Article(id=1246045609464021872, tenantId=1146029695717560320, journalId=1241755870837649424, issueId=1246045605047415288, articleNumber=null, orderNo=null, doi=10.19636/j.cnki.cjsm42-1250/o3.2024.028, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1717862400000, receivedDateStr=2024-06-09, revisedDate=null, revisedDateStr=null, acceptedDate=null, acceptedDateStr=null, onlineDate=1775010023703, onlineDateStr=2026-04-01, pubDate=1729785600000, pubDateStr=2024-10-25, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1775010023703, onlineIssueDateStr=2026-04-01, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1775010023703, creator=13701087609, updateTime=1775010023703, updator=13701087609, issue=Issue{id=1246045605047415288, tenantId=1146029695717560320, journalId=1241755870837649424, year='2024', volume='45', issue='5', pageStart='565', pageEnd='708', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1775010022651, creator=13701087609, updateTime=1775010094858, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1246045907972636933, tenantId=1146029695717560320, journalId=1241755870837649424, issueId=1246045605047415288, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1246045907972636934, tenantId=1146029695717560320, journalId=1241755870837649424, issueId=1246045605047415288, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=622, endPage=637, ext={EN=ArticleExt(id=1246045610164470653, articleId=1246045609464021872, tenantId=1146029695717560320, journalId=1241755870837649424, language=EN, title=Acquisition of Metal Plastic Parameters Based on Neural Network Learning and Residual Indentation Morphology, columnId=1244229834482757770, journalTitle=Chinese Journal of Solid Mechanics, columnName=Research Paper, runingTitle=null, highlight=null, articleAbstract=

Compared to conventional mechanical testing methods, the indentation method offers the advantages of simple manufacturing of samples and in-situ testing. This study proposes an alternative to deriving material mechanical parameters solely from indentation load-depth curves. It introduces an effective method for deducing metal plastic mechanical parameters based on residual indentation morphology and neural network learning. An Instron universal material testing machine was used to conduct spherical indentation tests on Cu, Mg, and Fe, followed by scanning their residual indentation morphology through the contour morphology system. The extracted morphology features served as the basis for further analysis. Data processing techniques such as amplification, rounding, binarization, and high-order digit supplementation were applied to the acquired data. Through Abaqus software and numerical simulations, residual indentation depth data associated with various material parameters were automatically extracted for neural network learning. Selections of activation function, neural network parameter initialization and updating mode, loss function, parameter optimization strategy, and neural network structure were carefully conducted to ensure effective learning. The plastic mechanical parameters of Cu, Mg, and Fe were obtained based on the residual indentation morphology feature data from indentation tests and the neural networks after learning. Additionally, the related plastic mechanical parameters of Cu, Mg, and Fe were also acquired through conventional uniaxial tensile tests and characterization using the Instron machine. By comparing the neural network learning results with tensile test data, relative errors in plastic mechanical parameters were identified. The effectiveness of the proposed method in obtaining metal plastic mechanical parameters based on neural network learning and residual indentation morphology was validated. This method can be expanded for characterizing mechanical properties and acquiring plastic parameters of other metal/alloy materials.

, correspAuthors=Gesheng Xiao, 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=Yanjiao He, Yongxi Tian, Haolin Jia, Xuefeng Shu, Gesheng Xiao), CN=ArticleExt(id=1246045615688369119, articleId=1246045609464021872, tenantId=1146029695717560320, journalId=1241755870837649424, language=CN, title=基于神经网络学习及残余压痕形貌获取金属塑性力学参数, columnId=1241831201896469478, journalTitle=固体力学学报, columnName=研究论文, runingTitle=null, highlight=null, articleAbstract=

压入法相比于其他传统力学测试方法具有试样加工简单及可实现原位测试等优势,区别于已有的基于压入载荷-深度曲线获取材料力学性能参数的方法,本文提出了一种基于残余压痕形貌及神经网络学习反演金属塑性力学参数的新方法;采用Instron万能材料试验机开展了紫铜、镁合金及低碳钢的球形压入测试,并通过轮廓形态系统对压入测试后的残余压痕形貌进行特征扫描以作为后续研究的数据基础,分析所提取数据的特点并进行放大、取整、二进制化及高位补充等处理;基于Abaqus二次开发自动提取不同材料参数模拟下的残余压痕深度数据并用于神经网络学习,比较并选取激活函数、初始化神经网络参数的方法、神经网络参数更新方式、损失函数、寻找最优参数策略及神经网络结构,使神经网络学习达到较好的效果;结合实验所得残余压痕形貌特征数据与学习后的神经网络得到紫铜、镁合金及低碳钢的相关塑性参数,将通过Instron万能材料试验机拉伸测试表征所得紫铜、镁合金及低碳钢的相关塑性参数值作为对照标准,得到了神经网络学习结果的相对误差,验证了所提出基于神经网络学习及残余压痕形貌获取金属塑性力学参数方法的有效性;该方法可推广到其他金属/合金材料的力学性能表征及塑性参数获取研究中.

, correspAuthors=肖革胜, authorNote=null, correspAuthorsNote=
** E-mail:.
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=13qDaIl73Y7b9zBheVVMVQ==, magXml=76FDi352dp0EVwGTyz+TJg==, pdfUrl=null, pdf=cHZKC99zvQZJ6TovSWcQWw==, pdfFileSize=9758248, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=aqDOhQgN1+hBXoNEPLukqA==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=X2fnJG/2jwqaybm0rlF1rg==, mapNumber=null, authorCompany=null, fund=null, authors=null, authorsList=何艳骄, 田永喜, 贾昊霖, 树学峰, 肖革胜)}, authors=[Author(id=1246045616078439409, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, 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=1246045616170714100, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, authorId=1246045616078439409, language=EN, stringName=Yanjiao He, firstName=Yanjiao, middleName=null, lastName=He, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=Institute of Applied Mechanics, College of Mechanical and Vehicle Engineering, Taiyuan University of Technology, Taiyuan, 030024, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1246045616304931831, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, authorId=1246045616078439409, language=CN, stringName=何艳骄, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=太原理工大学机械与运载工程学院应用力学研究所,太原,030024, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1246045615956804586, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, xref=null, ext=[AuthorCompanyExt(id=1246045615965193195, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, companyId=1246045615956804586, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Institute of Applied Mechanics, College of Mechanical and Vehicle Engineering, Taiyuan University of Technology, Taiyuan, 030024), AuthorCompanyExt(id=1246045615969387500, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, companyId=1246045615956804586, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=太原理工大学机械与运载工程学院应用力学研究所,太原,030024)])]), Author(id=1246045616413983737, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, 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=1246045616506258430, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, authorId=1246045616413983737, language=EN, stringName=Yongxi Tian, firstName=Yongxi, middleName=null, lastName=Tian, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=Institute of Applied Mechanics, College of Mechanical and Vehicle Engineering, Taiyuan University of Technology, Taiyuan, 030024, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1246045616640475137, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, authorId=1246045616413983737, language=CN, stringName=田永喜, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=太原理工大学机械与运载工程学院应用力学研究所,太原,030024, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1246045615956804586, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, xref=null, ext=[AuthorCompanyExt(id=1246045615965193195, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, companyId=1246045615956804586, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Institute of Applied Mechanics, College of Mechanical and Vehicle Engineering, Taiyuan University of Technology, Taiyuan, 030024), AuthorCompanyExt(id=1246045615969387500, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, companyId=1246045615956804586, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=太原理工大学机械与运载工程学院应用力学研究所,太原,030024)])]), Author(id=1246045616745332742, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, 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=1246045616837607434, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, authorId=1246045616745332742, language=EN, stringName=Haolin Jia, firstName=Haolin, middleName=null, lastName=Jia, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=Institute of Applied Mechanics, College of Mechanical and Vehicle Engineering, Taiyuan University of Technology, Taiyuan, 030024, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1246045616934076431, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, authorId=1246045616745332742, language=CN, stringName=贾昊霖, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=太原理工大学机械与运载工程学院应用力学研究所,太原,030024, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1246045615956804586, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, xref=null, ext=[AuthorCompanyExt(id=1246045615965193195, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, companyId=1246045615956804586, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Institute of Applied Mechanics, College of Mechanical and Vehicle Engineering, Taiyuan University of Technology, Taiyuan, 030024), AuthorCompanyExt(id=1246045615969387500, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, companyId=1246045615956804586, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=太原理工大学机械与运载工程学院应用力学研究所,太原,030024)])]), Author(id=1246045618473386002, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, 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=1246045618599215127, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, authorId=1246045618473386002, language=EN, stringName=Xuefeng Shu, firstName=Xuefeng, middleName=null, lastName=Shu, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=Institute of Applied Mechanics, College of Mechanical and Vehicle Engineering, Taiyuan University of Technology, Taiyuan, 030024, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1246045618699878426, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, authorId=1246045618473386002, language=CN, stringName=树学峰, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=太原理工大学机械与运载工程学院应用力学研究所,太原,030024, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1246045615956804586, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, xref=null, ext=[AuthorCompanyExt(id=1246045615965193195, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, companyId=1246045615956804586, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Institute of Applied Mechanics, College of Mechanical and Vehicle Engineering, Taiyuan University of Technology, Taiyuan, 030024), AuthorCompanyExt(id=1246045615969387500, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, companyId=1246045615956804586, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=太原理工大学机械与运载工程学院应用力学研究所,太原,030024)])]), Author(id=1246045618808930334, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, orderNo=4, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=xiaogesheng@tyut.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1246045618922176545, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, authorId=1246045618808930334, language=EN, stringName=Gesheng Xiao, firstName=Gesheng, middleName=null, lastName=Xiao, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=**, address=Institute of Applied Mechanics, College of Mechanical and Vehicle Engineering, Taiyuan University of Technology, Taiyuan, 030024, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1246045619014451237, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, authorId=1246045618808930334, language=CN, stringName=肖革胜, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=**, address=太原理工大学机械与运载工程学院应用力学研究所,太原,030024, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1246045615956804586, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, xref=null, ext=[AuthorCompanyExt(id=1246045615965193195, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, companyId=1246045615956804586, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Institute of Applied Mechanics, College of Mechanical and Vehicle Engineering, Taiyuan University of Technology, Taiyuan, 030024), AuthorCompanyExt(id=1246045615969387500, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, companyId=1246045615956804586, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=太原理工大学机械与运载工程学院应用力学研究所,太原,030024)])])], keywords=[Keyword(id=1246045619165446187, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, language=EN, orderNo=1, keyword=neural network learning), Keyword(id=1246045619249332270, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, language=EN, orderNo=2, keyword=residual indentation morphology), Keyword(id=1246045619375161393, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, language=EN, orderNo=3, keyword=plastic parameters), Keyword(id=1246045619488407605, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, language=EN, orderNo=4, keyword=metals), Keyword(id=1246045619572293688, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, language=EN, orderNo=5, keyword=numerical simulation), Keyword(id=1246045619681345596, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, language=CN, orderNo=1, keyword=神经网络学习), Keyword(id=1246045619786203199, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, language=CN, orderNo=2, keyword=残余压痕形貌), Keyword(id=1246045619912032323, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, language=CN, orderNo=3, keyword=塑性参数), Keyword(id=1246045620050444359, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, language=CN, orderNo=4, keyword=金属), Keyword(id=1246045620172079178, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, language=CN, orderNo=5, keyword=数值模拟)], refs=[Reference(id=1246045625859555507, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, doi=null, pmid=null, pmcid=null, year=2001, volume=null, issue=null, pageStart=45, pageEnd=58, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=桂立丰, 曹用涛, journalName=机械工程材料测试手册·力学卷, refType=null, unstructuredReference=桂立丰, 曹用涛. 机械工程材料测试手册·力学卷[M]. 沈阳: 辽宁科学技术出版社, 2001: 45-58., articleTitle=null, refAbstract=null), Reference(id=1246045625943441589, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, doi=null, pmid=null, pmcid=null, year=2001, volume=null, issue=null, pageStart=45, pageEnd=58, url=null, language=null, rfNumber=[1], rfOrder=1, authorNames=Gui L F, Cao Y T, journalName=Handbook of Materials Testing for Mechanical Engineering, refType=null, unstructuredReference=(Gui L F, Cao Y T. Handbook of Materials Testing for Mechanical Engineering[M]. Shenyang: Liaoning Science and Technology Press, 2001: 45-58. (in Chinese)), articleTitle=null, refAbstract=null), Reference(id=1246045627499528375, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, doi=null, pmid=null, pmcid=null, year=2013, volume=null, issue=null, pageStart=21, pageEnd=23, url=null, language=null, rfNumber=[2], rfOrder=2, authorNames=张泰华, journalName=微/纳米力学测试技术:仪器化压入的测量、分析、应用及其标准化, refType=null, unstructuredReference=张泰华. 微/纳米力学测试技术:仪器化压入的测量、分析、应用及其标准化[M]. 北京: 科学出版社, 2013: 21-23., articleTitle=null, refAbstract=null), Reference(id=1246045627583414457, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, doi=null, pmid=null, pmcid=null, year=2013, volume=null, issue=null, pageStart=21, pageEnd=23, url=null, language=null, rfNumber=[2], rfOrder=3, authorNames=Zhang T H, journalName=Micro/Nanomechanical Testing Techniques: Measurement, Analysis, Application and Standardization of Instrumented Indentation, refType=null, unstructuredReference=(Zhang T H. Micro/Nanomechanical Testing Techniques: Measurement, Analysis, Application and Standardization of Instrumented Indentation[M]. Beijing: Science Press, 2013: 21-23. (in Chinese)), articleTitle=null, refAbstract=null), Reference(id=1246045627675689147, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, doi=null, pmid=null, pmcid=null, year=2004, volume=44, issue=null, pageStart=91, pageEnd=149, url=null, language=null, rfNumber=[3], rfOrder=4, authorNames=Cheng Y T, Cheng C M, journalName=Materials Science and Engineering: R, refType=null, unstructuredReference=Cheng Y T, Cheng C M. Scaling, dimensional analysis, and indentationmeasurements[J]. Materials Science and Engineering: R, 2004, 44: 91-149., articleTitle=Scaling, dimensional analysis, and indentationmeasurements, refAbstract=null), Reference(id=1246045627759575228, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, doi=null, pmid=null, pmcid=null, year=2018, volume=57, issue=3, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[4], rfOrder=5, authorNames=Gao C H, Yao L G, Liu M, journalName=Optical Engineering, refType=null, unstructuredReference=Gao C H, Yao L G, Liu M. Berkovich nanoindentation of borosilicate K9 glass[J]. Optical Engineering, 2018, 57(3): 034104., articleTitle=Berkovich nanoindentation of borosilicate K9 glass, refAbstract=null), Reference(id=1246045627897987262, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, doi=null, pmid=null, pmcid=null, year=2024, volume=270, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[5], rfOrder=6, authorNames=Hou D Y, Liu M, Liu S, Yang F Q, journalName=International Journal of Mechanical Sciences, refType=null, unstructuredReference=Hou D Y, Liu M, Liu S, Yang F Q. Indentation fracture of 4H-SiC single crystal[J]. International Journal of Mechanical Sciences, 2024, 270: 109096., articleTitle=Indentation fracture of 4H-SiC single crystal, refAbstract=null), Reference(id=1246045627986067649, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, doi=null, pmid=null, pmcid=null, year=2014, volume=66, issue=null, pageStart=32, pageEnd=41, url=null, language=null, rfNumber=[6], rfOrder=7, authorNames=Pöhl F, Huth S, Theisen W, journalName=Journal of the Mechanics and Physics of Solids, refType=null, unstructuredReference=Pöhl F, Huth S, Theisen W. Indentation of self-similar indenters: An FEM-assisted energy-based analysis[J]. Journal of the Mechanics and Physics of Solids, 2014, 66: 32-41., articleTitle=Indentation of self-similar indenters: An FEM-assisted energy-based analysis, refAbstract=null), Reference(id=1246045628065759424, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, doi=null, pmid=null, pmcid=null, year=2014, volume=76, issue=null, pageStart=93, pageEnd=101, url=null, language=null, rfNumber=[7], rfOrder=8, authorNames=Song Z, Komvopoulos K, journalName=Mechanics of Materials, refType=null, unstructuredReference=Song Z, Komvopoulos K. An elastic-plastic analysis of spherical indentation: Constitutive equations for single-indentation unloading and development of plasticity due to repeated indentation[J]. Mechanics of Materials, 2014, 76: 93-101., articleTitle=An elastic-plastic analysis of spherical indentation: Constitutive equations for single-indentation unloading and development of plasticity due to repeated indentation, refAbstract=null), Reference(id=1246045628166422723, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, doi=null, pmid=null, pmcid=null, year=2023, volume=16, issue=null, pageStart=2617, pageEnd=null, url=null, language=null, rfNumber=[8], rfOrder=9, authorNames=Long X, Ding X Y, Li J, Dong R P, Su Y T, Chang C, journalName=Materials, refType=null, unstructuredReference=Long X, Ding X Y, Li J, Dong R P, Su Y T, Chang C. Indentation reverse algorithm of mechanical response for Elastoplastic Coatings based on LSTM Deep Learning[J]. Materials, 2023, 16: 2617., articleTitle=Indentation reverse algorithm of mechanical response for Elastoplastic Coatings based on LSTM Deep Learning, refAbstract=null), Reference(id=1246045628267086022, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, doi=null, pmid=null, pmcid=null, year=2023, volume=36, issue=1, pageStart=13, pageEnd=21, url=null, language=null, rfNumber=[9], rfOrder=10, authorNames=Long X, Lu C H, Shen Z Y, Su Y T, journalName=Acta Mechanica Solida Sinica, refType=null, unstructuredReference=Long X, Lu C H, Shen Z Y, Su Y T. Identification of mechanical properties of thin-film elastoplastic materials by machinelearning[J]. Acta Mechanica Solida Sinica, 2023, 36(1): 13-21., articleTitle=Identification of mechanical properties of thin-film elastoplastic materials by machinelearning, refAbstract=null), Reference(id=1246045628384526535, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, doi=null, pmid=null, pmcid=null, year=2023, volume=44, issue=05, pageStart=606, pageEnd=621, url=null, language=null, rfNumber=[10], rfOrder=11, authorNames=田静萱, 夏僮, 杨振宇, 卢子兴, 贺小帆, 贺自强, journalName=固体力学学报, refType=null, unstructuredReference=田静萱, 夏僮, 杨振宇, 卢子兴, 贺小帆, 贺自强. 基于纳米压痕试验的塑性本构参数反演方法研究[J]. 固体力学学报, 2023, 44(05): 606-621., articleTitle=基于纳米压痕试验的塑性本构参数反演方法研究, refAbstract=null), Reference(id=1246045628472606921, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, doi=null, pmid=null, pmcid=null, year=2023, volume=44, issue=05, pageStart=606, pageEnd=621, url=null, language=null, rfNumber=[10], rfOrder=12, authorNames=Tian J X, Xia T, Yang Z Y, Lu Z X, He X F, He Z Q, journalName=Chinese Journal of Solid Mechanics, refType=null, unstructuredReference=(Tian J X, Xia T, Yang Z Y, Lu Z X, He X F, He Z Q. Reverse analysis for plastic constitutive parameters based on nanoindentation test[J]. Chinese Journal of Solid Mechanics, 2023, 44(05): 606-621. (in Chinese)), articleTitle=Reverse analysis for plastic constitutive parameters based on nanoindentation test, refAbstract=null), Reference(id=1246045628581658828, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, doi=null, pmid=null, pmcid=null, year=2021, volume=53, issue=2, pageStart=413, pageEnd=423, url=null, language=null, rfNumber=[11], rfOrder=13, authorNames=刘明, 侯冬杨, 高城辉, journalName=力学学报, refType=null, unstructuredReference=刘明, 侯冬杨, 高城辉. 利用维氏和玻氏压头表征半导体材料断裂韧性[J]. 力学学报, 2021, 53(2): 413-423., articleTitle=利用维氏和玻氏压头表征半导体材料断裂韧性, refAbstract=null), Reference(id=1246045628686516428, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, doi=null, pmid=null, pmcid=null, year=2021, volume=53, issue=2, pageStart=413, pageEnd=423, url=null, language=null, rfNumber=[11], rfOrder=14, authorNames=Liu M, Hou D Y, Gao C H, journalName=Chinese Journal of Theoretical and Applied Mechanics, refType=null, unstructuredReference=(Liu M, Hou D Y, Gao C H. Study on fracture toughness of semiconductor material using vickers and berkovich indenters[J]. Chinese Journal of Theoretical and Applied Mechanics, 2021, 53(2): 413-423. (in Chinese)), articleTitle=Study on fracture toughness of semiconductor material using vickers and berkovich indenters, refAbstract=null), Reference(id=1246045628795568333, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, doi=null, pmid=null, pmcid=null, year=2019, volume=168, issue=null, pageStart=87, pageEnd=99, url=null, language=null, rfNumber=[12], rfOrder=15, authorNames=Campbell J E, Thompson R P, Dean J, Clyne T W, journalName=Acta Materialia, refType=null, unstructuredReference=Campbell J E, Thompson R P, Dean J, Clyne T W. Comparison between stress-strain plots obtained from indentationplastometry, based on residual indent profiles, and from uniaxial testing[J]. Acta Materialia, 2019, 168: 87-99., articleTitle=Comparison between stress-strain plots obtained from indentationplastometry, based on residual indent profiles, and from uniaxial testing, refAbstract=null), Reference(id=1246045628938174670, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, doi=null, pmid=null, pmcid=null, year=2021, volume=42, issue=4, pageStart=376, pageEnd=392, url=null, language=null, rfNumber=[13], rfOrder=16, authorNames=刘明, 郑强, 高城辉, journalName=固体力学学报, refType=null, unstructuredReference=刘明, 郑强, 高城辉. 基于努氏硬度表征大块金属玻璃的力学性能[J]. 固体力学学报, 2021, 42(4): 376-392., articleTitle=基于努氏硬度表征大块金属玻璃的力学性能, refAbstract=null), Reference(id=1246045629017866449, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, doi=null, pmid=null, pmcid=null, year=2021, volume=42, issue=4, pageStart=376, pageEnd=392, url=null, language=null, rfNumber=[13], rfOrder=17, authorNames=Liu M, Zheng Q, Gao C H, journalName=Chinese Journal of Solid Mechanics, refType=null, unstructuredReference=(Liu M, Zheng Q, Gao C H. Characterization of mechanical properties of bulk metallic glasses based on knoop hardness[J]. Chinese Journal of Solid Mechanics, 2021, 42(4): 376-392. (in Chinese)), articleTitle=Characterization of mechanical properties of bulk metallic glasses based on knoop hardness, refAbstract=null), Reference(id=1246045629114335441, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, doi=null, pmid=null, pmcid=null, year=2022, volume=175, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[14], rfOrder=18, authorNames=Zhang J W, Qin J H, Li Y X, Lu C S, Liu H T, Zhao M H, journalName=Mechanics of Materials, refType=null, unstructuredReference=Zhang J W, Qin J H, Li Y X, Lu C S, Liu H T, Zhao M H. Extraction of the plastic properties of metallic materials from scratch tests using deep learning[J]. Mechanics of Materials, 2022, 175: 104502., articleTitle=Extraction of the plastic properties of metallic materials from scratch tests using deep learning, refAbstract=null), Reference(id=1246045629223387347, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, doi=null, pmid=null, pmcid=null, year=2022, volume=11, issue=54, pageStart=3215, pageEnd=3222, url=null, language=null, rfNumber=[15], rfOrder=19, authorNames=魏新宇, 桑建兵, 张睿琳, 王静远, 刘宝友, journalName=力学学报, refType=null, unstructuredReference=魏新宇, 桑建兵, 张睿琳, 王静远, 刘宝友. 基于机器学习软骨细胞的时间依赖性力学行为及本构参数反演[J]. 力学学报, 2022, 11(54): 3215-3222., articleTitle=基于机器学习软骨细胞的时间依赖性力学行为及本构参数反演, refAbstract=null), Reference(id=1246045629349216468, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, doi=null, pmid=null, pmcid=null, year=2022, volume=11, issue=54, pageStart=3215, pageEnd=3222, url=null, language=null, rfNumber=[15], rfOrder=20, authorNames=Wei X Y, Sang J B, Zhang R L, Wang J Y, Liu B Y, journalName=Acta Mechanica Sinica, refType=null, unstructuredReference=(Wei X Y, Sang J B, Zhang R L, Wang J Y, Liu B Y. Time-dependent mechanical behavior and constitutive parameter identification of chondrocytes based on machine learning[J]. Acta Mechanica Sinica, 2022, 11(54): 3215-3222. (in Chinese)), articleTitle=Time-dependent mechanical behavior and constitutive parameter identification of chondrocytes based on machine learning, refAbstract=null), Reference(id=1246045629466656983, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, doi=null, pmid=null, pmcid=null, year=2021, volume=42, issue=06, pageStart=697, pageEnd=706, url=null, language=null, rfNumber=[16], rfOrder=21, authorNames=黄钟民, 陈思亚, 陈卫, 彭林欣, journalName=固体力学学报, refType=null, unstructuredReference=黄钟民, 陈思亚, 陈卫, 彭林欣. 薄板弯曲问题的神经网络方法[J]. 固体力学学报, 2021, 42(06): 697-706., articleTitle=薄板弯曲问题的神经网络方法, refAbstract=null), Reference(id=1246045629621846234, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, doi=null, pmid=null, pmcid=null, year=2021, volume=42, issue=06, pageStart=697, pageEnd=706, url=null, language=null, rfNumber=[16], rfOrder=22, authorNames=Huang Z M, Chen S Y, Chen W, Peng L X, journalName=Chinese Journal of Solid Mechanics, refType=null, unstructuredReference=(Huang Z M, Chen S Y, Chen W, Peng L X. Neural network method for thin plate bending problem[J]. Chinese Journal of Solid Mechanics, 2021, 42(06): 697-706. (in Chinese)), articleTitle=Neural network method for thin plate bending problem, refAbstract=null), Reference(id=1246045629701538011, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, doi=null, pmid=null, pmcid=null, year=2024, volume=45, issue=2, pageStart=170, pageEnd=187, url=null, language=null, rfNumber=[17], rfOrder=23, authorNames=高恩来, journalName=固体力学学报, refType=null, unstructuredReference=高恩来. 知识与数据交互驱动的力学性能极限研究进展[J]. 固体力学学报, 2024, 45(2): 170-187., articleTitle=知识与数据交互驱动的力学性能极限研究进展, refAbstract=null), Reference(id=1246045629798007004, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, doi=null, pmid=null, pmcid=null, year=2024, volume=45, issue=2, pageStart=170, pageEnd=187, url=null, language=null, rfNumber=[17], rfOrder=24, authorNames=Gao E L, journalName=Chinese Journal of Solid Mechanics, refType=null, unstructuredReference=(Gao E L. Knowledge and data-driven exploration of bounds on mechanical properties: a review[J]. Chinese Journal of Solid Mechanics, 2024, 45(2): 170-187. (in Chinese)), articleTitle=Knowledge and data-driven exploration of bounds on mechanical properties: a review, refAbstract=null), Reference(id=1246045629877698779, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, doi=null, pmid=null, pmcid=null, year=2018, volume=102, issue=2, pageStart=1645, pageEnd=1656, url=null, language=null, rfNumber=[18], rfOrder=25, authorNames=Wu Y C, Feng J W, journalName=Wireless Personal Communications, refType=null, unstructuredReference=Wu Y C, Feng J W. Development and application of artificial neuralnetwork[J]. Wireless Personal Communications, 2018, 102(2): 1645-1656., articleTitle=Development and application of artificial neuralnetwork, refAbstract=null), Reference(id=1246045629965779165, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, doi=null, pmid=null, pmcid=null, year=2018, volume=null, issue=null, pageStart=37, pageEnd=200, url=null, language=null, rfNumber=[19], rfOrder=26, authorNames=斋藤康毅, journalName=深度学习入门, refType=null, unstructuredReference=斋藤康毅. 深度学习入门[M]. 北京: 人民邮电出版社, 2018: 37-200., articleTitle=null, refAbstract=null), Reference(id=1246045630053859549, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, doi=null, pmid=null, pmcid=null, year=2018, volume=null, issue=null, pageStart=37, pageEnd=200, url=null, language=null, rfNumber=[19], rfOrder=27, authorNames=Zhai T K Y, journalName=Deep Learning from Scratch, refType=null, unstructuredReference=(Zhai T K Y, Deep Learning from Scratch[M]. Beijing: The People's Posts and Telecommunications Press, 2018: 37-200. (in Chinese)), articleTitle=null, refAbstract=null), Reference(id=1246045630150328543, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, doi=null, pmid=null, pmcid=null, year=2019, volume=40, issue=1, pageStart=55, pageEnd=63, url=null, language=null, rfNumber=[20], rfOrder=28, authorNames=刘勇勇, 肖革胜, 李志刚, 树学峰, journalName=力学季刊, refType=null, unstructuredReference=刘勇勇, 肖革胜, 李志刚, 树学峰. 基于微纳米压入法提取无铅焊料合金弹塑性力学参数的研究[J]. 力学季刊, 2019, 40(1): 55-63., articleTitle=基于微纳米压入法提取无铅焊料合金弹塑性力学参数的研究, refAbstract=null), Reference(id=1246045630225826019, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, doi=null, pmid=null, pmcid=null, year=2019, volume=40, issue=1, pageStart=55, pageEnd=63, url=null, language=null, rfNumber=[20], rfOrder=29, authorNames=Liu Y Y, Xiao G S, Li Z G, Shu X F, journalName=Chinese Quarterly of Mechanics, refType=null, unstructuredReference=(Liu Y Y, Xiao G S, Li Z G, Shu X F. Research on the elastic-plastic mechanical parameters of lead-free solder alloys using micro-/nano-indentation[J]. Chinese Quarterly of Mechanics, 2019, 40(1): 55-63. (in Chinese)), articleTitle=Research on the elastic-plastic mechanical parameters of lead-free solder alloys using micro-/nano-indentation, refAbstract=null), Reference(id=1246045630397792484, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, doi=null, pmid=null, pmcid=null, year=2019, volume=138, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[21], rfOrder=30, authorNames=Xiao G S, Yang X X, Qiu J, Chang C, Liu E Q, Duan Q, Shu X F, Wang Z H, journalName=Mechanics of Materials, refType=null, unstructuredReference=Xiao G S, Yang X X, Qiu J, Chang C, Liu E Q, Duan Q, Shu X F, Wang Z H. Determination of power hardening elastoplastic constitutive relation of metals through indentation tests with plural indenters[J]. Mechanics of Materials, 2019, 138: 103173., articleTitle=Determination of power hardening elastoplastic constitutive relation of metals through indentation tests with plural indenters, refAbstract=null), Reference(id=1246045632008405223, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, doi=null, pmid=null, pmcid=null, year=2021, volume=160, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[22], rfOrder=31, authorNames=Xiao G S, Ma Y H, Ji X K, Wang T J, Shu X F, Liu E Q, journalName=Mechanics of Materials, refType=null, unstructuredReference=Xiao G S, Ma Y H, Ji X K, Wang T J, Shu X F, Liu E Q. Effective acquisition of elastoplastic and creep parameters of lead-free solder alloy from high-temperature micro-indentation eliminating the sizeeffect[J]. Mechanics of Materials, 2021, 160: 103985., articleTitle=Effective acquisition of elastoplastic and creep parameters of lead-free solder alloy from high-temperature micro-indentation eliminating the sizeeffect, refAbstract=null), Reference(id=1246045632121651433, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, doi=null, pmid=null, pmcid=null, year=2022, volume=259, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[23], rfOrder=32, authorNames=Ji X K, Xiao G S, Lu P, Hao X, Fan X L, journalName=International Journal of Solids and Structures, refType=null, unstructuredReference=Ji X K, Xiao G S, Lu P, Hao X, Fan X L. Characterization of power-law constitutive relationship of nickel-based single crystal superalloys under different loading rates by nanoindentation with different types of indenters[J]. International Journal of Solids and Structures, 2022, 259: 112025., articleTitle=Characterization of power-law constitutive relationship of nickel-based single crystal superalloys under different loading rates by nanoindentation with different types of indenters, refAbstract=null), Reference(id=1246045632222314731, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, doi=null, pmid=null, pmcid=null, year=2009, volume=41, issue=5, pageStart=730, pageEnd=738, url=null, language=null, rfNumber=[24], rfOrder=33, authorNames=姜鹏, 张泰华, 杨荣, 梁乃刚, journalName=力学学报, refType=null, unstructuredReference=姜鹏, 张泰华, 杨荣, 梁乃刚. 基于球形压入法提取材料的塑性力学参数[J]. 力学学报, 2009, 41(5): 730-738., articleTitle=基于球形压入法提取材料的塑性力学参数, refAbstract=null), Reference(id=1246045632314589421, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, doi=null, pmid=null, pmcid=null, year=2009, volume=41, issue=5, pageStart=730, pageEnd=738, url=null, language=null, rfNumber=[24], rfOrder=34, authorNames=Jiang P, Zhang T H, Yang R, Liang N G, journalName=Chinese Journal of Theoretical and Applied Mechanics, refType=null, unstructuredReference=(Jiang P, Zhang T H, Yang R, Liang N G. A new spherical indentation-based method to extract plastic material parameters[J]. Chinese Journal of Theoretical and Applied Mechanics, 2009, 41(5): 730-738. (in Chinese)), articleTitle=A new spherical indentation-based method to extract plastic material parameters, refAbstract=null), Reference(id=1246045632394281197, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, doi=null, pmid=null, pmcid=null, year=2013, volume=61, issue=null, pageStart=91, pageEnd=101, url=null, language=null, rfNumber=[25], rfOrder=35, authorNames=Song Z, Komvopoulos K, journalName=Mechanics of Materials, refType=null, unstructuredReference=Song Z, Komvopoulos K. Elastic-plastic spherical indentation: Deformation regimes, evolution of plasticity, and hardening effect[J]. Mechanics of Materials, 2013, 61: 91-101., articleTitle=Elastic-plastic spherical indentation: Deformation regimes, evolution of plasticity, and hardening effect, refAbstract=null), Reference(id=1246045632528498927, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, doi=null, pmid=null, pmcid=null, year=1994, volume=26, issue=5, pageStart=636, pageEnd=640, url=null, language=null, rfNumber=[26], rfOrder=36, authorNames=南策文, journalName=力学学报, refType=null, unstructuredReference=南策文. 关于复合材料弹塑性的一个理论描述[J]. 力学学报, 1994, 26(5): 636-640., articleTitle=关于复合材料弹塑性的一个理论描述, refAbstract=null), Reference(id=1246045632599802097, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, doi=null, pmid=null, pmcid=null, year=1994, volume=26, issue=5, pageStart=636, pageEnd=640, url=null, language=null, rfNumber=[26], rfOrder=37, authorNames=Nan C W, journalName=Acta Mechanica Sinica, refType=null, unstructuredReference=(Nan C W. On a theory for elastoplasticity of composites[J]. Acta Mechanica Sinica, 1994, 26(5): 636-640. (in Chinese)), articleTitle=On a theory for elastoplasticity of composites, refAbstract=null), Reference(id=1246045632679493875, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, doi=null, pmid=null, pmcid=null, year=2000, volume=133-134, issue=null, pageStart=417, pageEnd=424, url=null, language=null, rfNumber=[27], rfOrder=38, authorNames=Cheng Y T, Cheng C M, journalName=Surface and Coatings Technology, refType=null, unstructuredReference=Cheng Y T, Cheng C M. What is indentation hardness?[J]. Surface and Coatings Technology, 2000, 133-134: 417-424., articleTitle=What is indentation hardness?, refAbstract=null), Reference(id=1246045632763379956, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, doi=null, pmid=null, pmcid=null, year=1994, volume=2, issue=3, pageStart=247, pageEnd=281, url=null, language=null, rfNumber=[28], rfOrder=39, authorNames=Abdi H, journalName=Journal of Biological Systems, refType=null, unstructuredReference=Abdi H. A neural networkprimer[J]. Journal of Biological Systems, 1994, 2(3): 247-281., articleTitle=A neural networkprimer, refAbstract=null), Reference(id=1246045632851460342, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, doi=null, pmid=null, pmcid=null, year=2005, volume=20, issue=8, pageStart=2225, pageEnd=2234, url=null, language=null, rfNumber=[29], rfOrder=40, authorNames=Ogasawara N, Chiba N, Chen X, journalName=Journal of Materials Research, refType=null, unstructuredReference=Ogasawara N, Chiba N, Chen X. Representative strain of indentationanalysis[J]. Journal of Materials Research, 2005, 20(8): 2225-2234., articleTitle=Representative strain of indentationanalysis, refAbstract=null), Reference(id=1246045632939540728, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, doi=null, pmid=null, pmcid=null, year=2019, volume=null, issue=null, pageStart=88, pageEnd=96, url=null, language=null, rfNumber=[30], rfOrder=41, authorNames=阿斯顿·张, 李沐, 扎卡里·C. 立顿, 亚历山大·J·斯莫拉, journalName=动手学深度学习, refType=null, unstructuredReference=阿斯顿·张, 李沐, 扎卡里·C. 立顿, 亚历山大·J·斯莫拉. 动手学深度学习[M]. 北京: 人民邮电出版社: 2019: 88-96., articleTitle=null, refAbstract=null), Reference(id=1246045633015038200, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, doi=null, pmid=null, pmcid=null, year=2019, volume=null, issue=null, pageStart=88, pageEnd=96, url=null, language=null, rfNumber=[30], rfOrder=42, authorNames=Zhang A, Li M, Lipton Z C, Alexander J S, journalName=Dive Into Deep Learning, refType=null, unstructuredReference=(Zhang A, Li M, Lipton Z C, Alexander J S. Dive Into Deep Learning[M]. The People's Posts and Telecommunications Press: 2019: 88-96. (in Chinese)), articleTitle=null, refAbstract=null)], funds=[Fund(id=1246045625691783343, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, awardId=12272249; 12272256, language=CN, fundingSource=国家自然科学基金项目(12272249; 12272256), fundOrder=null, country=null), Fund(id=1246045625767280819, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, awardId=202203021211180, language=CN, fundingSource=山西省基础研究计划项目(202203021211180), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1246045615956804586, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, xref=null, ext=[AuthorCompanyExt(id=1246045615965193195, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, companyId=1246045615956804586, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Institute of Applied Mechanics, College of Mechanical and Vehicle Engineering, Taiyuan University of Technology, Taiyuan, 030024), AuthorCompanyExt(id=1246045615969387500, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, companyId=1246045615956804586, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=太原理工大学机械与运载工程学院应用力学研究所,太原,030024)])], figs=[ArticleFig(id=1246045620323074127, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, language=EN, label=Fig.1, caption=Diagram of tensile specimen, figureFileSmall=P/fCTmY8Gf03KuFCvXbfUQ==, figureFileBig=aqDOhQgN1+hBXoNEPLukqA==, tableContent=null), ArticleFig(id=1246045620406960210, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, language=CN, label=图1, caption=拉伸试样示意图, figureFileSmall=P/fCTmY8Gf03KuFCvXbfUQ==, figureFileBig=aqDOhQgN1+hBXoNEPLukqA==, tableContent=null), ArticleFig(id=1246045620679589977, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, language=EN, label=Fig.2, caption=Tensile stress-strain curves and acquisition of related plastic parameters: (a)/(b) Cu, (c)/(d) Mg, (e)/(f) Fe, figureFileSmall=mDIVx7z1ps7l4lOLzwqZ/w==, figureFileBig=x21+Um8Add5BArJvSA1PkA==, tableContent=null), ArticleFig(id=1246045620767670365, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, language=CN, label=图2, caption=拉伸应力-应变曲线及相关塑性参数的获取:(a)/(b)紫铜,(c)/(d)镁合金,(e)/(f)低碳钢, figureFileSmall=mDIVx7z1ps7l4lOLzwqZ/w==, figureFileBig=x21+Um8Add5BArJvSA1PkA==, tableContent=null), ArticleFig(id=1246045620876722272, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, language=EN, label=Fig.3, caption=Residual indentation morphology scanned by the contour morphology system, figureFileSmall=3K1F6LHOo+o4zNGdPKDTVg==, figureFileBig=XL/6LepT8cmyerQ21ogueQ==, tableContent=null), ArticleFig(id=1246045620956414051, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, language=CN, label=图3, caption=残余压痕形貌的轮廓形态系统扫描图, figureFileSmall=3K1F6LHOo+o4zNGdPKDTVg==, figureFileBig=XL/6LepT8cmyerQ21ogueQ==, tableContent=null), ArticleFig(id=1246045621069660264, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, language=EN, label=Fig.4, caption=Residual indentation depth acquisition along the horizontal radial direction and corresponding data: (a)/(b) Cu, (c)/(d) Mg, (e)/(f) Fe, figureFileSmall=EXSSNb0HbPMN8Pi/2Azxwg==, figureFileBig=HoeWZfkCUV1TqpwFXdU3CA==, tableContent=null), ArticleFig(id=1246045621157740650, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, language=CN, label=图4, caption=沿水平径向的残余压痕深度获取及相应数据:(a)/(b)紫铜,(c)/(d)镁合金,(e)/(f)低碳钢, figureFileSmall=EXSSNb0HbPMN8Pi/2Azxwg==, figureFileBig=HoeWZfkCUV1TqpwFXdU3CA==, tableContent=null), ArticleFig(id=1246045621229043821, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, language=EN, label=Fig.5, caption=Schematic diagram of residual indentation depth extraction under different horizontal radial displacements (a) and curve equations of residual indentation contour: (b) Cu, (c) Mg, (d) Fe, figureFileSmall=wOg8TQmhPoS0lErmSIlfpQ==, figureFileBig=mVk8CVFfLHI3kelsDQihPQ==, tableContent=null), ArticleFig(id=1246045621312929903, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, language=CN, label=图5, caption=不同水平径向位移下残余压痕深度提取示意图(a)及残余压痕轮廓曲线方程:(b)紫铜,(c)镁合金,(d)低碳钢, figureFileSmall=wOg8TQmhPoS0lErmSIlfpQ==, figureFileBig=mVk8CVFfLHI3kelsDQihPQ==, tableContent=null), ArticleFig(id=1246045621401010289, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, language=EN, label=Fig.6, caption=Two-dimensional axisymmetric finite element model for spherical indentation, figureFileSmall=b7W+3kjOjxoB9oKNI2dF+w==, figureFileBig=cZHhXH+0ozrBEmlG3DgsIQ==, tableContent=null), ArticleFig(id=1246045622957097079, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, language=CN, label=图6, caption=球形压入的二维轴对称有限元模型, figureFileSmall=b7W+3kjOjxoB9oKNI2dF+w==, figureFileBig=cZHhXH+0ozrBEmlG3DgsIQ==, tableContent=null), ArticleFig(id=1246045623082926204, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, language=EN, label=Fig.7, caption=Schematic diagram of neural network structure with its input and output parameters, figureFileSmall=ymCWPnSbGKQ/nFkCosSPnA==, figureFileBig=LwGCyYpU/TOQdN8/Ie2zvA==, tableContent=null), ArticleFig(id=1246045623183589504, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, language=CN, label=图7, caption=神经网络结构与输入输出参数示意图, figureFileSmall=ymCWPnSbGKQ/nFkCosSPnA==, figureFileBig=LwGCyYpU/TOQdN8/Ie2zvA==, tableContent=null), ArticleFig(id=1246045623301030019, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, language=EN, label=Fig.8, caption=Influence of “He initial value” on the training process of neural network, figureFileSmall=7+dwDb9S6jXaSpGP28bfQg==, figureFileBig=YaKg73m0E8D+qr5DzdQYOQ==, tableContent=null), ArticleFig(id=1246045623401693318, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, language=CN, label=图8, caption=“He初始值”对神经网络训练过程的影响, figureFileSmall=7+dwDb9S6jXaSpGP28bfQg==, figureFileBig=YaKg73m0E8D+qr5DzdQYOQ==, tableContent=null), ArticleFig(id=1246045623498162311, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, language=EN, label=Fig.9, caption=Mean square error loss function of the mini-batch version, figureFileSmall=uYDjBLQwOP+QixZGByRjjg==, figureFileBig=rR7xm1WCHJXpZ8cQXDk92A==, tableContent=null), ArticleFig(id=1246045623603019913, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, language=CN, label=图9, caption=mini-batch版的均方误差损失函数, figureFileSmall=uYDjBLQwOP+QixZGByRjjg==, figureFileBig=rR7xm1WCHJXpZ8cQXDk92A==, tableContent=null), ArticleFig(id=1246045623703683214, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, language=EN, label=Fig.10, caption=Change of loss function value with training times under four optimal parameter search strategies, figureFileSmall=qus0qX8M7nzwR0NY4G8ZHA==, figureFileBig=ThDO93En6IM9ulwqm1t+Bg==, tableContent=null), ArticleFig(id=1246045623812735119, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, language=CN, label=图10, caption=4种寻找最优参数策略下损失函数值随训练次数的变化, figureFileSmall=qus0qX8M7nzwR0NY4G8ZHA==, figureFileBig=ThDO93En6IM9ulwqm1t+Bg==, tableContent=null), ArticleFig(id=1246045623951147153, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, language=EN, label=Fig.11, caption=Training effect of neural networks under different neuronal structures (taking Cu for example), figureFileSmall=bJlgybIUSRp8d9LfumnaHQ==, figureFileBig=Kue5Fd7wAz6eXanmIHIs1g==, tableContent=null), ArticleFig(id=1246045624064393364, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, language=CN, label=图11, caption=不同神经元结构下神经网络的训练效果(以紫铜为例), figureFileSmall=bJlgybIUSRp8d9LfumnaHQ==, figureFileBig=Kue5Fd7wAz6eXanmIHIs1g==, tableContent=null), ArticleFig(id=1246045624177639573, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, language=EN, label=Fig.12, caption=Loss function value and training time of neural networks with different neuronal structures after training, figureFileSmall=vw8glkkXeS3ApyPD/Hei0w==, figureFileBig=a1Nw6Uh7+l1K1SaCtW5MxQ==, tableContent=null), ArticleFig(id=1246045624282497177, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, language=CN, label=图12, caption=不同神经元结构下神经网络训练后的损失函数值与训练时间, figureFileSmall=vw8glkkXeS3ApyPD/Hei0w==, figureFileBig=a1Nw6Uh7+l1K1SaCtW5MxQ==, tableContent=null), ArticleFig(id=1246045624366383258, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, language=EN, label=Table 1, caption=

Relevant dimensions of tensile specimen

, figureFileSmall=null, figureFileBig=null, tableContent=
符号名称数值(mm)
l试样平行部分的长度36
l0试样的标距段长度25
r从头部到平行部分的过渡圆弧半径8
d0平行段的原始直径6
D夹持端的直径11
lc夹持端长度38
), ArticleFig(id=1246045624601264286, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, language=CN, label=表1, caption=

拉伸试样相关尺寸

, figureFileSmall=null, figureFileBig=null, tableContent=
符号名称数值(mm)
l试样平行部分的长度36
l0试样的标距段长度25
r从头部到平行部分的过渡圆弧半径8
d0平行段的原始直径6
D夹持端的直径11
lc夹持端长度38
), ArticleFig(id=1246045624727093411, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, language=EN, label=Table 2, caption=

Plastic parameters used for neural network learning of Cu

, figureFileSmall=null, figureFileBig=null, tableContent=
塑性参数数值
σy(MPa)290.0,295.0,300.0,305.0,310.0,315.0,320.0,325.0,330.0,335.0,340.0
K(MPa)60.0,65.0,70.0,75.0,80.0,85.0,90.0,95.0,100.0
n0.27,0.28,0.29,0.3,0.31,0.32,0.33,0.34,0.35,0.36,0.37,0.38,0.39,0.40
), ArticleFig(id=1246045624819368098, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, language=CN, label=表2, caption=

用于紫铜神经网络学习的塑性参数

, figureFileSmall=null, figureFileBig=null, tableContent=
塑性参数数值
σy(MPa)290.0,295.0,300.0,305.0,310.0,315.0,320.0,325.0,330.0,335.0,340.0
K(MPa)60.0,65.0,70.0,75.0,80.0,85.0,90.0,95.0,100.0
n0.27,0.28,0.29,0.3,0.31,0.32,0.33,0.34,0.35,0.36,0.37,0.38,0.39,0.40
), ArticleFig(id=1246045624920031397, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, language=EN, label=Table 3, caption=

Plastic parameters used for neural network learning of Mg

, figureFileSmall=null, figureFileBig=null, tableContent=
塑性参数数值
σy(MPa)120.0,125.0,130.0,135.0,140.0,145.0,150.0,155.0,160.0,165.0,170.0,175.0,180.0
K(MPa)200.0,210.0,220.0,230.0,240.0,250.0,260.0,270.0,280.0
n0.27,0.28,0.29,0.3,0.31,0.32,0.33,0.34,0.35,0.36,0.37,0.38,0.39,0.40
), ArticleFig(id=1246045625054249125, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, language=CN, label=表3, caption=

用于镁合金神经网络学习的塑性参数

, figureFileSmall=null, figureFileBig=null, tableContent=
塑性参数数值
σy(MPa)120.0,125.0,130.0,135.0,140.0,145.0,150.0,155.0,160.0,165.0,170.0,175.0,180.0
K(MPa)200.0,210.0,220.0,230.0,240.0,250.0,260.0,270.0,280.0
n0.27,0.28,0.29,0.3,0.31,0.32,0.33,0.34,0.35,0.36,0.37,0.38,0.39,0.40
), ArticleFig(id=1246045625175883942, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, language=EN, label=Table 4, caption=

Plastic parameters used for neural network learning of Fe

, figureFileSmall=null, figureFileBig=null, tableContent=
塑性参数数值
σy(MPa)210.0,215.0,220.0,225.0,230.0,235.0,240.0,245.0,250.0,255.0,260.0,265.0,270.0
K(MPa)510.0,515.0,520.0,525.0,530.0,535.0,540.0,545.0,550.0
n0.37,0.38,0.39,0.40,0.41,0.42,0.43,0.44,0.45,0.46,0.47,0.48,0.49,0.50
), ArticleFig(id=1246045625284935847, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, language=CN, label=表4, caption=

用于低碳钢神经网络学习的塑性参数

, figureFileSmall=null, figureFileBig=null, tableContent=
塑性参数数值
σy(MPa)210.0,215.0,220.0,225.0,230.0,235.0,240.0,245.0,250.0,255.0,260.0,265.0,270.0
K(MPa)510.0,515.0,520.0,525.0,530.0,535.0,540.0,545.0,550.0
n0.37,0.38,0.39,0.40,0.41,0.42,0.43,0.44,0.45,0.46,0.47,0.48,0.49,0.50
), ArticleFig(id=1246045625406570665, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, language=EN, label=Table 5, caption=

Plastic parameters of Cu, Mg and Fe obtained from neural networks/tensile test and the relative error

, figureFileSmall=null, figureFileBig=null, tableContent=
σy(MPa)K(MPa)n
Cu神经网络反演结果330.172.30.3406
拉伸测试结果313.372.50.3395
相对误差5.36%-0.28%0.32%
Mg神经网络反演结果139.1214.20.3096
拉伸测试结果145.0200.80.3099
相对误差-4.07%6.67%-0.1%
Fe神经网络反演结果246.7532.20.4327
拉伸测试结果261.4546.30.4551
相对误差-5.62%-2.58%-4.92%
), ArticleFig(id=1246045625557565612, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1246045609464021872, language=CN, label=表5, caption=

神经网络与拉伸测试所得紫铜、镁合金及低碳钢的塑性参数及相对误差

, figureFileSmall=null, figureFileBig=null, tableContent=
σy(MPa)K(MPa)n
Cu神经网络反演结果330.172.30.3406
拉伸测试结果313.372.50.3395
相对误差5.36%-0.28%0.32%
Mg神经网络反演结果139.1214.20.3096
拉伸测试结果145.0200.80.3099
相对误差-4.07%6.67%-0.1%
Fe神经网络反演结果246.7532.20.4327
拉伸测试结果261.4546.30.4551
相对误差-5.62%-2.58%-4.92%
)], 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/o3.2024.028, detailUrlEn=https://castjournals.cast.org.cn/joweb/gtlxxb/EN/10.19636/j.cnki.cjsm42-1250/o3.2024.028, pdfUrlCn=https://castjournals.cast.org.cn/joweb/gtlxxb/CN/PDF/10.19636/j.cnki.cjsm42-1250/o3.2024.028, pdfUrlEn=https://castjournals.cast.org.cn/joweb/gtlxxb/EN/PDF/10.19636/j.cnki.cjsm42-1250/o3.2024.028, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于神经网络学习及残余压痕形貌获取金属塑性力学参数
收藏切换
PDF下载
何艳骄 , 田永喜 , 贾昊霖 , 树学峰 , 肖革胜 **
固体力学学报 | 研究论文 2024,45(5): 622-637
收起
收藏切换
固体力学学报 | 研究论文 2024, 45(5): 622-637
基于神经网络学习及残余压痕形貌获取金属塑性力学参数
全屏
何艳骄, 田永喜, 贾昊霖, 树学峰, 肖革胜**
作者信息
  • 太原理工大学机械与运载工程学院应用力学研究所,太原,030024

通讯作者:

Acquisition of Metal Plastic Parameters Based on Neural Network Learning and Residual Indentation Morphology
Yanjiao He, Yongxi Tian, Haolin Jia, Xuefeng Shu, Gesheng Xiao**
Affiliations
  • Institute of Applied Mechanics, College of Mechanical and Vehicle Engineering, Taiyuan University of Technology, Taiyuan, 030024
出版时间: 2024-10-25 doi: 10.19636/j.cnki.cjsm42-1250/o3.2024.028
文章导航
收藏切换

压入法相比于其他传统力学测试方法具有试样加工简单及可实现原位测试等优势,区别于已有的基于压入载荷-深度曲线获取材料力学性能参数的方法,本文提出了一种基于残余压痕形貌及神经网络学习反演金属塑性力学参数的新方法;采用Instron万能材料试验机开展了紫铜、镁合金及低碳钢的球形压入测试,并通过轮廓形态系统对压入测试后的残余压痕形貌进行特征扫描以作为后续研究的数据基础,分析所提取数据的特点并进行放大、取整、二进制化及高位补充等处理;基于Abaqus二次开发自动提取不同材料参数模拟下的残余压痕深度数据并用于神经网络学习,比较并选取激活函数、初始化神经网络参数的方法、神经网络参数更新方式、损失函数、寻找最优参数策略及神经网络结构,使神经网络学习达到较好的效果;结合实验所得残余压痕形貌特征数据与学习后的神经网络得到紫铜、镁合金及低碳钢的相关塑性参数,将通过Instron万能材料试验机拉伸测试表征所得紫铜、镁合金及低碳钢的相关塑性参数值作为对照标准,得到了神经网络学习结果的相对误差,验证了所提出基于神经网络学习及残余压痕形貌获取金属塑性力学参数方法的有效性;该方法可推广到其他金属/合金材料的力学性能表征及塑性参数获取研究中.

神经网络学习  /  残余压痕形貌  /  塑性参数  /  金属  /  数值模拟

Compared to conventional mechanical testing methods, the indentation method offers the advantages of simple manufacturing of samples and in-situ testing. This study proposes an alternative to deriving material mechanical parameters solely from indentation load-depth curves. It introduces an effective method for deducing metal plastic mechanical parameters based on residual indentation morphology and neural network learning. An Instron universal material testing machine was used to conduct spherical indentation tests on Cu, Mg, and Fe, followed by scanning their residual indentation morphology through the contour morphology system. The extracted morphology features served as the basis for further analysis. Data processing techniques such as amplification, rounding, binarization, and high-order digit supplementation were applied to the acquired data. Through Abaqus software and numerical simulations, residual indentation depth data associated with various material parameters were automatically extracted for neural network learning. Selections of activation function, neural network parameter initialization and updating mode, loss function, parameter optimization strategy, and neural network structure were carefully conducted to ensure effective learning. The plastic mechanical parameters of Cu, Mg, and Fe were obtained based on the residual indentation morphology feature data from indentation tests and the neural networks after learning. Additionally, the related plastic mechanical parameters of Cu, Mg, and Fe were also acquired through conventional uniaxial tensile tests and characterization using the Instron machine. By comparing the neural network learning results with tensile test data, relative errors in plastic mechanical parameters were identified. The effectiveness of the proposed method in obtaining metal plastic mechanical parameters based on neural network learning and residual indentation morphology was validated. This method can be expanded for characterizing mechanical properties and acquiring plastic parameters of other metal/alloy materials.

neural network learning  /  residual indentation morphology  /  plastic parameters  /  metals  /  numerical simulation
何艳骄, 田永喜, 贾昊霖, 树学峰, 肖革胜. 基于神经网络学习及残余压痕形貌获取金属塑性力学参数. 固体力学学报, 2024 , 45 (5) : 622 -637 . DOI: 10.19636/j.cnki.cjsm42-1250/o3.2024.028
Yanjiao He, Yongxi Tian, Haolin Jia, Xuefeng Shu, Gesheng Xiao. Acquisition of Metal Plastic Parameters Based on Neural Network Learning and Residual Indentation Morphology[J]. Chinese Journal of Solid Mechanics, 2024 , 45 (5) : 622 -637 . DOI: 10.19636/j.cnki.cjsm42-1250/o3.2024.028
材料的塑性力学参数对于工程设计及材料性能评估具有重要意义,使用传统的拉伸、压缩、扭转等测试方法时需要将材料加工成特定的形状尺寸,且无法实现原位测试[1];相比而言,压入法具有试样加工方便及可实现特定场景下的原位测试等优点,只需对工程材料与结构的特定表面区域施加局部压入载荷即可,在得到相关压入响应的基础上结合压入接触理论分析及数值模拟可获得材料的相关力学参数,目前已得到科研人员的广泛关注[2].
为寻找一种高效准确的方法来获取金属材料的塑性力学参数,国内外研究者目前已围绕压入法开展了较为系统的研究,主要包括针对压入曲线的量纲分析[3,4]、压入能量标度法[5-7]及基于机器学习的反演[8-10]等,这类反演方法大多依赖于压入载荷-深度曲线的准确获取;而作为压入后材料直观特征的残余压痕形貌是其塑性力学性能的一个综合响应[11-13],基于此可提供一种新的通过压入测试获取金属材料塑性力学参数的表征方法. 随着机器学习技术的不断应用和发展,其在反演获取材料力学性能参数方面也显示出广阔的应用前景[14,15],结合机器学习技术及残余压痕形貌开展相关研究将是获取金属塑性力学参数的一个有力途径;神经网络作为机器学习的一个重要组成部分,是一种模仿人类神经系统结构和功能的数学模型,相比于传统的线性模型,神经网络可以学习和描述更加复杂且非线性的数据模型,具有较好的泛化能力,受到了科研工作者的青睐且近年来在相关领域中的应用也更加广泛[16-18];但已有的神经网络学习也存在一些不足,如对计算资源要求较高、容易发生过拟合等[19].
鉴于此,本文基于球形压头压入金属试样的数值模拟得到了一系列不同塑性参数组合下的残余压痕数据,分析数据并对其进行了放大、取整、二进制编码及高位补充等处理,依据输入和输出层的数据特点选定了激活函数、初始化参数方法、神经网络梯度更新方式、损失函数及寻找最优参数的策略,并搭建了具有一定防止过拟合和学习能力的神经网络,比较了不同神经网络结构的学习效果,同时将实验得到的残余压痕进行数据提取并输入到已经训练好的神经网络,进而得到金属材料的塑性参数(以紫铜、AZ31B镁合金及低碳钢为例);进一步通过传统拉伸测试获取了三种金属材料的塑性参数,与压入测试后由残余压痕结合神经网络学习计算所得的塑性参数值进行对比,验证了本研究通过神经网络学习与压痕残余形貌获取金属塑性力学参数方法的有效性.
针对用于压入测试的常见形状压头,锥形压头具有几何自相似性,单一锥角压头压入时材料的应力应变分布特征不受压入深度的影响,至少需要采用两种不同锥角压头才能有效获取材料的力学参数[20-23];相对而言,球形压头压入过程可反映材料从弹性到塑性起始及完全塑性的压入变形演化特征,基于单一球形压头压入可获取材料的相关力学参数[24,25].
本研究以典型金属材料紫铜、AZ31B镁合金及低碳钢为代表,采用Instron 68TM-50TAO万能材料试验机开展相应的单轴拉伸与球形压入测试;用于拉伸测试的金属试样加工成哑铃状,相关具体尺寸如图1表1所示,测试时将试样夹持在拉伸夹具上,确保试样夹持段与夹具之间紧密接触而不滑动,并在试样标距段上安装机械引伸计,拉伸加载速率为2 mm/min. 以半径为2.5 mm的碳化钨硬质合金(YG60)半球为球形压入测试的压头,其弹性模量与泊松比分别为635 GPa和0.21,用于球形压入测试的圆柱状金属试样的高度与直径均为20 mm,采用高强度胶将半径为2.5 mm半球形压头的平整面粘贴在试验机的上压盘中心处,压入加/卸载速率分别设置为1 mm/min、0.5 mm/min;为了避免压入过程中上压盘与被测金属可能发生压入凸起部分的接触以保证被测金属表面的自由压入变形,经前期预测试将紫铜、镁合金及低碳钢的最大压深分别设置为1.7 mm、1.8 mm及1.6 mm,该压入深度均小于球形压头的半径且可保证被测金属的充分塑性变形.
拉伸测试时金属材料处于单轴应力状态,压入法作为一种局部加载方式,测试过程中压头下方被测金属处于复杂应力状态;本研究旨在对于一些难以取得标准拉伸试件情况下金属塑性力学参数的获取提供一种新的基于残余压痕形貌及神经网络学习的压入表征方法,虽然单轴拉伸测试与压入测试时被测材料的应力状态不同,但在本文偏于宏观的压入测试情况下及被测金属各向同性假设的前提下,可通过压入测试反演获取与单轴拉伸测试表征结果等效的金属塑性力学参数.
根据拉伸测试时引伸计所采集的初始线弹性段数据得到紫铜、镁合金及低碳钢的弹性模量E分别为106.8 GPa、44.7 GPa、208.5 GPa,基于试验机所记录的实时拉伸载荷与位移及试样标距段的初始横截面积与长度可得拉伸时三种金属材料的名义应力σN与名义应变εN,再根据公式(1)、(2)计算出相应的真实应力与真实应变,真应力-真应变曲线如图2(a)、2(c)、2(e)所示;由图可知,紫铜/镁合金的应力-应变曲线无明显屈服段,为此先将产生0.2%塑性应变所对应的应力值作为屈服参考值并对该参考值之后的应力-应变曲线进行分析,分别如图2(a)图2(c)虚线框内的曲线所示,将图2(a)中插图内最高点之前的数据作为紫铜的强化段数据,由于镁合金拉伸测试过程中未出现颈缩段,故而将2(c)中虚线框内的所有数据作为镁合金的强化段数据;同时由于低碳钢的拉伸应力-应变曲线具有明显的屈服阶段,将屈服平台段结束处的应力值作为屈服参考值,并将该屈服参考值之后及应力最高点之前的数据作为低碳钢的强化段数据,如图2(e)中虚框内的曲线所示;图2(b)、2(d)中的等效塑性应变εp是在考虑线性卸载定律的前提下由ε-σ/E-0.2%计算得到(σε图2(a)、2(c)中强化段任一点的应力与应变值,E为弹性模量),图2(f)中的等效塑性应变εp是在考虑线性卸载定律的前提下由ε-σ/Eε0计算得到(σε图2(e)中强化段任一点的应力与应变值,E为弹性模量,Δε0为屈服平台段的长度).
常见金属/合金的塑性行为可用公式(3)来描述[26],基于式(3)对图2(b)、2(d)、2(f)中的强化段数据分别进行非线性拟合,得到紫铜的屈服应力、塑性强化系数及强化指数分别为:σy=313.3 MPa、K=72.5 MPa及n=0.3395,镁合金的屈服应力、塑性强化系数及强化指数分别为:σy=145.0 MPa、K=200.8 MPa及n=0.3099,低碳钢的屈服应力、塑性强化系数及强化指数分别为:σy=261.4 MPa、K=546.3 MPa及n=0.4551.
式(1)中σNσ分别为名义应力与真应力,单位均为MPa;
式(2)中εN为名义应变,ε为真应变;
式(3)中σy为屈服应力,单位为MPa;K为塑性强化系数,单位为MPa;n为塑性强化指数;εP为等效塑性应变.
通过三维轮廓形态系统(Keyence VK-X1000)扫描经球形压头压入后的紫铜、镁合金及低碳钢的残余压痕形貌,结果如图3所示;考虑到半球形压头及被压入圆柱状金属的轴对称性,为了提高后续基于数值模拟及神经网络学习进行数据积累的效率,针对球形压入测试所得金属残余压痕形貌开展沿球形压痕水平径向的残余压痕轮廓获取(如图4),图3所示扫描宽度范围已包含沿球形压痕水平径向的残余压痕轮廓;由图4可知,紫铜经球形压入后出现了压入凸起现象,鉴于压入凸起的不可控性及沿水平径向残余压痕轮廓的对称性,取试样原始表面以下对称轴一侧的残余压痕轮廓作为后续研究的数据基础,镁合金与低碳钢经球形压入后未出现压入凸起现象,残余压痕形貌都在原始表面以下,取对称轴一侧及水平径向残余压痕轮廓拐点以内的轮廓曲线作为后续研究的数据基础;此外,由拉伸测试表征结果可知紫铜与镁合金的σy/E值分别为0.00293与0.00324,而二者的塑性强化指数n(0.3395与0.3099)既非属于加工硬化明显(n=0.5)也非理想弹塑性或加工硬化不明显(n=0、n=0.1),在这种情况下σy/E值较小的紫铜相比于σy/E值较大的镁合金更容易发生压入凸起现象[27];虽然拉伸测试表征所得低碳钢的σy/E值相对较小(0.00125),但其加工硬化相对更为明显(n=0.4551),故而没有出现压入凸起现象;这与图4所示三种金属的残余压痕形貌特征相符.
在此基础上对试样原始表面以下对称轴一侧的轮廓曲线沿水平径向等间距地获取一系列残余压痕深度数据(如图5(a)),具体方法为先将一半的残余压痕轮廓曲线进行非线性拟合得到轮廓曲线方程,其中水平径向距离为自变量、残余压痕深度为因变量,等间距地取一系列自变量值并代入所得轮廓曲线方程即可获得一系列沿水平径向的残余压痕深度数据,图5(b)、5(c)及5(d)分别为紫铜、镁合金及低碳钢原始表面以下对称轴一侧的轮廓曲线方程拟合结果.
典型的神经网络包括输入层、隐藏层和输出层,其中输入层接收原始数据输入,输出层给出最终的结果,而隐藏层则负责对输入数据进行复杂的非线性变换和特征提取;在机器学习任务中,神经网络通过训练来调整其内部参数,使得网络能够对输入数据进行准确的预测或分类;神经网络的训练通常依赖于大量的标记数据,通过优化算法来最小化预测结果与真实标签之间的差距,从而使网络具有更好的泛化能力[28].
本文将建立一个经球形压头压入后的金属残余压痕形貌与其塑性参数关系的神经网络,基于有限元分析开展一系列不同塑性参数组合下的球形压入模拟计算,得到不同参数组合下的残余压痕形貌数据并对其进行处理以作为神经网络的输入层,对应的材料塑性参数为标签值,并对输入层数据与其对应标签值的关联性进行学习,最终建立压痕残余形貌与材料塑性本构参数之间的关系;为实现数据的自动化积累,编写Python脚本控制Abaqus软件自动建模、计算、提取并存储数据,存储的数据表记录的是数值模拟结果的残余压痕形貌水平径向等间距下的残余深度值,表名命名为对应的材料塑性参数,方便后期神经网络学习时标签值的获取.
考虑到球形压头压入圆柱状金属试样的轴对称性,压入数值模拟时采用二维轴对称模型(图6),球形压头以半径为2.5 mm的1/4圆代替,试样尺寸为10 mm(x方向)×20 mm(y方向),硬质合金压头的弹性模量与泊松比分别为635 GPa、0.21,紫铜的弹性模量为106.8 GPa、泊松比为0.3,镁合金的弹性模量为44.7 GPa、泊松比为0.35,低碳钢的弹性模量为208.5GPa、泊松比为0.3;采用公式(3)表征试样的塑性性能,相关参数(屈服应力、塑性强化系数及强化指数)为表2表3表4中的所列值的不同组合;对压头及试样的网格划分采用CAX4R四边形轴对称单元,压头下方的试样部分需进行网格细分,网格过渡区域采用CAX3三角形轴对称单元与CAX4R四边形轴对称单元;试样有限元模型的边界条件为最左侧节点的位移x=0、底部节点的位移x=y=0,压头与试样表面定义为法向硬接触,相应的接触摩擦系数设置为0.15[29],压入数值模拟采用与球形压入测试相一致的位移加载控制方式.
经数值模拟后得到用于神经网络学习的数据的存储形式为以材料塑性参数值命名的表,表内为该塑性参数组合下模拟所得水平径向等间距下的残余压痕深度数据,并按训练集与测试集7∶3的比例随机分配所有数据;鉴于数值模拟后不同塑性参数组合下的特定水平径向等间距下残余压痕深度的差别较小,为了使神经网络能充分学习这些残余压痕深度数据,对神经网络输入层数据进行如下处理:
首先将残余压痕深度数据放大1000倍后取整,然后将取整后的数进行二进制转化,最后为保证不同数据都能适应第一层神经网络的数量,二进制转化后得到的数据按可能出现的最长数据位数进行高位补充;由一个残余压痕形貌数据得到的二进制数将装入一个列表,所有的残余压痕形貌数据读取并处理完毕后将得到一个二维训练集数据数组,该二维训练集数据数组的第一个维度描述的是训练集里的每一个残余压痕形貌数据,第二个维度描述的是每一个残余压痕的数据经处理后的二进制列表里的元素(如图7),这样处理使得残余压痕深度数据的特点被放大并转变成对机器学习更友好的二进制形式,提高了神经网络学习的效率与准确性. 图7神经网络结构中[x11x12x1b]列表内是一系列数0或数1,残余压痕的第一个残余深度数据经放大、取整、二进制化并高位补充后得到一个二进制数,此二进制数的每一位都依次对应该列表中的一个数,其中x1b是此二进制数的最低位、x11是最高位,其余残余压痕深度下同理,[xa1xa2xab]表示由残余压痕的第a个残余压痕深度数据得到的二进制列表,本研究中沿残余压痕水平径向等间距地取了11个残余压痕深度数据(如图5(a)).
在读取训练集数组的同时也会提取表名作为标签集,即为神经网络训练的监督数据,也是材料的屈服应力σy、塑性强化系数K、塑性强化指数n,三者的量级分别为102、10~102、10-1;由于所采用的损失函数是均方误差损失函数,为提高塑性强化指数对神经网络训练的影响力,强化指数都统一放大100倍之后作为第三个标签值,一个残余形貌数据表对应的表名(一组材料塑性参数值)会装入一个列表,读取并处理完表名之后的二维列表将作为训练集标签数组,这个二维训练集标签数组的第一个维度描述的是训练集里的每一组材料塑性参数,第二个维度描述的是一组材料塑性参数值经处理后的列表里的元素;为方便神经网络在训练过程中对训练集数据数组与训练标签数组的读取,最终将这两组数据转化为NumPy数组,神经网络结构与输入输出参数的整体示意图如图7所示.
激活函数是将神经网络的线性求和转换成非线性的函数,旨在增加网络的复杂程度,神经元中输入的数据经一系列加权求和后作用于该激活函数,常用的激活函数有ReLu函数、Sigmiod函数、Softmax函数等;由于输出层不是独热编码形式,独热编码形式是列举输出值可能出现的所有情况并标记正确输出(标记为1),一般采用独热编码形式的输出层会使用Softmax函数作为激活函数(Softmax函数是用来计算概率的,取概率最高的输出为1)[19],所以输出层激活函数不选用Softmax函数,同时尝试使用Sigmiod函数后会出现值溢出现象,因此本文选取ReLu函数作为激活函数,其表达式为:
式中x为激活函数的输入值,也是神经网络前一层神经元的输出值经线性变换后的值.
初始化参数包括初始化权重与初始化偏置,在神经网络学习中权重的初值十分重要,经常关系到神经网络学习的成功与否;对于本文所用的ReLu激活函数,针对神经元数量为154-30-3的神经网络结构采用“He初始值”(是一种标准差与前一层神经网络节点数有关的随机高斯分布,即前一层节点数为n,则“He初始值”的标准差为)作为权重初值,经预训练得到“He初始值”对神经网络训练过程的影响如图8所示(横坐标为训练次数,纵坐标为损失函数值),可知在训练前期使用“He初始值”时相应的损失函数值下降更快,即学习的速度更快,在训练后期损失函数值更小,训练效果更好.
常见的神经网络参数更新方式中,一种是遍历全部的训练集后计算一次损失,得到各参数相对于损失函数的梯度并更新参数,这种方法更容易找到全局最优点,但计算量大、效率不高;另一种则是每遍历一个数据就更新一次参数,这种方法计算速度快但收敛性不好;对此,本文在每次进行参数学习前,从训练集中随机选取一批数据(称为minibatch)并用这些数据进行学习,在下一次学习时又随机选取一批数据,这就减小了下降的随机性和计算量[19]. 针对mini-batch版的参数更新方式,存在相应的mini-batch版的均方误差损失函数:
式中d代表一组mini-batch数据的数量,通过除以d可以求得单个数据的平均损失函数,获取与训练数据数量无关的统一指标;c为神经网络输出层神经元的数量,yij表示神经网络最后一层的输出值,tij代表监督数据. 损失函数在神经网络里的正反向传播如图9所示,损失函数反向传播到均方误差损失函数反向输出端时的导数为,这不仅保留了误差信息,也保留了mini-batch的数据量信息,因而使用mini-batch版均方误差损失函数的神经网络可以进行有效的学习.
神经网络寻找最优参数的策略主要有SGD策略、Momentum策略、AdaGrad策略及Adam策略[19]图10为使用这4种策略时相应损失函数值随训练次数的变化情况(神经元数量为154-30-3),横坐标为训练次数、纵坐标为损失函数值;由图可知,Momentum策略与AdaGrad策略下的损失函数值维持在一较高水平,故不适用于本研究,而Adam策略与SGD策略在训练前期的损失函数值均有大幅下降,且在训练后期Adam策略比SGD策略的效果更好,因此本文选用Adam策略作为神经网络结合残余压痕反演金属塑性参数的寻优策略.
本研究中神经网络的输入层有154个神经元,输出层有3个神经元,通过调节隐藏层神经元数量来获取较好的学习效果;如图11所示(以紫铜为例,设置的收敛条件为损失函数值低于20或者训练次数大于10000次则跳出循环),(a)-(i)的命名方式为神经网络的每一层神经元数量,在一定范围内隐藏层神经元数量越多时,可通过较少的学习次数达到相同的学习效果,且最终的学习结果会略好一些(最终的损失函数值略低),但随着神经网络中神经元数量的增加,学习一次的时间会变长;神经元数量较少时的学习次数变多,每次学习的时间会减小,但神经元数量过少容易出现欠拟合(如图11(a)、11(f)),图11(a)隐藏层只设计了一层且只有5个神经元,出现了较为严重的欠拟合,图11(f)隐藏层为2层,每一层有5个神经元,欠拟合现象没有图11(a)严重,但学习效果也较差. 对比不同神经元结构下紫铜、镁合金及低碳钢的神经网络训练效果(图12),可知神经元结构为“154-30-3”与“154-30-30-3”时的测试集损失函数最终值与每遍历一次训练集时间均相对较小;同时考虑到较为复杂的神经元结构的表达能力更好,能更好地拟合复杂的非线性关系且泛化能力更强[30],因此最终选择神经元结构“154-30-30-3”.
在上述所搭建的神经网络结构的基础上,得到紫铜训练集损失函数值为19.5、测试集损失函数值为26.9,镁合金训练集损失函数值为96.8、测试集损失函数值为105.0,低碳钢训练集损失函数值为86.3、测试集损失函数值为95.1;将球形压入测试所得紫铜、镁合金及低碳钢的残余压痕形貌数据输入到学习后的神经网络中进行计算,结果如表5所示,紫铜的塑性参数为σy=330.1 MPa、K=72.3 MPa、n=0.3406,与传统拉伸测试表征所得相应塑性参数(σy=313.3 MPa、K=72.5 MPa、n=0.3395)的相对误差的绝对值均小于6%,镁合金的塑性参数为σy=139.1 MPa、K=214.2 MPa、n=0.3096,与传统拉伸测试表征所得相应塑性参数(σy=145.0 MPa、K=200.8 MPa、n=0.3099)的相对误差的绝对值均小于7%,低碳钢的塑性参数为σy=246.7 MPa、K=532.2 MPa、n=0.4327,与传统拉伸测试表征所得相应塑性参数(σy=261.4 MPa、K=546.3 MPa、n=0.4551)的相对误差的绝对值均小于6%;表明所提出的基于神经网络结合残余压痕形貌获取紫铜、镁合金及低碳钢塑性参数方法的有效性,该方法可推广到其他金属/合金材料的力学性能表征及塑性参数获取研究中.
本文基于神经网络学习与球形压入残余压痕形貌开展了紫铜、镁合金及低碳钢的塑性力学参数获取研究,主要结论如下:
(1)采用轮廓形态系统对紫铜、镁合金及低碳钢的球形压入残余压痕形貌进行了特征提取,将数值模拟的残余压痕深度作为神经网络学习的数据集;根据残余压痕深度数据的特点对其进行放大、取整、二进制化和高位补充等操作,测试并选取神经网络的激活函数、初始化神经网络参数的方法、训练过程中的参数更新方式、损失函数、寻找最优参数策略及神经网络结构,使神经网络不仅对于训练集准确率较高且具有一定泛化能力;经神经网络学习,最终紫铜的训练集损失函数值为19.5、测试集损失函数值为26.9,镁合金训练集损失函数值为96.8、测试集损失函数值为105.0,低碳钢训练集损失函数值为86.3、测试集损失函数值为95.1,训练集损失函数值与测试集损失函数值差别不大,学习没有出现过拟合现象.
(2)将经球形压入测试后所得的残余压痕深度提取数据输入到学习后的神经网络,得到紫铜塑性参数的反演结果为σy=330.1 MPa、K=72.3 MPa、n=0.3406,与传统拉伸测试表征所得相应塑性参数(σy=313.3 MPa、K=72.5 MPa、n=0.3395)的相对误差的绝对值均小于6%,其中塑性强化系数K与强化指数n的误差很小;镁合金的塑性参数反演结果为σy=139.1 MPa、K=214.2 MPa、n=0.3096,与传统拉伸测试表征所得相应塑性参数(σy=145.0 MPa、K=200.8 MPa、n=0.3099)的相对误差的绝对值均小于7%,其中塑性强化指数n的误差很小;低碳钢的塑性参数为σy=246.7 MPa、K=532.2 MPa、n=0.4327,与传统拉伸测试表征所得相应塑性参数(σy=261.4 MPa、K=546.3 MPa、n=0.4551)的相对误差的绝对值均小于6%;表明所提出的基于神经网络学习结合球形压入残余压痕形貌获取金属塑性力学参数方法的有效性.
  • 国家自然科学基金项目(12272249; 12272256)
  • 山西省基础研究计划项目(202203021211180)
参考文献 引证文献
排序方式:
[1]
桂立丰, 曹用涛. 机械工程材料测试手册·力学卷[M]. 沈阳: 辽宁科学技术出版社, 2001: 45-58.
(Gui L F, Cao Y T. Handbook of Materials Testing for Mechanical Engineering[M]. Shenyang: Liaoning Science and Technology Press, 2001: 45-58. (in Chinese))
[2]
张泰华. 微/纳米力学测试技术:仪器化压入的测量、分析、应用及其标准化[M]. 北京: 科学出版社, 2013: 21-23.
(Zhang T H. Micro/Nanomechanical Testing Techniques: Measurement, Analysis, Application and Standardization of Instrumented Indentation[M]. Beijing: Science Press, 2013: 21-23. (in Chinese))
[3]
Cheng Y T, Cheng C M. Scaling, dimensional analysis, and indentationmeasurements[J]. Materials Science and Engineering: R, 2004, 44: 91-149.
[4]
Gao C H, Yao L G, Liu M. Berkovich nanoindentation of borosilicate K9 glass[J]. Optical Engineering, 2018, 57(3): 034104.
[5]
Hou D Y, Liu M, Liu S, Yang F Q. Indentation fracture of 4H-SiC single crystal[J]. International Journal of Mechanical Sciences, 2024, 270: 109096.
[6]
Pöhl F, Huth S, Theisen W. Indentation of self-similar indenters: An FEM-assisted energy-based analysis[J]. Journal of the Mechanics and Physics of Solids, 2014, 66: 32-41.
[7]
Song Z, Komvopoulos K. An elastic-plastic analysis of spherical indentation: Constitutive equations for single-indentation unloading and development of plasticity due to repeated indentation[J]. Mechanics of Materials, 2014, 76: 93-101.
[8]
Long X, Ding X Y, Li J, Dong R P, Su Y T, Chang C. Indentation reverse algorithm of mechanical response for Elastoplastic Coatings based on LSTM Deep Learning[J]. Materials, 2023, 16: 2617.
[9]
Long X, Lu C H, Shen Z Y, Su Y T. Identification of mechanical properties of thin-film elastoplastic materials by machinelearning[J]. Acta Mechanica Solida Sinica, 2023, 36(1): 13-21.
[10]
田静萱, 夏僮, 杨振宇, 卢子兴, 贺小帆, 贺自强. 基于纳米压痕试验的塑性本构参数反演方法研究[J]. 固体力学学报, 2023, 44(05): 606-621.
(Tian J X, Xia T, Yang Z Y, Lu Z X, He X F, He Z Q. Reverse analysis for plastic constitutive parameters based on nanoindentation test[J]. Chinese Journal of Solid Mechanics, 2023, 44(05): 606-621. (in Chinese))
[11]
刘明, 侯冬杨, 高城辉. 利用维氏和玻氏压头表征半导体材料断裂韧性[J]. 力学学报, 2021, 53(2): 413-423.
(Liu M, Hou D Y, Gao C H. Study on fracture toughness of semiconductor material using vickers and berkovich indenters[J]. Chinese Journal of Theoretical and Applied Mechanics, 2021, 53(2): 413-423. (in Chinese))
[12]
Campbell J E, Thompson R P, Dean J, Clyne T W. Comparison between stress-strain plots obtained from indentationplastometry, based on residual indent profiles, and from uniaxial testing[J]. Acta Materialia, 2019, 168: 87-99.
[13]
刘明, 郑强, 高城辉. 基于努氏硬度表征大块金属玻璃的力学性能[J]. 固体力学学报, 2021, 42(4): 376-392.
(Liu M, Zheng Q, Gao C H. Characterization of mechanical properties of bulk metallic glasses based on knoop hardness[J]. Chinese Journal of Solid Mechanics, 2021, 42(4): 376-392. (in Chinese))
[14]
Zhang J W, Qin J H, Li Y X, Lu C S, Liu H T, Zhao M H. Extraction of the plastic properties of metallic materials from scratch tests using deep learning[J]. Mechanics of Materials, 2022, 175: 104502.
[15]
魏新宇, 桑建兵, 张睿琳, 王静远, 刘宝友. 基于机器学习软骨细胞的时间依赖性力学行为及本构参数反演[J]. 力学学报, 2022, 11(54): 3215-3222.
(Wei X Y, Sang J B, Zhang R L, Wang J Y, Liu B Y. Time-dependent mechanical behavior and constitutive parameter identification of chondrocytes based on machine learning[J]. Acta Mechanica Sinica, 2022, 11(54): 3215-3222. (in Chinese))
[16]
黄钟民, 陈思亚, 陈卫, 彭林欣. 薄板弯曲问题的神经网络方法[J]. 固体力学学报, 2021, 42(06): 697-706.
(Huang Z M, Chen S Y, Chen W, Peng L X. Neural network method for thin plate bending problem[J]. Chinese Journal of Solid Mechanics, 2021, 42(06): 697-706. (in Chinese))
[17]
高恩来. 知识与数据交互驱动的力学性能极限研究进展[J]. 固体力学学报, 2024, 45(2): 170-187.
(Gao E L. Knowledge and data-driven exploration of bounds on mechanical properties: a review[J]. Chinese Journal of Solid Mechanics, 2024, 45(2): 170-187. (in Chinese))
[18]
Wu Y C, Feng J W. Development and application of artificial neuralnetwork[J]. Wireless Personal Communications, 2018, 102(2): 1645-1656.
[19]
斋藤康毅. 深度学习入门[M]. 北京: 人民邮电出版社, 2018: 37-200.
(Zhai T K Y, Deep Learning from Scratch[M]. Beijing: The People's Posts and Telecommunications Press, 2018: 37-200. (in Chinese))
[20]
刘勇勇, 肖革胜, 李志刚, 树学峰. 基于微纳米压入法提取无铅焊料合金弹塑性力学参数的研究[J]. 力学季刊, 2019, 40(1): 55-63.
(Liu Y Y, Xiao G S, Li Z G, Shu X F. Research on the elastic-plastic mechanical parameters of lead-free solder alloys using micro-/nano-indentation[J]. Chinese Quarterly of Mechanics, 2019, 40(1): 55-63. (in Chinese))
[21]
Xiao G S, Yang X X, Qiu J, Chang C, Liu E Q, Duan Q, Shu X F, Wang Z H. Determination of power hardening elastoplastic constitutive relation of metals through indentation tests with plural indenters[J]. Mechanics of Materials, 2019, 138: 103173.
[22]
Xiao G S, Ma Y H, Ji X K, Wang T J, Shu X F, Liu E Q. Effective acquisition of elastoplastic and creep parameters of lead-free solder alloy from high-temperature micro-indentation eliminating the sizeeffect[J]. Mechanics of Materials, 2021, 160: 103985.
[23]
Ji X K, Xiao G S, Lu P, Hao X, Fan X L. Characterization of power-law constitutive relationship of nickel-based single crystal superalloys under different loading rates by nanoindentation with different types of indenters[J]. International Journal of Solids and Structures, 2022, 259: 112025.
[24]
姜鹏, 张泰华, 杨荣, 梁乃刚. 基于球形压入法提取材料的塑性力学参数[J]. 力学学报, 2009, 41(5): 730-738.
(Jiang P, Zhang T H, Yang R, Liang N G. A new spherical indentation-based method to extract plastic material parameters[J]. Chinese Journal of Theoretical and Applied Mechanics, 2009, 41(5): 730-738. (in Chinese))
[25]
Song Z, Komvopoulos K. Elastic-plastic spherical indentation: Deformation regimes, evolution of plasticity, and hardening effect[J]. Mechanics of Materials, 2013, 61: 91-101.
[26]
南策文. 关于复合材料弹塑性的一个理论描述[J]. 力学学报, 1994, 26(5): 636-640.
(Nan C W. On a theory for elastoplasticity of composites[J]. Acta Mechanica Sinica, 1994, 26(5): 636-640. (in Chinese))
[27]
Cheng Y T, Cheng C M. What is indentation hardness?[J]. Surface and Coatings Technology, 2000, 133-134: 417-424.
[28]
Abdi H. A neural networkprimer[J]. Journal of Biological Systems, 1994, 2(3): 247-281.
[29]
Ogasawara N, Chiba N, Chen X. Representative strain of indentationanalysis[J]. Journal of Materials Research, 2005, 20(8): 2225-2234.
[30]
阿斯顿·张, 李沐, 扎卡里·C. 立顿, 亚历山大·J·斯莫拉. 动手学深度学习[M]. 北京: 人民邮电出版社: 2019: 88-96.
(Zhang A, Li M, Lipton Z C, Alexander J S. Dive Into Deep Learning[M]. The People's Posts and Telecommunications Press: 2019: 88-96. (in Chinese))
2024年第45卷第5期
PDF下载
47
21
引用本文
BibTeX
文章信息
doi: 10.19636/j.cnki.cjsm42-1250/o3.2024.028
  • 接收时间:2024-06-09
  • 首发时间:2026-04-01
  • 出版时间:2024-10-25
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2024-06-09
基金
国家自然科学基金项目(12272249; 12272256)
山西省基础研究计划项目(202203021211180)
作者信息
    太原理工大学机械与运载工程学院应用力学研究所,太原,030024

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/o3.2024.028
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