Article(id=1246031930760741606, tenantId=1146029695717560320, journalId=1241755870837649424, issueId=1246031922707677827, articleNumber=null, orderNo=null, doi=10.19636/j.cnki.cjsm42-1250/o3.2024.010, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1709395200000, receivedDateStr=2024-03-03, revisedDate=null, revisedDateStr=null, acceptedDate=null, acceptedDateStr=null, onlineDate=1775006762446, onlineDateStr=2026-04-01, pubDate=1724515200000, pubDateStr=2024-08-25, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1775006762446, onlineIssueDateStr=2026-04-01, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1775006762446, creator=13701087609, updateTime=1775006762446, updator=13701087609, issue=Issue{id=1246031922707677827, tenantId=1146029695717560320, journalId=1241755870837649424, year='2024', volume='45', issue='4', pageStart='427', pageEnd='564', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1775006760527, creator=13701087609, updateTime=1775006830786, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1246032217470779944, tenantId=1146029695717560320, journalId=1241755870837649424, issueId=1246031922707677827, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1246032217470779945, tenantId=1146029695717560320, journalId=1241755870837649424, issueId=1246031922707677827, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=427, endPage=440, ext={EN=ArticleExt(id=1246031930983039724, articleId=1246031930760741606, tenantId=1146029695717560320, journalId=1241755870837649424, language=EN, title=Data-driven and Continuum Damage Mechanics-based Approach for Predicting Fatigue Lifein Additive Manufacturing, columnId=1244229834482757770, journalTitle=Chinese Journal of Solid Mechanics, columnName=Research Paper, runingTitle=null, highlight=null, articleAbstract=

Additive manufacturing (AM) techniques have attracted widespread attention in aerospace and biomedical fields due to advantages like high material utilization and extensive design flexibility. However, process-induced defects in AM-built components pose significant challenges for evaluating fatigue performance. The AM-built components are subjected to complex alternating loads in service, making it imperative to develop accurate fatigue life prediction models. Currently, two main approaches are widely employed: theoretical analysis and data-driven methods. Traditional life prediction models like continuum damage mechanics (CDM) suffer from limitations such as low accuracy and restricted applicability. Conversely, data-driven models, such as artificial neural networks (ANN), encounter constraints when dealing with limited sample sizes. To address these issues, knowledge-data hybrid models have emerged as a promising approach that combines physical principles with data insights. In view of this, this study has developed a calibrated CDM model and seamlessly integrated it with an ANN-based data-driven model. Employing methods of feature, parameter, and output fusion, three types of hybrid models based on CDM and ANN have been developed. To quantitatively analyze the prediction accuracy and data requirements of these models, calculations using fatigue data obtained from laser powder bed fusion (LPBF)-processed AlSi10Mg alloy have been performed. The results highlight the crucial role played by the corrective function of training data in the parameter fusion-based model, while indicating a relatively minor influence from the CDM model in terms of prediction accuracy. Moreover, this model retains a commendable level of accuracy even with suboptimal fitting outcomes from the CDM model. The hybrid model, which leverages feature fusion, maximizes the utilization of physical information from the CDM model, thus achieving the highest prediction accuracy and stability when ample data are available. The model based on output fusion, primarily guided by results of the CDM model and enhanced by ANN adjustments, demonstrates relatively superior predictive capabilities in domains outside of the training set compared to other models. These findings provide significant reference value for the further development of high-accuracy, knowledge-data hybrid fatigue life prediction models in AM.

, correspAuthors=Hao Wu, 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=Anbin Wang, Lei Gan, Zhiqiang Gan, Zhiming Fan, Yonghui Su, Hao Wu), CN=ArticleExt(id=1246031937828143122, articleId=1246031930760741606, tenantId=1146029695717560320, journalId=1241755870837649424, language=CN, title=数据与连续损伤力学双驱动的增材疲劳寿命预测模型, columnId=1241831201896469478, journalTitle=固体力学学报, columnName=研究论文, runingTitle=null, highlight=null, articleAbstract=

传统的力学模型与新兴的数据驱动模型目前广泛用于增材制造的疲劳寿命预测中. 其中,以连续损伤力学(Continuum Damage Mechanics,CDM)为代表的传统模型寿命预测模型存在着精度低、适用范围有限等问题,而以神经网络(Artificial Neural Network,ANN)为代表的数据驱动模型则始终受限于小样本工况. 为解决上述问题,融合物理知识和数据信息的知识-数据双驱动模型近年来发展迅速. 以此类双驱动模型为研究目标,本文以激光粉末床熔融成型(Laser Powder Bed Fusion,LPBF)AlSi10Mg合金为研究对象,构建了可自动标定的CDM模型,并将其与基于ANN的数据驱动模型在各种工况下进行了结合,再进一步通过特征融合、参数融合和输出融合方法的手段,构建了三类以CDM模型与ANN模型为基础的知识-数据双驱动模型,并量化分析了它们在预测精度和数据需求等方面的性能. 研究结果表明:基于参数融合的模型,训练数据修正作用较为显著,在预测精度方面受CDM模型影响最小,并在CDM模型拟合结果较差时也能确保一定精度;基于特征融合的双驱动模型能最大化利用CDM模型中的物理信息,在数据充足时具有最高的预测精度与稳定性;基于输出融合的模型以CDM模型的结果为主导,利用ANN进行修正,具有五种模型中最好的非训练域(外推)预测性能. 这些结果对于进一步发展知识-数据双驱动的高精度增材制造疲劳寿命预测模型具有重要的参考价值.

, correspAuthors=吴昊, authorNote=null, correspAuthorsNote=
** E-mail:.
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=4WBaX7ehwJ6XmREHrbpLyg==, magXml=D/AR2e0cdd0czKZxtEGOgA==, pdfUrl=null, pdf=+8BWCwx1aag0HuwUrSKjIQ==, pdfFileSize=6032078, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=AJtBLUXBlLDwedKlzVG+TA==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=QlH/QUVNe1VhGcw18ymE/Q==, mapNumber=null, authorCompany=null, fund=null, authors=null, authorsList=王谙斌, 甘磊, 淦志强, 范志明, 苏永辉, 吴昊)}, authors=[Author(id=1246042377153003927, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, 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=1246042377249472925, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, authorId=1246042377153003927, language=EN, stringName=Anbin Wang, firstName=Anbin, middleName=null, lastName=Wang, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1School of Aerospace Engineering and Mechanics, Tongji University, Shanghai, 200092, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1246042377375302050, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, authorId=1246042377153003927, language=CN, stringName=王谙斌, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1同济大学航空航天与力学学院,上海,200092, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1246042376951677323, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, xref=1, ext=[AuthorCompanyExt(id=1246042376960065932, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, companyId=1246042376951677323, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1School of Aerospace Engineering and Mechanics, Tongji University, Shanghai, 200092), AuthorCompanyExt(id=1246042376964260237, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, companyId=1246042376951677323, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1同济大学航空航天与力学学院,上海,200092)])]), Author(id=1246042377459188134, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, 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=1246042377568240043, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, authorId=1246042377459188134, language=EN, stringName=Lei Gan, firstName=Lei, middleName=null, lastName=Gan, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2College of Science, Harbin Institute of Technology (Shenzhen), Shenzhen, 518055, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1246042377689874861, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, authorId=1246042377459188134, language=CN, stringName=甘磊, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2哈尔滨工业大学(深圳)理学院,深圳,518055, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1246042377052340624, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, xref=2, ext=[AuthorCompanyExt(id=1246042377056534929, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, companyId=1246042377052340624, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2College of Science, Harbin Institute of Technology (Shenzhen), Shenzhen, 518055), AuthorCompanyExt(id=1246042377064923538, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, companyId=1246042377052340624, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2哈尔滨工业大学(深圳)理学院,深圳,518055)])]), Author(id=1246042377782149553, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1246042377878618549, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, authorId=1246042377782149553, language=EN, stringName=Zhiqiang Gan, firstName=Zhiqiang, middleName=null, lastName=Gan, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1School of Aerospace Engineering and Mechanics, Tongji University, Shanghai, 200092, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1246042377975087546, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, authorId=1246042377782149553, language=CN, stringName=淦志强, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1同济大学航空航天与力学学院,上海,200092, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1246042376951677323, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, xref=1, ext=[AuthorCompanyExt(id=1246042376960065932, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, companyId=1246042376951677323, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1School of Aerospace Engineering and Mechanics, Tongji University, Shanghai, 200092), AuthorCompanyExt(id=1246042376964260237, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, companyId=1246042376951677323, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1同济大学航空航天与力学学院,上海,200092)])]), Author(id=1246042378050585021, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, 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=1246042378172219845, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, authorId=1246042378050585021, language=EN, stringName=Zhiming Fan, firstName=Zhiming, middleName=null, lastName=Fan, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1School of Aerospace Engineering and Mechanics, Tongji University, Shanghai, 200092, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1246042378230940105, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, authorId=1246042378050585021, language=CN, stringName=范志明, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1同济大学航空航天与力学学院,上海,200092, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1246042376951677323, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, xref=1, ext=[AuthorCompanyExt(id=1246042376960065932, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, companyId=1246042376951677323, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1School of Aerospace Engineering and Mechanics, Tongji University, Shanghai, 200092), AuthorCompanyExt(id=1246042376964260237, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, companyId=1246042376951677323, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1同济大学航空航天与力学学院,上海,200092)])]), Author(id=1246042378327409103, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, orderNo=4, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1246042378415489494, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, authorId=1246042378327409103, language=EN, stringName=Yonghui Su, firstName=Yonghui, middleName=null, lastName=Su, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1School of Aerospace Engineering and Mechanics, Tongji University, Shanghai, 200092, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1246042378474209755, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, authorId=1246042378327409103, language=CN, stringName=苏永辉, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1同济大学航空航天与力学学院,上海,200092, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1246042376951677323, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, xref=1, ext=[AuthorCompanyExt(id=1246042376960065932, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, companyId=1246042376951677323, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1School of Aerospace Engineering and Mechanics, Tongji University, Shanghai, 200092), AuthorCompanyExt(id=1246042376964260237, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, companyId=1246042376951677323, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1同济大学航空航天与力学学院,上海,200092)])]), Author(id=1246042378562290145, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, orderNo=5, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=wuhao@tongji.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1246042378696507877, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, authorId=1246042378562290145, language=EN, stringName=Hao Wu, firstName=Hao, middleName=null, lastName=Wu, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, **, address=1School of Aerospace Engineering and Mechanics, Tongji University, Shanghai, 200092, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1246042378772005352, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, authorId=1246042378562290145, language=CN, stringName=吴昊, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, **, address=1同济大学航空航天与力学学院,上海,200092, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1246042376951677323, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, xref=1, ext=[AuthorCompanyExt(id=1246042376960065932, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, companyId=1246042376951677323, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1School of Aerospace Engineering and Mechanics, Tongji University, Shanghai, 200092), AuthorCompanyExt(id=1246042376964260237, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, companyId=1246042376951677323, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1同济大学航空航天与力学学院,上海,200092)])])], keywords=[Keyword(id=1246042378918805998, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, language=EN, orderNo=1, keyword=additive manufacturing), Keyword(id=1246042379023663603, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, language=EN, orderNo=2, keyword=fatigue life), Keyword(id=1246042379115938292, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, language=EN, orderNo=3, keyword=continuum damage mechanics), Keyword(id=1246042379212407288, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, language=EN, orderNo=4, keyword=neural networks), Keyword(id=1246042379304681979, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, language=EN, orderNo=5, keyword=knowledge-data dual-driven), Keyword(id=1246042379392762367, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, language=CN, orderNo=1, keyword=增材制造), Keyword(id=1246042379510202884, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, language=CN, orderNo=2, keyword=疲劳寿命), Keyword(id=1246042379602477575, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, language=CN, orderNo=3, keyword=连续损伤力学), Keyword(id=1246042379686363659, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, language=CN, orderNo=4, keyword=神经网络), Keyword(id=1246042379812192783, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, language=CN, orderNo=5, keyword=知识-数据双驱动)], refs=[Reference(id=1246042383050195594, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, doi=null, pmid=null, pmcid=null, year=2022, volume=24, issue=4, pageStart=202, pageEnd=211, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=Wang L, Lu B H, journalName=Strategic Study of Chinese Academy of Engineering, refType=null, unstructuredReference=Wang L, Lu B H. Development of additive manufacturing technology and industry in China[J]. Strategic Study of Chinese Academy of Engineering, 2022, 24(4): 202-211., articleTitle=Development of additive manufacturing technology and industry in China, refAbstract=null), Reference(id=1246042383155053197, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, doi=null, pmid=null, pmcid=null, year=2021, volume=21, issue=01, pageStart=132, pageEnd=153, url=null, language=null, rfNumber=[2], rfOrder=1, authorNames=杨冰, 廖贞, 吴圣川, 肖守讷, 阳光武, 朱涛, 王明猛, 邓永权, journalName=交通运输工程学报, refType=null, unstructuredReference=杨冰, 廖贞, 吴圣川, 肖守讷, 阳光武, 朱涛, 王明猛, 邓永权. 增材制造技术发展和在先进轨道交通装备中的应用展望[J]. 交通运输工程学报, 2021, 21(01): 132-153., articleTitle=增材制造技术发展和在先进轨道交通装备中的应用展望, refAbstract=null), Reference(id=1246042383259910803, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, doi=null, pmid=null, pmcid=null, year=2021, volume=21, issue=01, pageStart=132, pageEnd=153, url=null, language=null, rfNumber=[2], rfOrder=2, authorNames=Yang B, Liao Z, Wu S C, Xiao S N, Yang G W, Zhu T, Wang M M, Deng Y Q, journalName=Journal of Traffic and Transportation Engineering, refType=null, unstructuredReference=(Yang B, Liao Z, Wu S C, Xiao S N, Yang G W, Zhu T, Wang M M, Deng Y Q. Development of additive manufacturing technology and its application prospect in advanced rail transit equipment[J]. Journal of Traffic and Transportation Engineering, 2021, 21(01): 132-153. (in Chinese)), articleTitle=Development of additive manufacturing technology and its application prospect in advanced rail transit equipment, refAbstract=null), Reference(id=1246042383352185495, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, doi=null, pmid=null, pmcid=null, year=2015, volume=45, issue=9, pageStart=1111, pageEnd=1126, url=null, language=null, rfNumber=[3], rfOrder=3, authorNames=林鑫, 黄卫东, journalName=中国科学(信息科学), refType=null, unstructuredReference=林鑫, 黄卫东. 高性能金属构件的激光增材制造[J]. 中国科学(信息科学), 2015, 45(9): 1111-1126., articleTitle=高性能金属构件的激光增材制造, refAbstract=null), Reference(id=1246042383444460188, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, doi=null, pmid=null, pmcid=null, year=2015, volume=45, issue=9, pageStart=1111, pageEnd=1126, url=null, language=null, rfNumber=[3], rfOrder=4, authorNames=Lin X, Huang W D, journalName=Scientia Sinica (Informationis), refType=null, unstructuredReference=(Lin X, Huang W D. Laser additive manufacturing of high-performance metal components[J]. Scientia Sinica (Informationis), 2015, 45(9): 1111-1126. (in Chinese)), articleTitle=Laser additive manufacturing of high-performance metal components, refAbstract=null), Reference(id=1246042383549317791, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, doi=null, pmid=null, pmcid=null, year=2014, volume=598, issue=null, pageStart=327, pageEnd=337, url=null, language=null, rfNumber=[4], rfOrder=5, authorNames=Edwards P, Ramulu M, journalName=Materials Science and Engineering: A, refType=null, unstructuredReference=Edwards P, Ramulu M. Fatigue performance evaluation of selective laser melted Ti-6Al-4V[J]. Materials Science and Engineering: A, 2014, 598: 327-337., articleTitle=Fatigue performance evaluation of selective laser melted Ti-6Al-4V, refAbstract=null), Reference(id=1246042383666758308, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, doi=null, pmid=null, pmcid=null, year=2015, volume=8, issue=null, pageStart=12, pageEnd=35, url=null, language=null, rfNumber=[5], rfOrder=6, authorNames=Shamsaei N, Yadollahi A, Bian L, Thompson S M, journalName=Additive Manufacturing, refType=null, unstructuredReference=Shamsaei N, Yadollahi A, Bian L, Thompson S M. An overview of Direct Laser Deposition for additive manufacturing; Part II: Mechanical behavior, process parameter optimization and control[J]. Additive Manufacturing, 2015, 8: 12-35., articleTitle=An overview of Direct Laser Deposition for additive manufacturing; Part II: Mechanical behavior, process parameter optimization and control, refAbstract=null), Reference(id=1246042383742255783, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, doi=null, pmid=null, pmcid=null, year=2021, volume=51, issue=3, pageStart=648, pageEnd=701, url=null, language=null, rfNumber=[6], rfOrder=7, authorNames=廉艳平, 王潘丁, 高杰, 刘继凯, 李取浩, 刘长猛, 贺小帆, 高亮, 李好, 雷红帅, 李会民, 肖登宝, 郭旭, 方岱宁, journalName=力学进展, refType=null, unstructuredReference=廉艳平, 王潘丁, 高杰, 刘继凯, 李取浩, 刘长猛, 贺小帆, 高亮, 李好, 雷红帅, 李会民, 肖登宝, 郭旭, 方岱宁. 金属增材制造若干关键力学问题研究进展[J]. 力学进展, 2021, 51(3): 648-701., articleTitle=金属增材制造若干关键力学问题研究进展, refAbstract=null), Reference(id=1246042383830336172, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, doi=null, pmid=null, pmcid=null, year=2021, volume=51, issue=3, pageStart=648, pageEnd=701, url=null, language=null, rfNumber=[6], rfOrder=8, authorNames=Lian Y P, Wang P D, Gao J, Liu J K, Li Q H, Liu C M, He X F, Gao L, Li H, Lei H S, Li H M, Xiao D B, Guo X, Fang D N, journalName=Advances in Mechanics, refType=null, unstructuredReference=(Lian Y P, Wang P D, Gao J, Liu J K, Li Q H, Liu C M, He X F, Gao L, Li H, Lei H S, Li H M, Xiao D B, Guo X, Fang D N. Fundamental mechanics problems in metal additive manufacturing: A state-of-art review[J]. Advances in Mechanics, 2021, 51(3): 648-701. (in Chinese)), articleTitle=Fundamental mechanics problems in metal additive manufacturing: A state-of-art review, refAbstract=null), Reference(id=1246042383918416560, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, doi=null, pmid=null, pmcid=null, year=2018, volume=716, issue=null, pageStart=140, pageEnd=149, url=null, language=null, rfNumber=[7], rfOrder=9, authorNames=Liu Z, Liu P F, Wang L, Lu Y Z, Lu X, Qin Z X, Wang H M, journalName=Materials Science and Engineering: A, refType=null, unstructuredReference=Liu Z, Liu P F, Wang L, Lu Y Z, Lu X, Qin Z X, Wang H M. Fatigue properties of Ti-6.5Al-3.5Mo-l.5Zr-0.3Si alloy produced by direct laser deposition[J]. Materials Science and Engineering: A, 2018, 716: 140-149., articleTitle=Fatigue properties of Ti-6.5Al-3.5Mo-l.5Zr-0.3Si alloy produced by direct laser deposition, refAbstract=null), Reference(id=1246042383981331123, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, doi=null, pmid=null, pmcid=null, year=2022, volume=221, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[8], rfOrder=10, authorNames=Peng X, Wu S C, Qian W J, Bao J G, Hu Y N, Zhan Z X, Withers P J, journalName=International Journal of Mechanical Sciences, refType=null, unstructuredReference=Peng X, Wu S C, Qian W J, Bao J G, Hu Y N, Zhan Z X, 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=1246042384056828598, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, doi=null, pmid=null, pmcid=null, year=2016, volume=655, issue=null, pageStart=100, pageEnd=112, url=null, language=null, rfNumber=[9], rfOrder=11, authorNames=Sterling A J, Torries B, Shamsaei N, Thompson S M, Seely D W, journalName=Materials Science & Engineering A, refType=null, unstructuredReference=Sterling A J, Torries B, Shamsaei N, Thompson S M, Seely D W. Fatigue behavior and failure mechanisms of direct laser deposited Ti-6Al-4V[J]. Materials Science & Engineering A, 2016, 655: 100-112., articleTitle=Fatigue behavior and failure mechanisms of direct laser deposited Ti-6Al-4V, refAbstract=null), Reference(id=1246042384191046331, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, doi=null, pmid=null, pmcid=null, year=2019, volume=28, issue=null, pageStart=373, pageEnd=393, url=null, language=null, rfNumber=[10], rfOrder=12, authorNames=Wang X, He X, Wang T, Li Y, journalName=Additive Manufacturing, refType=null, unstructuredReference=Wang X, He X, Wang T, Li Y. Internal pores in DED Ti-6.5Al-2Zr-Mo-V alloy and their influence on crack initiation and fatigue life in the mid-life regime[J]. Additive Manufacturing, 2019, 28: 373-393., articleTitle=Internal pores in DED Ti-6.5Al-2Zr-Mo-V alloy and their influence on crack initiation and fatigue life in the mid-life regime, refAbstract=null), Reference(id=1246042384308486847, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, doi=null, pmid=null, pmcid=null, year=2023, volume=44, issue=3, pageStart=381, pageEnd=394, url=null, language=null, rfNumber=[11], rfOrder=13, authorNames=詹志新, 高同州, 刘传奇, 吴圣川, journalName=固体力学学报, refType=null, unstructuredReference=詹志新, 高同州, 刘传奇, 吴圣川. 基于数据驱动的增材制造铝合金的疲劳寿命预测[J]. 固体力学学报, 2023, 44(3): 381-394., articleTitle=基于数据驱动的增材制造铝合金的疲劳寿命预测, refAbstract=null), Reference(id=1246042384396567237, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, doi=null, pmid=null, pmcid=null, year=2023, volume=44, issue=3, pageStart=381, pageEnd=394, url=null, language=null, rfNumber=[11], rfOrder=14, authorNames=Zhan Z X, Gao T Z, Liu C Q, Wu S C, journalName=Chinese Journal of Solid Mechanics, refType=null, unstructuredReference=(Zhan Z X, Gao T Z, Liu C Q, Wu S C. Data-driven fatigue life prediction of additive manufactured aluminum alloys[J]. Chinese Journal of Solid Mechanics, 2023, 44(3): 381-394. (in Chinese)), articleTitle=Data-driven fatigue life prediction of additive manufactured aluminum alloys, refAbstract=null), Reference(id=1246042384518202056, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, doi=null, pmid=null, pmcid=null, year=2018, volume=157, issue=null, pageStart=259, pageEnd=275, url=null, language=null, rfNumber=[12], rfOrder=15, authorNames=Zhu M L, Jin L, Xuan F Z, journalName=Acta Materialia, refType=null, unstructuredReference=Zhu M L, Jin L, Xuan F Z. Fatigue life and mechanistic modeling of interior micro-defect induced cracking in high cycle and very high cycle regimes[J]. Acta Materialia, 2018, 157: 259-275., articleTitle=Fatigue life and mechanistic modeling of interior micro-defect induced cracking in high cycle and very high cycle regimes, refAbstract=null), Reference(id=1246042384618865357, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, doi=null, pmid=null, pmcid=null, year=2012, volume=41, issue=null, pageStart=2, pageEnd=10, url=null, language=null, rfNumber=[13], rfOrder=16, authorNames=Murakami Y, journalName=International Journal of Fatigue, refType=null, unstructuredReference=Murakami Y. Material defects as the basis of fatigue design[J]. International Journal of Fatigue, 2012, 41: 2-10., articleTitle=Material defects as the basis of fatigue design, refAbstract=null), Reference(id=1246042384744694481, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, doi=null, pmid=null, pmcid=null, year=2019, volume=155, issue=null, pageStart=110, pageEnd=124, url=null, language=null, rfNumber=[14], rfOrder=17, authorNames=Zhan Z X, Li H, Lam K Y, journalName=International Journal of Mechanical ences, refType=null, unstructuredReference=Zhan Z X, Li H, Lam K Y. Development of a novel fatigue damage model with AM effects for life prediction of commonly-used alloys in aerospace[J]. International Journal of Mechanical ences, 2019, 155: 110-124., articleTitle=Development of a novel fatigue damage model with AM effects for life prediction of commonly-used alloys in aerospace, refAbstract=null), Reference(id=1246042384836969173, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, doi=null, pmid=null, pmcid=null, year=2023, volume=169, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[15], rfOrder=18, authorNames=Jan H, Jiří B, Petr H, journalName=International Journal of Fatigue, refType=null, unstructuredReference=Jan H, Jiří B, Petr H, et al. Modelling fatigue life prediction of additively manufactured Ti-6Al-4V samples using machine learning approach[J]. International Journal of Fatigue, 2023, 169: 107483., articleTitle=Modelling fatigue life prediction of additively manufactured Ti-6Al-4V samples using machine learning approach, refAbstract=null), Reference(id=1246042384941826780, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, doi=null, pmid=null, pmcid=null, year=2022, volume=160, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[16], rfOrder=19, authorNames=Maleki E, Bagherifard S, Razavi S M J, Bandini M, Du P A, Berto F, Guagliano M, journalName=International Journal of Fatigue, refType=null, unstructuredReference=Maleki E, Bagherifard S, Razavi S M J, Bandini M, Du P A, Berto F, Guagliano M. On the efficiency of machine learning for fatigue assessment of post-processed additively manufactured AlSi10Mg[J]. International Journal of Fatigue, 2022, 160: 106841., articleTitle=On the efficiency of machine learning for fatigue assessment of post-processed additively manufactured AlSi10Mg, refAbstract=null), Reference(id=1246042385067655906, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, doi=null, pmid=null, pmcid=null, year=2023, volume=178, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[17], rfOrder=20, authorNames=Lei L M, Li B, Wang H J, Huang G Q, Xuan F Z, journalName=International Journal of Fatigue, refType=null, unstructuredReference=Lei L M, Li B, Wang H J, Huang G Q, Xuan F Z. High-temperature high-cycle fatigue performance and machine learning-based fatigue life prediction of additively manufactured Hastelloy X[J]. International Journal of Fatigue, 2023, 178: 108012., articleTitle=High-temperature high-cycle fatigue performance and machine learning-based fatigue life prediction of additively manufactured Hastelloy X, refAbstract=null), Reference(id=1246042385164124903, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, doi=null, pmid=null, pmcid=null, year=2022, volume=48, issue=6, pageStart=950, pageEnd=956, url=null, language=null, rfNumber=[18], rfOrder=21, authorNames=洪海铭, 詹志新, 王佳莹, journalName=北京航空航天大学学报, refType=null, unstructuredReference=洪海铭, 詹志新, 王佳莹. 基于损伤力学的增材制造金属材料疲劳寿命预测[J]. 北京航空航天大学学报, 2022, 48(6): 950-956., articleTitle=基于损伤力学的增材制造金属材料疲劳寿命预测, refAbstract=null), Reference(id=1246042385260593898, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, doi=null, pmid=null, pmcid=null, year=2022, volume=48, issue=6, pageStart=950, pageEnd=956, url=null, language=null, rfNumber=[18], rfOrder=22, authorNames=Hong H M, Zhan Z X, Wang J Y, journalName=Journal of Beijing University of Aeronautics and Astronautics, refType=null, unstructuredReference=(Hong H M, Zhan Z X, Wang J Y. Damage mechanics-based fatigue life prediction for additive manufacturing metal materials[J]. Journal of Beijing University of Aeronautics and Astronautics, 2022, 48(6): 950-956. (in Chinese)), articleTitle=Damage mechanics-based fatigue life prediction for additive manufacturing metal materials, refAbstract=null), Reference(id=1246042385373840112, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, doi=null, pmid=null, pmcid=null, year=2007, volume=29, issue=3, pageStart=389, pageEnd=396, url=null, language=null, rfNumber=[19], rfOrder=23, authorNames=Freire R C S, Neto A D D, Aquino E M F, journalName=International Journal of Fatigue, refType=null, unstructuredReference=Freire R C S, Neto A D D, Aquino E M F. Use of modular networks in the building of constant life diagrams[J]. International Journal of Fatigue, 2007, 29(3): 389-396., articleTitle=Use of modular networks in the building of constant life diagrams, refAbstract=null), Reference(id=1246042385461920501, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, doi=null, pmid=null, pmcid=null, year=2023, volume=172, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[20], rfOrder=24, authorNames=Gan L, Wu H, Zhong Z, journalName=International Journal of Fatigue, refType=null, unstructuredReference=Gan L, Wu H, Zhong Z. On the integration of domain knowledge and branching neural network for fatigue life prediction with small samples[J]. International Journal of Fatigue, 2023, 172: 107648., articleTitle=On the integration of domain knowledge and branching neural network for fatigue life prediction with small samples, refAbstract=null), Reference(id=1246042385541612281, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, doi=null, pmid=null, pmcid=null, year=2022, volume=164, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[21], rfOrder=25, authorNames=Wang H J, Li B, Xuan F Z, journalName=International Journal of Fatigue, refType=null, unstructuredReference=Wang H J, Li B, Xuan F Z. Fatigue-life prediction of additively manufactured metals by continuous damage mechanics (CDM)-informed machine learning with sensitive features[J]. International Journal of Fatigue, 2022, 164: 107147., articleTitle=Fatigue-life prediction of additively manufactured metals by continuous damage mechanics (CDM)-informed machine learning with sensitive features, refAbstract=null), Reference(id=1246042385650664191, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, doi=null, pmid=null, pmcid=null, year=2022, volume=160, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[22], rfOrder=26, authorNames=Liu S, Shi W J, Zhan Z X, Hu W P, Meng Q C, journalName=International Journal of Fatigue, refType=null, unstructuredReference=Liu S, Shi W J, Zhan Z X, Hu W P, Meng Q C. On the development of error-trained BP-ANN technique with CDM model for the HCF life prediction of aluminum alloy[J]. International Journal of Fatigue, 2022, 160: 106836., articleTitle=On the development of error-trained BP-ANN technique with CDM model for the HCF life prediction of aluminum alloy, refAbstract=null), Reference(id=1246042385747133187, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, doi=null, pmid=null, pmcid=null, year=1988, volume=11, issue=1, pageStart=1, pageEnd=17, url=null, language=null, rfNumber=[23], rfOrder=27, authorNames=Chaboche J L, Lesne P M, journalName=Fatigue & Fracture of Engineering Materials & Structures, refType=null, unstructuredReference=Chaboche J L, Lesne P M. A non-linear continuous fatigue damage model[J]. Fatigue & Fracture of Engineering Materials & Structures, 1988, 11(1): 1-17., articleTitle=A non-linear continuous fatigue damage model, refAbstract=null), Reference(id=1246042385822630663, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, doi=null, pmid=null, pmcid=null, year=2016, volume=90, issue=sep., pageStart=125, pageEnd=138, url=null, language=null, rfNumber=[24], rfOrder=28, authorNames=Shen F, Hu W P, Meng Q C, journalName=International Journal of Fatigue, refType=null, unstructuredReference=Shen F, Hu W P, Meng Q C. A non-local approach based on the hypothesis of damage dissipation potential equivalence to the effect of stress gradient in fretting fatigue[J]. International Journal of Fatigue, 2016, 90(sep.): 125-138., articleTitle=A non-local approach based on the hypothesis of damage dissipation potential equivalence to the effect of stress gradient in fretting fatigue, refAbstract=null), Reference(id=1246042385919099659, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, doi=null, pmid=null, pmcid=null, year=2023, volume=166, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[25], rfOrder=29, authorNames=Chen D, Li Y Z, Liu K, Li Y, journalName=International Journal of Fatigue, refType=null, unstructuredReference=Chen D, Li Y Z, Liu K, Li Y. A physics-informed neural network approach to fatigue life prediction using small quantity of samples[J]. International Journal of Fatigue, 2023, 166: 107270., articleTitle=A physics-informed neural network approach to fatigue life prediction using small quantity of samples, refAbstract=null), Reference(id=1246042386015568655, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, doi=null, pmid=null, pmcid=null, year=2009, volume=1, issue=null, pageStart=62, pageEnd=64, url=null, language=null, rfNumber=[26], rfOrder=30, authorNames=李翱翔, 陈健, journalName=数字通信世界, refType=null, unstructuredReference=李翱翔, 陈健. BP神经网络参数改进方法综述[J]. 数字通信世界, 2009, 1: 62-64., articleTitle=BP神经网络参数改进方法综述, refAbstract=null), Reference(id=1246042386103649042, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, doi=null, pmid=null, pmcid=null, year=2009, volume=1, issue=null, pageStart=62, pageEnd=64, url=null, language=null, rfNumber=[26], rfOrder=31, authorNames=Li A X, Chen J, journalName=Digital Communication World, refType=null, unstructuredReference=(Li A X, Chen J. Summarize of parameter improve methods for BP neural network[J]. Digital Communication World, 2009, 1: 62-64. (in Chinese)), articleTitle=Summarize of parameter improve methods for BP neural network, refAbstract=null), Reference(id=1246042386191729430, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, doi=null, pmid=null, pmcid=null, year=2005, volume=3, issue=null, pageStart=398, pageEnd=403, url=null, language=null, rfNumber=[27], rfOrder=32, authorNames=周慧, 朱彬, 陈万隆, 朱国强, 黄赛群, journalName=南京气象学院学报, refType=null, unstructuredReference=周慧, 朱彬, 陈万隆, 朱国强, 黄赛群. 动态学习率神经网络预测气温的尝试[J]. 南京气象学院学报, 2005, 3: 398-403., articleTitle=动态学习率神经网络预测气温的尝试, refAbstract=null), Reference(id=1246042386309169945, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, doi=null, pmid=null, pmcid=null, year=2005, volume=3, issue=null, pageStart=398, pageEnd=403, url=null, language=null, rfNumber=[27], rfOrder=33, authorNames=Zhou H, Zhu B, Chen W L, Zhu G Q, Huang S Q, journalName=Journal of Nanjing Institute of Meteorology, refType=null, unstructuredReference=(Zhou H, Zhu B, Chen W L, Zhu G Q, Huang S Q. Daily air temperature prediction using a dynamic learning rate neural network system[J]. Journal of Nanjing Institute of Meteorology, 2005, 3: 398-403. (in Chinese)), articleTitle=Daily air temperature prediction using a dynamic learning rate neural network system, refAbstract=null), Reference(id=1246042386397250333, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, doi=null, pmid=null, pmcid=null, year=2011, volume=8, issue=1, pageStart=113, pageEnd=117, url=null, language=null, rfNumber=[28], rfOrder=34, authorNames=Yang S, Gregory N T, Stephen J W, journalName=Geoscience and Remote Sensing Letters, IEEE, refType=null, unstructuredReference=Yang S, Gregory N T, Stephen J W. Comparison of early stopping criteria for neural-network-based subpixel classification[J]. Geoscience and Remote Sensing Letters, IEEE, 2011, 8(1): 113-117., articleTitle=Comparison of early stopping criteria for neural-network-based subpixel classification, refAbstract=null), Reference(id=1246042386476942111, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, doi=null, pmid=null, pmcid=null, year=2020, volume=145, issue=2, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[29], rfOrder=35, 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, 2020, 145(2): 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=1246042386577605409, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, doi=null, pmid=null, pmcid=null, year=2017, volume=94, issue=2, pageStart=192, pageEnd=201, url=null, language=null, rfNumber=[30], rfOrder=36, authorNames=Tang M, Pistorius P C, journalName=International Journal of Fatigue, refType=null, unstructuredReference=Tang M, Pistorius P C. Oxides, porosity and fatigue performance of AlSi10Mg parts produced by selective laser melting[J]. International Journal of Fatigue, 2017, 94(2): 192-201., articleTitle=Oxides, porosity and fatigue performance of AlSi10Mg parts produced by selective laser melting, refAbstract=null), Reference(id=1246042386682463012, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, doi=null, pmid=null, pmcid=null, year=2011, volume=34, issue=null, pageStart=159, pageEnd=169, url=null, language=null, rfNumber=[31], rfOrder=37, authorNames=Erhard B, Ulrike H, Vitus H, Damien B, journalName=Materials and Design, refType=null, unstructuredReference=Erhard B, Ulrike H, Vitus H, Damien B. Additive manufactured AlSi10Mg samples using Selective Laser Melting (SLM): Microstructure, high cycle fatigue, and fracture behavior[J]. Materials and Design, 2011, 34: 159-169., articleTitle=Additive manufactured AlSi10Mg samples using Selective Laser Melting (SLM): Microstructure, high cycle fatigue, and fracture behavior, refAbstract=null), Reference(id=1246042386762154791, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, doi=null, pmid=null, pmcid=null, year=2017, volume=null, issue=null, pageStart=229, pageEnd=237, url=null, language=null, rfNumber=[32], rfOrder=38, authorNames=Uzan N E, Shneck R, Yeheskel O, Frage N, journalName=Materials Science and Engineering A, refType=null, unstructuredReference=Uzan N E, Shneck R, Yeheskel O, Frage N. Fatigue of AlSi10Mg specimens fabricated by additive manufacturing selective laser melting (AM-SLM)[J]. Materials Science and Engineering A, 2017, 229-237., articleTitle=Fatigue of AlSi10Mg specimens fabricated by additive manufacturing selective laser melting (AM-SLM), refAbstract=null), Reference(id=1246042386854429481, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, doi=null, pmid=null, pmcid=null, year=2016, volume=651, issue=null, pageStart=198, pageEnd=213, url=null, language=null, rfNumber=[33], rfOrder=39, authorNames=Mower T M, Long M J, journalName=Materials Science and Engineering A, refType=null, unstructuredReference=Mower T M, Long M J. Mechanical behavior of additive manufactured, powder-bed laser-fused materials[J]. Materials Science and Engineering A, 2016, 651: 198-213., articleTitle=Mechanical behavior of additive manufactured, powder-bed laser-fused materials, refAbstract=null)], funds=[Fund(id=1246042382882423428, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, awardId=12372081; 11972255, language=CN, fundingSource=国家自然科学基金项目(12372081; 11972255), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1246042376951677323, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, xref=1, ext=[AuthorCompanyExt(id=1246042376960065932, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, companyId=1246042376951677323, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1School of Aerospace Engineering and Mechanics, Tongji University, Shanghai, 200092), AuthorCompanyExt(id=1246042376964260237, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, companyId=1246042376951677323, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1同济大学航空航天与力学学院,上海,200092)]), AuthorCompany(id=1246042377052340624, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, xref=2, ext=[AuthorCompanyExt(id=1246042377056534929, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, companyId=1246042377052340624, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2College of Science, Harbin Institute of Technology (Shenzhen), Shenzhen, 518055), AuthorCompanyExt(id=1246042377064923538, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, companyId=1246042377052340624, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2哈尔滨工业大学(深圳)理学院,深圳,518055)])], figs=[ArticleFig(id=1246042380047073816, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, language=EN, label=Fig.1, caption=CDM model parameter calibration flowchart, figureFileSmall=KmESKceTCIiCbpysjieU4A==, figureFileBig=RHkYn4m+goJkhBBXlTMq2g==, tableContent=null), ArticleFig(id=1246042380139348509, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, language=CN, label=图1, caption=CDM模型参数标定流程图, figureFileSmall=KmESKceTCIiCbpysjieU4A==, figureFileBig=RHkYn4m+goJkhBBXlTMq2g==, tableContent=null), ArticleFig(id=1246042380252594721, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, language=EN, label=Fig.2, caption=Schematic diagram of a typical four-layer ANN structure, figureFileSmall=RNblnFSeH3CKtvWC5uQ8lw==, figureFileBig=+JV3saoQYb/RKdWM2M7foA==, tableContent=null), ArticleFig(id=1246042380365840931, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, language=CN, label=图2, caption=典型四层ANN结构示意图, figureFileSmall=RNblnFSeH3CKtvWC5uQ8lw==, figureFileBig=+JV3saoQYb/RKdWM2M7foA==, tableContent=null), ArticleFig(id=1246042380453921317, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, language=EN, label=Fig.3, caption=Neural network training workflow diagram, figureFileSmall=sli0ZqQyq/UloLtch6ZiPQ==, figureFileBig=iDS/QeCj3j/VNUKR/fkygQ==, tableContent=null), ArticleFig(id=1246042380533613097, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, language=CN, label=图3, caption=网络训练流程图, figureFileSmall=sli0ZqQyq/UloLtch6ZiPQ==, figureFileBig=iDS/QeCj3j/VNUKR/fkygQ==, tableContent=null), ArticleFig(id=1246042380630082092, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, language=EN, label=Fig.4, caption=Schematic diagram of F-FM based on CDM, figureFileSmall=sVJDYFpOvmC9gURxcXjA6Q==, figureFileBig=N5d2t/+GMgKF9N4xLHNdDA==, tableContent=null), ArticleFig(id=1246042380730745392, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, language=CN, label=图4, caption=基于CDM的F-FM示意图, figureFileSmall=sVJDYFpOvmC9gURxcXjA6Q==, figureFileBig=N5d2t/+GMgKF9N4xLHNdDA==, tableContent=null), ArticleFig(id=1246042380818825781, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, language=EN, label=Fig.5, caption=Schematic diagram of P-FM based on CDM, figureFileSmall=62vjLr49PhvFrcMzaZqd8g==, figureFileBig=y2qwZZ+hv4qnHLrIl0vntQ==, tableContent=null), ArticleFig(id=1246042380915294779, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, language=CN, label=图5, caption=基于CDM的P-FM示意图, figureFileSmall=62vjLr49PhvFrcMzaZqd8g==, figureFileBig=y2qwZZ+hv4qnHLrIl0vntQ==, tableContent=null), ArticleFig(id=1246042380999180863, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, language=EN, label=Fig.6, caption=Schematic diagram of O-FM based on CDM, figureFileSmall=yvOwLRwHi5ZNbqCN3B26MA==, figureFileBig=RdZhB/Xszem2RIRuvAX7Ng==, tableContent=null), ArticleFig(id=1246042381074678339, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, language=CN, label=图6, caption=基于CDM的O-FM示意图, figureFileSmall=yvOwLRwHi5ZNbqCN3B26MA==, figureFileBig=RdZhB/Xszem2RIRuvAX7Ng==, tableContent=null), ArticleFig(id=1246042381158564420, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, language=EN, label=Fig.7, caption=Distribution of fatigue data, figureFileSmall=TCZIKG4KxrdcEKlaMMY+Ew==, figureFileBig=DLvi+LzRgigobVFmSIEMQQ==, tableContent=null), ArticleFig(id=1246042381242450503, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, language=CN, label=图7, caption=疲劳数据分布, figureFileSmall=TCZIKG4KxrdcEKlaMMY+Ew==, figureFileBig=DLvi+LzRgigobVFmSIEMQQ==, tableContent=null), ArticleFig(id=1246042381317947978, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, language=EN, label=Fig.8, caption=Comparison of prediction accuracy among different models, figureFileSmall=P8kvcFqC3SWNEafhGdOgHw==, figureFileBig=K6jquu4TUzC9baYTr1IIIA==, tableContent=null), ArticleFig(id=1246042381380862541, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, language=CN, label=图8, caption=不同模型的预测精度对比, figureFileSmall=P8kvcFqC3SWNEafhGdOgHw==, figureFileBig=K6jquu4TUzC9baYTr1IIIA==, tableContent=null), ArticleFig(id=1246042381485720146, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, language=EN, label=Fig.9, caption=Variance comparison chart of prediction results for five models under different training sample sizes, figureFileSmall=kmHHXGtc3dKjVv9d1WkOQg==, figureFileBig=QQeHNGqW6SVwevejABAiuA==, tableContent=null), ArticleFig(id=1246042381561217621, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, language=CN, label=图9, caption=五类模型在不同训练样本量下预测结果的方差对比图, figureFileSmall=kmHHXGtc3dKjVv9d1WkOQg==, figureFileBig=QQeHNGqW6SVwevejABAiuA==, tableContent=null), ArticleFig(id=1246042381645103703, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, language=EN, label=Fig.10, caption=Comparison of results under different training sample sizes, figureFileSmall=VxyJUJLRZRqqHxeqWlgq4A==, figureFileBig=u9x1fhVS7PEnNECHgZHNnA==, tableContent=null), ArticleFig(id=1246042381754155610, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, language=CN, label=图10, caption=不同训练样本量下的结果比较, figureFileSmall=VxyJUJLRZRqqHxeqWlgq4A==, figureFileBig=u9x1fhVS7PEnNECHgZHNnA==, tableContent=null), ArticleFig(id=1246042381833847389, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, language=EN, label=Fig.11, caption=Extrapolating prediction results with different methods, figureFileSmall=5CHAsDIMJ0tYgYCc8cdSiw==, figureFileBig=4xMpUXB2X1eKfnv7Nhwhnw==, tableContent=null), ArticleFig(id=1246042381934510689, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, language=CN, label=图11, caption=不同方法外推预测结果, figureFileSmall=5CHAsDIMJ0tYgYCc8cdSiw==, figureFileBig=4xMpUXB2X1eKfnv7Nhwhnw==, tableContent=null), ArticleFig(id=1246042382030979685, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, language=EN, label=Table 1, caption=

Hyper parameters of ANN

, figureFileSmall=null, figureFileBig=null, tableContent=
超参数参数设置
结构6-15-15-15-1
激活函数(隐藏层)Sigmoid
激活函数(输出层)Linear
迭代次数(i10000
学习率(η线性递减(0.23-0.01)
输出疲劳寿命
), ArticleFig(id=1246042382119060072, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, language=CN, label=表1, caption=

ANN的超参数设置

, figureFileSmall=null, figureFileBig=null, tableContent=
超参数参数设置
结构6-15-15-15-1
激活函数(隐藏层)Sigmoid
激活函数(输出层)Linear
迭代次数(i10000
学习率(η线性递减(0.23-0.01)
输出疲劳寿命
), ArticleFig(id=1246042382207140461, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, language=EN, label=Table 2, caption=

Hyper parameters of models

, figureFileSmall=null, figureFileBig=null, tableContent=
模型网络结构最大迭代次数输出
ANN6-15-15-15-110000Fatigue life
F-FM7-15-15-15-15000Fatigue life
P-FM6-15-15-15-15000Fatigue life
O-FM6-15-15-15-15000Error
), ArticleFig(id=1246042382303609456, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, language=CN, label=表2, caption=

模型的超参数设置

, figureFileSmall=null, figureFileBig=null, tableContent=
模型网络结构最大迭代次数输出
ANN6-15-15-15-110000Fatigue life
F-FM7-15-15-15-15000Fatigue life
P-FM6-15-15-15-15000Fatigue life
O-FM6-15-15-15-15000Error
), ArticleFig(id=1246042382383301236, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, language=EN, label=Table 3, caption=

Database information of LPBF AlSi10Mg

, figureFileSmall=null, figureFileBig=null, tableContent=
编号激光功率(W)扫描速度(mm·s-1粉尘厚度(μm)舱口间距(mm)应力比体积能量密度比数量
1250500500.150.11.1126
23701300300.160.10.984
33701300300.190.10.834
43701300300.220.10.724
54001000300.2-10.5616
6100930500.1-10.3623
), ArticleFig(id=1246042382496547447, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, language=CN, label=表3, caption=

LPBF AlSi10Mg合金数据库信息

, figureFileSmall=null, figureFileBig=null, tableContent=
编号激光功率(W)扫描速度(mm·s-1粉尘厚度(μm)舱口间距(mm)应力比体积能量密度比数量
1250500500.150.11.1126
23701300300.160.10.984
33701300300.190.10.834
43701300300.220.10.724
54001000300.2-10.5616
6100930500.1-10.3623
), ArticleFig(id=1246042382567850618, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, language=EN, label=Table 4, caption=

Statistics table of outlier counts for each model

, figureFileSmall=null, figureFileBig=null, tableContent=
模型样本量=6
CDM4
ANN0
P-FM1
F-FM0
O-FM1
), ArticleFig(id=1246042382668513920, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246031930760741606, language=CN, label=表4, caption=

各模型离群值数量统计表

, figureFileSmall=null, figureFileBig=null, tableContent=
模型样本量=6
CDM4
ANN0
P-FM1
F-FM0
O-FM1
)], 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/o3.2024.010, detailUrlEn=https://castjournals.cast.org.cn/joweb/gtlxxb/EN/10.19636/j.cnki.cjsm42-1250/o3.2024.010, pdfUrlCn=https://castjournals.cast.org.cn/joweb/gtlxxb/CN/PDF/10.19636/j.cnki.cjsm42-1250/o3.2024.010, pdfUrlEn=https://castjournals.cast.org.cn/joweb/gtlxxb/EN/PDF/10.19636/j.cnki.cjsm42-1250/o3.2024.010, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
数据与连续损伤力学双驱动的增材疲劳寿命预测模型
收藏切换
PDF下载
王谙斌 1 , 甘磊 2 , 淦志强 1 , 范志明 1 , 苏永辉 1 , 吴昊 1, **
固体力学学报 | 研究论文 2024,45(4): 427-440
收起
收藏切换
固体力学学报 | 研究论文 2024, 45(4): 427-440
数据与连续损伤力学双驱动的增材疲劳寿命预测模型
全屏
王谙斌1, 甘磊2, 淦志强1, 范志明1, 苏永辉1, 吴昊1, **
作者信息
  • 1同济大学航空航天与力学学院,上海,200092
  • 2哈尔滨工业大学(深圳)理学院,深圳,518055

通讯作者:

** E-mail:.
Data-driven and Continuum Damage Mechanics-based Approach for Predicting Fatigue Lifein Additive Manufacturing
Anbin Wang1, Lei Gan2, Zhiqiang Gan1, Zhiming Fan1, Yonghui Su1, Hao Wu1, **
Affiliations
  • 1School of Aerospace Engineering and Mechanics, Tongji University, Shanghai, 200092
  • 2College of Science, Harbin Institute of Technology (Shenzhen), Shenzhen, 518055
出版时间: 2024-08-25 doi: 10.19636/j.cnki.cjsm42-1250/o3.2024.010
文章导航
收藏切换

传统的力学模型与新兴的数据驱动模型目前广泛用于增材制造的疲劳寿命预测中. 其中,以连续损伤力学(Continuum Damage Mechanics,CDM)为代表的传统模型寿命预测模型存在着精度低、适用范围有限等问题,而以神经网络(Artificial Neural Network,ANN)为代表的数据驱动模型则始终受限于小样本工况. 为解决上述问题,融合物理知识和数据信息的知识-数据双驱动模型近年来发展迅速. 以此类双驱动模型为研究目标,本文以激光粉末床熔融成型(Laser Powder Bed Fusion,LPBF)AlSi10Mg合金为研究对象,构建了可自动标定的CDM模型,并将其与基于ANN的数据驱动模型在各种工况下进行了结合,再进一步通过特征融合、参数融合和输出融合方法的手段,构建了三类以CDM模型与ANN模型为基础的知识-数据双驱动模型,并量化分析了它们在预测精度和数据需求等方面的性能. 研究结果表明:基于参数融合的模型,训练数据修正作用较为显著,在预测精度方面受CDM模型影响最小,并在CDM模型拟合结果较差时也能确保一定精度;基于特征融合的双驱动模型能最大化利用CDM模型中的物理信息,在数据充足时具有最高的预测精度与稳定性;基于输出融合的模型以CDM模型的结果为主导,利用ANN进行修正,具有五种模型中最好的非训练域(外推)预测性能. 这些结果对于进一步发展知识-数据双驱动的高精度增材制造疲劳寿命预测模型具有重要的参考价值.

增材制造  /  疲劳寿命  /  连续损伤力学  /  神经网络  /  知识-数据双驱动

Additive manufacturing (AM) techniques have attracted widespread attention in aerospace and biomedical fields due to advantages like high material utilization and extensive design flexibility. However, process-induced defects in AM-built components pose significant challenges for evaluating fatigue performance. The AM-built components are subjected to complex alternating loads in service, making it imperative to develop accurate fatigue life prediction models. Currently, two main approaches are widely employed: theoretical analysis and data-driven methods. Traditional life prediction models like continuum damage mechanics (CDM) suffer from limitations such as low accuracy and restricted applicability. Conversely, data-driven models, such as artificial neural networks (ANN), encounter constraints when dealing with limited sample sizes. To address these issues, knowledge-data hybrid models have emerged as a promising approach that combines physical principles with data insights. In view of this, this study has developed a calibrated CDM model and seamlessly integrated it with an ANN-based data-driven model. Employing methods of feature, parameter, and output fusion, three types of hybrid models based on CDM and ANN have been developed. To quantitatively analyze the prediction accuracy and data requirements of these models, calculations using fatigue data obtained from laser powder bed fusion (LPBF)-processed AlSi10Mg alloy have been performed. The results highlight the crucial role played by the corrective function of training data in the parameter fusion-based model, while indicating a relatively minor influence from the CDM model in terms of prediction accuracy. Moreover, this model retains a commendable level of accuracy even with suboptimal fitting outcomes from the CDM model. The hybrid model, which leverages feature fusion, maximizes the utilization of physical information from the CDM model, thus achieving the highest prediction accuracy and stability when ample data are available. The model based on output fusion, primarily guided by results of the CDM model and enhanced by ANN adjustments, demonstrates relatively superior predictive capabilities in domains outside of the training set compared to other models. These findings provide significant reference value for the further development of high-accuracy, knowledge-data hybrid fatigue life prediction models in AM.

additive manufacturing  /  fatigue life  /  continuum damage mechanics  /  neural networks  /  knowledge-data dual-driven
王谙斌, 甘磊, 淦志强, 范志明, 苏永辉, 吴昊. 数据与连续损伤力学双驱动的增材疲劳寿命预测模型. 固体力学学报, 2024 , 45 (4) : 427 -440 . DOI: 10.19636/j.cnki.cjsm42-1250/o3.2024.010
Anbin Wang, Lei Gan, Zhiqiang Gan, Zhiming Fan, Yonghui Su, Hao Wu. Data-driven and Continuum Damage Mechanics-based Approach for Predicting Fatigue Lifein Additive Manufacturing[J]. Chinese Journal of Solid Mechanics, 2024 , 45 (4) : 427 -440 . DOI: 10.19636/j.cnki.cjsm42-1250/o3.2024.010
近年来,增材制造技术因设计自由度大和材料利用率高等优点引起了各行业的广泛关注[1,2]. 当前,增材制造构件在静态强度上已能与传统构件媲美,但其在疲劳强度方面的表现仍不尽人意[3-5],这严重限制了该类构件的大规模工业应用.
目前,针对增材制造材料的疲劳寿命预测问题,主要方法有理论分析方法和数据驱动方法[6]. 由于增材的疲劳失效主要由工艺缺陷所导致的应力集中效应引起[7-10],因此,传统方法试图从工艺和缺陷两方面研究疲劳寿命的定量描述[11-14]. 其中,基于缺陷的模型需要对缺陷进行表征,因此十分依赖CT扫描、破坏性金相检查等检测技术,应用成本较为高昂. 与之相比,基于工艺的模型只需掌握增材制造工艺参数,便可通过拓展经典疲劳分析方法预测增材制造疲劳寿命,具有较好的工业应用前景. 通过引入激光功率、扫描速度、层厚和舱口间距等工艺参数,Zhan等[14]提出了一种考虑增材效应的连续损伤力学(Continuum Damage Mechanics,CDM)模型,并利用该模型预测了多种增材制造的疲劳寿命. 另一方面,数据驱动技术,尤其是人工神经网络(Artificial Neural Network,ANN),凭借其强大的非线性拟合能力,近年来被广泛应用于增材制造疲劳寿命预测问题. Jan等[15]结合ANN与斯皮尔曼秩相关分析,实现了增材制造Ti-6Al-4V的高精度疲劳寿命预测. Maleki等[16]以工艺参数及材料参数作为ANN建模特征,构建了一个可考虑工艺影响的增材疲劳寿命预测模型,成功地预测了经过后处理的LPBF AlSi10Mg试件的疲劳寿命. Lei等[17]利用ANN对LPBF哈氏合金疲劳寿命进行了预测,预测结果远优于传统疲劳寿命模型的预测结果. 上述研究工作充分证明了数据驱动技术在增材疲劳寿命预测问题上的适用性.
作为当前最具代表性的两种增材制造疲劳寿命模型,CDM模型和ANN模型受到了较多关注. CDM模型能够在经典CDM框架下量化各工艺参数对疲劳寿命的影响规律,理论基础坚实且物理意义明确;ANN模型则具有极强的自适应非线性拟合能力,使用灵活且精度较高. 然而,这两个模型同时也存在着各自缺陷. 一方面,CDM模型涉及大量经验成分,因此其适用范围通常较为有限,在缺乏标定数据的情况下其预测精度也无法得到保证[18];另一方面,ANN模型需要足量的训练数据,无法应用于小样本工况和非训练域的定寿计算[19].
鉴于CDM模型和ANN模型的各自优势和局限性,物理知识指导下以数据驱动技术为支撑的知识-数据双驱动模型在近年来逐渐兴起. 此类模型的核心思想在于将物理知识以各种形式融合进数据驱动的计算过程中,以提升模型在预测精度、数据需求等各方面的性能. 目前常用的知识-数据融合方法有特征融合、参数融合和输出融合. 特征融合将由物理知识构造的特征参量融合进原始数据特征集之中;参数融合多基于预训练-微调框架而展开,使用物理知识和原始数据依次地或并行地调整模型参数;输出融合则主要依据物理知识对模型的学习目标进行优化,其代表性方法为误差学习. 现有研究结果表明,上述三种融合方法均可提升疲劳寿命预测模型的预测性能. 例如,Gan等[20]构建了一类多输出分支ANN,通过将不同物理方法生成的低保真数据与试验得到的高保真数据集成于同一ANN架构下,不仅提升了预测精度,同时降低了数据需求. 在特征融合方法方面,Wang等[21]引入CDM数值计算结果作为ANN建模的额外输入特征,进一步提升了模型的预测精度. 此外,基于输出融合方法,Liu等[22]开发了一种以CDM理论预测与试验结果的误差为训练目标的ANN模型,并成功将其用于铝合金高周疲劳寿命预测. 与传统物理或数据方法相比,该模型被证明具有更佳的精度与鲁棒性. 需要指出的是,知识-数据双驱动模型的相关研究目前主要面向传统材料的疲劳问题,对于增材疲劳问题的研究与应用仍十分不足,不同模型的预测特点和适用边界尚待厘清.
本文以LPBF AlSi10Mg合金为研究对象,首先在使用相同标定/训练数据情况下,对比了CDM模型与ANN模型在不同工况下的预测性能;其次,依据特征融合、参数融合和输出融合方法,分别构建了三种用于增材疲劳寿命预测的知识-数据双驱动模型;最后,对各类模型的预测精度、稳定性、数据需求和外推性能展开了分析与对比.
作为传统力学模型与新兴数据驱动模型中各自的代表模型,面向增材疲劳的CDM模型与ANN模型在当前受到了广泛关注. 从本质上看,CDM模型与ANN模型都是结合某种给定的函数结构,通过对试验数据的标定(学习),预测不同工艺参数组合下增材制造疲劳寿命. 二者区别在于:CDM模型中的函数结构为描述疲劳损伤渐进累积过程的数理方程,具有明确的物理意义;而ANN模型中的函数结构则参考神经元链接模式,由大量待训练的内置参数(权重和偏置)层次关联而成,下面分别对两种方法进行介绍.
由缺陷引发的疲劳裂纹萌生与扩展是增材制造疲劳破坏的主要表现形式. CDM理论假设损伤为各向同性,使用模量退化形式描述疲劳损伤D的渐进累积过程:
式中E为无损伤时材料的弹性模量,ED为有损伤时的等效弹性模量.
根据Chaboche疲劳损伤累积模型[23],当外载为应力时,疲劳损伤演化方程有如下形式:
式中β为材料常数,加载指数α取决于加载参数(σmaxσm),σmax为最大应力,σm为平均应力. 为体现外部加载参数σmaxσm对于损伤变量D的影响,ασmaxσm)定义为[23]
式中σb为抗拉强度函数,σl为疲劳极限:
式中σ-l为拉压对称加载下的材料疲劳极限,σlσm)为非对称加载下的疲劳极限.
Mσm)选择了线性形式,表达为:
式中nm均为材料常数.
进一步地,Chaboche[23]模型引入了有效应力概念,将疲劳损伤D写为:
式(2)由此可变形为[24]
式中N为循环次数,σaσm分别为应力幅值和平均应力,αβmn为材料常数.
研究发现[6,7],增材制造中的工艺参数(如功率(p)、扫描速度(v)、层厚(t)、以及舱口间距(h))对材料内部的气孔和缺陷生成具有显著影响,宏观上可直接影响材料的疲劳性能. 具体而言,在激光扫描熔化粉末过程中,粉末的熔化程度与由这些工艺参数构成的体积能量密度有着密切联系. 例如,当激光功率减小、扫描速度提高、层厚增加或者舱口间距扩大时,粉末可能会因为激光能量不足而熔化不完全,进而形成未完全熔化的气孔. 反之,如果激光功率过高、扫描速度过低、层厚减少或舱口间距缩小,可能会导致粉末过熔,从而产生缺陷. 为考虑工艺参数对增材疲劳寿命的影响,可将体积能量密度引入损伤累积模型[14],得到如下疲劳损伤演化方程:
式中αβmn为材料性能参数,Δ(EdEd0)表示AM工艺对疲劳损伤的影响,表达如下:
式中Ed为体积能量密度,Ed0为参考体积能量密度,Ed/Ed0为体积能量密度比. 参考体积能量密度为最小化材料孔隙率的体积能量密度. 针对LPBF Al-Si10Mg合金,本研究使用Ed0=60 J/mm3.
假设材料内部初始损伤为0,临界损伤为1,在恒定应力条件下,疲劳寿命可通过积分式(8)得:
式中βn以及积分项系数由最小二乘法从光滑件疲劳实验数据中获得,αm在此基础上由实验数据标定校准. 对于同种材料,参数αβn相同,m随工艺参数的改变而改变.
如式(11)所示,对于不同的工艺参数组合,CDM模型参数都需要使用相关数据进行标定. 为简化模型应用流程,本文构建了一个CDM参数标定程序,如图1所示. 首先,将式(11)进行整合简化,得到:
式中A为工艺相关参数,与制造工艺相关,BC为材料相关参数,与材料种类相关.
其次,针对式(12),构建基于最小二乘法的迭代流程对参数ABC开展分阶段标定:
第一阶段:针对加载平均应力为0的情况,标定参数A和参数B. 这一过程采用阶梯式方法:首先固定A值以标定B值,随后固定B值以标定A值,如此反复循环;在每轮循环中,使用当前的CDM模型对标定数据进行预测,并观察预测结果;若预测结果稳定收敛(即R2值不再变化),则停止此阶段标定流程,输出对参数AB的标定值.
第二阶段:基于第一阶段确定的参数B,标定加载平均应力不为0时的参数A和参数C. 根据文献[14]所列参考值,首先在0.00001至0.001的范围内对C进行遍历,随后选择拟合效果最优(即R2值最大)的A值和C值作为标定结果.
ANN是通过数学和物理建模对人脑神经网络进行抽象后建立的简化模型. 它利用大量的节点和权重对输入进行非线性转换,从而输出对目标的预测结果. 图2为典型四层前馈ANN,包括输入层、输出层和隐藏层. 通过各层连接的权值和节点,ANN能够提取、转换和传递特征信息.
ANN中第l层的第j个节点的输出表示为:
式中k为上一层的节点数量,ωij为连接第(l-1)层第i个节点与第l层第j个节点的权重,b为偏置,f为节点的激活函数,l为网络层数.
本文使用的ANN基本架构为误差反向传播神经网络,即Back propagation neural network(BPNN). BPNN基于链式规则通过结合梯度下降法减小训练损失,训练损失函数如下:
式中yi为预测值,为实际值,E为单次输出的误差.
基于式(14),权重更新形式为:
式中t为迭代步数,η为学习率,用于控制训练的速度.
sigmoid函数由于图像平滑且具备非线性转化性能,常用做ANN隐含层激活函数:
ANN输出层激活函数常选用线性函数,有:
ANN模型中需人为设定的模型参数(即超参数)包括两类:结构超参数(如网络隐含层数和激活函数)和训练超参数(如学习率和最大训练步数). 由于目前尚无针对ANN模型超参数优化的理论方法,因此本文主要采用试错法进行超参数设置. 在网络结构超参数方面,通过文献调研[17,22,25,26]并使用网格搜索法进行结构寻优,最终确定网络结构为6-15-15-15-1. 其他超参数的详细配置由表1列出:
图3为ANN模型的训练流程图. 为确保模型在指定迭代范围被有效训练,引入动态学习率策略[27]和早停法[28]. 训练初期使用较大的学习率加快收敛,中后期减小学习率以防止过度跳动. 具体而言,初始学习率设定为0.23,并规定每500次迭代后减少0.01,直到达到预设的迭代次数上限. 同时,为平衡训练速度与模型精准度,最大训练迭代次数设为10000次. 在训练中,一旦验证集预测误差达到最小值或无法显著降低(1000次迭代后每500次迭代均方误差(Mean Squared Error,MSE)降低低于0.002),则输出模型权重参数为最优权重参数.
当前研究表明[20-22],知识-数据双驱动模型通过融合先验物理知识与数据驱动建模技术,可显著提高模型的预测精度同时降低数据需求. 鉴于此,本节分别从输入特征、网络参数和输出目标三个方面开展ANN模型与CDM模型的融合研究,构造三种知识-数据双驱动模型,分别称为特征融合模型(Feature Fusion Model,F-FM)、参数融合模型(Parameter Fusion Model,P-FM)、输出融合模型(Output Fusion Model,O-FM).
F-FM将CDM模型的预测结果作为独立特征引入到特征空间之中以实现物理特征融合. 如图4(b)所示,首先通过物理节点产生低保真疲劳寿命,随后将得到的低保真结果与其余特征一起输入图4(a)中的ANN结构,最终完成F-FM模型构建.
P-FM旨在通过融合物理先验信息对数据驱动模型进行合理初始化[20],其中预训练-微调策略[20,29]是目前最为常用的一种模型参数初始化技术途径. 本文所构建的P-FM如图5所示:首先使用CDM模型的预测结果作为伪标签以构建低保真数据集,然后利用该数据集对ANN进行预训练,(训练完成后,仅最后一层的权重被重新初始化,其余权重冻结),最后使用高保真数据(即试验数据集)进一步微调网络参数.
输出融合方法是结合物理知识构造特定输出目标以优化数据驱动模型的学习过程. 将理论结果和试验结果的差值作为输出目标,此误差学习方法能够让模型专注于关键信息的拟合,减少了冗余信息的影响. 基于CDM模型结果与试验结果的差值,O-FM对网格进行训练,从而得到更优的疲劳寿命预测结果. 基于CDM的O-FM具体架构如图6所示.
本节对前文所介绍的各种模型进行对比. 将数据驱动模型的关键超参数(如激活函数和学习率)进行相同设置,不同的超参数设置可参考表2. 需要指出的是,F-FM输出层由于包含一个额外的CDM节点,因此其结构布局为7-15-15-15-1. 此外,由于物理信息的引导,知识-数据双驱动模型收敛速度显著快于ANN模型[25],故最大迭代次数设置为5000次,以减少计算开销.
为分析五种模型的预测性能及体积能量密度变化对疲劳寿命的影响,从已有文献中选取77组LPBF AlSi10Mg合金的疲劳试验数据[30-33]构建数据库. 数据库包含激光功率P、扫描速度v、粉层厚度t、舱口间距h、应力幅σa、应力比R以及Ed0这7个特征以及目标变量——疲劳寿命. 其中4个制造工艺参数(Pvth)构成6种组合,每种组合对应一个体积能量密度比. 不同体积能量密度比样本对应的加载方式和样本数量可参见表3.
图7为选取的AlSi10Mg合金材料的疲劳寿命分布情况及对应的S-N拟合曲线. 图中不同的颜色代表不同工艺参数组合. 由图7可得,相同的应力比下,体积能量密度越接近参考体积能量密度,材料的疲劳性能就越好. 考虑到体积能量密度比为0.98、0.83和0.72的数据样本量较小,选用其他的65组数据来进行模型的训练工作从而确保模型训练的可靠性.
数据库样本不同特征之间数值差距较大,不利于ANN学习. 因此,利用式(19)对输入特征(PvthσaR)和输出参数(疲劳寿命)进行了最小-最大归一化处理. 此外,由于输出参数量级较大,在进行归一化之前进行了取对数处理.
为了对模型进行定量比较,使用决定系数(R2)和MSE衡量和量化预测精度. R2值的范围在-∞到1之间,值越接近1表示模型拟合度越好. MSE为预测值与实际值差异的平方的平均值,值越低表示预测精度越高. R2和MSE计算公式如下:
为对比CDM模型和ANN模型的内插预测性能,设置训练集规模分别为6、13、20、26、33. 每种规模下,模型随机抽取训练样本训练,剩余数据作为测试集,并计算测试集预测精度(R2与MSE),重复15次取均值以减少误差. 需要指出的是,在标定数据过少时,CDM模型由于形式给定,会在给定的形式下过度调整以适应数据点,导致计算R2与MSE时出现极端离群值. 为避免极端离群点的影响,引入中位数绝对偏差(Median Absolute Deviation,MAD)方法,计算数据点和中位数的差值,并利用其与MAD的比值识别超过设定阈值的离群值,离群值将不被纳入最终的平均值计算. 同时,对离群值数量进行统计分析. 由于仅在训练集规模最小时(样本数=6),才会出现离群值. 因此,表4仅给出样本数为6时不同模型的离群值.
表4结果可知,训练样本量为6时,CDM模型出现了4次离群值,相较ANN模型预测波动较大. 排除产生离群值的工况后,对模型性能进行对比. 如图8所示,训练数据量较少时,CDM模型精度更高. 然而,随着训练样本增加,ANN模型性能逐步提升. 训练样本量增至20时,其预测精度超过CDM模型.
本节主要对三种融合模型与基准模型(CDM,ANN)的性能差异进行评估. 考虑本文研究目的以及不同融合策略间的难兼容性,不讨论各融合方法的组合应用模型. 为直观展现各模型预测性能,以精度和稳定性为评价指标. 如图9图10所示,F-FM模型和P-FM的预测精度与稳定性总体优于传统模型. 具体而言,小数据量情况下,P-FM表现出色. 而随着数据量的增加,ANN模型和F-FM的预测性能均进一步提升,且F-FM模型性能总体优于ANN模型. 这是因为两种融合模型以不同的方式对ANN进行了物理约束引导,从而得到各有特色并总体优于传统模型的预测性能. 同时,三种模型的预测性能最终趋于稳定,并十分接近. 这说明在数据充足时,融合模型中的ANN成分起主导作用. 此外,在图9(c)中,O-FM的总体表现与CDM模型呈现一致性,这可能是由于数据的离散性导致输出结果对CDM结果的修正较小造成的. 图10(d)中通过对三种融合模型的预测性能进行对比,分析了不同的融合方式对神经网络性能的影响差异.
从上述结果可以得出,在小数据量情况下,PFM具备最优的预测性能. P-FM融合CDM的趋势特征以及ANN的学习机制,不易受CDM模型预测结果影响,因此预测结果波动的较小. 与此不同的是,F-FM模型能够最大化利用CDM模型包含的信息,但其性能同时也会受CDM模型结果波动的影响. 因此,F-FM模型更适用于数据量充足时疲劳寿命的高精度预测. 然而,O-FM通过预测误差对理论结果进行修正,结果接近于CDM模型,故总体表现劣于其余融合模型.
为评估上述五种模型的外推性能同时兼顾数据均匀性,将疲劳寿命低于105次的数据设为训练集,高于105次的数据设为测试集. 图11表明,在进行疲劳寿命的外推预测时,ANN模型、F-FM和P-FM的预测结果偏保守,精度较低. 相比之下,OFM和CDM模型预测结果基本落在3倍误差带内,性能更优. O-FM由于在CDM基础上接受了网络修正,精度略高于CDM模型. 尽管如此,所有数据驱动预测方法均有结果超出3倍误差带,未表现出比CDM模型更优的性能,因此在当前的应用中不推荐使用机器学习进行高低周疲劳寿命的外推预测.
本文基于CDM,通过构建三种不同的知识-数据双驱动模型对LPBF AlSi10Mg合金疲劳寿命进行预测. 并将三种融合模型预测结果分别与CDM模型和ANN模型预测结果进行对比,分析它们之间的性能差异. 主要结论如下:
(1)比较CDM模型与ANN模型,训练样本有限时,CDM模型预测精度较高,但当拟合数据发生变动时,其预测结果的波动较大. 训练样本充足时,ANN模型预测精度与稳定性都显著强于CDM模型.
(2)内插预测结果显示,P-FM融合了CDM的趋势特征与ANN的学习机制,结果波动较小,适用于小数据情境预测;F-FM能够最大化利用CDM包含的信息,但预测精度会随CDM模型的拟合情况而波动,适用于数据充足的高精度预测;O-FM基于对CDM预测结果的修正,预测性能与CDM模型表现出一致性,内插性能最弱.
(3)外推预测结果表明,数据驱动模型中,ANN模型、F-FM与P-FM不具备外推预测能力. 相比之下,O-FM外推性能较优,但未明显高于CDM模型. ANN模型与文中知识-数据双驱动模型当前不适用于高低周疲劳寿命的外推预测.
  • 国家自然科学基金项目(12372081; 11972255)
参考文献 引证文献
排序方式:
[1]
Wang L, Lu B H. Development of additive manufacturing technology and industry in China[J]. Strategic Study of Chinese Academy of Engineering, 2022, 24(4): 202-211.
[2]
杨冰, 廖贞, 吴圣川, 肖守讷, 阳光武, 朱涛, 王明猛, 邓永权. 增材制造技术发展和在先进轨道交通装备中的应用展望[J]. 交通运输工程学报, 2021, 21(01): 132-153.
(Yang B, Liao Z, Wu S C, Xiao S N, Yang G W, Zhu T, Wang M M, Deng Y Q. Development of additive manufacturing technology and its application prospect in advanced rail transit equipment[J]. Journal of Traffic and Transportation Engineering, 2021, 21(01): 132-153. (in Chinese))
[3]
林鑫, 黄卫东. 高性能金属构件的激光增材制造[J]. 中国科学(信息科学), 2015, 45(9): 1111-1126.
(Lin X, Huang W D. Laser additive manufacturing of high-performance metal components[J]. Scientia Sinica (Informationis), 2015, 45(9): 1111-1126. (in Chinese))
[4]
Edwards P, Ramulu M. Fatigue performance evaluation of selective laser melted Ti-6Al-4V[J]. Materials Science and Engineering: A, 2014, 598: 327-337.
[5]
Shamsaei N, Yadollahi A, Bian L, Thompson S M. An overview of Direct Laser Deposition for additive manufacturing; Part II: Mechanical behavior, process parameter optimization and control[J]. Additive Manufacturing, 2015, 8: 12-35.
[6]
廉艳平, 王潘丁, 高杰, 刘继凯, 李取浩, 刘长猛, 贺小帆, 高亮, 李好, 雷红帅, 李会民, 肖登宝, 郭旭, 方岱宁. 金属增材制造若干关键力学问题研究进展[J]. 力学进展, 2021, 51(3): 648-701.
(Lian Y P, Wang P D, Gao J, Liu J K, Li Q H, Liu C M, He X F, Gao L, Li H, Lei H S, Li H M, Xiao D B, Guo X, Fang D N. Fundamental mechanics problems in metal additive manufacturing: A state-of-art review[J]. Advances in Mechanics, 2021, 51(3): 648-701. (in Chinese))
[7]
Liu Z, Liu P F, Wang L, Lu Y Z, Lu X, Qin Z X, Wang H M. Fatigue properties of Ti-6.5Al-3.5Mo-l.5Zr-0.3Si alloy produced by direct laser deposition[J]. Materials Science and Engineering: A, 2018, 716: 140-149.
[8]
Peng X, Wu S C, Qian W J, Bao J G, Hu Y N, Zhan Z X, Withers P J. The potency of defects on fatigue of additively manufactured metals[J]. International Journal of Mechanical Sciences, 2022, 221: 107185.
[9]
Sterling A J, Torries B, Shamsaei N, Thompson S M, Seely D W. Fatigue behavior and failure mechanisms of direct laser deposited Ti-6Al-4V[J]. Materials Science & Engineering A, 2016, 655: 100-112.
[10]
Wang X, He X, Wang T, Li Y. Internal pores in DED Ti-6.5Al-2Zr-Mo-V alloy and their influence on crack initiation and fatigue life in the mid-life regime[J]. Additive Manufacturing, 2019, 28: 373-393.
[11]
詹志新, 高同州, 刘传奇, 吴圣川. 基于数据驱动的增材制造铝合金的疲劳寿命预测[J]. 固体力学学报, 2023, 44(3): 381-394.
(Zhan Z X, Gao T Z, Liu C Q, Wu S C. Data-driven fatigue life prediction of additive manufactured aluminum alloys[J]. Chinese Journal of Solid Mechanics, 2023, 44(3): 381-394. (in Chinese))
[12]
Zhu M L, Jin L, Xuan F Z. Fatigue life and mechanistic modeling of interior micro-defect induced cracking in high cycle and very high cycle regimes[J]. Acta Materialia, 2018, 157: 259-275.
[13]
Murakami Y. Material defects as the basis of fatigue design[J]. International Journal of Fatigue, 2012, 41: 2-10.
[14]
Zhan Z X, Li H, Lam K Y. Development of a novel fatigue damage model with AM effects for life prediction of commonly-used alloys in aerospace[J]. International Journal of Mechanical ences, 2019, 155: 110-124.
[15]
Jan H, Jiří B, Petr H, et al. Modelling fatigue life prediction of additively manufactured Ti-6Al-4V samples using machine learning approach[J]. International Journal of Fatigue, 2023, 169: 107483.
[16]
Maleki E, Bagherifard S, Razavi S M J, Bandini M, Du P A, Berto F, Guagliano M. On the efficiency of machine learning for fatigue assessment of post-processed additively manufactured AlSi10Mg[J]. International Journal of Fatigue, 2022, 160: 106841.
[17]
Lei L M, Li B, Wang H J, Huang G Q, Xuan F Z. High-temperature high-cycle fatigue performance and machine learning-based fatigue life prediction of additively manufactured Hastelloy X[J]. International Journal of Fatigue, 2023, 178: 108012.
[18]
洪海铭, 詹志新, 王佳莹. 基于损伤力学的增材制造金属材料疲劳寿命预测[J]. 北京航空航天大学学报, 2022, 48(6): 950-956.
(Hong H M, Zhan Z X, Wang J Y. Damage mechanics-based fatigue life prediction for additive manufacturing metal materials[J]. Journal of Beijing University of Aeronautics and Astronautics, 2022, 48(6): 950-956. (in Chinese))
[19]
Freire R C S, Neto A D D, Aquino E M F. Use of modular networks in the building of constant life diagrams[J]. International Journal of Fatigue, 2007, 29(3): 389-396.
[20]
Gan L, Wu H, Zhong Z. On the integration of domain knowledge and branching neural network for fatigue life prediction with small samples[J]. International Journal of Fatigue, 2023, 172: 107648.
[21]
Wang H J, Li B, Xuan F Z. Fatigue-life prediction of additively manufactured metals by continuous damage mechanics (CDM)-informed machine learning with sensitive features[J]. International Journal of Fatigue, 2022, 164: 107147.
[22]
Liu S, Shi W J, Zhan Z X, Hu W P, Meng Q C. On the development of error-trained BP-ANN technique with CDM model for the HCF life prediction of aluminum alloy[J]. International Journal of Fatigue, 2022, 160: 106836.
[23]
Chaboche J L, Lesne P M. A non-linear continuous fatigue damage model[J]. Fatigue & Fracture of Engineering Materials & Structures, 1988, 11(1): 1-17.
[24]
Shen F, Hu W P, Meng Q C. A non-local approach based on the hypothesis of damage dissipation potential equivalence to the effect of stress gradient in fretting fatigue[J]. International Journal of Fatigue, 2016, 90(sep.): 125-138.
[25]
Chen D, Li Y Z, Liu K, Li Y. A physics-informed neural network approach to fatigue life prediction using small quantity of samples[J]. International Journal of Fatigue, 2023, 166: 107270.
[26]
李翱翔, 陈健. BP神经网络参数改进方法综述[J]. 数字通信世界, 2009, 1: 62-64.
(Li A X, Chen J. Summarize of parameter improve methods for BP neural network[J]. Digital Communication World, 2009, 1: 62-64. (in Chinese))
[27]
周慧, 朱彬, 陈万隆, 朱国强, 黄赛群. 动态学习率神经网络预测气温的尝试[J]. 南京气象学院学报, 2005, 3: 398-403.
(Zhou H, Zhu B, Chen W L, Zhu G Q, Huang S Q. Daily air temperature prediction using a dynamic learning rate neural network system[J]. Journal of Nanjing Institute of Meteorology, 2005, 3: 398-403. (in Chinese))
[28]
Yang S, Gregory N T, Stephen J W. Comparison of early stopping criteria for neural-network-based subpixel classification[J]. Geoscience and Remote Sensing Letters, IEEE, 2011, 8(1): 113-117.
[29]
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, 2020, 145(2): 106089.
[30]
Tang M, Pistorius P C. Oxides, porosity and fatigue performance of AlSi10Mg parts produced by selective laser melting[J]. International Journal of Fatigue, 2017, 94(2): 192-201.
[31]
Erhard B, Ulrike H, Vitus H, Damien B. Additive manufactured AlSi10Mg samples using Selective Laser Melting (SLM): Microstructure, high cycle fatigue, and fracture behavior[J]. Materials and Design, 2011, 34: 159-169.
[32]
Uzan N E, Shneck R, Yeheskel O, Frage N. Fatigue of AlSi10Mg specimens fabricated by additive manufacturing selective laser melting (AM-SLM)[J]. Materials Science and Engineering A, 2017, 229-237.
[33]
Mower T M, Long M J. Mechanical behavior of additive manufactured, powder-bed laser-fused materials[J]. Materials Science and Engineering A, 2016, 651: 198-213.
2024年第45卷第4期
PDF下载
52
23
引用本文
BibTeX
文章信息
doi: 10.19636/j.cnki.cjsm42-1250/o3.2024.010
  • 接收时间:2024-03-03
  • 首发时间:2026-04-01
  • 出版时间:2024-08-25
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2024-03-03
基金
国家自然科学基金项目(12372081; 11972255)
作者信息
    1同济大学航空航天与力学学院,上海,200092
    2哈尔滨工业大学(深圳)理学院,深圳,518055

通讯作者:

** E-mail:.
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/gtlxxb/CN/10.19636/j.cnki.cjsm42-1250/o3.2024.010
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