Article(id=1241408878966002130, tenantId=1146029695717560320, journalId=1227999626482147330, issueId=1241408875602178849, articleNumber=null, orderNo=null, doi=10.16579/j.issn.1001.9669.2025.08.003, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1700668800000, receivedDateStr=2023-11-23, revisedDate=1705334400000, revisedDateStr=2024-01-16, acceptedDate=null, acceptedDateStr=null, onlineDate=1773904541007, onlineDateStr=2026-03-19, pubDate=1755187200000, pubDateStr=2025-08-15, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1773904541007, onlineIssueDateStr=2026-03-19, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1773904541007, creator=13701087609, updateTime=1773904541007, updator=13701087609, issue=Issue{id=1241408875602178849, tenantId=1146029695717560320, journalId=1227999626482147330, year='2025', volume='47', issue='8', pageStart='1', pageEnd='174', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1773904540204, creator=13701087609, updateTime=1773904658798, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1241409373071798309, tenantId=1146029695717560320, journalId=1227999626482147330, issueId=1241408875602178849, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1241409373071798310, tenantId=1146029695717560320, journalId=1227999626482147330, issueId=1241408875602178849, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=19, endPage=27, ext={EN=ArticleExt(id=1241408881419669989, articleId=1241408878966002130, tenantId=1146029695717560320, journalId=1227999626482147330, language=EN, title=Research on carbides in M50 bearing steel based on Mask R-CNN deep learning model, columnId=1228282192162390694, journalTitle=Journal of Mechanical Strength, columnName=Experimental Research·Testing Technology, runingTitle=null, highlight=null, articleAbstract=

The main types of carbides in M50 bearing steel are MC, M2C and M23C6. Under the scanning electron microscopy (SEM), they exhibit significant differences in the shape, size, and distribution. Some carbides have larger sizes and uneven distribution. They become areas of stress concentration under loading,which has a negative impact on the bearing fatigue performance. So an improved mask region-based convolutional neural network (Mask R-CNN) model was proposed which can batch identify the types of three kinds of carbides in SEM pictures, the diameters of carbides were measured, and the distribution of carbides was showed. The output images and histogram results show that the size of M2C carbide in M50 bearing steel is large and unevenly distributed, but the distribution of MC carbide with the largest size and M23C6 with the smallest size is reasonably uniform.

, correspAuthors=null, authorNote=null, correspAuthorsNote=
LI Shuxin, E-mail:
, 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=Ruiming SUN, Shuxin LI, Siyuan LU, Yongsheng JIN, Huahai XIAO), CN=ArticleExt(id=1241408890399675031, articleId=1241408878966002130, tenantId=1146029695717560320, journalId=1227999626482147330, language=CN, title=基于深度学习模型Mask R-CNN对M50轴承钢中碳化物的研究, columnId=1228282192288219817, journalTitle=机械强度, columnName=实验研究·测试技术, runingTitle=null, highlight=null, articleAbstract=

M50轴承钢中主要的碳化物类型为MC、M2C和M23C6。扫描电子显微镜(Scanning Electron Microscopy, SEM)下,3种碳化物的形状、尺寸和在材料中的分布存在明显的区别。有些碳化物的尺寸较大且分布不均匀。轴承受载过程中,这些碳化物会成为应力集中的区域,对轴承疲劳性能产生负面影响。为了高效地获得材料中的碳化物信息,提出一种改进的掩膜基于区域的卷积神经网络(Mask Region-based Convolutional Neural Network, Mask R-CNN)模型,可批量鉴别SEM图像中3种碳化物的种类,确定其尺寸大小及分布。网络模型输出的图像和数值结果显示,M50轴承钢中M2C型碳化物尺寸大且分布不均匀,但总体尺寸最大的MC型碳化物和尺寸最小的M23C6型碳化物分布相对均匀。

, correspAuthors=null, authorNote=null, correspAuthorsNote=
李淑欣,女,1975年生,宁夏中卫人,博士,教授,博士研究生导师;主要研究方向为机械结构强度;E-mail:
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=YZKygjIqYSVXqrZ2/tDWXQ==, magXml=9WWbyqsHAVJb63CGPLUzQw==, pdfUrl=null, pdf=DC/xIyjp7m99sApPxJUElw==, pdfFileSize=33765472, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=Isqx7J/PJqMDp6QumPRr+w==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=Gj56KVPUSJi2J5R4XrBzkg==, mapNumber=null, authorCompany=null, fund=null, authors=

孙瑞明,男,1993年生,河南鹤壁人,硕士研究生;主要研究方向为机械结构强度;E-mail:

, authorsList=孙瑞明, 李淑欣, 鲁思渊, 金永生, 肖华海)}, authors=[Author(id=1241451338165441189, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=15658028610@163.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1241451338333213367, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, authorId=1241451338165441189, language=EN, stringName=Ruiming SUN, firstName=Ruiming, middleName=null, lastName=SUN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1.Faculty of Mechanical Engineering and Mechanics, Ningbo University, Ningbo 315211, China
2.Part Rolling Key Laboratory of Zhejiang Province, Ningbo 315211, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1241451338454848190, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, authorId=1241451338165441189, language=CN, stringName=孙瑞明, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1.宁波大学 机械工程与力学学院,宁波 315211
2.浙江省零件轧制成形技术研究重点实验室,宁波 315211, bio={"content":"

孙瑞明,男,1993年生,河南鹤壁人,硕士研究生;主要研究方向为机械结构强度;E-mail:

"}, bioImg=null, bioContent=

孙瑞明,男,1993年生,河南鹤壁人,硕士研究生;主要研究方向为机械结构强度;E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1241451336408027781, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, xref=1., ext=[AuthorCompanyExt(id=1241451336420610695, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, companyId=1241451336408027781, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.Faculty of Mechanical Engineering and Mechanics, Ningbo University, Ningbo 315211, China), AuthorCompanyExt(id=1241451336428999305, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, companyId=1241451336408027781, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.宁波大学 机械工程与力学学院,宁波 315211)]), AuthorCompany(id=1241451337917977232, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, xref=2., ext=[AuthorCompanyExt(id=1241451337926365843, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, companyId=1241451337917977232, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.Part Rolling Key Laboratory of Zhejiang Province, Ningbo 315211, China), AuthorCompanyExt(id=1241451337934754452, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, companyId=1241451337917977232, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.浙江省零件轧制成形技术研究重点实验室,宁波 315211)])]), Author(id=1241451338555511495, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=lishuxin@nbu.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1241451338672952012, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, authorId=1241451338555511495, language=EN, stringName=Shuxin LI, firstName=Shuxin, middleName=null, lastName=LI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1.Faculty of Mechanical Engineering and Mechanics, Ningbo University, Ningbo 315211, China
2.Part Rolling Key Laboratory of Zhejiang Province, Ningbo 315211, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1241451338819752659, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, authorId=1241451338555511495, language=CN, stringName=李淑欣, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1.宁波大学 机械工程与力学学院,宁波 315211
2.浙江省零件轧制成形技术研究重点实验室,宁波 315211, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1241451336408027781, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, xref=1., ext=[AuthorCompanyExt(id=1241451336420610695, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, companyId=1241451336408027781, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.Faculty of Mechanical Engineering and Mechanics, Ningbo University, Ningbo 315211, China), AuthorCompanyExt(id=1241451336428999305, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, companyId=1241451336408027781, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.宁波大学 机械工程与力学学院,宁波 315211)]), AuthorCompany(id=1241451337917977232, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, xref=2., ext=[AuthorCompanyExt(id=1241451337926365843, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, companyId=1241451337917977232, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.Part Rolling Key Laboratory of Zhejiang Province, Ningbo 315211, China), AuthorCompanyExt(id=1241451337934754452, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, companyId=1241451337917977232, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.浙江省零件轧制成形技术研究重点实验室,宁波 315211)])]), Author(id=1241451338983330522, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, 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=1241451339281126122, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, authorId=1241451338983330522, language=EN, stringName=Siyuan LU, firstName=Siyuan, middleName=null, lastName=LU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1.Faculty of Mechanical Engineering and Mechanics, Ningbo University, Ningbo 315211, China
2.Part Rolling Key Laboratory of Zhejiang Province, Ningbo 315211, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1241451339465675510, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, authorId=1241451338983330522, language=CN, stringName=鲁思渊, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1.宁波大学 机械工程与力学学院,宁波 315211
2.浙江省零件轧制成形技术研究重点实验室,宁波 315211, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1241451336408027781, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, xref=1., ext=[AuthorCompanyExt(id=1241451336420610695, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, companyId=1241451336408027781, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.Faculty of Mechanical Engineering and Mechanics, Ningbo University, Ningbo 315211, China), AuthorCompanyExt(id=1241451336428999305, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, companyId=1241451336408027781, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.宁波大学 机械工程与力学学院,宁波 315211)]), AuthorCompany(id=1241451337917977232, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, xref=2., ext=[AuthorCompanyExt(id=1241451337926365843, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, companyId=1241451337917977232, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.Part Rolling Key Laboratory of Zhejiang Province, Ningbo 315211, China), AuthorCompanyExt(id=1241451337934754452, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, companyId=1241451337917977232, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.浙江省零件轧制成形技术研究重点实验室,宁波 315211)])]), Author(id=1241451339587310337, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, 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=1241451339708945161, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, authorId=1241451339587310337, language=EN, stringName=Yongsheng JIN, firstName=Yongsheng, middleName=null, lastName=JIN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3.Ningbo Silver-ball Technology Co., Ltd., Ningbo 315207, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1241451339805414163, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, authorId=1241451339587310337, language=CN, stringName=金永生, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3.宁波银球科技股份有限公司,宁波 315207, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1241451338048000669, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, xref=3., ext=[AuthorCompanyExt(id=1241451338056389279, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, companyId=1241451338048000669, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3.Ningbo Silver-ball Technology Co., Ltd., Ningbo 315207, China), AuthorCompanyExt(id=1241451338060583583, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, companyId=1241451338048000669, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3.宁波银球科技股份有限公司,宁波 315207)])]), Author(id=1241451339901883160, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, 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=1241451339998352161, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, authorId=1241451339901883160, language=EN, stringName=Huahai XIAO, firstName=Huahai, middleName=null, lastName=XIAO, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3.Ningbo Silver-ball Technology Co., Ltd., Ningbo 315207, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1241451340103209765, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, authorId=1241451339901883160, language=CN, stringName=肖华海, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3.宁波银球科技股份有限公司,宁波 315207, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1241451338048000669, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, xref=3., ext=[AuthorCompanyExt(id=1241451338056389279, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, companyId=1241451338048000669, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3.Ningbo Silver-ball Technology Co., Ltd., Ningbo 315207, China), AuthorCompanyExt(id=1241451338060583583, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, companyId=1241451338048000669, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3.宁波银球科技股份有限公司,宁波 315207)])])], keywords=[Keyword(id=1241451340287759157, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, language=EN, orderNo=1, keyword=Deep learning), Keyword(id=1241451340363256633, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, language=EN, orderNo=2, keyword=Mask R-CNN), Keyword(id=1241451340455531327, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, language=EN, orderNo=3, keyword=M50 bearing steel), Keyword(id=1241451340547806023, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, language=EN, orderNo=4, keyword=Carbide), Keyword(id=1241451340702995275, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, language=CN, orderNo=1, keyword=深度学习), Keyword(id=1241451340795269971, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, language=CN, orderNo=2, keyword=Mask R-CNN), Keyword(id=1241451340904321884, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, language=CN, orderNo=3, keyword=M50轴承钢), Keyword(id=1241451342376522595, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, language=CN, orderNo=4, keyword=碳化物)], refs=[Reference(id=1241451348223381612, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, doi=null, pmid=null, pmcid=null, year=2012, volume=57, issue=2, pageStart=268, pageEnd=435, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=BHADESHIA H K D H, journalName=Progress in Materials Science, refType=null, unstructuredReference=BHADESHIA H K D H. Steels for bearings[J]. Progress in Materials Science201257(2):268-435., articleTitle=Steels for bearings, refAbstract=null), Reference(id=1241451348340822129, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, doi=null, pmid=null, pmcid=null, year=1992, volume=266, issue=1/2/3, pageStart=391, pageEnd=396, url=null, language=null, rfNumber=[2], rfOrder=1, authorNames=KINKUS T J, OLSON G B, journalName=Surface Science, refType=null, unstructuredReference=KINKUS T JOLSON G B. Microanalytical evaluation of a prototype stainless bearing steel[J]. Surface Science1992266(1/2/3):391-396., articleTitle=Microanalytical evaluation of a prototype stainless bearing steel, refAbstract=null), Reference(id=1241451348449874041, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, doi=null, pmid=null, pmcid=null, year=2011, volume=59, issue=19, pageStart=7155, pageEnd=7167, url=null, language=null, rfNumber=[3], rfOrder=2, authorNames=BARROW A T W, RIVERA-DÍAZ-DEL-CASTILLO P E J, journalName=Acta Materialia, refType=null, unstructuredReference=BARROW A T WRIVERA-DÍAZ-DEL-CASTILLO P E J. Nanoprecipitation in bearing steels[J]. Acta Materialia201159(19):7155-7167., articleTitle=Nanoprecipitation in bearing steels, refAbstract=null), Reference(id=1241451348542148734, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, doi=null, pmid=null, pmcid=null, year=2013, volume=67, issue=null, pageStart=364, pageEnd=372, url=null, language=null, rfNumber=[4], rfOrder=3, authorNames=KANG J H, RIVERA-DÍAZ-DEL-CASTILLO P E J, journalName=Computational Materials Science, refType=null, unstructuredReference=KANG J HRIVERA-DÍAZ-DEL-CASTILLO P E J. Carbide dissolution in bearing steels[J]. Computational Materials Science201367:364-372., articleTitle=Carbide dissolution in bearing steels, refAbstract=null), Reference(id=1241451348626034819, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, doi=null, pmid=null, pmcid=null, year=2016, volume=91, issue=null, pageStart=59, pageEnd=67, url=null, language=null, rfNumber=[5], rfOrder=4, authorNames=GUETARD G, TODA-CARABALLO I, RIVERA-DÍAZ-DEL-CASTILLO P E J, journalName=International Journal of Fatigue, refType=null, unstructuredReference=GUETARD GTODA-CARABALLO IRIVERA-DÍAZ-DEL-CASTILLO P E J. Damage evolution around primary carbides under rolling contact fatigue in VIM-VAR M50[J]. International Journal of Fatigue201691:59-67., articleTitle=Damage evolution around primary carbides under rolling contact fatigue in VIM-VAR M50, refAbstract=null), Reference(id=1241451348722503817, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, doi=null, pmid=null, pmcid=null, year=2018, volume=119, issue=null, pageStart=165, pageEnd=174, url=null, language=null, rfNumber=[6], rfOrder=5, authorNames=GUAN J, WANG L Q, ZHANG Z Q, journalName=Tribology International, refType=null, unstructuredReference=GUAN JWANG L QZHANG Z Q,et al. Fatigue crack nucleation and propagation at clustered metallic carbides in M50 bearing steel[J]. Tribology International2018119:165-174., articleTitle=Fatigue crack nucleation and propagation at clustered metallic carbides in M50 bearing steel, refAbstract=null), Reference(id=1241451348827361422, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, doi=null, pmid=null, pmcid=null, year=2018, volume=108, issue=null, pageStart=68, pageEnd=78, url=null, language=null, rfNumber=[7], rfOrder=6, authorNames=JELITA RYDEL J, TODA-CARABALLO I, GUETARD G, journalName=International Journal of Fatigue, refType=null, unstructuredReference=JELITA RYDEL JTODA-CARABALLO IGUETARD G,et al.Understanding the factors controlling rolling contact fatigue damage in VIM-VAR M50 steel[J]. International Journal of Fatigue2018108:68-78., articleTitle=Understanding the factors controlling rolling contact fatigue damage in VIM-VAR M50 steel, refAbstract=null), Reference(id=1241451348944801938, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, doi=null, pmid=null, pmcid=null, year=2022, volume=186, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[8], rfOrder=7, authorNames=DU N Y, LIU H H, CAO Y F, journalName=Materials Characterization, refType=null, unstructuredReference=DU N YLIU H HCAO Y F,et al. In situ investigation of the fracture of primary carbides and its mechanism in M50 steel[J]. Materials Characterization2022186:111822., articleTitle=In situ investigation of the fracture of primary carbides and its mechanism in M50 steel, refAbstract=null), Reference(id=1241451349037076629, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, doi=null, pmid=null, pmcid=null, year=2021, volume=889, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[9], rfOrder=8, authorNames=LIU W F, GUO Y F, CAO Y F, journalName=Journal of Alloys and Compounds, refType=null, unstructuredReference=LIU W FGUO Y FCAO Y F,et al. Transformation behavior of primary MC and M2C carbides in Cr4Mo4V steel[J]. Journal of Alloys and Compounds2021889:161755., articleTitle=Transformation behavior of primary MC and M2C carbides in Cr4Mo4V steel, refAbstract=null), Reference(id=1241451349167100059, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, doi=null, pmid=null, pmcid=null, year=2024, volume=53, issue=1, pageStart=105, pageEnd=110, url=null, language=null, rfNumber=[10], rfOrder=9, authorNames=侯志远, 刘威峰, 徐斌, journalName=热加工工艺, refType=null, unstructuredReference=侯志远,刘威峰,徐斌,等. 热加工过程中M50轴承钢一次碳化物的形成与演化[J]. 热加工工艺202453(1):105-110., articleTitle=热加工过程中M50轴承钢一次碳化物的形成与演化, refAbstract=null), Reference(id=1241451349267763362, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, doi=null, pmid=null, pmcid=null, year=2024, volume=53, issue=1, pageStart=105, pageEnd=110, url=null, language=null, rfNumber=[10], rfOrder=10, authorNames=HOU Zhiyuan, LIU Weifeng, XU Bin, journalName=Hot Working Technology, refType=null, unstructuredReference=HOU ZhiyuanLIU WeifengXU Bin,et al. Formation and evolution of primary carbides in M50 bearing steel during hot working[J]. Hot Working Technology202453(1):105-110.(In Chinese), articleTitle=Formation and evolution of primary carbides in M50 bearing steel during hot working, refAbstract=null), Reference(id=1241451349372620963, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, doi=null, pmid=null, pmcid=null, year=2020, volume=30, issue=9, pageStart=98, pageEnd=103, url=null, language=null, rfNumber=[11], rfOrder=11, authorNames=吴玉成, 姜宏伟, 胡园, journalName=中国冶金, refType=null, unstructuredReference=吴玉成,姜宏伟,胡园,等. 多向锻造对M50钢一次碳化物破碎机制的影响[J]. 中国冶金202030(9):98-103., articleTitle=多向锻造对M50钢一次碳化物破碎机制的影响, refAbstract=null), Reference(id=1241451349511032999, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, doi=null, pmid=null, pmcid=null, year=2020, volume=30, issue=9, pageStart=98, pageEnd=103, url=null, language=null, rfNumber=[11], rfOrder=12, authorNames=WU Yucheng, JIANG Hongwei, HU Yuan, journalName=China Metallurgy, refType=null, unstructuredReference=WU YuchengJIANG HongweiHU Yuan,et al. Effect of multi-direction forging on carbide evolution of M50 steel[J]. China Metallurgy202030(9):98-103.(In Chinese), articleTitle=Effect of multi-direction forging on carbide evolution of M50 steel, refAbstract=null), Reference(id=1241451349594919083, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, doi=null, pmid=null, pmcid=null, year=2015, volume=110, issue=null, pageStart=126, pageEnd=133, url=null, language=null, rfNumber=[12], rfOrder=13, authorNames=DECOST B L, HOLM E A, journalName=Computational Materials Science, refType=null, unstructuredReference=DECOST B LHOLM E A.A computer vision approach for automated analysis and classification of microstructural image data[J].Computational Materials Science2015110:126-133., articleTitle=A computer vision approach for automated analysis and classification of microstructural image data, refAbstract=null), Reference(id=1241451349712359600, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, doi=null, pmid=null, pmcid=null, year=2021, volume=12, issue=1, pageStart=6272, pageEnd=null, url=null, language=null, rfNumber=[13], rfOrder=14, authorNames=DURMAZ A R, MÜLLER M, LEI B, journalName=Nature Communications, refType=null, unstructuredReference=DURMAZ A RMÜLLER MLEI B,et al. A deep learning approach for complex microstructure inference[J]. Nature Communications202112(1):6272., articleTitle=A deep learning approach for complex microstructure inference, refAbstract=null), Reference(id=1241451349825605814, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, doi=null, pmid=null, pmcid=null, year=2022, volume=162, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[14], rfOrder=15, authorNames=YANG J Y, KANG G Z, KAN Q H, journalName=International Journal of Fatigue, refType=null, unstructuredReference=YANG J YKANG G ZKAN Q H. A novel deep learning approach of multiaxial fatigue life-prediction with a self-attention mechanism characterizing the effects of loading history and varying temperature[J]. International Journal of Fatigue2022162:106851., articleTitle=A novel deep learning approach of multiaxial fatigue life-prediction with a self-attention mechanism characterizing the effects of loading history and varying temperature, refAbstract=null), Reference(id=1241451351322972344, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, doi=null, pmid=null, pmcid=null, year=2020, volume=32, issue=1, pageStart=33, pageEnd=43, url=null, language=null, rfNumber=[15], rfOrder=16, authorNames=李维刚, 谌竟成, 范丽霞, journalName=钢铁研究学报, refType=null, unstructuredReference=李维刚,谌竟成,范丽霞,等. 基于卷积神经网络的钢铁材料微观组织自动辨识[J]. 钢铁研究学报202032(1):33-43., articleTitle=基于卷积神经网络的钢铁材料微观组织自动辨识, refAbstract=null), Reference(id=1241451351411052732, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, doi=null, pmid=null, pmcid=null, year=2020, volume=32, issue=1, pageStart=33, pageEnd=43, url=null, language=null, rfNumber=[15], rfOrder=17, authorNames=LI Weigang, CHEN Jingcheng, FAN Lixia, journalName=Journal of Iron and Steel Research, refType=null, unstructuredReference=LI WeigangCHEN JingchengFAN Lixia,et al. Automatic identification of microstructure of iron and steel material based on convolutional neural network[J]. Journal of Iron and Steel Research202032(1):33-43.(In Chinese), articleTitle=Automatic identification of microstructure of iron and steel material based on convolutional neural network, refAbstract=null), Reference(id=1241451351499133120, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, doi=null, pmid=null, pmcid=null, year=2022, volume=60, issue=1, pageStart=43, pageEnd=47, url=null, language=null, rfNumber=[16], rfOrder=18, authorNames=段献宝, 何惠珍, 李平平, journalName=铁道车辆, refType=null, unstructuredReference=段献宝,何惠珍,李平平,等. 基于深度卷积神经网络的钢材微观组织分类识别[J]. 铁道车辆202260(1):43-47., articleTitle=基于深度卷积神经网络的钢材微观组织分类识别, refAbstract=null), Reference(id=1241451351612379331, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, doi=null, pmid=null, pmcid=null, year=2022, volume=60, issue=1, pageStart=43, pageEnd=47, url=null, language=null, rfNumber=[16], rfOrder=19, authorNames=DUAN Xianbao, HE Huizhen, LI Pingping, journalName=Rolling Stock, refType=null, unstructuredReference=DUAN XianbaoHE HuizhenLI Pingping,et al. Classification and identification of steel microstructure based on deep convolution neural network[J]. Rolling Stock202260(1):43-47.(In Chinese), articleTitle=Classification and identification of steel microstructure based on deep convolution neural network, refAbstract=null), Reference(id=1241451351729819850, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, doi=null, pmid=null, pmcid=null, year=2023, volume=41, issue=2, pageStart=78, pageEnd=84, url=null, language=null, rfNumber=[17], rfOrder=20, authorNames=苏晨, 任志俊, 范彪, journalName=轻工机械, refType=null, unstructuredReference=苏晨,任志俊,范彪,等. 基于注意力机制与ResNet的残余奥氏体评级研究[J]. 轻工机械202341(2):78-84., articleTitle=基于注意力机制与ResNet的残余奥氏体评级研究, refAbstract=null), Reference(id=1241451351847260364, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, doi=null, pmid=null, pmcid=null, year=2023, volume=41, issue=2, pageStart=78, pageEnd=84, url=null, language=null, rfNumber=[17], rfOrder=21, authorNames=SU Chen, REN Zhijun, FAN Biao, journalName=Light Industry Machinery, refType=null, unstructuredReference=SU ChenREN ZhijunFAN Biao,et al. Research on retained austenite rating based on attention mechanism and ResNet[J]. Light Industry Machinery202341(2):78-84.(In Chinese), articleTitle=Research on retained austenite rating based on attention mechanism and ResNet, refAbstract=null), Reference(id=1241451351973089491, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, doi=null, pmid=null, pmcid=null, year=2023, volume=45, issue=2, pageStart=447, pageEnd=453, url=null, language=null, rfNumber=[18], rfOrder=22, authorNames=彭凡, 邹司农, 任毅如, journalName=机械强度, refType=null, unstructuredReference=彭凡,邹司农,任毅如. 基于深度学习的复合材料螺栓连接失效预测[J]. 机械强度202345(2):447-453., articleTitle=基于深度学习的复合材料螺栓连接失效预测, refAbstract=null), Reference(id=1241451352077947093, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, doi=null, pmid=null, pmcid=null, year=2023, volume=45, issue=2, pageStart=447, pageEnd=453, url=null, language=null, rfNumber=[18], rfOrder=23, authorNames=PENG Fan, ZOU Sinong, REN Yiru, journalName=Journal of Mechanical Strength, refType=null, unstructuredReference=PENG FanZOU SinongREN Yiru. Failure prediction of bolted connection of composite materials based on deep learning[J]. Journal of Mechanical Strength202345(2):447-453.(In Chinese), articleTitle=Failure prediction of bolted connection of composite materials based on deep learning, refAbstract=null), Reference(id=1241451352178610393, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, doi=null, pmid=null, pmcid=null, year=2020, volume=42, issue=2, pageStart=386, pageEnd=397, url=null, language=null, rfNumber=[19], rfOrder=24, authorNames=HE K M, GKIOXARI G, DOLLAR P, journalName=IEEE Transactions on Pattern Analysis and Machine Intelligence, refType=null, unstructuredReference=HE K MGKIOXARI GDOLLAR P,et al. Mask R-CNN[J].IEEE Transactions on Pattern Analysis and Machine Intelligence202042(2):386-397., articleTitle=Mask R-CNN, refAbstract=null), Reference(id=1241451352304439520, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, doi=null, pmid=null, pmcid=null, year=2021, volume=9, issue=null, pageStart=107024, pageEnd=107032, url=null, language=null, rfNumber=[20], rfOrder=25, authorNames=WANG C Y, ZHONG C M, journalName=IEEE Access, refType=null, unstructuredReference=WANG C YZHONG C M. Adaptive feature pyramid networks for object detection[J]. IEEE Access20219:107024-107032., articleTitle=Adaptive feature pyramid networks for object detection, refAbstract=null), Reference(id=1241451352497377509, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, doi=null, pmid=null, pmcid=null, year=2020, volume=42, issue=5, pageStart=1024, pageEnd=1032, url=null, language=null, rfNumber=[21], rfOrder=26, authorNames=吴定海, 任国全, 王怀光, journalName=机械强度, refType=null, unstructuredReference=吴定海,任国全,王怀光,等. 基于卷积神经网络的机械故障诊断方法综述[J]. 机械强度202042(5):1024-1032., articleTitle=基于卷积神经网络的机械故障诊断方法综述, refAbstract=null), Reference(id=1241451352593846507, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, doi=null, pmid=null, pmcid=null, year=2020, volume=42, issue=5, pageStart=1024, pageEnd=1032, url=null, language=null, rfNumber=[21], rfOrder=27, authorNames=WU Dinghai, REN Guoquan, WANG Huaiguang, journalName=Journal of Mechanical Strength, refType=null, unstructuredReference=WU DinghaiREN GuoquanWANG Huaiguang,et al. The review of mechanical fault diagnosis methods based on convolutional neural network[J]. Journal of Mechanical Strength202042(5):1024-1032.(In Chinese), articleTitle=The review of mechanical fault diagnosis methods based on convolutional neural network, refAbstract=null), Reference(id=1241451352694509807, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, doi=null, pmid=null, pmcid=null, year=2015, volume=null, issue=null, pageStart=1, pageEnd=15, url=null, language=null, rfNumber=[22], rfOrder=28, authorNames=KINGMA D P, BA J L, journalName=null, refType=null, unstructuredReference=KINGMA D PBA J L. Adam:a method for stochastic optimization[C]// 3rd International Conference on Learning Representations,ICLR 2015-Conference Track Proceedings.Ithaca:ArXiv,2015:1-15., articleTitle=Adam:a method for stochastic optimization, refAbstract=null), Reference(id=1241451352807756021, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, doi=null, pmid=null, pmcid=null, year=2020, volume=8, issue=null, pageStart=67735, pageEnd=67744, url=null, language=null, rfNumber=[23], rfOrder=29, authorNames=HE G Q, HUO Y C, HE M Y, journalName=IEEE Access, refType=null, unstructuredReference=HE G QHUO Y CHE M Y,et al. A novel orthogonality loss for deep hierarchical multi-task learning[J]. IEEE Access20208:67735-67744., articleTitle=A novel orthogonality loss for deep hierarchical multi-task learning, refAbstract=null), Reference(id=1241451353021665533, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, doi=null, pmid=null, pmcid=null, year=2019, volume=29, issue=5, pageStart=1, pageEnd=5, url=null, language=null, rfNumber=[24], rfOrder=30, authorNames=高楚寒, 葛思楠, 李万明, journalName=中国冶金, refType=null, unstructuredReference=高楚寒,葛思楠,李万明,等. 高速钢碳化物偏析的研究现状[J].中国冶金201929(5):1-5., articleTitle=高速钢碳化物偏析的研究现状, refAbstract=null), Reference(id=1241451353109745921, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, doi=null, pmid=null, pmcid=null, year=2019, volume=29, issue=5, pageStart=1, pageEnd=5, url=null, language=null, rfNumber=[24], rfOrder=31, authorNames=GAO Chuhan, GE Sinan, LI Wanming, journalName=China Metallurgy, refType=null, unstructuredReference=GAO ChuhanGE SinanLI Wanming,et al. Research status of carbide segregation in high speed steel[J]. China Metallurgy201929(5):1-5.(In Chinese), articleTitle=Research status of carbide segregation in high speed steel, refAbstract=null)], funds=[Fund(id=1241451347506155590, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, awardId=52075271, language=EN, fundingSource=Natural Science Foundation of China(52075271), fundOrder=null, country=null), Fund(id=1241451347602624585, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, awardId=52075271, language=CN, fundingSource=国家自然科学基金项目(52075271), fundOrder=null, country=null), Fund(id=1241451347686510670, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, awardId=2022Z050, language=EN, fundingSource=Major Science and Technology Task Tackling Project of Ningbo(2022Z050), fundOrder=null, country=null), Fund(id=1241451347791368278, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, awardId=2022Z050, language=CN, fundingSource=宁波市重大科技任务攻关项目(2022Z050), fundOrder=null, country=null), Fund(id=1241451347908808796, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, awardId=CZ2022009, language=EN, fundingSource=Cixi Industry-Specific Technology Research and Development Project(CZ2022009), fundOrder=null, country=null), Fund(id=1241451347996889184, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, awardId=CZ2022009, language=CN, fundingSource=慈溪市行业共性技术攻关项目(CZ2022009), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1241451336408027781, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, xref=1., ext=[AuthorCompanyExt(id=1241451336420610695, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, companyId=1241451336408027781, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.Faculty of Mechanical Engineering and Mechanics, Ningbo University, Ningbo 315211, China), AuthorCompanyExt(id=1241451336428999305, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, companyId=1241451336408027781, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.宁波大学 机械工程与力学学院,宁波 315211)]), AuthorCompany(id=1241451337917977232, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, xref=2., ext=[AuthorCompanyExt(id=1241451337926365843, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, companyId=1241451337917977232, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.Part Rolling Key Laboratory of Zhejiang Province, Ningbo 315211, China), AuthorCompanyExt(id=1241451337934754452, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, companyId=1241451337917977232, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.浙江省零件轧制成形技术研究重点实验室,宁波 315211)]), AuthorCompany(id=1241451338048000669, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, xref=3., ext=[AuthorCompanyExt(id=1241451338056389279, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, companyId=1241451338048000669, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3.Ningbo Silver-ball Technology Co., Ltd., Ningbo 315207, China), AuthorCompanyExt(id=1241451338060583583, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, companyId=1241451338048000669, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3.宁波银球科技股份有限公司,宁波 315207)])], figs=[ArticleFig(id=1241451342598820721, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, language=EN, label=Fig.1, caption=Flow chart of the Mask R-CNN structure, figureFileSmall=n0yNfKW4MFaOmjTDj/Y+Eg==, figureFileBig=pNQFsIshUUDpiADNITE3yA==, tableContent=null), ArticleFig(id=1241451342728844156, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, language=CN, label=图1, caption=Mask R-CNN 结构流程图, figureFileSmall=n0yNfKW4MFaOmjTDj/Y+Eg==, figureFileBig=pNQFsIshUUDpiADNITE3yA==, tableContent=null), ArticleFig(id=1241451342863061901, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, language=EN, label=Fig.2, caption=Identity mapping unit, figureFileSmall=Gave/p/Y8Inei2zONXRrIQ==, figureFileBig=E2WJhGwQ3Z7+tgl/rRrpTQ==, tableContent=null), ArticleFig(id=1241451342959530898, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, language=CN, label=图2, caption=恒等映射单元, figureFileSmall=Gave/p/Y8Inei2zONXRrIQ==, figureFileBig=E2WJhGwQ3Z7+tgl/rRrpTQ==, tableContent=null), ArticleFig(id=1241451343081165720, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, language=EN, label=Fig.3, caption=SEM images of M50 bearing steel, figureFileSmall=yZ+NDeJvlXmoO9ZUYy/tMA==, figureFileBig=d4r+hk9rxF20FwaeV2hFBw==, tableContent=null), ArticleFig(id=1241451343198606241, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, language=CN, label=图3, caption=M50轴承钢的SEM图像, figureFileSmall=yZ+NDeJvlXmoO9ZUYy/tMA==, figureFileBig=d4r+hk9rxF20FwaeV2hFBw==, tableContent=null), ArticleFig(id=1241451343324435366, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, language=EN, label=Fig.4, caption=TEM-EDS images of M50 bearing steel,carbides’morphology and distribution of V,Mo,Cr,Fe element, figureFileSmall=gfF6U993Rjf+/tYPELZjyg==, figureFileBig=5Dy6JrAqizddKBmkut91aQ==, tableContent=null), ArticleFig(id=1241451343458653102, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, language=CN, label=图4, caption=M50轴承钢的TEM-EDS图像,碳化物形貌及V、Mo、Cr、Fe元素分布, figureFileSmall=gfF6U993Rjf+/tYPELZjyg==, figureFileBig=5Dy6JrAqizddKBmkut91aQ==, tableContent=null), ArticleFig(id=1241451343567705016, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, language=EN, label=Fig.5, caption=TEM images of M2C,MC and M23C6 and their diffraction patterns in M50 bearing steel, figureFileSmall=/uh0hEy4haoUcxxN79JF0A==, figureFileBig=S4wU4Mt/xClvSl7NA6UypQ==, tableContent=null), ArticleFig(id=1241451343668368317, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, language=CN, label=图5, caption=M50轴承钢中M2C、MC、M23C6的TEM图像及衍射花样, figureFileSmall=/uh0hEy4haoUcxxN79JF0A==, figureFileBig=S4wU4Mt/xClvSl7NA6UypQ==, tableContent=null), ArticleFig(id=1241451343810974663, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, language=EN, label=Fig.6, caption=Original SEM images of M50 bearing steel and their label images, figureFileSmall=3tgVCSTogSMZSIKiDxGmWg==, figureFileBig=wJMy1Ju+nRydU98HQHuJSg==, tableContent=null), ArticleFig(id=1241451343920026574, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, language=CN, label=图6, caption=M50轴承钢的SEM原图及标注图, figureFileSmall=3tgVCSTogSMZSIKiDxGmWg==, figureFileBig=wJMy1Ju+nRydU98HQHuJSg==, tableContent=null), ArticleFig(id=1241451344033272788, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, language=EN, label=Fig.7, caption=Three images of testing results, figureFileSmall=c5shLYUx6Li4fmrQKniExQ==, figureFileBig=a+SlMMOGmPDd3AISXtYuCg==, tableContent=null), ArticleFig(id=1241451344150713306, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, language=CN, label=图7, caption=3张测试结果图, figureFileSmall=c5shLYUx6Li4fmrQKniExQ==, figureFileBig=a+SlMMOGmPDd3AISXtYuCg==, tableContent=null), ArticleFig(id=1241451344247182304, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, language=EN, label=Fig.8, caption=Distribution histogram of equivalent diameters of MC,M2C and M23C6, figureFileSmall=v8awk9RLgS5HYxJ1tVKTFg==, figureFileBig=l+niJOMfhX5WLT2DNjtTjg==, tableContent=null), ArticleFig(id=1241451344389788646, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, language=CN, label=图8, caption=MC,M2C和M23C6的当量直径分布直方图, figureFileSmall=v8awk9RLgS5HYxJ1tVKTFg==, figureFileBig=l+niJOMfhX5WLT2DNjtTjg==, tableContent=null), ArticleFig(id=1241451344532394986, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, language=EN, label=Fig.9, caption=Distribution histogram of Ferret diameters of MC,M2C and M23C6, figureFileSmall=Uklk68MW5dEAfHrk8fcpuA==, figureFileBig=f/oGlbiAI4yI4KSwnIoXLA==, tableContent=null), ArticleFig(id=1241451344641446895, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, language=CN, label=图9, caption=MC、 M2C和M23C6的费雷特直径分布直方图, figureFileSmall=Uklk68MW5dEAfHrk8fcpuA==, figureFileBig=f/oGlbiAI4yI4KSwnIoXLA==, tableContent=null), ArticleFig(id=1241451344851161089, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, language=EN, label=Fig.10, caption=Learning rate of the Mask R-CNN, figureFileSmall=ki763chVgWLEuArE/yi/6A==, figureFileBig=9DCimy8XTTeb8xFrRm3W1Q==, tableContent=null), ArticleFig(id=1241451344972795910, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, language=CN, label=图10, caption=Mask R-CNN的学习率, figureFileSmall=ki763chVgWLEuArE/yi/6A==, figureFileBig=9DCimy8XTTeb8xFrRm3W1Q==, tableContent=null), ArticleFig(id=1241451345069264908, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, language=EN, label=Fig.11, caption=Loss value of the Mask R-CNN, figureFileSmall=3qCxheO0kaAb6hYlmjn6og==, figureFileBig=cw4G1CVMeAaL+rFFr2LoIA==, tableContent=null), ArticleFig(id=1241451345211871252, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, language=CN, label=图11, caption=Mask R-CNN的损失值, figureFileSmall=3qCxheO0kaAb6hYlmjn6og==, figureFileBig=cw4G1CVMeAaL+rFFr2LoIA==, tableContent=null), ArticleFig(id=1241451345320923163, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, language=EN, label=Fig.12, caption=PMAP of the Mask R-CNN, figureFileSmall=Lnhjmoru+ThPy2Ovp+NCgQ==, figureFileBig=J8qM/Y7BS98S39H5TSPt3A==, tableContent=null), ArticleFig(id=1241451346809901087, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, language=CN, label=图12, caption=Mask R-CNN的PMAP, figureFileSmall=Lnhjmoru+ThPy2Ovp+NCgQ==, figureFileBig=J8qM/Y7BS98S39H5TSPt3A==, tableContent=null), ArticleFig(id=1241451346939924516, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, language=EN, label=Tab.1, caption=

Confusion matrix

, figureFileSmall=null, figureFileBig=null, tableContent=
混淆矩阵
Confusion matrix
真实值True value
阳性Positive阴性Negative
预测值
Predicted value
阳性
Positive
真阳性
True positive
假阳性
False positive
阴性
Negative
假阴性
False negative
真阴性
True negative
), ArticleFig(id=1241451347015421992, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, language=CN, label=表1, caption=

混淆矩阵

, figureFileSmall=null, figureFileBig=null, tableContent=
混淆矩阵
Confusion matrix
真实值True value
阳性Positive阴性Negative
预测值
Predicted value
阳性
Positive
真阳性
True positive
假阳性
False positive
阴性
Negative
假阴性
False negative
真阴性
True negative
), ArticleFig(id=1241451347153834032, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, language=EN, label=Tab.2, caption=

Distribution of three kinds of carbides’ diameters

, figureFileSmall=null, figureFileBig=null, tableContent=
碳化物
Carbide
当量直径Equivalent diameter/ μm费雷特直径Ferret diameter/ μm
分布范围
Distribution range
最大值
Maximum value
平均值
Average value
分布范围
Distribution range
最大值
Maximum value
平均值
Average value
MC0~14.58141.170~16.02161.47
M2C0~5.1350.590~13.14130.96
M23C60~1.261.20.450~1.351.30.45
), ArticleFig(id=1241451347258691638, tenantId=1146029695717560320, journalId=1227999626482147330, articleId=1241408878966002130, language=CN, label=表2, caption=

3种碳化物的直径分布

, figureFileSmall=null, figureFileBig=null, tableContent=
碳化物
Carbide
当量直径Equivalent diameter/ μm费雷特直径Ferret diameter/ μm
分布范围
Distribution range
最大值
Maximum value
平均值
Average value
分布范围
Distribution range
最大值
Maximum value
平均值
Average value
MC0~14.58141.170~16.02161.47
M2C0~5.1350.590~13.14130.96
M23C60~1.261.20.450~1.351.30.45
)], attaches=null, journal=Journal(id=1227999351742652416, delFlag=0, nameCn=机械强度, nameEn=Journal of Mechanical Strength, nameHistory1=null, nameHistory2=null, issn=1001-9669, eissn=null, cn=41-1134/TH, coden=null, periodic=0, language=CN, oaType=null, ccby=null, superviseOffice=null, ownerOffice=null, pubOffice=null, editorOffice=null, officeType=null, aims=null, clcCode=null, officeProv=null, officeCity=null, officeAddr=null, officeZip=null, officeEmail=null, officePhone=null, editDirector=null, officeDirector=null, officeDirectorPhone=null, officeStaffNum=null, officeEmpNum=null, coverPicUrl=9ETNXOzwmuGm49pLRqXxWw==, journalPrice=null, startedYear=null, abbrevIsoEn=Journal of Mechanical Strength, journalRemark=null, publicationField=null, createdTime=1770707460585, updatedTime=1770707700588, createdBy=18614031015, updatedBy=13701087609, firstLetterCn=J, firstLetterEn=J, subjectCode=Engineering, subjectName=null, subjectCodeEn=Engineering, subjectNameEn=null, picCn=9ETNXOzwmuGm49pLRqXxWw==, picEn=sS2ogjwdwM8GMbFtuWTIkA==, jcr=null, cjcr=null, exts=[JournalExt(id=1228000358505578506, language=CN, name=机械强度, 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=1770707700611, updatedTime=1770707700611, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=https://journal.ids.fzyun.cn/auth/realms/journal/protocol/openid-connect/auth?client_id=journal-jxqd-author&redirect_uri=https%3A%2F%2Fjxqd.portal.founderss.cn%2Foauth%2Fcallback&response_type=code&scope=phone+openid+email+profile&state=aa1eff81-489d-4951, submissionEditorUrl=https://journal.ids.fzyun.cn/auth/realms/journal/protocol/openid-connect/auth?client_id=journal-portal&redirect_uri=https%3A%2F%2Fjournal.portal.founderss.cn%2Foauth%2Fcallback&response_type=code&scope=phone+openid+email+profile&state=df5d5e38-1d45-4fcd-b, submissionReviewUrl=https://journal.ids.fzyun.cn/auth/realms/journal/protocol/openid-connect/auth?client_id=journal-jxqd-author&redirect_uri=https%3A%2F%2Fjxqd.portal.founderss.cn%2Foauth%2Fcallback&response_type=code&scope=phone+openid+email+profile&state=49f73d27-439e-4d5b, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1228000358551715851, language=EN, name=Journal of Mechanical Strength, 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=1770707700622, updatedTime=1770707700622, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=https://journal.ids.fzyun.cn/auth/realms/journal/protocol/openid-connect/auth?client_id=journal-jxqd-author&redirect_uri=https%3A%2F%2Fjxqd.portal.founderss.cn%2Foauth%2Fcallback&response_type=code&scope=phone+openid+email+profile&state=aa1eff81-489d-4951, submissionEditorUrl=https://journal.ids.fzyun.cn/auth/realms/journal/protocol/openid-connect/auth?client_id=journal-portal&redirect_uri=https%3A%2F%2Fjournal.portal.founderss.cn%2Foauth%2Fcallback&response_type=code&scope=phone+openid+email+profile&state=df5d5e38-1d45-4fcd-b, submissionReviewUrl=https://journal.ids.fzyun.cn/auth/realms/journal/protocol/openid-connect/auth?client_id=journal-jxqd-author&redirect_uri=https%3A%2F%2Fjxqd.portal.founderss.cn%2Foauth%2Fcallback&response_type=code&scope=phone+openid+email+profile&state=49f73d27-439e-4d5b, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1227999626482147330, websiteList=[Website(id=1228000871984853626, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1227999626482147330, 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/jxqd/CN, language=CN, createTime=1770707823034, createBy=18614031015, updateTime=1770707851936, updateBy=18614031015, name=机械强度-中文, tplId=1146099689490845704, title=机械强度, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1228001259580486284, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1228000871984853626, code=articleTextType, value=kx, createTime=1770707915444, updateTime=1770707915444, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001259555320457, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1228000871984853626, code=banner, value=null, createTime=1770707915438, updateTime=1770707915438, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001259605652111, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1228000871984853626, code=grayFlag, value=0, createTime=1770707915450, updateTime=1770707915450, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001259542737544, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1228000871984853626, code=logo, value=https://castjournals.cast.org.cn/joweb/jxqd/CN/file/pic?fileId=wrginrTxTIens2Yn6gXaKA==, createTime=1770707915435, updateTime=1770707915435, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001259622429329, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1228000871984853626, code=minRunFlag, value=0, createTime=1770707915454, updateTime=1770707915454, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001259572097675, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1228000871984853626, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/jxqd/CN/file/pic, createTime=1770707915442, updateTime=1770707915442, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001259614040720, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1228000871984853626, code=silenceFlag, value=0, createTime=1770707915452, updateTime=1770707915452, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001259567903370, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1228000871984853626, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1770707915441, updateTime=1770707915441, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001259588874893, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1228000871984853626, code=themeColor, value=null, createTime=1770707915446, updateTime=1770707915446, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001259597263502, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1228000871984853626, code=themeStyle, value=null, createTime=1770707915448, updateTime=1770707915448, creator=18614031015, updator=18614031015)]), Website(id=1228000872056156796, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1227999626482147330, 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/jxqd/EN, language=EN, createTime=1770707823051, createBy=18614031015, updateTime=1770707871019, updateBy=18614031015, name=机械强度-英文, tplId=1146101810881728533, title=Journal of Mechanical Strength, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1228001314525868694, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1228000872056156796, code=articleTextType, value=kx, createTime=1770707928544, updateTime=1770707928544, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001314504897171, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1228000872056156796, code=banner, value=null, createTime=1770707928539, updateTime=1770707928539, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001314542645913, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1228000872056156796, code=grayFlag, value=0, createTime=1770707928548, updateTime=1770707928548, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001314496508562, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1228000872056156796, code=logo, value=https://castjournals.cast.org.cn/joweb/jxqd/EN/file/pic?fileId=wrginrTxTIens2Yn6gXaKA==, createTime=1770707928537, updateTime=1770707928537, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001314555228827, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1228000872056156796, code=minRunFlag, value=0, createTime=1770707928551, updateTime=1770707928551, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001314517480085, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1228000872056156796, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/jxqd/EN/file/pic, createTime=1770707928542, updateTime=1770707928542, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001314551034522, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1228000872056156796, code=silenceFlag, value=0, createTime=1770707928550, updateTime=1770707928550, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001314513285780, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1228000872056156796, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_en_623/, createTime=1770707928541, updateTime=1770707928541, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001314530062999, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1228000872056156796, code=themeColor, value=null, createTime=1770707928545, updateTime=1770707928545, creator=18614031015, updator=18614031015), WebsiteProps(id=1228001314538451608, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1228000872056156796, code=themeStyle, value=null, createTime=1770707928547, updateTime=1770707928547, creator=18614031015, updator=18614031015)])], journalTitle=机械强度, weixinUrl=null, journalUrl=https://www.jxqd.net.cn/, iacademicId=null, status=1, seqNo=null, journalTitleEn=Journal of Mechanical Strength, journalPhotoCn=9ETNXOzwmuGm49pLRqXxWw==, journalPhotoEn=sS2ogjwdwM8GMbFtuWTIkA==, journalFirstLetter=J, 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/jxqd/CN/10.16579/j.issn.1001.9669.2025.08.003, detailUrlEn=https://castjournals.cast.org.cn/joweb/jxqd/EN/10.16579/j.issn.1001.9669.2025.08.003, pdfUrlCn=https://castjournals.cast.org.cn/joweb/jxqd/CN/PDF/10.16579/j.issn.1001.9669.2025.08.003, pdfUrlEn=https://castjournals.cast.org.cn/joweb/jxqd/EN/PDF/10.16579/j.issn.1001.9669.2025.08.003, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于深度学习模型Mask R-CNN对M50轴承钢中碳化物的研究
收藏切换
PDF下载
孙瑞明 1, 2 , 李淑欣 1, 2 , 鲁思渊 1, 2 , 金永生 3 , 肖华海 3
机械强度 | 实验研究·测试技术 2025,47(8): 19-27
收起
收藏切换
机械强度 | 实验研究·测试技术 2025, 47(8): 19-27
基于深度学习模型Mask R-CNN对M50轴承钢中碳化物的研究
全屏
孙瑞明1, 2 , 李淑欣1, 2 , 鲁思渊1, 2, 金永生3, 肖华海3
作者信息
  • 1.宁波大学 机械工程与力学学院,宁波 315211
  • 2.浙江省零件轧制成形技术研究重点实验室,宁波 315211
  • 3.宁波银球科技股份有限公司,宁波 315207
  • 孙瑞明,男,1993年生,河南鹤壁人,硕士研究生;主要研究方向为机械结构强度;E-mail:

通讯作者:

李淑欣,女,1975年生,宁夏中卫人,博士,教授,博士研究生导师;主要研究方向为机械结构强度;E-mail:
Research on carbides in M50 bearing steel based on Mask R-CNN deep learning model
Ruiming SUN1, 2 , Shuxin LI1, 2 , Siyuan LU1, 2, Yongsheng JIN3, Huahai XIAO3
Affiliations
  • 1.Faculty of Mechanical Engineering and Mechanics, Ningbo University, Ningbo 315211, China
  • 2.Part Rolling Key Laboratory of Zhejiang Province, Ningbo 315211, China
  • 3.Ningbo Silver-ball Technology Co., Ltd., Ningbo 315207, China
出版时间: 2025-08-15 doi: 10.16579/j.issn.1001.9669.2025.08.003
文章导航
收藏切换

M50轴承钢中主要的碳化物类型为MC、M2C和M23C6。扫描电子显微镜(Scanning Electron Microscopy, SEM)下,3种碳化物的形状、尺寸和在材料中的分布存在明显的区别。有些碳化物的尺寸较大且分布不均匀。轴承受载过程中,这些碳化物会成为应力集中的区域,对轴承疲劳性能产生负面影响。为了高效地获得材料中的碳化物信息,提出一种改进的掩膜基于区域的卷积神经网络(Mask Region-based Convolutional Neural Network, Mask R-CNN)模型,可批量鉴别SEM图像中3种碳化物的种类,确定其尺寸大小及分布。网络模型输出的图像和数值结果显示,M50轴承钢中M2C型碳化物尺寸大且分布不均匀,但总体尺寸最大的MC型碳化物和尺寸最小的M23C6型碳化物分布相对均匀。

深度学习  /  Mask R-CNN  /  M50轴承钢  /  碳化物

The main types of carbides in M50 bearing steel are MC, M2C and M23C6. Under the scanning electron microscopy (SEM), they exhibit significant differences in the shape, size, and distribution. Some carbides have larger sizes and uneven distribution. They become areas of stress concentration under loading,which has a negative impact on the bearing fatigue performance. So an improved mask region-based convolutional neural network (Mask R-CNN) model was proposed which can batch identify the types of three kinds of carbides in SEM pictures, the diameters of carbides were measured, and the distribution of carbides was showed. The output images and histogram results show that the size of M2C carbide in M50 bearing steel is large and unevenly distributed, but the distribution of MC carbide with the largest size and M23C6 with the smallest size is reasonably uniform.

Deep learning  /  Mask R-CNN  /  M50 bearing steel  /  Carbide
孙瑞明, 李淑欣, 鲁思渊, 金永生, 肖华海. 基于深度学习模型Mask R-CNN对M50轴承钢中碳化物的研究. 机械强度, 2025 , 47 (8) : 19 -27 . DOI: 10.16579/j.issn.1001.9669.2025.08.003
Ruiming SUN, Shuxin LI, Siyuan LU, Yongsheng JIN, Huahai XIAO. Research on carbides in M50 bearing steel based on Mask R-CNN deep learning model[J]. Journal of Mechanical Strength, 2025 , 47 (8) : 19 -27 . DOI: 10.16579/j.issn.1001.9669.2025.08.003
M50轴承钢是一种高合金钢,具有优异的耐磨性、耐蚀性,广泛用于航空航天、船舶、汽车等领域[1]。该轴承钢主要成分为C、Cr、Mo、V、Ni等元素,其中V、Mo、Cr有利于碳化物的形成。碳化物和合金元素可提供二次硬化,使组织更加稳定[2-4]。碳化物按析出先后顺序分为一次碳化物和二次碳化物。一次碳化物在液态金属固化时形成,二次碳化物由固相转变析出。研究发现,M50轴承钢中存在较多尺寸偏大且分布不均匀的一次碳化物,其严重危害了其冲击韧性和疲劳寿命,不利于轴承的长期服役[5-7]。针对M50轴承钢中的碳化物展开了大量的研究[8]111822[9]161755[10]105-110发现,M50轴承钢中的一次碳化物多为MC型和M2C型,二次碳化物主要为M23C6[11]98-103。一次碳化物MC和M2C尺寸较大,二次碳化物M23C6尺寸相对较小。碳化物MC形状为类圆状或棒状,M2C形状为棒状或层片状[9]161755,M23C6为颗粒状。MC的元素中富含V,M2C富含Mo,M23C6富含Cr。扫描电子显微镜(Scanning Electron Microscopy, SEM)图片中MC比M23C6衬度深[10]107
近年来,在深度学习与材料研究的结合方面取得了一定的成果。DECOST等[12]使用视觉特征提取单元结合支持向量机(Support Vector Machine, SVM)算法对黄铜、青铜、球墨铸铁、灰铸铁、亚共析钢、可锻铸铁、高温合金等7种材料的微观组织进行分类识别,准确率达80%。DURMAZ等[13]6272使用不同的Unet模型,对复杂金相组织中的贝氏体进行识别分割,准确率超过90%。YANG等[14]使用全连接神经网络(Fully Connected Neural Network, FCNN)、长短期记忆网络(Long Short-Term Memory, LSTM)、注意力机制等拟合了不同材料的疲劳寿命曲线,寿命数据在拟合寿命曲线的2倍分散带以内。李维刚等[15]利用不同的深度学习模型自动识别钢铁中的铁素体、马氏体、珠光体等,在测试集中的准确率达到100%。段献宝等[16]使用3种神经网络,完成了对钢材微观组织的高效、准确识别,分类精度达到99.6%。苏晨等[17]78-84将注意力机制与ResNet结合对钢材中残余奥氏体进行识别并评级。彭凡等[18]使用深度学习对螺栓连接失效载荷进行了非线性拟合。
综合来看,深度神经网络在材料学科的应用仍以图片识别、曲线拟合为主,对图片中内容的定量分析较少。本文设计了一种改进的掩膜基于区域的卷积神经网络(Mask Region-based Convolutional Neural Network, Mask R-CNN),用以分析M50轴承钢的碳化物,可以同时实现如下功能:①识别SEM图片中的碳化物并确定其类别;②对SEM图片中的碳化物进行分割标记;③确定碳化物在图片中的占比;④统计图片中每个碳化物的尺寸,并输出碳化物的直径分布直方图。
Mask R-CNN模型是一种用于目标检测和实例分割的深度学习模型,是R-CNN系列模型的一种扩展,由HE等[19]386-397于2017年提出。结合待识别碳化物图片的特点,本文在原Mask R-CNN模型的基础上进行了一系列的修改,具体细节见下文。本文还在最后程序中加入了数据处理模块,可对识别到的碳化物进行量化统计。整体网络主要由Faster R-CNN Predictor和Mask Branch这2个分支组成,网络结构如图1所示。
结构中Backbone+FPN是特征提取模块。Backbone使用的是残差网络ResNet50。ResNet50中使用了恒等映射结构。恒等映射单元如图2所示。对应式(1),函数Fxlwl)的输出值可为0。当Fxlwl)=0时,就有xl+1=xl,即输出和输入相同,这样就实现了恒等映射。该结构保证了神经网络层数的增加,不会使训练出的结果变差。特征金字塔网络(Feature Pyramid Network, FPN)[20]能够在不同的尺寸上提取特征。原始输入的SEM图片经Backbone部分处理后,存在多次尺寸的变化,使用特征金字塔结构可以较好地弥补图片在尺寸变化时部分特征信息丢失的缺点,提高了模型的鲁棒性。
区域建议网络(Region Proposal Network, RPN)的作用是在图片的特定位置生成一系列预选边界框。
RoIAlign中RoI是Region of Interest的简写,即感兴趣区域。该模块的功能是将指定的边界框(来自RPN或者Fast R-CNN Predictor)先映射到Backbone+FPN生成的特征图上,之后将对应区域变换为特定的大小,最后对变换后的区域进行最大池化处理。Fast R-CNN Predictor模块使用的RoIAlign(使用的边界框来自RPN)将特征层处理后生成的图像大小是7×7。Mask Branch模块使用的RoIAlign(使用的边界框来自Fast R-CNN Predictor)将特征层处理后生成的图像的大小是14×14。14×14的图像可以在一定程度上保留更多和尺寸相关的特征信息,有利于对碳化物进行像素级的掩码分割。
Fast R-CNN Predictor模块用于执行目标分类、确定边界框回归参数,即确定输入的SEM图片中哪些区域是碳化物,将非碳化物区域确定为背景,同时确定碳化物的边界框的大小及位置。
Mask Branch模块用于生成每个目标的精确掩码,即在目标边界框的内部确定每一个像素属于何种类别,是MC、M2C、M23C6或者背景,以二值图像的形式表示出来。
最后,将Mask Branch生成的二值图像和Fast R-CNN Predictor生成的分类信息与边界框信息映射到原图上,得到具有碳化物类别信息、碳化物的边界框和碳化物像素分割信息的图像。
设定的神经网络的初始参数和数据处理方法直接影响训练的时间和最后的结果。在参考一些文献[13]6272[19]386-393[21]1025-1029和实践的基础上,对设定的参数、超参数、数据集的处理方法进行了如下思考。
迁移学习是深度学习中一个重要的方法。本文使用的Mask R-CNN结构较为复杂,若从0开始训练该网络,则需要较长的时间。迁移学习是将之前学习到的参数迁移到新的任务或领域中,从而改善新任务的学习效果,能在较短的时间内使网络收敛。迁移学习还可以减少数据需求[21]1028,提高模型的泛化能力,改善模型的表现等。通常情况下,迁移学习应用于两个相关但不同的任务,分别称为源任务和目标任务。
本文综合使用了特征提取和微调两种迁移学习方法,使用Coco数据集训练出的参数作为Backbone+FPN初始参数。Coco数据集的图片数量达328 000张,有82个类别,经该数据集训练出来的参数有较好的特征提取能力。设定前10个Epoch为预训练阶段,该阶段使Backbone+FPN参数不变,仅在训练中更新Fast R-CNN Predictor和Mask Branch的参数。当大于10个Epoch后,解除对Backbone+FPN参数的冻结,整体网络参数一起训练。
数据增强是深度学习中一种常用的技术,通过对原始数据进行一系列的变换和处理,生成新的训练样本,从而扩充训练数据集的规模和多样性。数据增强技术对输入数据进行随机变换,提高了模型的泛化能力和鲁棒性。本文使用的SEM图片共有240张,与常见的数据集,如ImageNet(100万张)、MS Coco(328 000张)、PASCAL VOC(11 540张)对比,可知本文数据集的数量是相对较少的。因此使用数据增强是必要的。DURMAZ等[13]6272使用数据增强的方法,用相对较少的图片完成了网络的训练,达到了预期的效果。
常见的数据增强技术有镜像翻转、随机裁剪、旋转和缩放、增加噪声、图像亮度和对比度调整等。本次研究的重点是图片中的碳化物种类和形状。在数据增强时,改变宽高比会明显地改变图片中碳化物的形状,改变颜色会影响原有的衬度,进而影响结果的准确性。因此,本文数据增强时仅采用水平翻转和垂直翻转,以保证碳化物的形状、衬度不变。
在深度学习中,传统的优化算法,如梯度下降使用固定的学习率,但对于复杂的深度神经网络,固定学习率可能不够有效。自适应学习率是一种根据模型训练过程中的情况自动调整学习率的技术,可以更加高效地训练模型,加速模型的收敛,提高模型的性能。
常见的自适应学习率方法包括:动量法、学习率衰减、AdaGrad、RMSprop、AdaDelta、Adam等。本次使用学习率衰减法,设定学习率随着训练次数的增加而减小。学习率越小,网络训练时参数变化越小,该做法保证了模型在训练到后期时的精度。本文将初始学习率设置为0.002,学习率的下限设为0.000 02。基于数据集图片的数量,本文选取的迭代次数为300。
混淆矩阵是深度学习中常用的评估模型性能的工具。混淆矩阵所包含的内容如表1所示。
混淆矩阵是一个二维矩阵,用于比较分类模型的预测结果与真实标注之间的差异。通过混淆矩阵,可以计算出各种性能指标,如准确率(Accuracy)、精确率(Precision)、召回率(Recall)等。其中Precision和Recall公式定义为
式中,PTP为真阳性数量;PFP为假阳性数量;PFN为假阴性数量。由其定义可知PPrecisionRRecall的值均小于1。以PPrecision值为纵坐标、RRecall值为横坐标作图,便构成了评价神经网络的PPrecision-RRecall曲线图。PPrecision-RRecall曲线下的面积用PAP(Average Precision,AP)表示,相关计算式为式(4);均值平均精度(Mean Average Precision, MAP)是所有类别的平均精度的均值,相关计算式为式(5)。
PPrecision-RRecall曲线下的面积越大,说明网络输出结果与标注图越匹配,即PMAP的值越大说明网络的性能越好,PMAP的上限为1,以PMAP为指标衡量神经网络具有综合性;因此,本文选取PMAP为网络的评价指标。
本文研究的M50轴承钢的化学成分(质量分数,%)为:0.81~0.85C,4.00~4.25Cr,4.00~4.50Mo,0.90~1.10V,≤0.15Ni,0.15~0.35Mn,≤0.25Si,≤0.25Co,≤0.25W,其余为Fe。材料的热处理工艺影响碳化物的产生及分布,本试验所用材料选取常规的热处理方法,具体工艺是:真空感应熔炼-自耗电极-真空自耗熔-自耗锭-高温均匀化-锻造-轧制棒材。所制成的坯料棒材的直径为65 mm,将Φ65 mm坯料经切割、车削、磨削等工艺制成Φ12 mm的试样轴,将试样轴切片、打磨、抛光、腐蚀后在扫描电子显微镜SU5000下观察,得到图3(a)所示的图片。图3(a)中的碳化物按外形可分为圆棒形、类圆形和颗粒形3种,分别对应图3(a)中的1、2、3。为进一步确定材料中碳化物的种类,将材料经离子减薄制成可用透射电子显微镜(Transmission Electron Microscope, TEM)JEM-F200观察的样品。样品在TEM中经能量色散谱(Energy Dispersive Spectroscopy, EDS)分析得到图4所示结果。由图4可知,圆棒形碳化物富含Mo,类圆形较大的碳化物富含V,相对较小的颗粒状碳化物富含Cr。初步判断3种碳化物分别为M2C、MC和M23C6。对相同形状的碳化物做衍射斑分析,结果如图5所示。标定结果显示,3种碳化物分别为M2C、MC和M23C6。上述结果也与文献[9]161755、文献[10]107-109、文献[11]101-103的描述相符。最终确定SEM图片的碳化物类型,如图3(b)所示。
使用SEM观察并采集图像,随机在表面的不同位置获取多张图片,每张图像的分辨率是1 280×960。受限于计算机的计算能力,输入神经网络的图片的尺寸不宜太大。在制作数据集时,去除原始图片中有文字的部分,将剩下的部分截取为两张,每张图片大小为512×512。然后结合图3(b)所示的结果,使用神经网络标注工具Labelme对图片中的碳化物进行手动标注。将衬度较浅、面积较小的颗粒状碳化物标注为M23C6。将衬度较深、面积相对较大的类圆形碳化物标注为MC。将圆棒形的碳化物标注为M2C。标注前后的图片如图6所示。标注时忽略特别细小的碳化物。标注完成后使用转化程序将标注好的数据集转化为json格式,用于之后对模型的训练。
本文使用的图片分为训练集、验证集和测试集,分别为160张、40张和40张。训练集和验证集都是带有标注的图片,用于前期对网络模型的训练。测试集用于最后对模型的检验。为了提高训练速度,本次使用图形处理器(Graphics Processing Unit, GPU)进行并行训练,优化器选用了Adam[22],使用的框架是PyTorch。经过8 h完成300个Epoch的训练。训练后网络达到了使用要求,结果见下文。
将测试集的40张图片输入训练好的网络,取置信度为50%,得到所有的图片处理结果,其中的3张结果如图7所示。图7中用不同的颜色标识出不同的碳化物,碳化物的种类在边界框的左上角标出。由图7可看出,网络能较为准确地识别出图中的碳化物并正确地确定其种类。由图7还可直观地看出3种碳化物在图片内的分布。图7(c)展示了在材料的局部区域多个M2C型碳化物集中出现的现象,该结果说明M50轴承钢材料内存在M2C分布不均的情况。
材料中碳化物的多少也是影响材料性能的一个关键因素。本文的模型以像素面积占比计算40张测试集图片中碳化物的面积占比,所得的结果为5%。相关表达式为
式中,NC为一张图片内属于碳化物的像素点的总数;NP为一张图片中像素点的总数。
碳化物的尺寸直接影响了材料的性能。明确碳化物的尺寸对分析材料的品质、判断材料的性能具有重要意义。本文的网络使用两种尺寸表示碳化物的大小,分别为当量直径和费雷特直径。
SEM图片中单个碳化物的当量直径计算式为
式中,N为1个碳化物的像素面积;I为图片比例尺。
网络能输出每个碳化物的当量直径。为了直观展示,本次将所有碳化物的直径以直方图的形式输出。使用测试集图片得到的当量直径分布直方图如图8所示。
图7中,每个碳化物的边界框的4个顶点都有相应的坐标,通过坐标可以计算边界框的长和宽。本文选取边界框中较长边作为对应碳化物的费雷特直径。基于此,可求得测试集40张图片中的3种碳化物的费雷特直径。用得到的3种碳化物的费雷特直径生成费雷特直径分布直方图,如图9所示。
改进的Mask R-CNN共进行了300轮的迭代,学习率和损失值分别反映了网络的训练精度和测试结果的准确度。图10所示为学习率随迭代次数变化的曲线,图11所示为损失值[23]随迭代次数变化的曲线。
前10个Epoch是预训练阶段,该阶段Backbone+FPN模块的参数保持不变,仅更新网络其他部分的参数。图10中,在第200个Epoch时学习率从0.002衰减到0.000 2,在第270个Epoch时学习率衰减为最小值0.000 02,之后保持不变。由图11可看出,在前50轮迭代时损失值快速下降。在第200个Epoch后损失值逐渐稳定,最后数值约为0.2。该损失值为分类损失、边界框损失、图片分割损失的平均值。损失值为0.2,该数值较小,满足使用要求。
图12所示为网络的PMAP值随着迭代次数的变化曲线。网络的MAP值在迭代了220个Epoch后趋于稳定,最后数值约为0.9,即平均精度达90%。该精确度达到了同类网络的较高水平[13]6272[17]83,满足实验室测试的精度要求。
图8图9分别展示了3种碳化物的当量直径和费雷特直径。从每一个直方图上看,在数量占比上,3种碳化物中,都是小直径的碳化物占比大,大直径的碳化物占比小。该结果能直观地看出材料中每种碳化物的细化情况,可帮助研究者判断材料的品质。将三种碳化物的两种直径进行对比,汇总结果如表2所示。对比同一种碳化物的2种直径可知,MC和M23C6的2种直径差异不大,M2C的2种直径差异明显。一个碳化物的当量直径和费雷特直径的差异越大,其宽高比越大,宽高比越大的碳化物越容易断裂[8]111822。由此可知,M2C更容易断裂,断裂的碳化物易成为材料裂纹的萌生点。碳化物发生断裂的频率与碳化物的尺寸、强度、形状相关[8]111822。考虑到3种碳化物外形的不规则性,相较于当量直径,费雷特直径能更准确地从数字上表达碳化物的大小。因此,在从尺寸和形状上判断碳化物的断裂难易性时,费雷特直径可作为判断依据。在同一类直径3种碳化物之间相互对比可知,MC和M2C的尺寸比M23C6大,且3种碳化物的直径最大值分别是16、13、1.3 μm。碳化物的尺寸越大,越容易引起局部应力集中,进而导致材料产生裂纹[24]。因此,较大的一次碳化物MC和M2C更容易引起材料内部应力集中,而M23C6的影响较小。综上所述,无论是同一种碳化物2类直径的对比还是同一类直径几种碳化物之间的对比,都能进一步获得材料中微观组织的信息,该信息可为材料的优化提供指导。
本文改进的Mask R-CNN使用训练集160张图片、验证集40张图片,经300轮迭代完成了模型的训练。用训练好的网络对测试集的40张SEM图片进行处理,得到了碳化物分割结果图和直径分布直方图。对输出的图像和数值结果进行分析,得到以下主要结论:
1)M50轴承钢的SEM图片中的碳化物MC、M2C、M23C6能被网络识别并标记,平均准确度为90%。
2)网络输出的碳化物的图片面积占比是5%,可以粗略推断本次研究的材料中碳化物的体积占比为5%。
3)直径分布直方图显示,M50轴承钢中一次碳化物MC和M2C的尺寸明显比M23C6的大。MC、M2C、M23C6的费雷特直径均值分别为1.47、0.96、0.45 μm。
本文验证了深度神经网络作为一种工具,既可以用来识别材料的微观组织,帮助研究者认识学习,也可以定量分析特定的微观组织,帮助研究者判断材料的品质。在分析或处理较多的数据时,深度神经网络明显具有准确、高效的优势。
  • 国家自然科学基金项目(52075271)
  • 宁波市重大科技任务攻关项目(2022Z050)
  • 慈溪市行业共性技术攻关项目(CZ2022009)
参考文献 引证文献
排序方式:
[1]
BHADESHIA H K D H. Steels for bearings[J]. Progress in Materials Science201257(2):268-435.
[2]
KINKUS T JOLSON G B. Microanalytical evaluation of a prototype stainless bearing steel[J]. Surface Science1992266(1/2/3):391-396.
[3]
BARROW A T WRIVERA-DÍAZ-DEL-CASTILLO P E J. Nanoprecipitation in bearing steels[J]. Acta Materialia201159(19):7155-7167.
[4]
KANG J HRIVERA-DÍAZ-DEL-CASTILLO P E J. Carbide dissolution in bearing steels[J]. Computational Materials Science201367:364-372.
[5]
GUETARD GTODA-CARABALLO IRIVERA-DÍAZ-DEL-CASTILLO P E J. Damage evolution around primary carbides under rolling contact fatigue in VIM-VAR M50[J]. International Journal of Fatigue201691:59-67.
[6]
GUAN JWANG L QZHANG Z Q,et al. Fatigue crack nucleation and propagation at clustered metallic carbides in M50 bearing steel[J]. Tribology International2018119:165-174.
[7]
JELITA RYDEL JTODA-CARABALLO IGUETARD G,et al.Understanding the factors controlling rolling contact fatigue damage in VIM-VAR M50 steel[J]. International Journal of Fatigue2018108:68-78.
[8]
DU N YLIU H HCAO Y F,et al. In situ investigation of the fracture of primary carbides and its mechanism in M50 steel[J]. Materials Characterization2022186:111822.
[9]
LIU W FGUO Y FCAO Y F,et al. Transformation behavior of primary MC and M2C carbides in Cr4Mo4V steel[J]. Journal of Alloys and Compounds2021889:161755.
[10]
侯志远,刘威峰,徐斌,等. 热加工过程中M50轴承钢一次碳化物的形成与演化[J]. 热加工工艺202453(1):105-110.
HOU ZhiyuanLIU WeifengXU Bin,et al. Formation and evolution of primary carbides in M50 bearing steel during hot working[J]. Hot Working Technology202453(1):105-110.(In Chinese)
[11]
吴玉成,姜宏伟,胡园,等. 多向锻造对M50钢一次碳化物破碎机制的影响[J]. 中国冶金202030(9):98-103.
WU YuchengJIANG HongweiHU Yuan,et al. Effect of multi-direction forging on carbide evolution of M50 steel[J]. China Metallurgy202030(9):98-103.(In Chinese)
[12]
DECOST B LHOLM E A.A computer vision approach for automated analysis and classification of microstructural image data[J].Computational Materials Science2015110:126-133.
[13]
DURMAZ A RMÜLLER MLEI B,et al. A deep learning approach for complex microstructure inference[J]. Nature Communications202112(1):6272.
[14]
YANG J YKANG G ZKAN Q H. A novel deep learning approach of multiaxial fatigue life-prediction with a self-attention mechanism characterizing the effects of loading history and varying temperature[J]. International Journal of Fatigue2022162:106851.
[15]
李维刚,谌竟成,范丽霞,等. 基于卷积神经网络的钢铁材料微观组织自动辨识[J]. 钢铁研究学报202032(1):33-43.
LI WeigangCHEN JingchengFAN Lixia,et al. Automatic identification of microstructure of iron and steel material based on convolutional neural network[J]. Journal of Iron and Steel Research202032(1):33-43.(In Chinese)
[16]
段献宝,何惠珍,李平平,等. 基于深度卷积神经网络的钢材微观组织分类识别[J]. 铁道车辆202260(1):43-47.
DUAN XianbaoHE HuizhenLI Pingping,et al. Classification and identification of steel microstructure based on deep convolution neural network[J]. Rolling Stock202260(1):43-47.(In Chinese)
[17]
苏晨,任志俊,范彪,等. 基于注意力机制与ResNet的残余奥氏体评级研究[J]. 轻工机械202341(2):78-84.
SU ChenREN ZhijunFAN Biao,et al. Research on retained austenite rating based on attention mechanism and ResNet[J]. Light Industry Machinery202341(2):78-84.(In Chinese)
[18]
彭凡,邹司农,任毅如. 基于深度学习的复合材料螺栓连接失效预测[J]. 机械强度202345(2):447-453.
PENG FanZOU SinongREN Yiru. Failure prediction of bolted connection of composite materials based on deep learning[J]. Journal of Mechanical Strength202345(2):447-453.(In Chinese)
[19]
HE K MGKIOXARI GDOLLAR P,et al. Mask R-CNN[J].IEEE Transactions on Pattern Analysis and Machine Intelligence202042(2):386-397.
[20]
WANG C YZHONG C M. Adaptive feature pyramid networks for object detection[J]. IEEE Access20219:107024-107032.
[21]
吴定海,任国全,王怀光,等. 基于卷积神经网络的机械故障诊断方法综述[J]. 机械强度202042(5):1024-1032.
WU DinghaiREN GuoquanWANG Huaiguang,et al. The review of mechanical fault diagnosis methods based on convolutional neural network[J]. Journal of Mechanical Strength202042(5):1024-1032.(In Chinese)
[22]
KINGMA D PBA J L. Adam:a method for stochastic optimization[C]// 3rd International Conference on Learning Representations,ICLR 2015-Conference Track Proceedings.Ithaca:ArXiv,2015:1-15.
[23]
HE G QHUO Y CHE M Y,et al. A novel orthogonality loss for deep hierarchical multi-task learning[J]. IEEE Access20208:67735-67744.
[24]
高楚寒,葛思楠,李万明,等. 高速钢碳化物偏析的研究现状[J].中国冶金201929(5):1-5.
GAO ChuhanGE SinanLI Wanming,et al. Research status of carbide segregation in high speed steel[J]. China Metallurgy201929(5):1-5.(In Chinese)
2025年第47卷第8期
PDF下载
69
33
引用本文
BibTeX
文章信息
doi: 10.16579/j.issn.1001.9669.2025.08.003
  • 接收时间:2023-11-23
  • 首发时间:2026-03-19
  • 出版时间:2025-08-15
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2023-11-23
  • 修回日期:2024-01-16
基金
Natural Science Foundation of China(52075271)
国家自然科学基金项目(52075271)
Major Science and Technology Task Tackling Project of Ningbo(2022Z050)
宁波市重大科技任务攻关项目(2022Z050)
Cixi Industry-Specific Technology Research and Development Project(CZ2022009)
慈溪市行业共性技术攻关项目(CZ2022009)
作者信息
    1.宁波大学 机械工程与力学学院,宁波 315211
    2.浙江省零件轧制成形技术研究重点实验室,宁波 315211
    3.宁波银球科技股份有限公司,宁波 315207

通讯作者:

李淑欣,女,1975年生,宁夏中卫人,博士,教授,博士研究生导师;主要研究方向为机械结构强度;E-mail:
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/jxqd/CN/10.16579/j.issn.1001.9669.2025.08.003
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