestern Polytechnical University, Xi'an, 710072, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1241831212013126029, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, authorId=1241831211815993735, language=CN, stringName=孙兴悦, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1西北工业大学航空学院,西安,710072, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1241831211585307003, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, xref=1, ext=[AuthorCompanyExt(id=1241831211597889915, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, companyId=1241831211585307003, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1School of Aeronautics, Northwestern Polytechnical University, Xi'an, 710072), AuthorCompanyExt(id=1241831211606278524, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, companyId=1241831211585307003, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1西北工业大学航空学院,西安,710072)])]), Author(id=1241831212088623504, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, 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=1241831212201869717, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, authorId=1241831212088623504, language=EN, stringName=Yunyu Liu, firstName=Yunyu, middleName=null, lastName=Liu, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1School of Aeronautics, Northwestern Polytechnical University, Xi'an, 710072, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1241831212336087449, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, authorId=1241831212088623504, language=CN, stringName=刘耘宇, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1西北工业大学航空学院,西安,710072, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1241831211585307003, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, xref=1, ext=[AuthorCompanyExt(id=1241831211597889915, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, companyId=1241831211585307003, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1School of Aeronautics, Northwestern Polytechnical University, Xi'an, 710072), AuthorCompanyExt(id=1241831211606278524, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, companyId=1241831211585307003, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1西北工业大学航空学院,西安,710072)])]), Author(id=1241831212457722270, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=ma.yu.e@nwpu.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1241831212575162787, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, authorId=1241831212457722270, language=EN, stringName=Yu'e Ma, firstName=Yu'e, middleName=null, lastName=Ma, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, **, address=1School of Aeronautics, Northwestern Polytechnical University, Xi'an, 710072, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1241831212663243174, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, authorId=1241831212457722270, language=CN, stringName=马玉娥, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, **, address=1西北工业大学航空学院,西安,710072, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1241831211585307003, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, xref=1, ext=[AuthorCompanyExt(id=1241831211597889915, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, companyId=1241831211585307003, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1School of Aeronautics, Northwestern Polytechnical University, Xi'an, 710072), AuthorCompanyExt(id=1241831211606278524, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, companyId=1241831211585307003, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1西北工业大学航空学院,西安,710072)])]), Author(id=1241831214236107179, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, 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=1241831214324187569, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, authorId=1241831214236107179, language=EN, stringName=Weihong Zhang, firstName=Weihong, middleName=null, lastName=Zhang, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2School of Mechanical Engineering, Northwestern Polytechnical University, Xi'an, 710072, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1241831214424850867, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, authorId=1241831214236107179, language=CN, stringName=张卫红, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2西北工业大学机电学院,西安,710072, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1241831211681776000, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, xref=2, ext=[AuthorCompanyExt(id=1241831211690164610, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, companyId=1241831211681776000, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2School of Mechanical Engineering, Northwestern Polytechnical University, Xi'an, 710072), AuthorCompanyExt(id=1241831211698553219, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, companyId=1241831211681776000, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2西北工业大学机电学院,西安,710072)])])], keywords=[Keyword(id=1241831214538097078, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, language=EN, orderNo=1, keyword=multiaxial fatigue), Keyword(id=1241831214613594553, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, language=EN, orderNo=2, keyword=life prediction), Keyword(id=1241831214735229372, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, language=EN, orderNo=3, keyword=Ti-6Al-4V), Keyword(id=1241831214840086975, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, language=EN, orderNo=4, keyword=physics-informed), Keyword(id=1241831214923973058, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, language=EN, orderNo=5, keyword=machine learning), Keyword(id=1241831214999470533, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, language=CN, orderNo=1, keyword=多轴疲劳), Keyword(id=1241831215074968008, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, language=CN, orderNo=2, keyword=寿命预测), Keyword(id=1241831215209185740, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, language=CN, orderNo=3, keyword=Ti6Al4V), Keyword(id=1241831215326626258, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, language=CN, orderNo=4, keyword=物理信息), Keyword(id=1241831215427289559, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, language=CN, orderNo=5, keyword=机器学习)], refs=[Reference(id=1241831220338819676, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, doi=null, pmid=null, pmcid=null, year=2020, volume=63, issue=22, pageStart=54, pageEnd=62, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=谢勇, 王福德, 从保强, 严振宇, 董鹏, journalName=航空制造技术, refType=null, unstructuredReference=谢勇, 王福德, 从保强, 严振宇, 董鹏. 电弧增材制造Ti-6Al-4V组织和力学性能调控研究进展[J]. 航空制造技术, 2020, 63(22): 54-62., articleTitle=电弧增材制造Ti-6Al-4V组织和力学性能调控研究进展, refAbstract=null), Reference(id=1241831220414317150, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, doi=null, pmid=null, pmcid=null, year=2020, volume=63, issue=22, pageStart=54, pageEnd=62, url=null, language=null, rfNumber=[1], rfOrder=1, authorNames=Xie Y, Wang F D, Cong B Q, Yan Z Y, Dong P, journalName=Aeronautical Manufacturing Technology, refType=null, unstructuredReference=(Xie Y, Wang F D, Cong B Q, Yan Z Y, Dong P. A review of micro-structure and mechanical properties in wire arc additive manufactured titanium alloys[J]. Aeronautical Manufacturing Technology, 2020, 63(22): 54-62. (in Chinese)), articleTitle=A review of micro-structure and mechanical properties in wire arc additive manufactured titanium alloys, refAbstract=null), Reference(id=1241831220523369055, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, doi=null, pmid=null, pmcid=null, year=2017, volume=4, issue=8, pageStart=8971, pageEnd=8982, url=null, language=null, rfNumber=[2], rfOrder=2, authorNames=Singh P, Pungotra H, Kalsi N S, journalName=Materials today: proceedings, refType=null, unstructuredReference=Singh P, Pungotra H, Kalsi N S. On the characteristics of titanium alloys for the aircraft applications[J]. Materials today: proceedings, 2017, 4(8): 8971-8982., articleTitle=On the characteristics of titanium alloys for the aircraft applications, refAbstract=null), Reference(id=1241831220636615267, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, doi=null, pmid=null, pmcid=null, year=2018, volume=145, issue=null, pageStart=80, pageEnd=89, url=null, language=null, rfNumber=[3], rfOrder=3, authorNames=Gai X, Bai Y, Li J, Li S J, Hou W T, Hao Y L, Zhang X, Yang R, Misra R D K, journalName=Corrosion Science, refType=null, unstructuredReference=Gai X, Bai Y, Li J, Li S J, Hou W T, Hao Y L, Zhang X, Yang R, Misra R D K. Electrochemical behaviour of passive film formed on the surface of Ti-6Al-4V alloys fabricated by electron beam melting[J]. Corrosion Science, 2018, 145: 80-89., articleTitle=Electrochemical behaviour of passive film formed on the surface of Ti-6Al-4V alloys fabricated by electron beam melting, refAbstract=null), Reference(id=1241831220733084262, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, doi=null, pmid=null, pmcid=null, year=2021, volume=44, issue=10, pageStart=2625, pageEnd=2642, url=null, language=null, rfNumber=[4], rfOrder=4, authorNames=Renzo D A, Sgambitterra E, Maletta C, Furgiuele F, Biffi C A, Fiocchi J, Tuissi A, journalName=Fatigue & Fracture of Engineering Materials & Structures, refType=null, unstructuredReference=Renzo D A, Sgambitterra E, Maletta C, Furgiuele F, Biffi C A, Fiocchi J, Tuissi A. Multiaxial fatigue behavior of SLM Ti6Al4V alloy under different loading conditions[J]. Fatigue & Fracture of Engineering Materials & Structures, 2021, 44(10): 2625-2642., articleTitle=Multiaxial fatigue behavior of SLM Ti6Al4V alloy under different loading conditions, refAbstract=null), Reference(id=1241831220829553257, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, doi=null, pmid=null, pmcid=null, year=2019, volume=18, issue=null, pageStart=914, pageEnd=920, url=null, language=null, rfNumber=[5], rfOrder=5, authorNames=Renzo D A, Sgambitterra E, Magarò P, Furgiuele F, Maletta C, Biffi C, Fiocchi J, Tuissi A, journalName=Procedia Structural Integrity, refType=null, unstructuredReference=Renzo D A, Sgambitterra E, Magarò P, Furgiuele F, Maletta C, Biffi C, Fiocchi J, Tuissi A. Multiaxial fatigue behavior of additive manufactured Ti-6Al-4V under in-phase stresses[J]. Procedia Structural Integrity, 2019, 18: 914-920., articleTitle=Multiaxial fatigue behavior of additive manufactured Ti-6Al-4V under in-phase stresses, refAbstract=null), Reference(id=1241831220905050731, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, doi=null, pmid=null, pmcid=null, year=2023, volume=33, issue=03, pageStart=781, pageEnd=791, url=null, language=null, rfNumber=[6], rfOrder=6, authorNames=郑战光, 张剑, 孙腾, 谢昌吉, 黄增, journalName=中国有色金属学报, refType=null, unstructuredReference=郑战光, 张剑, 孙腾, 谢昌吉, 黄增. 基于多轴载荷相位差的神经网络预测钛合金疲劳寿命[J]. 中国有色金属学报, 2023, 33(03): 781-791., articleTitle=基于多轴载荷相位差的神经网络预测钛合金疲劳寿命, refAbstract=null), Reference(id=1241831221001519726, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, doi=null, pmid=null, pmcid=null, year=2023, volume=33, issue=03, pageStart=781, pageEnd=791, url=null, language=null, rfNumber=[6], rfOrder=7, authorNames=Zheng Z G, Zhang J, Sun T, Xie C H, Huang Z, journalName=The Chinese Journal of Nonferrous Metals, refType=null, unstructuredReference=(Zheng Z G, Zhang J, Sun T, Xie C H, Huang Z. Multi-axial fatigue life prediction of titanium alloy based on neural network of load phase difference[J]. The Chinese Journal of Nonferrous Metals, 2023, 33(03): 781-791. (in Chinese)), articleTitle=Multi-axial fatigue life prediction of titanium alloy based on neural network of load phase difference, refAbstract=null), Reference(id=1241831221102183026, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, doi=null, pmid=null, pmcid=null, year=2022, volume=65, issue=Z1, pageStart=20, pageEnd=31, url=null, language=null, rfNumber=[7], rfOrder=8, authorNames=兰亮, 白澄岩, 高双, 何博, 王江, journalName=航空制造技术, refType=null, unstructuredReference=兰亮, 白澄岩, 高双, 何博, 王江. 电子束熔化成形Ti-6Al-4V钛合金研究进展和应用现状[J]. 航空制造技术, 2022, 65(Z1): 20-31., articleTitle=电子束熔化成形Ti-6Al-4V钛合金研究进展和应用现状, refAbstract=null), Reference(id=1241831221186069109, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, doi=null, pmid=null, pmcid=null, year=2022, volume=65, issue=Z1, pageStart=20, pageEnd=31, url=null, language=null, rfNumber=[7], rfOrder=9, authorNames=Lan L, Bai C Y, Gao S, He B, Wang J, journalName=Aeronautical Manufacturing Technology, refType=null, unstructuredReference=(Lan L, Bai C Y, Gao S, He B, Wang J. Research progress and application status of Ti-6Al-4V titanium alloy fabricated via electron beam melting[J]. Aeronautical Manufacturing Technology, 2022, 65(Z1): 20-31. (in Chinese)), articleTitle=Research progress and application status of Ti-6Al-4V titanium alloy fabricated via electron beam melting, refAbstract=null), Reference(id=1241831221316092536, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, doi=null, pmid=null, pmcid=null, year=2022, volume=46, issue=08, pageStart=100, pageEnd=104, url=null, language=null, rfNumber=[8], rfOrder=10, authorNames=赵金猛, 卢林, 王静荣, 张亮, 吴文恒, journalName=机械工程材料, refType=null, unstructuredReference=赵金猛, 卢林, 王静荣, 张亮, 吴文恒. 工艺参数对激光选区熔化成形Ti6Al4V合金致密性的影响[J]. 机械工程材料, 2022, 46(08): 100-104., articleTitle=工艺参数对激光选区熔化成形Ti6Al4V合金致密性的影响, refAbstract=null), Reference(id=1241831221420950140, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, doi=null, pmid=null, pmcid=null, year=2022, volume=46, issue=08, pageStart=100, pageEnd=104, url=null, language=null, rfNumber=[8], rfOrder=11, authorNames=Zhao J M, Lu L, Wang J R, Zhang L, Wu W H, journalName=Journal of Mechanical Engineering Materials, refType=null, unstructuredReference=(Zhao J M, Lu L, Wang J R, Zhang L, Wu W H. Effect of process parameters on compactness of Ti6Al4V alloy formed by laser selective melting[J]. Journal of Mechanical Engineering Materials, 2022, 46(08): 100-104. (in Chinese)), articleTitle=Effect of process parameters on compactness of Ti6Al4V alloy formed by laser selective melting, refAbstract=null), Reference(id=1241831221534196353, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, doi=null, pmid=null, pmcid=null, year=2023, volume=43, issue=06, pageStart=36, pageEnd=43, url=null, language=null, rfNumber=[9], rfOrder=12, authorNames=戴志伟, 吴亚东, 朱伟健, 王泽铭, 苏磊, 彭康, 王红洁, journalName=航空材料学报, refType=null, unstructuredReference=戴志伟, 吴亚东, 朱伟健, 王泽铭, 苏磊, 彭康, 王红洁. 制备工艺对多孔Ti6Al4V微观结构和性能的影响[J]. 航空材料学报, 2023, 43(06): 36-43., articleTitle=制备工艺对多孔Ti6Al4V微观结构和性能的影响, refAbstract=null), Reference(id=1241831221643248257, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, doi=null, pmid=null, pmcid=null, year=2023, volume=43, issue=06, pageStart=36, pageEnd=43, url=null, language=null, rfNumber=[9], rfOrder=13, authorNames=Dai Z W, Wu Y D, Zhu W J, Wang Z M, Su L, Peng K, Wang H J, journalName=Journal of Aeronautical Materials, refType=null, unstructuredReference=(Dai Z W, Wu Y D, Zhu W J, Wang Z M, Su L, Peng K, Wang H J. Effects of preparation process on micro-structure and properties of porous Ti6Al4V[J]. Journal of Aeronautical Materials, 2023, 43(06): 36-43. (in Chinese)), articleTitle=Effects of preparation process on micro-structure and properties of porous Ti6Al4V, refAbstract=null), Reference(id=1241831221718745732, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, doi=null, pmid=null, pmcid=null, year=2020, volume=130, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[10], rfOrder=14, authorNames=Sun W B, Ma Y E, Huang W, Zhang W H, Qian X D, journalName=International Journal of Fatigue, refType=null, unstructuredReference=Sun W B, Ma Y E, Huang W, Zhang W H, Qian X D. Effects of build direction on tensile and fatigue performance of selective laser melting Ti6Al4V titanium alloy[J]. International Journal of Fatigue, 2020, 130: 105260., articleTitle=Effects of build direction on tensile and fatigue performance of selective laser melting Ti6Al4V titanium alloy, refAbstract=null), Reference(id=1241831223169974918, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, doi=null, pmid=null, pmcid=null, year=2024, volume=56, issue=7, pageStart=1892, pageEnd=1915, url=null, language=null, rfNumber=[11], rfOrder=15, authorNames=胡雅楠, 余欢, 吴圣川, 奥妮, 阚前华, 吴正凯, 康国政, journalName=力学学报, refType=null, unstructuredReference=胡雅楠, 余欢, 吴圣川, 奥妮, 阚前华, 吴正凯, 康国政. 基于机器学习的增材制造合金材料力学性能预测研究进展与挑战[J]. 力学学报, 2024, 56(7): 1892-1915., articleTitle=基于机器学习的增材制造合金材料力学性能预测研究进展与挑战, refAbstract=null), Reference(id=1241831223262249607, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, doi=null, pmid=null, pmcid=null, year=2024, volume=56, issue=7, pageStart=1892, pageEnd=1915, url=null, language=null, rfNumber=[11], rfOrder=16, authorNames=Hu Y, Yu H, Wu S C, Ao N, Kan Q H, Wu G Z, Kang G Z, journalName=Chinese Journal of Theoretical and Applied Mechanics, refType=null, unstructuredReference=(Hu Y, Yu H, Wu S C, Ao N, Kan Q H, Wu G Z, Kang G Z. Machine learned mechanical properties prediction of additively manufactured metallic alloys: progress and challenges[J]. Chinese Journal of Theoretical and Applied Mechanics, 2024, 56(7): 1892-1915. (in Chinese)), articleTitle=Machine learned mechanical properties prediction of additively manufactured metallic alloys: progress and challenges, refAbstract=null), Reference(id=1241831223341941386, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, doi=null, pmid=null, pmcid=null, year=2025, volume=47, issue=02, pageStart=44, pageEnd=52, url=null, language=null, rfNumber=[12], rfOrder=17, authorNames=张颛利, 孙兴悦, 陈旭, journalName=机械强度, refType=null, unstructuredReference=张颛利, 孙兴悦, 陈旭. 基于物理信息神经网络的金属多轴疲劳寿命预测进展[J]. 机械强度, 2025, 47(02): 44-52., articleTitle=基于物理信息神经网络的金属多轴疲劳寿命预测进展, refAbstract=null), Reference(id=1241831223463576205, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, doi=null, pmid=null, pmcid=null, year=2025, volume=47, issue=02, pageStart=44, pageEnd=52, url=null, language=null, rfNumber=[12], rfOrder=18, authorNames=Zhang Z L, Sun X Y, Chen X, journalName=Journal of Mechanical Strength, refType=null, unstructuredReference=(Zhang Z L, Sun X Y, Chen X. Development in metal multiaxial fatigue life prediction based on physics-informed neural network[J]. Journal of Mechanical Strength, 2025, 47(02): 44-52. (in Chinese)), articleTitle=Development in metal multiaxial fatigue life prediction based on physics-informed neural network, refAbstract=null), Reference(id=1241831223560045199, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, doi=null, pmid=null, pmcid=null, year=2023, volume=284, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[13], rfOrder=19, authorNames=Wang H J, Li B, Gong J G, Xuan F Z, journalName=Engineering Fracture Mechanics, refType=null, unstructuredReference=Wang H J, Li B, Gong J G, Xuan F Z. Machine learning-based fatigue life prediction of metal materials: Perspectives of physics-informed and data-driven hybrid methods[J]. Engineering Fracture Mechanics, 2023, 284: 109242., articleTitle=Machine learning-based fatigue life prediction of metal materials: Perspectives of physics-informed and data-driven hybrid methods, refAbstract=null), Reference(id=1241831223635542673, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, doi=null, pmid=null, pmcid=null, year=2021, volume=23, issue=12, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[14], rfOrder=20, authorNames=Sun W B, Ma Y E, Zhang W H, Qian X D, Huang W, Wang Z H, journalName=Advanced Engineering Materials, refType=null, unstructuredReference=Sun W B, Ma Y E, Zhang W H, Qian X D, Huang W, Wang Z H. Effects of the build direction on mechanical performance of laser powder bed fusion additively manufactured Ti6Al4V under different loadings[J]. Advanced Engineering Materials, 2021, 23(12): 2100611., articleTitle=Effects of the build direction on mechanical performance of laser powder bed fusion additively manufactured Ti6Al4V under different loadings, refAbstract=null), Reference(id=1241831223740400278, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, doi=null, pmid=null, pmcid=null, year=2022, volume=135, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[15], rfOrder=21, authorNames=He Y X, Ma Y E, Zhang W H, Wang Z H, journalName=Engineering Failure Analysis, refType=null, unstructuredReference=He Y X, Ma Y E, Zhang W H, Wang Z H. Effects of build direction on thermal exposure and creep performance of SLM Ti6Al4V titanium alloy[J]. Engineering Failure Analysis, 2022, 135: 106063., articleTitle=Effects of build direction on thermal exposure and creep performance of SLM Ti6Al4V titanium alloy, refAbstract=null), Reference(id=1241831223828480663, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, doi=null, pmid=null, pmcid=null, year=2021, volume=244, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[16], rfOrder=22, authorNames=Li P Y, Ma Y E, Sun W B, Qian X D, Zhang W H, Wang Z H, journalName=Engineering Fracture Mechanics, refType=null, unstructuredReference=Li P Y, Ma Y E, Sun W B, Qian X D, Zhang W H, Wang Z H. Fracture and failure behavior of additive manufactured Ti6Al4V lattice structures under compressive load[J]. Engineering Fracture Mechanics, 2021, 244: 107537., articleTitle=Fracture and failure behavior of additive manufactured Ti6Al4V lattice structures under compressive load, refAbstract=null), Reference(id=1241831223920755352, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, doi=null, pmid=null, pmcid=null, year=2022, volume=160, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[17], rfOrder=23, authorNames=Sun W B, Ma Y E, Li P Y, Wang Z H, journalName=International Journal of Fatigue, refType=null, unstructuredReference=Sun W B, Ma Y E, Li P Y, Wang Z H. Residual stress and long fatigue crack growth behaviour of laser powder bed fused Ti6Al4V: Role of build direction[J]. International Journal of Fatigue, 2022, 160: 106850., articleTitle=Residual stress and long fatigue crack growth behaviour of laser powder bed fused Ti6Al4V: Role of build direction, refAbstract=null), Reference(id=1241831224050778777, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, doi=null, pmid=null, pmcid=null, year=2025, volume=193, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[18], rfOrder=24, authorNames=Lindström S B, Moverare J, Franke M, Persson J, Leidermark D, Thore C J, Lindström T, Kapidžić Z, journalName=International Journal of Fatigue, refType=null, unstructuredReference=Lindström S B, Moverare J, Franke M, Persson J, Leidermark D, Thore C J, Lindström T, Kapidžić Z. Fatigue life prediction for PBF-LB Ti6A14V with asbuilt surface under nonproportional loads using an incremental fatigue damage model[J]. International Journal of Fatigue, 2025, 193: 108777., articleTitle=Fatigue life prediction for PBF-LB Ti6A14V with asbuilt surface under nonproportional loads using an incremental fatigue damage model, refAbstract=null), Reference(id=1241831224130470553, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, doi=null, pmid=null, pmcid=null, year=2021, volume=241, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[19], rfOrder=25, authorNames=Nalli F, Cortese L, Concli F, journalName=Engineering Fracture Mechanics, refType=null, unstructuredReference=Nalli F, Cortese L, Concli F. Ductile damage assessment of Ti6Al4V, 17-4PH and AlSi10Mg for additive manufacturing[J]. Engineering Fracture Mechanics, 2021, 241: 107395., articleTitle=Ductile damage assessment of Ti6Al4V, 17-4PH and AlSi10Mg for additive manufacturing, refAbstract=null), Reference(id=1241831224222745242, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, doi=null, pmid=null, pmcid=null, year=2017, volume=100, issue=null, pageStart=347, pageEnd=366, url=null, language=null, rfNumber=[20], rfOrder=26, authorNames=Fatemi A, Molaei R, Sharifimehr S, Phan N, Shamsaei N, journalName=International Journal of Fatigue, refType=null, unstructuredReference=Fatemi A, Molaei R, Sharifimehr S, Phan N, Shamsaei N. Multiaxial fatigue behavior of wrought and additive manufactured Ti-6Al-4V including surface finish effect[J]. International Journal of Fatigue, 2017, 100: 347-366., articleTitle=Multiaxial fatigue behavior of wrought and additive manufactured Ti-6Al-4V including surface finish effect, refAbstract=null), Reference(id=1241831224310825626, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, doi=null, pmid=null, pmcid=null, year=2025, volume=16, issue=5, pageStart=1048, pageEnd=1091, url=null, language=null, rfNumber=[21], rfOrder=27, authorNames=Yu W Q, Sun X Y, Chen X, journalName=International Journal of Structural Integrity, refType=null, unstructuredReference=Yu W Q, Sun X Y, Chen X. From mechanism empirical to physics-informed: a comprehensive review of multiaxial non-proportional low-cycle fatigue life prediction[J]. International Journal of Structural Integrity, 2025, 16(5): 1048-1091., articleTitle=From mechanism empirical to physics-informed: a comprehensive review of multiaxial non-proportional low-cycle fatigue life prediction, refAbstract=null), Reference(id=1241831224436654749, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, doi=null, pmid=null, pmcid=null, year=2016, volume=90, issue=null, pageStart=526, pageEnd=533, url=null, language=null, rfNumber=[22], rfOrder=28, authorNames=Moghaddam T B, Soltani M, Shahraki H S, Shamshirband S, Noor N B M, Karim M R, journalName=Measurement, refType=null, unstructuredReference=Moghaddam T B, Soltani M, Shahraki H S, Shamshirband S, Noor N B M, Karim M R. The use of SVR-FFA in estimating fatigue life of polyethylene terephthalate modified asphalt mixtures[J]. Measurement, 2016, 90: 526-533., articleTitle=The use of SVR-FFA in estimating fatigue life of polyethylene terephthalate modified asphalt mixtures, refAbstract=null), Reference(id=1241831224549900959, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, doi=null, pmid=null, pmcid=null, year=2021, volume=145, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[23], rfOrder=29, authorNames=Zhan Z X, Li H, journalName=International Journal of Fatigue, refType=null, unstructuredReference=Zhan Z X, Li H. A novel approach based on the elastoplastic fatigue damage and machine learning models for life prediction of aerospace alloy parts fabricated by additive manufacturing[J]. International Journal of Fatigue, 2021, 145: 106089., articleTitle=A novel approach based on the elastoplastic fatigue damage and machine learning models for life prediction of aerospace alloy parts fabricated by additive manufacturing, refAbstract=null), Reference(id=1241831224658952865, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, doi=null, pmid=null, pmcid=null, year=2023, volume=176, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[24], rfOrder=30, authorNames=Zhou T G, Sun X Y, Chen X, journalName=International Journal of Fatigue, refType=null, unstructuredReference=Zhou T G, Sun X Y, Chen X. A multiaxial low-cycle fatigue prediction method under irregular loading by ANN model with knowledge-based features[J]. International Journal of Fatigue, 2023, 176: 107868., articleTitle=A multiaxial low-cycle fatigue prediction method under irregular loading by ANN model with knowledge-based features, refAbstract=null), Reference(id=1241831224772199075, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, doi=null, pmid=null, pmcid=null, year=2023, volume=167, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[25], rfOrder=31, authorNames=Sun X Y, Zhou T G, Song K, Chen X, journalName=International Journal of Fatigue, refType=null, unstructuredReference=Sun X Y, Zhou T G, Song K, Chen X. An image recognition based multiaxial low-cycle fatigue life prediction method with CNN model[J]. International Journal of Fatigue, 2023, 167: 107324., articleTitle=An image recognition based multiaxial low-cycle fatigue life prediction method with CNN model, refAbstract=null), Reference(id=1241831224868668069, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, doi=null, pmid=null, pmcid=null, year=2024, volume=295, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[26], rfOrder=32, authorNames=Zhou T G, Sun X Y, Yu Z, Chen X, journalName=Engineering Fracture Mechanics, refType=null, unstructuredReference=Zhou T G, Sun X Y, Yu Z, Chen X. A generalization ability-enhanced image recognition based multiaxial fatigue life prediction method for complex loading conditions[J]. Engineering Fracture Mechanics, 2024, 295: 109802., articleTitle=A generalization ability-enhanced image recognition based multiaxial fatigue life prediction method for complex loading conditions, refAbstract=null), Reference(id=1241831224986108584, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, doi=null, pmid=null, pmcid=null, year=2021, volume=151, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[27], rfOrder=33, authorNames=Yang J Y, Kang G Z, Liu Y J, Kan Q H, journalName=International Journal of Fatigue, refType=null, unstructuredReference=Yang J Y, Kang G Z, Liu Y J, Kan Q H. A novel method of multiaxial fatigue life prediction based on deep learning[J]. International Journal of Fatigue, 2021, 151: 106356., articleTitle=A novel method of multiaxial fatigue life prediction based on deep learning, refAbstract=null), Reference(id=1241831225090966188, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, doi=null, pmid=null, pmcid=null, year=2021, volume=3, issue=6, pageStart=422, pageEnd=440, url=null, language=null, rfNumber=[28], rfOrder=34, authorNames=Karniadakis G E, Kevrekidis I G, Lu L, Perdikaris P, Wang S, Yang L, journalName=Nature Reviews Physics, refType=null, unstructuredReference=Karniadakis G E, Kevrekidis I G, Lu L, Perdikaris P, Wang S, Yang L. Physics-informed machine learning[J]. Nature Reviews Physics, 2021, 3(6): 422-440., articleTitle=Physics-informed machine learning, refAbstract=null), Reference(id=1241831225204212400, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, doi=null, pmid=null, pmcid=null, year=2023, volume=98, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[29], rfOrder=35, authorNames=He G Y, Zhao Y X, Yan C L, journalName=European Journal of Mechanics-A/Solids, refType=null, unstructuredReference=He G Y, Zhao Y X, Yan C L. MFLP-PINN: A physics-informed neural network for multiaxial fatigue life prediction[J]. European Journal of Mechanics-A/Solids, 2023, 98: 104889., articleTitle=MFLP-PINN: A physics-informed neural network for multiaxial fatigue life prediction, refAbstract=null), Reference(id=1241831225300681393, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, doi=null, pmid=null, pmcid=null, year=2025, volume=193, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[30], rfOrder=36, authorNames=Liao H Y, Pan J, Su X H, Sun X Y, Chen X, journalName=International Journal of Fatigue, refType=null, unstructuredReference=Liao H Y, Pan J, Su X H, Sun X Y, Chen X. A path-dependent adaptive physics-informed neural network for multiaxial fatigue life prediction[J]. International Journal of Fatigue, 2025, 193: 108799., articleTitle=A path-dependent adaptive physics-informed neural network for multiaxial fatigue life prediction, refAbstract=null), Reference(id=1241831225392956081, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, doi=null, pmid=null, pmcid=null, year=2023, volume=166, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[31], rfOrder=37, authorNames=Zhou T T, Jiang S, Han T, Zhu S P, Cai Y N, journalName=International Journal of Fatigue, refType=null, unstructuredReference=Zhou T T, Jiang S, Han T, Zhu S P, Cai Y N. A physically consistent framework for fatigue life prediction using probabilistic physics-informed neural network[J]. International Journal of Fatigue, 2023, 166: 107234., articleTitle=A physically consistent framework for fatigue life prediction using probabilistic physics-informed neural network, refAbstract=null), Reference(id=1241831225506202290, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, doi=null, pmid=null, pmcid=null, year=2023, volume=289, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[32], rfOrder=38, authorNames=He G Y, Zhao Y X, Yan C L, journalName=Engineering Fracture Mechanics, refType=null, unstructuredReference=He G Y, Zhao Y X, Yan C L. Multiaxial fatigue life prediction using physics-informed neural networks with sensitive features[J]. Engineering Fracture Mechanics, 2023, 289: 109456., articleTitle=Multiaxial fatigue life prediction using physics-informed neural networks with sensitive features, refAbstract=null), Reference(id=1241831225632031414, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, doi=null, pmid=null, pmcid=null, year=2022, volume=221, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[33], rfOrder=39, authorNames=Peng X, Wu S, Qian W J, Bao J G, Hu Y N, Zhan Z X, Guo G P, Withers P J, journalName=International Journal of Mechanical Sciences, refType=null, unstructuredReference=Peng X, Wu S, Qian W J, Bao J G, Hu Y N, Zhan Z X, Guo G P, Withers P J. The potency of defects on fatigue of additively manufactured metals[J]. International Journal of Mechanical Sciences, 2022, 221: 107185., articleTitle=The potency of defects on fatigue of additively manufactured metals, refAbstract=null), Reference(id=1241831225720111800, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, doi=null, pmid=null, pmcid=null, year=2022, volume=222, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[34], rfOrder=40, authorNames=Salvati E, Tognan A, Laurenti L, Pelegatti M, Bona F D, journalName=Materials & Design, refType=null, unstructuredReference=Salvati E, Tognan A, Laurenti L, Pelegatti M, Bona F D. A defect-based physics-informed machine learning framework for fatigue finite life prediction in additive manufacturing[J]. Materials & Design, 2022, 222: 111089., articleTitle=A defect-based physics-informed machine learning framework for fatigue finite life prediction in additive manufacturing, refAbstract=null), Reference(id=1241831225833358010, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, doi=null, pmid=null, pmcid=null, year=2023, volume=381, issue=2260, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[35], rfOrder=41, authorNames=Zhou T G, Sun X Y, Chen X, journalName=Philosophical Transactions of the Royal Society A, refType=null, unstructuredReference=Zhou T G, Sun X Y, Chen X. A physics-guided modelling method of artificial neural network for multiaxial fatigue life prediction under irregular loading[J]. Philosophical Transactions of the Royal Society A, 2023, 381(2260): 20220392., articleTitle=A physics-guided modelling method of artificial neural network for multiaxial fatigue life prediction under irregular loading, refAbstract=null), Reference(id=1241831225942409917, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, doi=null, pmid=null, pmcid=null, year=2017, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[36], rfOrder=42, authorNames=Lundberg S M, Lee S I, journalName=null, refType=null, unstructuredReference=Lundberg S M, Lee S I. A unified approach to interpreting model predictions: Advances in neural information processing systems 30 (NIPS 2017), Long Beach, CA, 2017[C]., articleTitle=A unified approach to interpreting model predictions: Advances in neural information processing systems 30 (NIPS 2017), refAbstract=null), Reference(id=1241831226043073216, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, doi=null, pmid=null, pmcid=null, year=2022, volume=218, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[37], rfOrder=43, authorNames=Zhang Z Y, Liu Q Y, Wu D Z, journalName=Materials & Design, refType=null, unstructuredReference=Zhang Z Y, Liu Q Y, Wu D Z. Predicting stress-strain curves using transfer learning: Knowledge transfer across polymer composites[J]. Materials & Design, 2022, 218: 110700., articleTitle=Predicting stress-strain curves using transfer learning: Knowledge transfer across polymer composites, refAbstract=null)], funds=[Fund(id=1241831220250739290, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, awardId=12302098, language=CN, fundingSource=国家重大科技项目和国家自然科学基金项目(12302098), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1241831211585307003, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, xref=1, ext=[AuthorCompanyExt(id=1241831211597889915, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, companyId=1241831211585307003, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1School of Aeronautics, Northwestern Polytechnical University, Xi'an, 710072), AuthorCompanyExt(id=1241831211606278524, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, companyId=1241831211585307003, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1西北工业大学航空学院,西安,710072)]), AuthorCompany(id=1241831211681776000, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, xref=2, ext=[AuthorCompanyExt(id=1241831211690164610, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, companyId=1241831211681776000, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2School of Mechanical Engineering, Northwestern Polytechnical University, Xi'an, 710072), AuthorCompanyExt(id=1241831211698553219, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, companyId=1241831211681776000, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2西北工业大学机电学院,西安,710072)])], figs=[ArticleFig(id=1241831215595061732, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, language=EN, label=Fig.1, caption=The distribution of multiaxial fatigue experimental data for LPBF Ti6Al4V, figureFileSmall=/yZaiDJ1NGZzr1/9xfjtow==, figureFileBig=hIvnzOGDKUls7ZDrS1gtKQ==, tableContent=null), ArticleFig(id=1241831215720890856, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, language=CN, label=图1, caption=LPBF增材制造Ti6Al4V多轴疲劳试验数据分布, figureFileSmall=/yZaiDJ1NGZzr1/9xfjtow==, figureFileBig=hIvnzOGDKUls7ZDrS1gtKQ==, tableContent=null), ArticleFig(id=1241831215934800369, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, language=EN, label=Fig.2, caption=The schematic diagram of data-driven machine learning model algorithm, figureFileSmall=AZEW6e3ukAKzXqR+ttRuRg==, figureFileBig=lBZ87QwucdJbzHn+xyttxw==, tableContent=null), ArticleFig(id=1241831216089989622, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, language=CN, label=图2, caption=数据驱动机器学习模型算法示意图, figureFileSmall=AZEW6e3ukAKzXqR+ttRuRg==, figureFileBig=lBZ87QwucdJbzHn+xyttxw==, tableContent=null), ArticleFig(id=1241831216169681402, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, language=EN, label=Fig.3, caption=The schematic diagram of physical information data-driven model algorithm, figureFileSmall=n0259+xRpDPAZfUY5jBWZg==, figureFileBig=b0M9YR/5vsGQbBEzn6daTg==, tableContent=null), ArticleFig(id=1241831216253567487, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, language=CN, label=图3, caption=物理信息数据驱动模型算法示意图, figureFileSmall=n0259+xRpDPAZfUY5jBWZg==, figureFileBig=b0M9YR/5vsGQbBEzn6daTg==, tableContent=null), ArticleFig(id=1241831216345842178, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, language=EN, label=Fig.4, caption=The box plot of data-driven model prediction performance, figureFileSmall=td5KKi1coKxelwzUqYcopg==, figureFileBig=wchGoNhrcLkw+Vccy7AgRQ==, tableContent=null), ArticleFig(id=1241831216425533957, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, language=CN, label=图4, caption=数据驱动模型预测性能箱线图, figureFileSmall=td5KKi1coKxelwzUqYcopg==, figureFileBig=wchGoNhrcLkw+Vccy7AgRQ==, tableContent=null), ArticleFig(id=1241831216509420043, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, language=EN, label=Fig.5, caption=The fatigue life distribution predicted by data-driven models, figureFileSmall=tLt4atBGz6eky1tjOJMfnA==, figureFileBig=5Eh+aONMSk4dIA8W0M7ETg==, tableContent=null), ArticleFig(id=1241831216580723215, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, language=CN, label=图5, caption=数据驱动模型预测的疲劳寿命分布, figureFileSmall=tLt4atBGz6eky1tjOJMfnA==, figureFileBig=5Eh+aONMSk4dIA8W0M7ETg==, tableContent=null), ArticleFig(id=1241831216668803602, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, language=EN, label=Fig.6, caption=The feature importance analysis of data driven models based on SHAP algorithm, figureFileSmall=2JRdjABEhDYAgIKOZUV2zg==, figureFileBig=Qlkp0ik7TZ4W4AHVWHvkMQ==, tableContent=null), ArticleFig(id=1241831216777855512, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, language=CN, label=图6, caption=基于SHAP算法的数据驱动模型特征重要性分析, figureFileSmall=2JRdjABEhDYAgIKOZUV2zg==, figureFileBig=Qlkp0ik7TZ4W4AHVWHvkMQ==, tableContent=null), ArticleFig(id=1241831216920461851, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, language=EN, label=Fig.7, caption=Prediction performance of different physical informed neural network architectures, figureFileSmall=z5RzG6CNehN7rwwbWpaaAA==, figureFileBig=2G33wej9ylllhCLooUQcqg==, tableContent=null), ArticleFig(id=1241831217071456798, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, language=CN, label=图7, caption=不同物理信息神经网络架构的预测性能, figureFileSmall=z5RzG6CNehN7rwwbWpaaAA==, figureFileBig=2G33wej9ylllhCLooUQcqg==, tableContent=null), ArticleFig(id=1241831217155342881, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, language=EN, label=Fig.8, caption=The distribution of multiaxial fatigue life of Ti6Al4V material predicted by physical informed data-driven model, figureFileSmall=BhoG4VjFhLws6C3GkVAFtg==, figureFileBig=zDcJJFr7kqYe9JqaYhiTcQ==, tableContent=null), ArticleFig(id=1241831217222451750, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, language=CN, label=图8, caption=基于物理信息数据驱动模型预测的Ti6Al4V材料多轴疲劳寿命分布, figureFileSmall=BhoG4VjFhLws6C3GkVAFtg==, figureFileBig=zDcJJFr7kqYe9JqaYhiTcQ==, tableContent=null), ArticleFig(id=1241831218724012590, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, language=EN, label=Fig.9, caption=Prediction performance of physics-informed data-driven models under different loading paths, figureFileSmall=34+6qLb4I6FgqFEYY3HbcQ==, figureFileBig=GgXsoJvSOyQRpUrqUCvs+Q==, tableContent=null), ArticleFig(id=1241831218828870190, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, language=CN, label=图9, caption=不同加载路径下物理信息数据驱动模型的预测效果, figureFileSmall=34+6qLb4I6FgqFEYY3HbcQ==, figureFileBig=GgXsoJvSOyQRpUrqUCvs+Q==, tableContent=null), ArticleFig(id=1241831218912756272, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, language=EN, label=Fig.10, caption=The schematic diagram of transfer learning based on fine-tuning method, figureFileSmall=YLRBmOBnFusx133Rx8tsWQ==, figureFileBig=PJnQaE42hZA5OtYh2c7Hfw==, tableContent=null), ArticleFig(id=1241831218988253746, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, language=CN, label=图10, caption=基于微调的迁移学习示意图, figureFileSmall=YLRBmOBnFusx133Rx8tsWQ==, figureFileBig=PJnQaE42hZA5OtYh2c7Hfw==, tableContent=null), ArticleFig(id=1241831219080528439, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, language=EN, label=Fig.11, caption=Model prediction performance under different transfer learning conditions, figureFileSmall=Kn8pDn9SLcLCn0wSMHV8rg==, figureFileBig=cNaKL2YqygXmyFwp0urBvQ==, tableContent=null), ArticleFig(id=1241831219147637306, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, language=CN, label=图11, caption=不同迁移学习条件下模型预测性能, figureFileSmall=Kn8pDn9SLcLCn0wSMHV8rg==, figureFileBig=cNaKL2YqygXmyFwp0urBvQ==, tableContent=null), ArticleFig(id=1241831219227329085, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, language=EN, label=Fig.12, caption=Prediction performance of Res PINN model for Ti6Al4V machined materials with and without transfer learning conditions, figureFileSmall=yPoH1RBpTgCOJP3j4GEFuw==, figureFileBig=NQhVkTdE02BqV9fiG4+1ow==, tableContent=null), ArticleFig(id=1241831219315409473, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, language=CN, label=图12, caption=Res-PINN模型在迁移学习和无迁移学习条件下的表面加工Ti6Al4V材料预测效果, figureFileSmall=yPoH1RBpTgCOJP3j4GEFuw==, figureFileBig=NQhVkTdE02BqV9fiG4+1ow==, tableContent=null), ArticleFig(id=1241831219403489859, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, language=EN, label=Table 1, caption=

Multiaxial fatigue experimental data of as-built LPBF Ti6Al4V specimens

, figureFileSmall=null, figureFileBig=null, tableContent=
加载路径σa(MPa)εa(%)τa(MPa)γa(%)σMises(MPa)疲劳寿命(2Nf
Axial3320.3020033220780
Axial2230.2030022353990
Axial1910.1740019193952
Axial1910.1740019136668
Axial1400.12800140818690
Axial1000.089001006981714
Torsion006031.4471044498
Torsion004431.06176715708
Torsion003120.74954036558
Torsion002830.67949028924
Torsion002670.64046257500
Torsion002140.512371159194
Torsion001920.460333253442
Torsion001910.458331286220
Torsion001850.443320236442
Torsion001850.443320469430
IP2340.2131350.32433135236
IP2330.2121340.32232943916
IP1350.123780.187191355618
IP1350.122780.186191144922
IP600.0541040.249190626392
IP1330.122770.185188191602
IP1090.099630.1511542803040
), ArticleFig(id=1241831219512541766, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, language=CN, label=表1, caption=

表面未加工L-PBF Ti6Al4V多轴疲劳实验数据

, figureFileSmall=null, figureFileBig=null, tableContent=
加载路径σa(MPa)εa(%)τa(MPa)γa(%)σMises(MPa)疲劳寿命(2Nf
Axial3320.3020033220780
Axial2230.2030022353990
Axial1910.1740019193952
Axial1910.1740019136668
Axial1400.12800140818690
Axial1000.089001006981714
Torsion006031.4471044498
Torsion004431.06176715708
Torsion003120.74954036558
Torsion002830.67949028924
Torsion002670.64046257500
Torsion002140.512371159194
Torsion001920.460333253442
Torsion001910.458331286220
Torsion001850.443320236442
Torsion001850.443320469430
IP2340.2131350.32433135236
IP2330.2121340.32232943916
IP1350.123780.187191355618
IP1350.122780.186191144922
IP600.0541040.249190626392
IP1330.122770.185188191602
IP1090.099630.1511542803040
), ArticleFig(id=1241831219629982281, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, language=EN, label=Table 2, caption=

Multiaxial fatigue experimental data of machined LPBF Ti6Al4V specimens

, figureFileSmall=null, figureFileBig=null, tableContent=
加载路径σa(MPa)εa(%)τa(MPa)γa(%)σMises(MPa)疲劳寿命(2Nf
Axial3500.3190035087246
Axial2680.24400268170240
Axial2050.18700205246796
Axial2040.18600204193132
Torsion006452.003111772
Torsion005511.2499543098
Torsion004150.97671923650
Torsion003500.82360657668
Torsion003500.823606113380
Torsion002620.617454155366
Torsion002100.494364530916
IP3760.3422170.5115322098
IP3760.3422170.51153223380
IP2830.2571630.38440048844
IP2130.1941220.288300222850
IP1630.148940.2212303623270
OP4750.4332740.64567113304
OP3000.2731730.40742446200
OP2680.2441550.36537954046
OP2050.1871180.273289574256
), ArticleFig(id=1241831219730645580, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, language=CN, label=表2, caption=

表面加工L-PBF Ti6Al4V多轴疲劳实验数据

, figureFileSmall=null, figureFileBig=null, tableContent=
加载路径σa(MPa)εa(%)τa(MPa)γa(%)σMises(MPa)疲劳寿命(2Nf
Axial3500.3190035087246
Axial2680.24400268170240
Axial2050.18700205246796
Axial2040.18600204193132
Torsion006452.003111772
Torsion005511.2499543098
Torsion004150.97671923650
Torsion003500.82360657668
Torsion003500.823606113380
Torsion002620.617454155366
Torsion002100.494364530916
IP3760.3422170.5115322098
IP3760.3422170.51153223380
IP2830.2571630.38440048844
IP2130.1941220.288300222850
IP1630.148940.2212303623270
OP4750.4332740.64567113304
OP3000.2731730.40742446200
OP2680.2441550.36537954046
OP2050.1871180.273289574256
), ArticleFig(id=1241831219852280400, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, language=EN, label=Table A1, caption=

The hyperparameters of data-driven models and data-physics hybrid models

, figureFileSmall=null, figureFileBig=null, tableContent=
模型超参数取值
ANN网络层数5
SVR神经元个数7-64-32-16-1
激活函数ReLU
核函数径向基函数
正则化参数C100
gamma参数0.1
RFepsilon参数0.1
决策树数量100
最大树深度10
PF-ANN网络层数5
PF-SVR神经元个数8-64-32-16-1
激活函数ReLU
核函数径向基函数
正则化参数C100
gamma参数0.1
PF-RFepsilon参数0.1
决策树数量100
最大树深度10
PI-Loss网络层数5
PI-Res神经元个数7-64-32-16-1
激活函数LeakyReLU
网络层数5
神经元个数7-64-32-16-1
激活函数LeakyReLU
), ArticleFig(id=1241831219952943696, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, language=CN, label=表A1, caption=

数据驱动模型及数据-物理融合模型的超参数情况

, figureFileSmall=null, figureFileBig=null, tableContent=
模型超参数取值
ANN网络层数5
SVR神经元个数7-64-32-16-1
激活函数ReLU
核函数径向基函数
正则化参数C100
gamma参数0.1
RFepsilon参数0.1
决策树数量100
最大树深度10
PF-ANN网络层数5
PF-SVR神经元个数8-64-32-16-1
激活函数ReLU
核函数径向基函数
正则化参数C100
gamma参数0.1
PF-RFepsilon参数0.1
决策树数量100
最大树深度10
PI-Loss网络层数5
PI-Res神经元个数7-64-32-16-1
激活函数LeakyReLU
网络层数5
神经元个数7-64-32-16-1
激活函数LeakyReLU
), ArticleFig(id=1241831220041024083, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, language=EN, label=Table B1, caption=

The hyperparameters of data-driven models and data-physics hybrid models

, figureFileSmall=null, figureFileBig=null, tableContent=
材料参数Ti6Al4V As-builtTi6Al4V Machined
疲劳强度系数(MPa)33592994
疲劳强度指数-0.241-0.198
), ArticleFig(id=1241831220154270294, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241831203842621709, language=CN, label=表B1, caption=

增材制造Ti6Al4V材料疲劳参数情况

, figureFileSmall=null, figureFileBig=null, tableContent=
材料参数Ti6Al4V As-builtTi6Al4V Machined
疲劳强度系数(MPa)33592994
疲劳强度指数-0.241-0.198
)], attaches=null, journal=Journal(id=1241752460218384393, delFlag=0, nameCn=固体力学学报, nameEn=Chinese Journal of Solid Mechanics, nameHistory1=null, nameHistory2=null, issn=0254-7805, eissn=null, cn=42-1250/O3, coden=null, periodic=1, 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=QijUwme6mcFRwEfHnJkyaw==, journalPrice=null, startedYear=null, abbrevIsoEn=Chinese Journal of Solid Mechanics, journalRemark=null, publicationField=null, createdTime=1773986457163, updatedTime=1773987385031, createdBy=18614031015, updatedBy=13701087609, firstLetterCn=C, firstLetterEn=C, subjectCode=Engineering, subjectName=null, subjectCodeEn=Engineering, subjectNameEn=null, picCn=QijUwme6mcFRwEfHnJkyaw==, picEn=3rj3gh183UJiEfa2LeH0yw==, jcr=null, cjcr=null, exts=[JournalExt(id=1241756352066941240, language=CN, name=固体力学学报, 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=1773987385050, updatedTime=1773987385050, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=http://manu39.magtech.com.cn/Journalx_gtlxxb/authorLogOn.action, submissionEditorUrl=http://manu39.magtech.com.cn/Journalx_gtlxxb/editorLogOn.action, submissionReviewUrl=http://manu39.magtech.com.cn/Journalx_gtlxxb/expertLogOn.action, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1241756352121467193, language=EN, name=Chinese Journal of Solid Mechanics, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1773987385063, updatedTime=1773987385063, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=http://manu39.magtech.com.cn/Journalx_gtlxxb/authorLogOn.action, submissionEditorUrl=http://manu39.magtech.com.cn/Journalx_gtlxxb/editorLogOn.action, submissionReviewUrl=http://manu39.magtech.com.cn/Journalx_gtlxxb/expertLogOn.action, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1241755870837649424, websiteList=[Website(id=1241757301007242027, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1241755870837649424, 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/gtlxxb/CN, language=CN, createTime=1773987611295, createBy=18614031015, updateTime=1773987633317, updateBy=18614031015, name=固体力学学报-中文, tplId=1146099689490845704, title=固体力学学报, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1241757704407012157, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1241757301007242027, code=articleTextType, value=kx, createTime=1773987707473, updateTime=1773987707473, creator=18614031015, updator=18614031015), WebsiteProps(id=1241757704386040634, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1241757301007242027, code=banner, value=null, createTime=1773987707468, updateTime=1773987707468, creator=18614031015, updator=18614031015), WebsiteProps(id=1241757704427983680, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1241757301007242027, code=grayFlag, value=0, createTime=1773987707478, updateTime=1773987707478, creator=18614031015, updator=18614031015), WebsiteProps(id=1241757704381846329, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1241757301007242027, code=logo, value=https://castjournals.cast.org.cn/joweb/gtlxxb/CN/file/pic?fileId=gh/BtLvApxKS7pGvgd4faA==, createTime=1773987707467, updateTime=1773987707467, creator=18614031015, updator=18614031015), WebsiteProps(id=1241757704453149506, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1241757301007242027, code=minRunFlag, value=0, createTime=1773987707484, updateTime=1773987707484, creator=18614031015, updator=18614031015), WebsiteProps(id=1241757704398623548, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1241757301007242027, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/gtlxxb/CN/file/pic, createTime=1773987707471, updateTime=1773987707471, creator=18614031015, updator=18614031015), WebsiteProps(id=1241757704436372289, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1241757301007242027, code=silenceFlag, value=0, createTime=1773987707481, updateTime=1773987707481, creator=18614031015, updator=18614031015), WebsiteProps(id=1241757704394429243, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1241757301007242027, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1773987707470, updateTime=1773987707470, creator=18614031015, updator=18614031015), WebsiteProps(id=1241757704415400766, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1241757301007242027, code=themeColor, value=null, createTime=1773987707475, updateTime=1773987707475, creator=18614031015, updator=18614031015), WebsiteProps(id=1241757704423789375, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1241757301007242027, code=themeStyle, value=null, createTime=1773987707477, updateTime=1773987707477, creator=18614031015, updator=18614031015)]), Website(id=1241757301070156588, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1241755870837649424, 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/gtlxxb/EN, language=EN, createTime=1773987611311, createBy=18614031015, updateTime=1773987648333, updateBy=18614031015, name=固体力学学报-英文, tplId=1146101810881728533, title=Chinese Journal of Solid Mechanics, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1241757732924093216, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1241757301070156588, code=articleTextType, value=kx, createTime=1773987714272, updateTime=1773987714272, creator=18614031015, updator=18614031015), WebsiteProps(id=1241757732865372957, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1241757301070156588, code=banner, value=null, createTime=1773987714258, updateTime=1773987714258, creator=18614031015, updator=18614031015), WebsiteProps(id=1241757732953453347, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1241757301070156588, code=grayFlag, value=0, createTime=1773987714279, updateTime=1773987714279, creator=18614031015, updator=18614031015), WebsiteProps(id=1241757732836012828, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1241757301070156588, code=logo, value=https://castjournals.cast.org.cn/joweb/gtlxxb/EN/file/pic?fileId=gh/BtLvApxKS7pGvgd4faA==, createTime=1773987714251, updateTime=1773987714251, creator=18614031015, updator=18614031015), WebsiteProps(id=1241757732966036261, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1241757301070156588, code=minRunFlag, value=0, createTime=1773987714282, updateTime=1773987714282, creator=18614031015, updator=18614031015), WebsiteProps(id=1241757732911510303, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1241757301070156588, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/gtlxxb/EN/file/pic, createTime=1773987714269, updateTime=1773987714269, creator=18614031015, updator=18614031015), WebsiteProps(id=1241757732961841956, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1241757301070156588, code=silenceFlag, value=0, createTime=1773987714281, updateTime=1773987714281, creator=18614031015, updator=18614031015), WebsiteProps(id=1241757732903121694, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1241757301070156588, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_en_623/, createTime=1773987714267, updateTime=1773987714267, creator=18614031015, updator=18614031015), WebsiteProps(id=1241757732936676129, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1241757301070156588, code=themeColor, value=null, createTime=1773987714275, updateTime=1773987714275, creator=18614031015, updator=18614031015), WebsiteProps(id=1241757732945064738, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1241757301070156588, code=themeStyle, value=null, createTime=1773987714277, updateTime=1773987714277, creator=18614031015, updator=18614031015)])], journalTitle=固体力学学报, weixinUrl=null, journalUrl=http://manu39.magtech.com.cn/Jwk_gtlxxb, iacademicId=null, status=1, seqNo=null, journalTitleEn=Chinese Journal of Solid Mechanics, journalPhotoCn=QijUwme6mcFRwEfHnJkyaw==, journalPhotoEn=3rj3gh183UJiEfa2LeH0yw==, journalFirstLetter=C, journalRecommend=null, journalNew=null, journalCollection=null, jcrJf=null, cjcrJf=null, jcrJfStr=null, cjcrJfStr=null, submissionFirstDecision=null, sciSubjectClassification=null, casSubjectClassification=null, citeScore=null, totalCitationFrequency=null, icpCode=null, psCode=null, advertisingLicenseCode=null, copyrightInformation=null, country=null, option=, provinceCode=null, provinceName=null, collectFlag=false), detailUrlCn=https://castjournals.cast.org.cn/joweb/gtlxxb/CN/10.19636/j.cnki.cjsm42-1250/o3.2025.032, detailUrlEn=https://castjournals.cast.org.cn/joweb/gtlxxb/EN/10.19636/j.cnki.cjsm42-1250/o3.2025.032, pdfUrlCn=https://castjournals.cast.org.cn/joweb/gtlxxb/CN/PDF/10.19636/j.cnki.cjsm42-1250/o3.2025.032, pdfUrlEn=https://castjournals.cast.org.cn/joweb/gtlxxb/EN/PDF/10.19636/j.cnki.cjsm42-1250/o3.2025.032, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于数据-物理融合驱动方法的Ti6Al4V多轴疲劳寿命预测研究
收藏切换
PDF下载
孙兴悦 1 , 刘耘宇 1 , 马玉娥 1, ** , 张卫红 2
固体力学学报 | 研究论文 2025,46(5): 571-588
收起
收藏切换
固体力学学报 | 研究论文 2025, 46(5): 571-588
基于数据-物理融合驱动方法的Ti6Al4V多轴疲劳寿命预测研究
全屏
孙兴悦1, 刘耘宇1, 马玉娥1, ** , 张卫红2
作者信息
  • 1西北工业大学航空学院,西安,710072
  • 2西北工业大学机电学院,西安,710072

通讯作者:

A Data-Physics Hybrid Approach for Multiaxial Fatigue Life Prediction of Ti-6Al-4V Alloy
Xingyue Sun1, Yunyu Liu1, Yu'e Ma1, ** , Weihong Zhang2
Affiliations
  • 1School of Aeronautics, Northwestern Polytechnical University, Xi'an, 710072
  • 2School of Mechanical Engineering, Northwestern Polytechnical University, Xi'an, 710072
出版时间: 2025-10-27 doi: 10.19636/j.cnki.cjsm42-1250/o3.2025.032
文章导航
收藏切换

随着增材制造Ti-6Al-4V合金在航空航天与高性能结构领域的广泛应用,其在复杂载荷条件下的疲劳性能研究愈发重要. 针对传统数据驱动方法在小样本和多轴加载条件下存在预测精度不足与物理一致性欠缺的问题,本文以实验载荷计算Mises等效应力为基础,结合Basquin模型获得理论寿命作为先验,提出了一种基于残差连接的物理信息融合神经网络(PI-Res). 以激光粉末床融合(L-PBF)Ti-6Al-4V材料为研究对象,对比了人工神经网络、随机森林与支持向量回归等多种数据驱动方法性能,以及三种典型的数据-物理融合策略(物理信息特征工程、物理信息损失函数和物理信息残差连接). 结果表明,PI-Res模型在多轴加载条件下展现出更优的预测精度和物理一致性,能够兼顾不同寿命区间的适应性. 该研究为构建兼具可靠性与可解释性的疲劳寿命预测模型提供了新的思路与参考.

多轴疲劳  /  寿命预测  /  Ti6Al4V  /  物理信息  /  机器学习

With the increasing deployment of additively manufactured Ti-6Al-4V in aerospace and other high-performance structural applications, reliable prediction of fatigue life under complex multiaxial loading has become essential for safe design and lifecycle management. However, conventional data-driven approaches often lack predictive accuracy and physical consistency on small datasets and non-proportional multiaxial stress states, limiting their generalizability and interpretability. To address these limitations, this work computes the Mises equivalent stress directly from experimental loading histories and incorporates a Basquin-model-based theoretical fatigue life as prior physics knowledge. Building on this prior, we propose a residual connection-based physics-informed neural network (PI-Res) that learns only the datadriven residual relative to the theoretical life, thereby merging mechanistic fidelity with statistical adaptability. Using laser powder bed fusion (L-PBF) Ti-6Al-4V as the case material, we conduct a systematic comparison against representative purely data-driven baselines—artificial neural networks, random forests, and support vector regression—as well as three canonical data-physics fusion strategies: physics-informed feature engineering, physics-informed loss functions, and physics-informed residual connections. Across multiaxial loading scenarios and distinct life regimes, the PI-Res framework consistently demonstrates superior predictive accuracy alongside stronger adherence to physical trends implied by the stress-life relationship. Moreover, by anchoring the learning process to a mechanistic prior and delegating only the unexplained variance to the network, PI-Res improves robustness under data scarcity and enhances interpretability of model behavior. These findings indicate that residual-style injection of domain knowledge offers a principled pathway to reconcile small-sample constraints with mechanistic coherence in fatigue modeling. Practically, the proposed approach provides a reliable tool to support fatigue life assessment, design margins, and maintenance scheduling for additively manufactured components. Theoretically, it illustrates a transferable physics-data fusion paradigm that can be extended to other material systems and generalized multiaxial fatigue problems where integrating prior physics with flexible learners is crucial.

multiaxial fatigue  /  life prediction  /  Ti-6Al-4V  /  physics-informed  /  machine learning
孙兴悦, 刘耘宇, 马玉娥, 张卫红. 基于数据-物理融合驱动方法的Ti6Al4V多轴疲劳寿命预测研究. 固体力学学报, 2025 , 46 (5) : 571 -588 . DOI: 10.19636/j.cnki.cjsm42-1250/o3.2025.032
Xingyue Sun, Yunyu Liu, Yu'e Ma, Weihong Zhang. A Data-Physics Hybrid Approach for Multiaxial Fatigue Life Prediction of Ti-6Al-4V Alloy[J]. Chinese Journal of Solid Mechanics, 2025 , 46 (5) : 571 -588 . DOI: 10.19636/j.cnki.cjsm42-1250/o3.2025.032
钛合金因其优异的比强度、耐腐蚀性和高温性能,被广泛应用于航空航天、医疗和能源等领域的关键承载结构中[1-3]. 然而,在复杂服役环境下,该类材料往往面临多轴疲劳载荷作用,其疲劳失效机制显著区别于单轴载荷情形,对结构完整性构成严峻挑战[4-6]. 近年来,增材制造(Additive Manufacturing,AM)技术的兴起使得Ti6Al4V构件在复杂几何成形方面展现出独特优势[7-9],但同时也引入了微观缺陷与各向异性等因素,进一步加剧了疲劳行为的复杂性[10]. 针对这种复杂行为,数据驱动方法在增材制造材料及构件力学性能预测具有明显优势,在挖掘增材制造工艺参数-影响因素-力学性能的关联关系方面得到了学者们的广泛关注[11]. 但同时也面临着数据样本不足,泛化性能差等问题. 随着物理约束深度学习的发展,物理信息神经网络(Physics-informed Neural Network,PINN)因其可将物理定律直接嵌入损失函数中,在小样本、复杂加载场景下表现出良好的预测能力,为疲劳寿命建模提供了新的思路与工具[12,13].
当前研究表明,在不同加载路径(如拉压、扭转以及拉-扭组合)下增材制造Ti6Al4V钛合金表现出明显的各向异性力学行为[14-16],其裂纹萌生位置与扩展路径受到材料微观组织、残余应力、缺陷分布等多因素共同影响[17]. 构件表面的粗糙度和孔隙缺陷会降低其疲劳强度,并且在多轴载荷下材料的裂纹模式呈现出更复杂的演化规律,而通过热处理、表面加工以及工艺参数优化,这些影响也可以被有效缓解. Renzo等[4]针对SLM Ti6Al4V材料开展了同相位下的拉扭疲劳试验,借助DIC(Digital Image Correlation)、SEM(Scanning Electron Microscopy)等观测手段分析了起始裂纹的主要原因,进一步提出了一种考虑平均应力效应的多轴疲劳损伤参数以实现准确的寿命预测. Lindström等[18]针对PBF-LB(Powder Bed Fusion with Laser Beam)成形且未经表面处理的Ti6Al4V材料,提出了一种增量式疲劳损伤模型,用于预测非比例加载下的疲劳寿命. 该方法能够较好地反映不同加载路径下的疲劳响应,展示了增材制造材料在寿命预测中的工程应用潜力. Nalli等[19]针对增材制造工艺制备的Ti6Al4V、17-4PH和AlSi10Mg材料,开展了系统的单轴及多轴静载实验研究,并比较了与同种锻造材料的力学性能差异. 结果表明,增材制造材料的屈服强度和极限强度已接近锻造材料水平,尽管延性有所降低,但通过材料改性可以得到改善. Fatemi等[20]研究了增材制造Ti-6Al-4V合金在多轴加载下的疲劳行为,并评估了表面粗糙度的影响. 结果表明,AM材料在未经优化处理时延性不足,疲劳载荷下的表现受到影响,经表面加工和后处理后材料的疲劳寿命得到明显提升. 目前,围绕不同加载路径下疲劳行为的深入理解与预测模型的持续优化,成为增材制造Ti6Al4V材料疲劳研究领域的重要方向. 总体而言,增材制造Ti-6Al-4V材料在复杂加载条件下既面临挑战,也具备独特优势,其复杂几何成形、高材料利用率和轻量化潜力为航空航天等领域应用提供了新的可能. 因此,深入探究多轴疲劳机理并发展可靠的预测模型,是推动增材制造材料从实验室走向工程应用的关键环节.
近年来越来越多的研究尝试借助数据驱动方法提升多轴疲劳寿命预测的效果[21]. 通过引入支持向量机[22]、随机森林[23]、人工神经网络[24]、卷积神经网络[25,26]和循环神经网络[27]等算法构建回归预测模型,可以在一定程度上更好地捕捉复杂载荷特别是多轴载荷与疲劳响应之间的非线性关系,并在训练数据充足的条件下表现出较高的拟合精度. Sun等[25,26]利用材料多轴应力应变图像,设计了一系列卷积神经网络模型,并通过迁移学习的方法在不锈钢、钛合金、铝合金等多种材料中实现了良好的预测效果. Yang等[27]利用循环神经网络模型,在考虑加载路径、加载模式、加载水平等多种因素的情况下,实现了准确的多轴疲劳寿命预测. 其研究表明,当训练数据和测试数据所涉及的加载路径之间差异增大时,模型的外推能力就会减弱. 数据驱动模型普遍依赖大量高质量实验样本,获取成本高、可扩展性差,且缺乏对力学机理的表达能力. 在面对多轴非比例载荷、复杂加载路径或新型材料系统时,模型的泛化能力和解释性仍显不足.
为克服纯数据驱动模型的局限,PINN作为一种融合物理约束与深度学习的新兴建模框架[28],近年来受到了广泛关注. PINN通过将控制方程、物理定律或本构关系嵌入神经网络的损失函数中[29-31],实现了对有限数据下材料行为的高精度建模,具备良好的物理一致性与外推能力. He等[29]通过将多个临界面模型作为物理惩罚项引入损失函数中构建了MFLP-PINN模型,并在三种材料中验证了该模型的预测精度. Liao等[30]更进一步通过元学习的方式实现了不同物理惩罚项间平衡权重的自适应设计,从而使得不同路径案例间可以具有最优的权重参数,实现更好的预测效果. 除了将物理信息引入损失函数外,物理信息特征[31,32]和物理信息框架[33,34]等方式也是常用的PINN模型构建方法. 相较于经验模型和纯机器学习方法,PINN具备从物理角度理解模型预测结果的潜力,尤其适用于疲劳寿命建模中“样本少、机理强”的典型问题结构.
针对上述研究现状,本文聚焦于L-PBF增材制造Ti6Al4V材料在多轴疲劳载荷下的寿命预测问题,以Mises等效应力及寿命预测结果作为先验物理知识,提出了一种基于残差连接的物理信息融合方法. 通过在网络结构层面引入考虑物理经验模型的残差连接,使模型能够在Mises等效应力模型提供的物理基线约束下,学习并修正复杂加载路径与材料特异性对疲劳寿命的影响. 这种结构化融合不仅提升了预测的精度与稳定性,也更契合疲劳损伤建模在物理一致性与泛化能力之间的本质需求. 相关研究不仅可以实现对增材制造Ti6Al4V材料多轴疲劳寿命的准确预测,也可以为物理特征与深度网络融合方式的设计提供思路.
本文所采用的多轴疲劳数据集来源于Fatemi等[20]所开展的增材制造Ti-6Al-4V材料多轴疲劳实验数据. 实验材料为采用激光粉末床融合(L-PBF)方法制备的Ti-6Al-4V合金. 加工后的试样被分为两组,其中一组试样表面不进行抛光处理(记为As-built),另一组试样表面通过机加工的方式进行抛光处理(记为Machined). 图1展示了这两组材料多轴疲劳实验数据的详细情况.
表1表2分别列出了未抛光试样和表面抛光试样的疲劳实验数据,包括加载方式、载荷幅值、Mises等效应力和疲劳寿命(2Nf)等. 实验加载方式包括轴向拉压加载(Axial)、扭转加载(Torsional)、拉-扭同相位加载(IP)及拉-扭90°异步相位加载(OP)等四种典型单、多轴载荷路径. 从图1中可以看出,在每种加载路径下,L-PBF Ti-6Al-4V材料的疲劳寿命和等效应力之间呈现近似双对数线性关系. 但不同加载路径之间的关系并不相同,这种由于载荷路径差异引起的疲劳寿命差异导致了传统等效应力模型难以给出理想的寿命预测结果.
根据1.1节中所介绍实验数据情况,本文将采用轴向应力幅值(σa)、轴向应变幅值(εa)、扭转应力幅值(τa)、扭转应变幅值(γa)、Mises等效应力(σMises)、拉扭应力比(λ)和相位差(φ)等7个特征作为后续模型的输入特征,以对数化疲劳寿命(lg(Nf))作为模型的输出特征. 通过取对数化的方式,可以降低不同样本间疲劳寿命数量级差异的影响.
为确保模型训练的稳定性与泛化能力,在进行模型训练前,需要对实验数据进行归一化预处理,以消除不同特征间的量纲和数量级差异. 本文采用z-score方法分别对输入和输出特征进行归一化预处理,具体如式(1)所示. 通过该方法可以将数据集中各特征的均值与标准差进行标准化变换,确保各输入维度具有零均值和单位方差,从而避免在模型训练过程中因特征尺度差异导致的梯度不平衡问题.
其中,x为原始模型输入或输出特征,为归一化后的模型输入或输出特征.Ex)为特征的平均值,Dx)为特征的标准差.
为实现对L-PBF Ti-6Al-4V材料的准确多轴疲劳寿命预测,本文分别构建了以数据驱动为核心的传统机器学习模型以及数据-物理融合驱动模型. 在对比不同模型在疲劳数据建模与预测精度方面的能力基础上,进一步探讨了物理信息引入方式对模型性能的影响.
数据驱动方法通过从实验数据中学习载荷—寿命之间的映射关系,在无需明确物理机制建模的前提下即可实现疲劳寿命预测. 本文选取了3类具有代表性的模型进行对比分析,分别是人工神经网络(Artificial Neural Network,ANN)、随机森林(Random Forest,RF)与支持向量回归(Support Vector Regression,SVR). 图2展示了这3种机器学习模型的算法示意图.
ANN模型采用多层全连接结构,能够学习输入特征与输出变量之间的非线性关系,适用于高维复杂问题. RF模型通过集成多个决策树构建强预测器,具有良好的泛化能力和抗过拟合能力,尤其适用于特征重要性分析. SVR模型基于核函数实现高维特征空间的映射,在小样本学习中表现稳定,适用于线性或非线性可分数据的回归建模. 三类模型均不依赖于具体的疲劳机理假设,而通过拟合已有实验数据样本进行寿命预测. 本文所用数据驱动模型的具体超参数架构列在附录A中.
由于单一数据驱动模型需要较大的样本量以完成权重优化训练,这对于疲劳问题特别是多轴疲劳问题而言意味着过高的实验成本. 此外,数据驱动模型在物理一致性与小样本泛化方面通常也难以满足工程问题的需求. 因此,本文综合考虑了实验数据的可用性以及传统模型的匹配程度,基于实验结果计算Mises等效应力,并以此计算疲劳寿命构建先验物理信息. 相比与Fatemi-Socie、Smith-Watson-Topper等经典临界面准则相比,Mises等效应力计算简便、效率高且不依赖额外材料参数,在保证物理一致性的同时兼具可行性与材料独立性. 此外,考虑到原始实验研究中仅提供了Basquin模型参数,并指出材料呈现出脆性特征,本文在寿命计算中选取Basquin模型以保持与数据来源的一致性,并将该寿命预测结果加入物理信息模型的输入特征中. 相关的材料疲劳参数可通过文献[20]获得,并列在附录B中. 在此基础上,尝试构建了包括了物理信息特征工程、引入物理惩罚项的损失函数和物理信息残差神经网络等不同的数据-物理融合方法用于疲劳寿命预测. 通过将物理先验机制进行融合嵌入,实现对小样本条件下模型训练效果的提升. 图3以神经网络模型为代表,展示了这三种数据-物理融合方法的模型架构. 接下来,将对这三种模型架构进行逐一介绍.
(1)物理信息特征工程
考虑到实验数据的形式和来源,本文所采用的物理先验信息主要来自基于Mises等效应力幅预测的疲劳寿命(如图3(a)所示). 传统特征工程通常依赖经验公式或信号处理方法从原始数据中提取统计特征(如均值、方差、峰值、频率成分等)提取能够表征疲劳行为的指标. 然而,这类方法往往忽略了材料内部真实的疲劳损伤情况,难以反映复杂加载条件下的疲劳损伤演化机制. 相比之下,物理信息特征工程(Physics-informed Feature Engineering)则基于材料力学中的基本原理,将物理量(如Mises等效应力、应变能密度等)直接引入特征构造过程[35]. 不仅提升了特征的物理可解释性,也使得模型更容易学习到损伤演化的本质规律.
这一方法由于仅在特征层面引入物理信息,不受模型架构的影响,因此在本文中物理信息特征工程方法分别用于ANN、RF和SVR模型中. 对应模型分别记为PF-ANN、PF-RF和PF-SVR.
(2)引入物理惩罚项的损失函数
损失函数是数据驱动模型特别是神经网络模型训练过程中的一个模块,其决定着模型权重的优化方向. 传统的数据驱动模型中常用的损失函数包括均方误差(Mean Squared Error,MSE)和平均绝对误差(Mean Absolute Error,MAE)等. 这些函数主要衡量模型预测结果与实际观测值之间的数值误差. 然而,在涉及复杂物理过程建模(如多轴疲劳寿命预测)的问题中,仅依赖数据差异作为训练信号,往往会导致模型预测结果缺乏物理一致性,尤其在数据分布稀疏或加载条件复杂的场景下更为明显.
为克服上述不足,近年来提出了物理信息损失函数(Physics-informed Loss Functions)的思想,其核心在于在传统数据驱动损失基础上,融合基于物理规律的惩罚项. 这类方法通过显式构建表示材料行为的物理项,并将其引入损失函数中,构成融合目标函数. 在本研究中,我们引入基于Mises等效应力寿命预测结果的物理惩罚项(如式(2)所示),用以构建疲劳寿命预测过程中的物理一致性目标,促使模型在数值精度与物理合理性之间取得更优权衡.
其中,Npre为模型预测值,Nexp为实验值;为基于Mises等效应力幅值得到的疲劳寿命值;α为惩罚权重,在本文中经过对比测试,取0.025.
这一方法由于在损失函数层面引入物理信息,需与模型的反向传播机制紧密耦合,因此仅适用于具有端到端训练结构的神经网络模型. 在本文中,物理信息损失函数方法仅与ANN模型结合,对应模型记为PI-Loss.
(3)物理信息残差神经网络
传统神经网络在回归预测任务中,通常采用前馈全连接结构,通过堆叠多个线性变换与非线性激活单元实现复杂映射. 然而这类结构往往依赖大量训练数据,且易受梯度消失或爆炸问题的影响,在深层网络中模型训练稳定性和泛化性能较差.
本文构建了一种物理信息残差神经网络(Physics-informed Residual Neural Network,PI-Res). 如图3(c)所示,该模型将物理约束信息嵌入神经网络结构中,并引入残差连接以提升训练稳定性. 该网络采用残差结构的设计思想,结合Mises等效应力得到的疲劳寿命值作为物理先验信息,以物理信息残差的形式作为附加分支,与主网络共同参与训练,确保模型在学习数据特征的同时,保持输出与物理定律之间的一致性.
其中,Ndata为数据驱动模型预测结果,为物理信息残差连接后的模型预测结果.
综上所述,本文提出并构建了三种数据-物理融合架构:通过引入Mises等效应力预测寿命,增强了输入特征的物理可解释性;在损失函数中引入物理约束,实现了预测精度与物理一致性的兼顾;在网络结构层面融合物理残差信息,提升了模型的训练稳定性与泛化能力. 以上几种数据-物理融合驱动模型的具体超参数架构同样列在附录A中. 在后续研究中将对比分析三种架构在多个评价指标下的预测性能表现.
为了全面评估各类模型在疲劳寿命预测任务中的表现,本文均方根误差(Root Mean Squared Error,RMSE)作为评价指标,用于衡量模型预测值与真实值之间的数值偏差,反映模型的拟合能力和预测精度. RMSE计算如式(5)所示.
其中,ypre是模型预测的对数化疲劳寿命值,yexp是实验得到的对数化疲劳寿命值. 为了避免不同样本间疲劳寿命的数量级差异,本文采用对数化疲劳寿命计算RMSE值. RMSE值越小表明模型的预测准确度越高.
为了全面评估本文所关注的数据驱动模型和物理信息神经网络模型性能,本文首先以表面未加工L-PBF Ti6Al4V多轴疲劳实验数据为训练样本. 在每个加载路径中采用分层抽样的方式,以1∶1的比例划分训练集和测试集. 每个模型进行10次重复独立实验,以重复实验结果来对数据驱动模型和物理信息融合模型分别进行评估. 而后选择具有最佳预测性能的模型,采用迁移学习的方法应用至表面加工LPBF Ti6Al4V多轴疲劳实验数据中,以验证模型的泛化能力.
图4展示了ANN、RF和SVR模型在Ti6Al4V多轴疲劳寿命预测任务中的RMSE性能分布情况. 可以看出,ANN模型的误差波动范围最大,箱线图显示其25%-75%区间显著高于RF和SVR,表明其预测稳定性较差,易受到训练初始权重或局部最优解的影响. 而RF模型整体误差水平较低,波动范围也最小,说明其在该任务中具有较强的鲁棒性和稳定性. SVR模型的预测误差居中,但同样存在一定程度的波动. 综合来看,虽然ANN模型具有较强的非线性拟合能力,但在小样本或高噪声条件下,其稳定性和泛化能力可能不足,而RF在本场景中表现出更优的综合性能.
为减小随机初始化与数据划分带来的偶然性,本研究在每种模型下均进行了10次独立实验,并以RMSE排序后的中位数结果作为代表进行分析. 该结果在误差水平上与整体均值接近,能够反映模型的典型性能,同时避免极端实验的干扰. 因此,后续结果分析与对比均以相应的中位数实验为例展开.
图5以重复实验中具有中位数RMSE值的实验结果为例,展现了预测寿命与实验寿命的对比情况. 从结果来看,RF模型在训练集与测试集上均展现出良好的拟合能力,大部分样本点分布在二倍分散带内. SVR、模型在训练集上表现尚可,但在测试集上部分样本出现较大偏离,特别是在高寿命段预测偏差明显. ANN模型虽然在训练集上部分样本拟合准确,但在测试集上存在较大波动,多个样本预测结果超出二倍分散带,说明其对样本分布敏感,易出现过拟合现象.
进一步分析可见,三种模型在预测性能上的差异不仅体现在整体拟合精度上,也体现在对不同寿命区间样本的适应能力上. 对于SVR模型,其在中低寿命区间的预测结果相对集中,但在高寿命段表现出一定的欠拟合趋势,说明其对非线性疲劳寿命增长规律的建模能力有限. RF模型在不同寿命区间均保持了较好的分布一致性,预测点沿对角线均匀分布,且大多数落于二倍误差带以内,反映出其在处理非线性、非均匀分布数据时具有良好的稳健性. 相比之下,ANN模型虽然在某些数据点上拟合精准,但整体分布呈现出更大的离散性,特别是在测试集上,部分样本偏离程度显著,显示出其在样本量不足或特征表达能力受限情况下的泛化不足问题. 因此,尽管ANN具备强大的非线性建模能力,但在缺乏物理约束和充分数据支持的条件下,其预测结果稳定性较差.
为进一步理解数据驱动模型在疲劳寿命预测任务中不同输入特征的影响程度,本文采用了基于SHAP(SHapley Additive exPlanations)的方法[23,34]对ANN、SVR和RF三种模型进行特征重要性分析. SHAP方法通过量化各输入特征对模型输出的贡献大小,能够揭示模型内部的决策逻辑并提升结果的可解释性[36].
图6展示了基于SHAP方法的特征重要性分析结果,通过雷达图的形式对比了ANN、RF和SVR三种模型对输入物理特征的依赖程度. 整体来看,Mises等效应力对所有模型的预测结果影响最大. Mises等效应力通过整合轴向与扭转载荷,能够反映多轴载荷下的主要损伤驱动力,因此与疲劳寿命具有最稳定的相关性. 在对数寿命域中,这种关系更加线性化,从而使其在不同模型中均表现为最具主导性的特征. 从图中可以看出,不同模型在各特征重要性上的表现存在一定差异. SVR整体上分布较为均衡,各特征之间相差不大,表现出一定的全局适应性. 相比之下,ANN在Mises等效应力、扭转应变幅值、拉扭应力比等特征上表现出更高的关注,表明其更突出关键变量的作用. 而RF则在Mises等效应力上呈现出明显峰值,整体上针对输入特征呈现出明显的选择性依赖. 总体来看,SVR更偏向全面性,ANN则注重关键特征的选择性依赖,而RF强调少数特征的主导作用. 这些差异表明在疲劳寿命预测中,不同模型的特征利用方式会显著影响其泛化能力和解释性.
结果表明,纯数据驱动方法在疲劳寿命预测中展现出较好的拟合精度,能够有效捕捉输入特征与寿命之间的非线性映射关系. 然而,该类方法在物理一致性、材料损伤演化机制的可解释性以及对极端样本和分布外数据的鲁棒性方面仍存在显著不足. 尤其在多轴非比例加载和小样本条件下,模型的预测性能和稳定性受到一定限制.
综上所述,尽管传统数据驱动模型在预测精度方面具备一定优势,但其在物理一致性和泛化能力方面仍存在不足. 为进一步提升疲劳寿命预测的可信性与稳定性,本节将探讨引入物理约束后的神经网络模型在多轴疲劳建模中的表现.
在本节中,研究构建并对比了三种不同的物理信息融合策略,包括物理信息特征工程(PF-ANN/RF/SVR)、引入物理惩罚项的损失函数(PI-Loss)以及物理信息残差连接(PI-Res)架构. 图7展示了这几种物理信息融合模型的10次独立实验的箱线图统计结果. 从图中可以看出,引入物理信息后,整体模型性能较纯数据驱动方法有明显提升. PI-Res模型的RMSE均值和波动范围最小,表现出最优的预测精度和稳定性,说明通过残差方式引入物理知识有助于提升模型对复杂疲劳机理的拟合能力. 相比之下,PI-Loss模型在精度上略逊一筹,但仍显著优于传统机器学习模型. 基于特征工程的PF-RF模型也展现出较好的稳健性,而PF-SVR模型误差波动较大,稳定性较差. 总体而言,物理信息的有效融合不仅提升了模型性能,也增强了预测结果的物理一致性和工程可信度.
图8展示了不同物理信息融合策略下模型以及经典Mises等效应力模型之间的疲劳寿命预测结果对比. 整体来看,所有物理信息的预测效果都显著优于Mises等效应力模型. PI-Res在训练集和测试集上均表现出最优的拟合效果,预测点紧密分布在对角线附近,且大多数样本位于二倍分散带以内,说明其在保持高精度的同时具有良好的泛化能力. PI-Loss模型在精度上略逊一筹,但同样优于各类传统机器学习方法,表明物理损失函数在提升预测可信度方面具有明显作用. PF-RF模型在传统机器学习框架下保持了较好的拟合能力,但对部分极端样本仍存在一定误差偏离. PF-ANN和PF-SVR模型的预测结果波动较大,部分样本点远离对角线,尤其PF-SVR在长寿命段存在较为明显的欠拟合现象. 综合分析表明,通过深度神经网络结构引入物理约束(特别是残差引导方式)能够有效提升多轴疲劳寿命预测的精度与稳定性,是一种更具潜力的建模策略.
在整体预测性能分析的基础上,图9进一步将不同加载路径下的疲劳寿命预测结果进行了分开展示,对比了各单一数据驱动模型与不同物理信息引入模型的表现. 可以观察到,在单轴加载工况下,各模型的预测点分布较为分散,传统SVR与ANN模型在高应力区域存在偏离,而物理信息引导模型(如PF-RF、PI-Loss、PI-Res)预测结果更加集中,表现出更好的应力-寿命一致性.
在扭转主导加载中(图9(b)),大多数模型在中等应力水平范围内预测结果密集. 在300-500 MPa的应力区间,ANN与SVR在部分样本点上表现出更低的预测误差. 这一结果表明Mises等效应力预测的疲劳寿命值作为物理先验虽能在比例加载下提供稳健的物理特征,但在不同加载路径下可能引入局部偏置. 尽管如此,引入物理信息的模型特别是PI-Res,在整个寿命跨度内保持了较好的分布规律性,进一步验证了其在非比例加载场景下的鲁棒性. 未来若能结合相位差敏感的临界面参数或其他非比例损伤判据,将有助于进一步提升模型在复杂加载条件下的适用性与精度.
在控制比例变化的复杂加载路径下,模型间差异更为显著,传统模型普遍出现预测精度下降的情况,而PI-Loss和PI-Res仍能保持较高的拟合质量和物理合理性,体现出基于物理约束的神经网络模型在处理复杂应力路径时的优势. 总体而言,引入物理信息显著提升了模型在多轴疲劳寿命预测任务中的适应能力与泛化性能.
综合不同模型在多项评价指标下的表现可以看出,物理信息残差神经网络(PI-Res)在多轴疲劳寿命预测方面,性能要优于物理信息特征工程(PF-ANN/RF/SVR)与物理损失函数(PI-Loss)的方法. 这主要得益于其在网络结构层面实现了数据驱动与物理先验的深度融合. 一方面,残差结构有效缓解了深层神经网络中常见的梯度消失问题,增强了模型的训练稳定性和表达能力;另一方面,物理信息以残差信息形式持续传入网络,有助于模型在特征演化过程中保持物理规律的约束. 这种结构性引导不仅提升了模型对复杂非线性关系的学习能力,也显著增强了其在极端样本和小样本条件下的泛化性能.
为了进一步验证各模型在实际工程中的可推广性,本文设计了跨材料迁移学习实验,即在表面未加工LPBF Ti6Al4V的疲劳实验数据上完成训练后,迁移应用于表面加工LPBF Ti6Al4V多轴疲劳实验数据上. 该过程模拟了现实工程场景中模型需在有限标注数据条件下,快速适配新材料新场景的应用需求[25,26,37].
图10展示了本研究设计的迁移学习流程示意图. 在该迁移学习过程中,已训练的PI-Res模型在面对新目标任务时,其中前若干层参数被部分或完全“冻结”,仅对部分网络层进行微调(Fine-tuning),以适应新的数据分布与力学响应特性. 在迁移过程中,保持物理信息嵌入结构不变,确保模型在适应新任务的同时,仍然保有对物理规律的约束能力. 迁移学习实验仅在表现最优的PI-Res模型上进行,以进一步验证其在跨材料场景下的适应性和推广能力.
为了进一步评估PI-Res模型的跨材料迁移能力,图11以PI-Res模型为预训练模型,探究了不同迁移策略下的疲劳寿命预测效果. 结果表明,直接在目标域训练的“无迁移”模型RMSE最高,误差波动也最为显著,说明在小样本条件下模型难以稳定收敛. 而引入迁移策略后,模型整体精度显著提升,误差分布趋于集中. 冻结0层和1层时性能相对接近,说明此时源模型的预训练特征对目标任务具有良好迁移性;当冻结2层时,模型达到最佳效果,RMSE最小且分布最紧凑,表明合理冻结部分结构有助于提升泛化能力并抑制过拟合. 然而当冻结层数增加至3层时,模型预测精度和稳定性均下降,推测是由于模型可调参数过少,导致在目标域难以充分适应新任务特征分布.
在迁移学习训练中,冻结层数的选择对模型性能影响显著. 若冻结层数过少,容易因参数更新过多而导致过拟合;若冻结层数过多,则会限制模型的灵活性,从而引起欠拟合. 冻结前两层既能够保留基于Mises等效应力的物理先验,确保跨加工方式预测结果的一致性,又使未冻结的高层能够继续学习表面状态和微观结构差异对裂纹萌生的影响. 正是这种在物理一致性与特征适应性之间的平衡,使得冻结两层的策略在跨域迁移中表现最优. 整体来看,适度的参数迁移策略对于提升小样本多轴疲劳寿命预测模型的性能具有积极作用.
在确定了冻结两层作为最优迁移策略之后,图12进一步具体直观地展示了采用迁移学习与直接训练(无迁移)两种方法以及与经典Mises等效应力模型,在表面加工Ti6Al4V材料多轴疲劳寿命预测任务中的效果对比. 图12(b)为直接训练模型在目标域的预测结果,存在多个样本偏离对角线,尤其在高寿命区间预测误差较大,部分点落于二倍误差带之外,表明在小样本条件下模型拟合能力受限. 图12(c)为基于预训练源模型并采用冻结层微调策略的迁移学习结果,相较于无迁移模型,预测点整体更接近对角线,训练集与测试集样本分布更集中于二倍分散带之间,误差显著减小. 结果表明,通过在源任务上预训练并合理迁移网络参数,可有效提升目标任务中模型的泛化能力与稳定性,验证了迁移学习策略在多轴疲劳小样本建模场景下的实用价值.
综上所述,本小节在PI-Res模型基础上引入基于微调的迁移学习策略,并成功实现了从表面无加工Ti6Al4V材料向表面加工Ti6Al4V材料的迁移应用. 实验结果表明,迁移模型在预测精度、物理一致性及小样本适应能力方面均优于无迁移训练,尤其在样本数量受限的场景下表现出更为显著的性能优势. 这充分说明:融合物理先验的迁移学习方法不仅能够提升模型的工程适用性,还为解决新材料疲劳数据匮乏问题提供了有效路径. 未来,该方法有望进一步扩展至多材料、多结构体系,实现更大范围的疲劳寿命预测泛化.
本文围绕L-PBF Ti-6Al-4V合金在多轴疲劳载荷作用下的寿命预测问题,构建了一种融合物理约束与数据驱动的建模框架. 通过引入物理信息神经网络方法,将基于Mises等效应力预测结果作为先验物理信息,分别嵌入至模型的特征工程、损失函数和残差连接结构中,并与传统ANN、RF、SVR等数据驱动模型进行了系统对比. 研究结果表明:
(1)纯数据驱动方法在建模效率和拟合精度方面具有一定优势,能够捕捉输入特征与寿命之间的非线性关系,但在保持物理一致性、解释损伤演化机制以及应对极端样本和复杂多轴非比例加载条件下仍存在明显局限;
(2)所提出的物理信息残差神经网络(PI-Res)在不显著增加模型训练复杂度的前提下,通过残差引导的方式融合Mises等效应力预测结果,显著提升了模型在短寿命区域和非比例加载条件下的预测精度与稳定性,在精度和物理可解释性之间实现了良好平衡;
(3)不同的物理信息引入策略对模型表现存在显著影响,其中通过残差连接方式的物理信息融合不仅提供了基于Mises等效应力预测结果的物理一致性约束,还通过残差修正的方式,模型能够在物理模型预测结果的基础上更好地捕捉实际疲劳寿命分布规律,实现了在物理约束下的精细化预测,在稳定性和泛化性上均表现优异;
(4)进一步引入迁移学习机制,尤其通过冻结部分特征提取层的微调策略,能够有效缓解目标域样本不足带来的性能下降问题,在表面加工Ti6Al4V材料的疲劳寿命预测中验证了该策略的泛化优势.
(5)未来研究可进一步融合更多与疲劳损伤密切相关的物理机制信息,如通过引入微观缺陷演化规律,将裂纹萌生和扩展的多尺度耦合关系以先验分支形式嵌入;同时考虑残余应力与表面加工硬化效应,在输入端增加相应物理量,以表征加工与服役条件对疲劳寿命的影响. 通过这些物理机制的引入,模型有望在复杂工况下获得更强的解释性与预测能力.
  • 国家重大科技项目和国家自然科学基金项目(12302098)
参考文献 引证文献
排序方式:
[1]
谢勇, 王福德, 从保强, 严振宇, 董鹏. 电弧增材制造Ti-6Al-4V组织和力学性能调控研究进展[J]. 航空制造技术, 2020, 63(22): 54-62.
(Xie Y, Wang F D, Cong B Q, Yan Z Y, Dong P. A review of micro-structure and mechanical properties in wire arc additive manufactured titanium alloys[J]. Aeronautical Manufacturing Technology, 2020, 63(22): 54-62. (in Chinese))
[2]
Singh P, Pungotra H, Kalsi N S. On the characteristics of titanium alloys for the aircraft applications[J]. Materials today: proceedings, 2017, 4(8): 8971-8982.
[3]
Gai X, Bai Y, Li J, Li S J, Hou W T, Hao Y L, Zhang X, Yang R, Misra R D K. Electrochemical behaviour of passive film formed on the surface of Ti-6Al-4V alloys fabricated by electron beam melting[J]. Corrosion Science, 2018, 145: 80-89.
[4]
Renzo D A, Sgambitterra E, Maletta C, Furgiuele F, Biffi C A, Fiocchi J, Tuissi A. Multiaxial fatigue behavior of SLM Ti6Al4V alloy under different loading conditions[J]. Fatigue & Fracture of Engineering Materials & Structures, 2021, 44(10): 2625-2642.
[5]
Renzo D A, Sgambitterra E, Magarò P, Furgiuele F, Maletta C, Biffi C, Fiocchi J, Tuissi A. Multiaxial fatigue behavior of additive manufactured Ti-6Al-4V under in-phase stresses[J]. Procedia Structural Integrity, 2019, 18: 914-920.
[6]
郑战光, 张剑, 孙腾, 谢昌吉, 黄增. 基于多轴载荷相位差的神经网络预测钛合金疲劳寿命[J]. 中国有色金属学报, 2023, 33(03): 781-791.
(Zheng Z G, Zhang J, Sun T, Xie C H, Huang Z. Multi-axial fatigue life prediction of titanium alloy based on neural network of load phase difference[J]. The Chinese Journal of Nonferrous Metals, 2023, 33(03): 781-791. (in Chinese))
[7]
兰亮, 白澄岩, 高双, 何博, 王江. 电子束熔化成形Ti-6Al-4V钛合金研究进展和应用现状[J]. 航空制造技术, 2022, 65(Z1): 20-31.
(Lan L, Bai C Y, Gao S, He B, Wang J. Research progress and application status of Ti-6Al-4V titanium alloy fabricated via electron beam melting[J]. Aeronautical Manufacturing Technology, 2022, 65(Z1): 20-31. (in Chinese))
[8]
赵金猛, 卢林, 王静荣, 张亮, 吴文恒. 工艺参数对激光选区熔化成形Ti6Al4V合金致密性的影响[J]. 机械工程材料, 2022, 46(08): 100-104.
(Zhao J M, Lu L, Wang J R, Zhang L, Wu W H. Effect of process parameters on compactness of Ti6Al4V alloy formed by laser selective melting[J]. Journal of Mechanical Engineering Materials, 2022, 46(08): 100-104. (in Chinese))
[9]
戴志伟, 吴亚东, 朱伟健, 王泽铭, 苏磊, 彭康, 王红洁. 制备工艺对多孔Ti6Al4V微观结构和性能的影响[J]. 航空材料学报, 2023, 43(06): 36-43.
(Dai Z W, Wu Y D, Zhu W J, Wang Z M, Su L, Peng K, Wang H J. Effects of preparation process on micro-structure and properties of porous Ti6Al4V[J]. Journal of Aeronautical Materials, 2023, 43(06): 36-43. (in Chinese))
[10]
Sun W B, Ma Y E, Huang W, Zhang W H, Qian X D. Effects of build direction on tensile and fatigue performance of selective laser melting Ti6Al4V titanium alloy[J]. International Journal of Fatigue, 2020, 130: 105260.
[11]
胡雅楠, 余欢, 吴圣川, 奥妮, 阚前华, 吴正凯, 康国政. 基于机器学习的增材制造合金材料力学性能预测研究进展与挑战[J]. 力学学报, 2024, 56(7): 1892-1915.
(Hu Y, Yu H, Wu S C, Ao N, Kan Q H, Wu G Z, Kang G Z. Machine learned mechanical properties prediction of additively manufactured metallic alloys: progress and challenges[J]. Chinese Journal of Theoretical and Applied Mechanics, 2024, 56(7): 1892-1915. (in Chinese))
[12]
张颛利, 孙兴悦, 陈旭. 基于物理信息神经网络的金属多轴疲劳寿命预测进展[J]. 机械强度, 2025, 47(02): 44-52.
(Zhang Z L, Sun X Y, Chen X. Development in metal multiaxial fatigue life prediction based on physics-informed neural network[J]. Journal of Mechanical Strength, 2025, 47(02): 44-52. (in Chinese))
[13]
Wang H J, Li B, Gong J G, Xuan F Z. Machine learning-based fatigue life prediction of metal materials: Perspectives of physics-informed and data-driven hybrid methods[J]. Engineering Fracture Mechanics, 2023, 284: 109242.
[14]
Sun W B, Ma Y E, Zhang W H, Qian X D, Huang W, Wang Z H. Effects of the build direction on mechanical performance of laser powder bed fusion additively manufactured Ti6Al4V under different loadings[J]. Advanced Engineering Materials, 2021, 23(12): 2100611.
[15]
He Y X, Ma Y E, Zhang W H, Wang Z H. Effects of build direction on thermal exposure and creep performance of SLM Ti6Al4V titanium alloy[J]. Engineering Failure Analysis, 2022, 135: 106063.
[16]
Li P Y, Ma Y E, Sun W B, Qian X D, Zhang W H, Wang Z H. Fracture and failure behavior of additive manufactured Ti6Al4V lattice structures under compressive load[J]. Engineering Fracture Mechanics, 2021, 244: 107537.
[17]
Sun W B, Ma Y E, Li P Y, Wang Z H. Residual stress and long fatigue crack growth behaviour of laser powder bed fused Ti6Al4V: Role of build direction[J]. International Journal of Fatigue, 2022, 160: 106850.
[18]
Lindström S B, Moverare J, Franke M, Persson J, Leidermark D, Thore C J, Lindström T, Kapidžić Z. Fatigue life prediction for PBF-LB Ti6A14V with asbuilt surface under nonproportional loads using an incremental fatigue damage model[J]. International Journal of Fatigue, 2025, 193: 108777.
[19]
Nalli F, Cortese L, Concli F. Ductile damage assessment of Ti6Al4V, 17-4PH and AlSi10Mg for additive manufacturing[J]. Engineering Fracture Mechanics, 2021, 241: 107395.
[20]
Fatemi A, Molaei R, Sharifimehr S, Phan N, Shamsaei N. Multiaxial fatigue behavior of wrought and additive manufactured Ti-6Al-4V including surface finish effect[J]. International Journal of Fatigue, 2017, 100: 347-366.
[21]
Yu W Q, Sun X Y, Chen X. From mechanism empirical to physics-informed: a comprehensive review of multiaxial non-proportional low-cycle fatigue life prediction[J]. International Journal of Structural Integrity, 2025, 16(5): 1048-1091.
[22]
Moghaddam T B, Soltani M, Shahraki H S, Shamshirband S, Noor N B M, Karim M R. The use of SVR-FFA in estimating fatigue life of polyethylene terephthalate modified asphalt mixtures[J]. Measurement, 2016, 90: 526-533.
[23]
Zhan Z X, Li H. A novel approach based on the elastoplastic fatigue damage and machine learning models for life prediction of aerospace alloy parts fabricated by additive manufacturing[J]. International Journal of Fatigue, 2021, 145: 106089.
[24]
Zhou T G, Sun X Y, Chen X. A multiaxial low-cycle fatigue prediction method under irregular loading by ANN model with knowledge-based features[J]. International Journal of Fatigue, 2023, 176: 107868.
[25]
Sun X Y, Zhou T G, Song K, Chen X. An image recognition based multiaxial low-cycle fatigue life prediction method with CNN model[J]. International Journal of Fatigue, 2023, 167: 107324.
[26]
Zhou T G, Sun X Y, Yu Z, Chen X. A generalization ability-enhanced image recognition based multiaxial fatigue life prediction method for complex loading conditions[J]. Engineering Fracture Mechanics, 2024, 295: 109802.
[27]
Yang J Y, Kang G Z, Liu Y J, Kan Q H. A novel method of multiaxial fatigue life prediction based on deep learning[J]. International Journal of Fatigue, 2021, 151: 106356.
[28]
Karniadakis G E, Kevrekidis I G, Lu L, Perdikaris P, Wang S, Yang L. Physics-informed machine learning[J]. Nature Reviews Physics, 2021, 3(6): 422-440.
[29]
He G Y, Zhao Y X, Yan C L. MFLP-PINN: A physics-informed neural network for multiaxial fatigue life prediction[J]. European Journal of Mechanics-A/Solids, 2023, 98: 104889.
[30]
Liao H Y, Pan J, Su X H, Sun X Y, Chen X. A path-dependent adaptive physics-informed neural network for multiaxial fatigue life prediction[J]. International Journal of Fatigue, 2025, 193: 108799.
[31]
Zhou T T, Jiang S, Han T, Zhu S P, Cai Y N. A physically consistent framework for fatigue life prediction using probabilistic physics-informed neural network[J]. International Journal of Fatigue, 2023, 166: 107234.
[32]
He G Y, Zhao Y X, Yan C L. Multiaxial fatigue life prediction using physics-informed neural networks with sensitive features[J]. Engineering Fracture Mechanics, 2023, 289: 109456.
[33]
Peng X, Wu S, Qian W J, Bao J G, Hu Y N, Zhan Z X, Guo G P, Withers P J. The potency of defects on fatigue of additively manufactured metals[J]. International Journal of Mechanical Sciences, 2022, 221: 107185.
[34]
Salvati E, Tognan A, Laurenti L, Pelegatti M, Bona F D. A defect-based physics-informed machine learning framework for fatigue finite life prediction in additive manufacturing[J]. Materials & Design, 2022, 222: 111089.
[35]
Zhou T G, Sun X Y, Chen X. A physics-guided modelling method of artificial neural network for multiaxial fatigue life prediction under irregular loading[J]. Philosophical Transactions of the Royal Society A, 2023, 381(2260): 20220392.
[36]
Lundberg S M, Lee S I. A unified approach to interpreting model predictions: Advances in neural information processing systems 30 (NIPS 2017), Long Beach, CA, 2017[C].
[37]
Zhang Z Y, Liu Q Y, Wu D Z. Predicting stress-strain curves using transfer learning: Knowledge transfer across polymer composites[J]. Materials & Design, 2022, 218: 110700.
2025年第46卷第5期
PDF下载
130
62
引用本文
BibTeX
文章信息
doi: 10.19636/j.cnki.cjsm42-1250/o3.2025.032
  • 接收时间:2025-09-30
  • 首发时间:2026-03-20
  • 出版时间:2025-10-27
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2025-09-30
基金
国家重大科技项目和国家自然科学基金项目(12302098)
作者信息
    1西北工业大学航空学院,西安,710072
    2西北工业大学机电学院,西安,710072

通讯作者:

参考文献
分享链接
https://castjournals.cast.org.cn/joweb/gtlxxb/CN/10.19636/j.cnki.cjsm42-1250/o3.2025.032
分享至
全文二维码

扫描看全文

引用本文
BibTeX
本文的引用情况
2种不同金属材料的力学参数

Family
属数
Number of
genus
种数
Number of
species
占总种数比例
Percentage of
total species (%)

Genus
种数
Number of
species
占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏