首页 期刊 论文 学科刊群 资讯 加盟 关于
EN
image
Article(id=1241838628876390410, tenantId=1146029695717560320, journalId=1241755870837649424, issueId=1241838624241681037, articleNumber=null, orderNo=null, doi=10.19636/j.cnki.cjsm42-1250/o3.2024.044, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1726329600000, receivedDateStr=2024-09-15, revisedDate=null, revisedDateStr=null, acceptedDate=null, acceptedDateStr=null, onlineDate=1774007001369, onlineDateStr=2026-03-20, pubDate=1740672000000, pubDateStr=2025-02-28, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1774007001369, onlineIssueDateStr=2026-03-20, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1774007001369, creator=13701087609, updateTime=1774007001369, updator=13701087609, issue=Issue{id=1241838624241681037, tenantId=1146029695717560320, journalId=1241755870837649424, year='2025', volume='46', issue='1', pageStart='1', pageEnd='148', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1774007000265, creator=13701087609, updateTime=1774007104623, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1241839062017966445, tenantId=1146029695717560320, journalId=1241755870837649424, issueId=1241838624241681037, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1241839062017966446, tenantId=1146029695717560320, journalId=1241755870837649424, issueId=1241838624241681037, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=105, endPage=116, ext={EN=ArticleExt(id=1241838629144825868, articleId=1241838628876390410, tenantId=1146029695717560320, journalId=1241755870837649424, language=EN, title=A Study on Constraint-Related Fracture Toughness Prediction Based on Random Forest Algorithm and Data Enhancement Strategies, columnId=1241831201674171363, journalTitle=Chinese Journal of Solid Mechanics, columnName=Research Papers, runingTitle=null, highlight=null, articleAbstract=

The study of data-driven predictions for constraint-related fracture toughness is an interdisciplinary scientific problem relevant to mechanics, mechanical engineering, as well as computer science and technology, and is of great significance for accurate structural integrity assessment. This research focused on nuclear power steel A508. The predictive capabilities of four algorithms, namely the K-nearest neighbors (KNN) regression, kernel regression (KR), linear regression (LR), and random forest (RF) regression, for constraint-related fracture toughness predictions were investigated. The RF algorithm outperformed the others, while the KR algorithm had the least effective predictions. The prediction accuracy ranked as follows: RF>LR>KNN>KR. Furthermore, based on the RF algorithm, data under plane strain conditions were added for data enhancement, enabling the prediction and verification of constraint-related fracture toughness for single-edge notch bending (SENB) specimens. The validated model was successfully transplanted to single-edge notch tension (SENT), compact tension (CT), and central crack tension (CCT) specimens. Results indicated that the RF algorithm with data augmentation improved prediction accuracy and capability, particularly at boundary points. The RF-based model, enhanced with additional data strategies, demonstrated strong generalization across different specimen types. For SENB and CT specimens, bending loads dominate at the crack tip; thus, altering a/W and B/W enhances restraint. For SENT and CCT specimens, where shear loads predominate at the crack tip, adjusting a and B proves more effective. Finally, a unified, high-accuracy prediction model was developed by incorporating sample category features using the RF algorithm and data enhancement strategies.

, correspAuthors=Jie Yang, 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=Kangzhong Shan, Xiaoxiao Wang, Fang Liu, Yuanyuan Cui, Jie Yang), CN=ArticleExt(id=1241838635796992177, articleId=1241838628876390410, tenantId=1146029695717560320, journalId=1241755870837649424, language=CN, title=基于随机森林算法和数据增强策略的拘束相关断裂韧性预测研究, columnId=1241831201896469478, journalTitle=固体力学学报, columnName=研究论文, runingTitle=null, highlight=null, articleAbstract=

选用核电用钢A508为研究对象，对K近邻回归（KNN）、核回归（KR）、线性回归（LR）和随机森林回归（RE）四种算法拘束相关断裂韧性的预测能力进行了考察，发现四种算法对拘束相关断裂韧性的预测效果为RE>LR>KNN>KR. 进一步，基于RE算法，在数据中加入了平面应变状态下的数据进行数据增强，对单边缺口弯曲（SENB）试样的拘束相关断裂韧性进行了预测与验证. 并基于验证过的模型，向单边裂纹拉伸（SENT）、紧凑拉伸（CT）和中心裂纹拉伸（CCT）试样进行了移植. 结果表明：通过添加数据增强策略，试样在边界点处的断裂韧性预测能力得到有效提高，预测结果更加准确，基于RE算法并添加数据增强策略的模型具有较好的泛化能力. 最后，在基于RE算法和数据增强的基础上，加入试样类别这一特征，构建了准确度较高的统一预测模型.

, correspAuthors=杨杰, authorNote=null, correspAuthorsNote=
**E-mail：
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=WhArZZ7MRl4GeKEP54xDcg==, magXml=oArbzopTNbl6B+mRmAyeUA==, pdfUrl=null, pdf=/ntBlXiNLtH9FHzSZt/aWA==, pdfFileSize=5710999, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=cZDcTT/1OLg/l7xsVeS8yg==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=dz7b3vTYGEYpP7G4Oykswg==, mapNumber=null, authorCompany=null, fund=null, authors=null, authorsList=单康中, 王骁晓, 刘芳, 崔元元, 杨杰)}, authors=[Author(id=1241838637831229651, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, 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=1241838637940281562, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, authorId=1241838637831229651, language=EN, stringName=Kangzhong Shan, firstName=Kangzhong, middleName=null, lastName=Shan, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1Shanghai Key Laboratory of Multiphase Flow and Heat Transfer in Power Engineering, School of Energy and Power Engineering, University of Shanghai for Science and Technology, Shanghai, 200093, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1241838638045139167, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, authorId=1241838637831229651, language=CN, stringName=单康中, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1上海理工大学能源与动力工程学院，上海市动力工程多相流动与传热重点实验室，上海，200093, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1241838636036067513, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, xref=1, ext=[AuthorCompanyExt(id=1241838636044456122, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, companyId=1241838636036067513, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1Shanghai Key Laboratory of Multiphase Flow and Heat Transfer in Power Engineering, School of Energy and Power Engineering, University of Shanghai for Science and Technology, Shanghai, 200093), AuthorCompanyExt(id=1241838636052844731, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, companyId=1241838636036067513, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1上海理工大学能源与动力工程学院，上海市动力工程多相流动与传热重点实验室，上海，200093)])]), Author(id=1241838638141608162, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, 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=1241838638233882853, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, authorId=1241838638141608162, language=EN, stringName=Xiaoxiao Wang, firstName=Xiaoxiao, middleName=null, lastName=Wang, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2Key Laboratory of Pressure Systems and Safety, Ministry of Education, East China University of Science and Technology, Shanghai, 200237, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1241838638393266409, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, authorId=1241838638141608162, language=CN, stringName=王骁晓, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2华东理工大学承压系统与安全教育部重点实验室，上海，200237, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1241838637529239747, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, xref=2, ext=[AuthorCompanyExt(id=1241838637533434052, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, companyId=1241838637529239747, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2Key Laboratory of Pressure Systems and Safety, Ministry of Education, East China University of Science and Technology, Shanghai, 200237), AuthorCompanyExt(id=1241838637541822662, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, companyId=1241838637529239747, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2华东理工大学承压系统与安全教育部重点实验室，上海，200237)])]), Author(id=1241838638565232882, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, 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=1241838638670090487, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, authorId=1241838638565232882, language=EN, stringName=Fang Liu, firstName=Fang, middleName=null, lastName=Liu, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3School of Mechanical Engineering, University of Shanghai for Science and Technology, Shanghai, 200093, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1241838638791725308, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, authorId=1241838638565232882, language=CN, stringName=刘芳, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3上海理工大学机械工程学院，上海，200093, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1241838637692817613, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, xref=3, ext=[AuthorCompanyExt(id=1241838637701206221, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, companyId=1241838637692817613, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3School of Mechanical Engineering, University of Shanghai for Science and Technology, Shanghai, 200093), AuthorCompanyExt(id=1241838637709594830, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, companyId=1241838637692817613, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3上海理工大学机械工程学院，上海，200093)])]), Author(id=1241838638925943039, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, 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=1241838639014023426, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, authorId=1241838638925943039, language=EN, stringName=Yuanyuan Cui, firstName=Yuanyuan, middleName=null, lastName=Cui, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3School of Mechanical Engineering, University of Shanghai for Science and Technology, Shanghai, 200093, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1241838639097909508, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, authorId=1241838638925943039, language=CN, stringName=崔元元, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3上海理工大学机械工程学院，上海，200093, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1241838637692817613, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, xref=3, ext=[AuthorCompanyExt(id=1241838637701206221, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, companyId=1241838637692817613, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3School of Mechanical Engineering, University of Shanghai for Science and Technology, Shanghai, 200093), AuthorCompanyExt(id=1241838637709594830, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, companyId=1241838637692817613, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3上海理工大学机械工程学院，上海，200093)])]), Author(id=1241838639198572810, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, orderNo=4, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=yangjie@usst.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1241838639278264589, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, authorId=1241838639198572810, language=EN, stringName=Jie Yang, firstName=Jie, middleName=null, lastName=Yang, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, **, address=1Shanghai Key Laboratory of Multiphase Flow and Heat Transfer in Power Engineering, School of Energy and Power Engineering, University of Shanghai for Science and Technology, Shanghai, 200093, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1241838639349567760, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, authorId=1241838639198572810, language=CN, stringName=杨杰, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, **, address=1上海理工大学能源与动力工程学院，上海市动力工程多相流动与传热重点实验室，上海，200093, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1241838636036067513, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, xref=1, ext=[AuthorCompanyExt(id=1241838636044456122, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, companyId=1241838636036067513, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1Shanghai Key Laboratory of Multiphase Flow and Heat Transfer in Power Engineering, School of Energy and Power Engineering, University of Shanghai for Science and Technology, Shanghai, 200093), AuthorCompanyExt(id=1241838636052844731, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, companyId=1241838636036067513, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1上海理工大学能源与动力工程学院，上海市动力工程多相流动与传热重点实验室，上海，200093)])])], keywords=[Keyword(id=1241838639483785493, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, language=EN, orderNo=1, keyword=constraint), Keyword(id=1241838639588643096, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, language=EN, orderNo=2, keyword=fracture toughness), Keyword(id=1241838639706083612, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, language=EN, orderNo=3, keyword=machine learning), Keyword(id=1241838639810941216, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, language=EN, orderNo=4, keyword=random forest algorithm), Keyword(id=1241838639899021603, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, language=EN, orderNo=5, keyword=data enhancement), Keyword(id=1241838639966130470, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, language=CN, orderNo=1, keyword=拘束), Keyword(id=1241838640112931114, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, language=CN, orderNo=2, keyword=断裂韧性), Keyword(id=1241838640213594414, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, language=CN, orderNo=3, keyword=机器学习), Keyword(id=1241838640305869107, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, language=CN, orderNo=4, keyword=随机森林算法), Keyword(id=1241838640431698230, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, language=CN, orderNo=5, keyword=数据增强)], refs=[Reference(id=1241838647079670242, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, doi=null, pmid=null, pmcid=null, year=1993, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=Brocks W, Schmitt W, journalName=Proceedings of the 1993 Conference on Constraint Effects in Fracture: Theory and Applications, refType=null, unstructuredReference=Brocks W, Schmitt W. Second parameter in J-R curves: constraint or triaxiality in: Proceedings of the 1993 Conference on Constraint Effects in Fracture: Theory and Applications[C], ASTM, Dallas, TX, USA, 1993., articleTitle=Second parameter in J-R curves: constraint or triaxiality, refAbstract=null), Reference(id=1241838647213887975, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, doi=null, pmid=null, pmcid=null, year=2023, volume=40, issue=01, pageStart=30, pageEnd=37, url=null, language=null, rfNumber=[2], rfOrder=1, authorNames=张经伟, 林嘉铭, 谈建平, 郭子键, 刘康林, journalName=压力容器, refType=null, unstructuredReference=张经伟, 林嘉铭, 谈建平, 郭子键, 刘康林. 试样几何尺寸对347L材料断裂性能的影响[J]. 压力容器, 2023, 40(01): 30-37., articleTitle=试样几何尺寸对347L材料断裂性能的影响, refAbstract=null), Reference(id=1241838647280996846, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, doi=null, pmid=null, pmcid=null, year=2023, volume=40, issue=01, pageStart=30, pageEnd=37, url=null, language=null, rfNumber=[2], rfOrder=2, authorNames=Zhang J W, Lin J M, Tan J P, Guo Z J, Lin K L, journalName=Pressure Vessel Technology, refType=null, unstructuredReference=(Zhang J W, Lin J M, Tan J P, Guo Z J, Lin K L. Effect of specimen geometries on fracture toughness of 347L materials[J]. Pressure Vessel Technology, 2023, 40(01): 30-37. (in Chinese)), articleTitle=Effect of specimen geometries on fracture toughness of 347L materials, refAbstract=null), Reference(id=1241838647364882927, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, doi=null, pmid=null, pmcid=null, year=2023, volume=44, issue=02, pageStart=385, pageEnd=393, url=null, language=null, rfNumber=[3], rfOrder=3, authorNames=张宏, 吴锴, 冯庆善, 隋永莉, 刘啸奔, 杨悦, 杨叠, 戴联双, 王东营, 王冲, journalName=石油学报, refType=null, unstructuredReference=张宏, 吴锴, 冯庆善, 隋永莉, 刘啸奔, 杨悦, 杨叠, 戴联双, 王东营, 王冲. 高钢级管道环焊缝断裂韧性与裂尖拘束关系[J]. 石油学报, 2023, 44(02): 385-393., articleTitle=高钢级管道环焊缝断裂韧性与裂尖拘束关系, refAbstract=null), Reference(id=1241838647444574706, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, doi=null, pmid=null, pmcid=null, year=2023, volume=44, issue=02, pageStart=385, pageEnd=393, url=null, language=null, rfNumber=[3], rfOrder=4, authorNames=Zhang H, Wu K, Feng Q S, Sui Y L, Liu X B, Yang Y, Yang D, Dai L S, Wang D Y, Wang C, journalName=Acta Petrolei Sinica, refType=null, unstructuredReference=(Zhang H, Wu K, Feng Q S, Sui Y L, Liu X B, Yang Y, Yang D, Dai L S, Wang D Y, Wang C. Relationship between fracture toughness and crack tip constraint of high-strength pipe girth welds[J]. Acta Petrolei Sinica, 2023, 44(02): 385-393. (in Chinese)), articleTitle=Relationship between fracture toughness and crack tip constraint of high-strength pipe girth welds, refAbstract=null), Reference(id=1241838647549432309, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, doi=null, pmid=null, pmcid=null, year=2021, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[4], rfOrder=5, authorNames=孙彤, journalName=null, refType=null, unstructuredReference=孙彤. 考虑面内/面外拘束的G20Mn5QT铸钢材料断裂韧性研究[D]. 天津大学, 2021., articleTitle=考虑面内/面外拘束的G20Mn5QT铸钢材料断裂韧性研究, refAbstract=null), Reference(id=1241838647629124087, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, doi=null, pmid=null, pmcid=null, year=2021, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[4], rfOrder=6, authorNames=Sun T, journalName=null, refType=null, unstructuredReference=(Sun T. Research on Fracture Toughness of G20Mn5QT Cast Steel ConsideringIn-plane and Out-of-plane Constrain[D]. Tianjin University, 2021. (in Chinese)), articleTitle=Research on Fracture Toughness of G20Mn5QT Cast Steel ConsideringIn-plane and Out-of-plane Constrain, refAbstract=null), Reference(id=1241838647759147517, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, doi=null, pmid=null, pmcid=null, year=2024, volume=130, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[5], rfOrder=7, authorNames=Huang X, Xie Q, Li S L, Qi H Y, Yang X G, Shi D Q, journalName=Theoretical and Applied Fracture Mechanics, refType=null, unstructuredReference=Huang X, Xie Q, Li S L, Qi H Y, Yang X G, Shi D Q. Novel framework for predicting constraint effects on fracture toughness using an elastic-plastic phase field model and modified boundary layer formulations[J]. Theoretical and Applied Fracture Mechanics, 2024, 130: 104279., articleTitle=Novel framework for predicting constraint effects on fracture toughness using an elastic-plastic phase field model and modified boundary layer formulations, refAbstract=null), Reference(id=1241838647847227903, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, doi=null, pmid=null, pmcid=null, year=2016, volume=4, issue=5, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[6], rfOrder=8, authorNames=Agrawal A, Choudhary A, journalName=APL Materials, refType=null, unstructuredReference=Agrawal A, Choudhary A. Perspective: Materials informatics and big data: Realization of the “fourth paradigm” of science in materials science[J]. APL Materials, 2016, 4(5): 053208., articleTitle=Perspective: Materials informatics and big data: Realization of the “fourth paradigm” of science in materials science, refAbstract=null), Reference(id=1241838647956279813, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, doi=null, pmid=null, pmcid=null, year=2019, volume=2, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[7], rfOrder=9, authorNames=Schleder G R, Padilha A C M, Acosta C M, Costa M, Fazzio A, journalName=Journal of Physics: Materials, refType=null, unstructuredReference=Schleder G R, Padilha A C M, Acosta C M, Costa M, Fazzio A. From DFT to machine learning: recent approaches to materials science - a review[J]. Journal of Physics: Materials, 2019, 2: 032001., articleTitle=From DFT to machine learning: recent approaches to materials science - a review, refAbstract=null), Reference(id=1241838648040165899, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, doi=null, pmid=null, pmcid=null, year=2018, volume=54, issue=12, pageStart=115, pageEnd=124, url=null, language=null, rfNumber=[8], rfOrder=10, authorNames=赵申坤, 姜潮, 龙湘云, journalName=机械工程学报, refType=null, unstructuredReference=赵申坤, 姜潮, 龙湘云. 一种基于数据驱动和贝叶斯理论的机械系统剩余寿命预测方法[J]. 机械工程学报, 2018, 54(12): 115-124., articleTitle=一种基于数据驱动和贝叶斯理论的机械系统剩余寿命预测方法, refAbstract=null), Reference(id=1241838648136634895, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, doi=null, pmid=null, pmcid=null, year=2018, volume=54, issue=12, pageStart=115, pageEnd=124, url=null, language=null, rfNumber=[8], rfOrder=11, authorNames=Zhao S K, Jiang C, Long X Y, journalName=Journal of Mechanical Engineering, refType=null, unstructuredReference=(Zhao S K, Jiang C, Long X Y. Remaining useful life estimation of mechanical systems based on the data-driven method and bayesian theory[J]. Journal of Mechanical Engineering, 2018, 54(12): 115-124. (in Chinese)), articleTitle=Remaining useful life estimation of mechanical systems based on the data-driven method and bayesian theory, refAbstract=null), Reference(id=1241838648224715284, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, doi=null, pmid=null, pmcid=null, year=2020, volume=57, issue=null, pageStart=113, pageEnd=122, url=null, language=null, rfNumber=[9], rfOrder=12, authorNames=Liu Y L, Niu C, Wang Z, Wang Z, Gan Y, Zhu Y, Sun S H, Shen T, journalName=Journal of Materials Science & Technology, refType=null, unstructuredReference=Liu Y L, Niu C, Wang Z, Wang Z, Gan Y, Zhu Y, Sun S H, Shen T. Machine learning in materials genome initiative: A review[J]. Journal of Materials Science & Technology, 2020, 57: 113-122., articleTitle=Machine learning in materials genome initiative: A review, refAbstract=null), Reference(id=1241838648337961501, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, doi=null, pmid=null, pmcid=null, year=2023, volume=117, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[10], rfOrder=13, authorNames=Ma E H, Shin S H, Choi W J, Byun J M, Hwang B C, journalName=International Journal of Refractory Metals and Hard Materials, refType=null, unstructuredReference=Ma E H, Shin S H, Choi W J, Byun J M, Hwang B C. Machine learning approach for predicting the fracture toughness of Nb-Si based alloys[J]. International Journal of Refractory Metals and Hard Materials, 2023, 117: 106420., articleTitle=Machine learning approach for predicting the fracture toughness of Nb-Si based alloys, refAbstract=null), Reference(id=1241838648434430499, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, doi=null, pmid=null, pmcid=null, year=2024, volume=298, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[11], rfOrder=14, authorNames=Albaijan I, Samadi H, Mahmood Z M F, Mahmoodzadeh A, Fakhri D, Ibrahim H H, Ouni E H M, journalName=Engineering Fracture Mechanics, refType=null, unstructuredReference=Albaijan I, Samadi H, Mahmood Z M F, Mahmoodzadeh A, Fakhri D, Ibrahim H H, Ouni E H M. Evaluation of concrete's fracture toughness under an acidic environment condition using advanced machine learning algorithms[J]. Engineering Fracture Mechanics, 2024, 298: 109948., articleTitle=Evaluation of concrete's fracture toughness under an acidic environment condition using advanced machine learning algorithms, refAbstract=null), Reference(id=1241838648522510891, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, doi=null, pmid=null, pmcid=null, year=2023, volume=19, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[12], rfOrder=15, authorNames=Hu X J, Liao D, Ma D D, Xie S L, Xie N, Hu H B, Gong X N, journalName=Case Studies in Construction Materials, refType=null, unstructuredReference=Hu X J, Liao D, Ma D D, Xie S L, Xie N, Hu H B, Gong X N. Machine learning models for predicting rock fracture toughness at different temperature conditions[J]. Case Studies in Construction Materials, 2023, 19: e02622., articleTitle=Machine learning models for predicting rock fracture toughness at different temperature conditions, refAbstract=null), Reference(id=1241838648627368496, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, doi=null, pmid=null, pmcid=null, year=2022, volume=61, issue=2, pageStart=205, pageEnd=212, url=null, language=null, rfNumber=[13], rfOrder=16, authorNames=肖立志, journalName=石油物探, refType=null, unstructuredReference=肖立志. 机器学习数据驱动与机理模型融合及可解释性问题[J]. 石油物探, 2022, 61(2): 205-212., articleTitle=机器学习数据驱动与机理模型融合及可解释性问题, refAbstract=null), Reference(id=1241838648707060275, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, doi=null, pmid=null, pmcid=null, year=2022, volume=61, issue=2, pageStart=205, pageEnd=212, url=null, language=null, rfNumber=[13], rfOrder=17, authorNames=Xiao L Z, journalName=Geophysical Prospecting for Petroleum, refType=null, unstructuredReference=(Xiao L Z. The fusion of data-driven machine learning with mechanism models and interpretability issues[J]. Geophysical Prospecting for Petroleum, 2022, 61(2): 205-212. (in Chinese)), articleTitle=The fusion of data-driven machine learning with mechanism models and interpretability issues, refAbstract=null), Reference(id=1241838648841278010, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, doi=null, pmid=null, pmcid=null, year=2021, volume=3, issue=null, pageStart=422, pageEnd=440, url=null, language=null, rfNumber=[14], rfOrder=18, authorNames=Karniadakis G E, Kevrekidis I G, Lu L, Perdikaris P, Wang S, Yang L, journalName=Nature Reviews Physics, refType=null, unstructuredReference=Karniadakis G E, Kevrekidis I G, Lu L, Perdikaris P, Wang S, Yang L. Physics-informed machine learning[J]. Nature Reviews Physics, 2021, 3: 422-440., articleTitle=Physics-informed machine learning, refAbstract=null), Reference(id=1241838648920969790, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, doi=null, pmid=null, pmcid=null, year=2017, volume=29, issue=10, pageStart=2318, pageEnd=2331, url=null, language=null, rfNumber=[15], rfOrder=19, authorNames=Karpatne A, Atluri G, Faghmous J H, Steinbach M, Banerjee A, Ganguly A, Shekhar S, Samatova N, Kumar V, journalName=IEEE Transactions on Knowledge and Data Engineering, refType=null, unstructuredReference=Karpatne A, Atluri G, Faghmous J H, Steinbach M, Banerjee A, Ganguly A, Shekhar S, Samatova N, Kumar V. Theory-guided data science: A new paradigm for scientific discovery from data[J]. IEEE Transactions on Knowledge and Data Engineering, 2017, 29(10): 2318-2331., articleTitle=Theory-guided data science: A new paradigm for scientific discovery from data, refAbstract=null), Reference(id=1241838649021633091, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, doi=null, pmid=null, pmcid=null, year=2022, volume=163, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[16], rfOrder=20, authorNames=Yang J Y, Kang G Z, Kan Q H, journalName=International Journal of Fatigue, refType=null, unstructuredReference=Yang J Y, Kang G Z, Kan Q H. Rate-dependent multiaxial life prediction for polyamide-6 considering ratchetting: Semi-empirical and physics-informed machine learning models[J]. International Journal of Fatigue, 2022, 163: 107086., articleTitle=Rate-dependent multiaxial life prediction for polyamide-6 considering ratchetting: Semi-empirical and physics-informed machine learning models, refAbstract=null), Reference(id=1241838649126490694, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, doi=null, pmid=null, pmcid=null, year=2014, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[17], rfOrder=21, authorNames=杨杰, journalName=null, refType=null, unstructuredReference=杨杰. 面内/面外统一拘束参数及其与材料及焊接接头断裂韧性的关联[D]. 华东理工大学, 2014., articleTitle=面内/面外统一拘束参数及其与材料及焊接接头断裂韧性的关联, refAbstract=null), Reference(id=1241838649269097032, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, doi=null, pmid=null, pmcid=null, year=2014, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[17], rfOrder=22, authorNames=Yang J, journalName=null, refType=null, unstructuredReference=(Yang J. Unified Characterization Parameter of In-plane and Out-of Plane Constraint and Its Correlation with Fracture Toughness of Materials and Welded Joints[D]. East China University of Science and Technology, 2014. (in Chinese)), articleTitle=Unified Characterization Parameter of In-plane and Out-of Plane Constraint and Its Correlation with Fracture Toughness of Materials and Welded Joints, refAbstract=null), Reference(id=1241838649378148942, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, doi=null, pmid=null, pmcid=null, year=2013, volume=36, issue=6, pageStart=504, pageEnd=514, url=null, language=null, rfNumber=[18], rfOrder=23, authorNames=Yang J, Wang G Z, Xuan F Z, Tu S T, journalName=Fatigue & Fracture of Engineering Materials & Structures, refType=null, unstructuredReference=Yang J, Wang G Z, Xuan F Z, Tu S T. Unified characterisation of in-plane and out-of-plane constraint based on crack-tip equivalent plastic strain[J]. Fatigue & Fracture of Engineering Materials & Structures, 2013, 36(6): 504-514., articleTitle=Unified characterisation of in-plane and out-of-plane constraint based on crack-tip equivalent plastic strain, refAbstract=null), Reference(id=1241838649474617936, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, doi=null, pmid=null, pmcid=null, year=2014, volume=37, issue=2, pageStart=132, pageEnd=145, url=null, language=null, rfNumber=[19], rfOrder=24, authorNames=Yang J, Wang G Z, Xuan F Z, Tu S T, journalName=Fatigue & Fracture of Engineering Materials & Structures, refType=null, unstructuredReference=Yang J, Wang G Z, Xuan F Z, Tu S T. Unified correlation of in-plane and out-of-plane constraints with fracture toughness[J]. Fatigue & Fracture of Engineering Materials & Structures, 2014, 37(2): 132-145., articleTitle=Unified correlation of in-plane and out-of-plane constraints with fracture toughness, refAbstract=null)], funds=[Fund(id=1241838646958035421, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, awardId=52375154; 52311530067, language=CN, fundingSource=国家自然科学基金项目(52375154; 52311530067), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1241838636036067513, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, xref=1, ext=[AuthorCompanyExt(id=1241838636044456122, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, companyId=1241838636036067513, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1Shanghai Key Laboratory of Multiphase Flow and Heat Transfer in Power Engineering, School of Energy and Power Engineering, University of Shanghai for Science and Technology, Shanghai, 200093), AuthorCompanyExt(id=1241838636052844731, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, companyId=1241838636036067513, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1上海理工大学能源与动力工程学院，上海市动力工程多相流动与传热重点实验室，上海，200093)]), AuthorCompany(id=1241838637529239747, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, xref=2, ext=[AuthorCompanyExt(id=1241838637533434052, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, companyId=1241838637529239747, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2Key Laboratory of Pressure Systems and Safety, Ministry of Education, East China University of Science and Technology, Shanghai, 200237), AuthorCompanyExt(id=1241838637541822662, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, companyId=1241838637529239747, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2华东理工大学承压系统与安全教育部重点实验室，上海，200237)]), AuthorCompany(id=1241838637692817613, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, xref=3, ext=[AuthorCompanyExt(id=1241838637701206221, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, companyId=1241838637692817613, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3School of Mechanical Engineering, University of Shanghai for Science and Technology, Shanghai, 200093), AuthorCompanyExt(id=1241838637709594830, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, companyId=1241838637692817613, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3上海理工大学机械工程学院，上海，200093)])], figs=[ArticleFig(id=1241838642012950844, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, language=EN, label=Fig.1, caption=Schematic diagram of four specimens[17-19], figureFileSmall=UoE3iAoGu/lYV/b7weQiag==, figureFileBig=cZDcTT/1OLg/l7xsVeS8yg==, tableContent=null), ArticleFig(id=1241838642222666049, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, language=CN, label=图1, caption=四种试样的示意图[17-19], figureFileSmall=UoE3iAoGu/lYV/b7weQiag==, figureFileBig=cZDcTT/1OLg/l7xsVeS8yg==, tableContent=null), ArticleFig(id=1241838642491101513, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, language=EN, label=Fig.2, caption=The constructing process of a decision tree based on random forest (RE) algorithm, figureFileSmall=ftUT2I3KXLng7eNiS2PDUw==, figureFileBig=UBzHQXVnaj1UDDQarvTs2A==, tableContent=null), ArticleFig(id=1241838642558210381, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, language=CN, label=图2, caption=随机森林（RE）算法决策树的构建过程, figureFileSmall=ftUT2I3KXLng7eNiS2PDUw==, figureFileBig=UBzHQXVnaj1UDDQarvTs2A==, tableContent=null), ArticleFig(id=1241838642629513551, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, language=EN, label=Fig.3, caption=Comparison of prediction results of four machine learning algorithms, figureFileSmall=MnBjIaaP6qUeVsmb6HjJfg==, figureFileBig=pkf8uagFGX0cdCfnD3HCjQ==, tableContent=null), ArticleFig(id=1241838642709205335, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, language=CN, label=图3, caption=四种机器学习算法预测结果的对比, figureFileSmall=MnBjIaaP6qUeVsmb6HjJfg==, figureFileBig=pkf8uagFGX0cdCfnD3HCjQ==, tableContent=null), ArticleFig(id=1241838642780508509, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, language=EN, label=Fig.4, caption=Comparison of the prediction results of four machine learning algorithms for SENT (a), CT (b) and CCT specimens (c), figureFileSmall=OoeX/61Eu4pboD6Db9xDxQ==, figureFileBig=KFYgNIq6AhnyhQj7CGFjOw==, tableContent=null), ArticleFig(id=1241838642889560418, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, language=CN, label=图4, caption=SENT（a）、CT（b）和CCT试样（c）四种机器学习算法预测结果的对比, figureFileSmall=OoeX/61Eu4pboD6Db9xDxQ==, figureFileBig=KFYgNIq6AhnyhQj7CGFjOw==, tableContent=null), ArticleFig(id=1241838642965057895, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, language=EN, label=Fig.5, caption=Comparison of prediction results for SENB specimens with different in-plane constraints before and after data enhancement, figureFileSmall=XyPke4am8C4Y34y7LpAcgQ==, figureFileBig=tNkz4uyyXHOEzsM4t5ICvQ==, tableContent=null), ArticleFig(id=1241838643048943978, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, language=CN, label=图5, caption=不同面内拘束SENB试样数据增强前后预测结果对比, figureFileSmall=XyPke4am8C4Y34y7LpAcgQ==, figureFileBig=tNkz4uyyXHOEzsM4t5ICvQ==, tableContent=null), ArticleFig(id=1241838643162190194, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, language=EN, label=Fig.6, caption=Comparison of prediction results for SENB specimens with different out-of-plane constraints before and after data enhancement, figureFileSmall=du8eZjLBX1on3gsHI8TdYg==, figureFileBig=YSfl+usRWryvg8Uj7Tsa9A==, tableContent=null), ArticleFig(id=1241838643225104757, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, language=CN, label=图6, caption=不同面外拘束SENB试样数据增强前后预测结果对比, figureFileSmall=du8eZjLBX1on3gsHI8TdYg==, figureFileBig=YSfl+usRWryvg8Uj7Tsa9A==, tableContent=null), ArticleFig(id=1241838643342545275, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, language=EN, label=Fig.7, caption=Verification of prediction results when in-plane and out-of-plane constraints change simultaneously, figureFileSmall=jVuvxEJaUTLCI7V3r7LLMQ==, figureFileBig=nW29GF8A4KtEwdQU8EBRBw==, tableContent=null), ArticleFig(id=1241838643485151619, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, language=CN, label=图7, caption=面内、面外拘束同时变化时的预测结果验证, figureFileSmall=jVuvxEJaUTLCI7V3r7LLMQ==, figureFileBig=nW29GF8A4KtEwdQU8EBRBw==, tableContent=null), ArticleFig(id=1241838643594203524, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, language=EN, label=Fig.8, caption=The importance ranking of key characteristic quantities of SENB specimens, figureFileSmall=dbk5sDNq8mpHzGBVK05WHg==, figureFileBig=uASeAsLWtVfhfnI2+8Y6FA==, tableContent=null), ArticleFig(id=1241838643669701000, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, language=CN, label=图8, caption=SENB试样关键特征量重要性排序, figureFileSmall=dbk5sDNq8mpHzGBVK05WHg==, figureFileBig=uASeAsLWtVfhfnI2+8Y6FA==, tableContent=null), ArticleFig(id=1241838643761975695, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, language=EN, label=Fig.9, caption=Comparison of prediction results for SENT specimens before and after data enhancement, figureFileSmall=NxamXGWgl5OoloUBoxAIgQ==, figureFileBig=ISQiQfv1NlIuwwYg0BrZbw==, tableContent=null), ArticleFig(id=1241838643875221906, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, language=CN, label=图9, caption=SENT试样数据增强前后预测结果对比, figureFileSmall=NxamXGWgl5OoloUBoxAIgQ==, figureFileBig=ISQiQfv1NlIuwwYg0BrZbw==, tableContent=null), ArticleFig(id=1241838643996856725, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, language=EN, label=Fig.10, caption=The importance ranking of key characteristic quantities of SENT specimens, figureFileSmall=XpTBN/oo8gXmQ+8FuQz5EA==, figureFileBig=ccZLx7LVhpafrhey6ZbC4Q==, tableContent=null), ArticleFig(id=1241838644068159897, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, language=CN, label=图10, caption=SENT试样关键特征量重要性排序, figureFileSmall=XpTBN/oo8gXmQ+8FuQz5EA==, figureFileBig=ccZLx7LVhpafrhey6ZbC4Q==, tableContent=null), ArticleFig(id=1241838644160434589, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, language=EN, label=Fig.11, caption=Comparison of prediction results for CT specimens before and after data enhancement, figureFileSmall=yg6XIBCVzoCcXYn2oXenDQ==, figureFileBig=t5v80MTqdFiYuyGV5KSVmw==, tableContent=null), ArticleFig(id=1241838644244320675, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, language=CN, label=图11, caption=CT试样数据增强前后预测结果对比, figureFileSmall=yg6XIBCVzoCcXYn2oXenDQ==, figureFileBig=t5v80MTqdFiYuyGV5KSVmw==, tableContent=null), ArticleFig(id=1241838644298846629, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, language=EN, label=Fig.12, caption=The importance ranking of key characteristic quantities of CT specimens, figureFileSmall=H/5mopQqKeRflDy+h5+G1g==, figureFileBig=GBDT3YTaH/NpdoOCJR9UxA==, tableContent=null), ArticleFig(id=1241838644378538408, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, language=CN, label=图12, caption=CT试样关键特征量重要性排序, figureFileSmall=H/5mopQqKeRflDy+h5+G1g==, figureFileBig=GBDT3YTaH/NpdoOCJR9UxA==, tableContent=null), ArticleFig(id=1241838644441452972, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, language=EN, label=Fig.13, caption=Comparison of prediction results for CCT specimens before and after data enhancement, figureFileSmall=PLBDHuenPTwyETpP4XfxbA==, figureFileBig=/Hm/mmglXyP54hwDsaUHgg==, tableContent=null), ArticleFig(id=1241838644525339056, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, language=CN, label=图13, caption=CCT试样数据增强前后预测结果对比, figureFileSmall=PLBDHuenPTwyETpP4XfxbA==, figureFileBig=/Hm/mmglXyP54hwDsaUHgg==, tableContent=null), ArticleFig(id=1241838644621808053, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, language=EN, label=Fig.14, caption=The importance ranking of key characteristic quantities of CCT specimens, figureFileSmall=uDDjTipGTJ5QFpHavzRQ3g==, figureFileBig=EbJ205F1OENB3YEXx2YGqw==, tableContent=null), ArticleFig(id=1241838644730859960, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, language=CN, label=图14, caption=CCT试样关键特征量重要性排序, figureFileSmall=uDDjTipGTJ5QFpHavzRQ3g==, figureFileBig=EbJ205F1OENB3YEXx2YGqw==, tableContent=null), ArticleFig(id=1241838644823134652, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, language=EN, label=Fig.15, caption=Prediction results of different specimens in the unified model, figureFileSmall=DiJpx8Z06YtA4Yb4w+VneQ==, figureFileBig=vvR2sOjWyR8OYhgY7PySbQ==, tableContent=null), ArticleFig(id=1241838644927992257, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, language=CN, label=图15, caption=统一模型中不同试样的预测结果, figureFileSmall=DiJpx8Z06YtA4Yb4w+VneQ==, figureFileBig=vvR2sOjWyR8OYhgY7PySbQ==, tableContent=null), ArticleFig(id=1241838646425358790, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, language=EN, label=Table 1, caption=

Number of datasets for different specimens

, figureFileSmall=null, figureFileBig=null, tableContent=
SpecimensNumbers
SENB18
SENT20
CT10
CCT20
), ArticleFig(id=1241838646534410699, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, language=CN, label=表1, caption=

不同试样数据集的数量

, figureFileSmall=null, figureFileBig=null, tableContent=
SpecimensNumbers
SENB18
SENT20
CT10
CCT20
), ArticleFig(id=1241838646605713867, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, language=EN, label=Table 2, caption=

The correlation of feature

, figureFileSmall=null, figureFileBig=null, tableContent=
a/W B/W B W a
a/W1.000000-0.048381-0.047423-0.0048819319960.
B/W-0.0483811.0000000.929033-0.106963-0.140845
B-0.0474230.9290331.0000000.111798039838-0.
W-0.004881-0.1069630.1117981.0000000.219458
a0.931996-0.140845-0.0398380.2194581.000000
), ArticleFig(id=1241838646697988560, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, language=CN, label=表2, caption=

特征相关性

, figureFileSmall=null, figureFileBig=null, tableContent=
a/W B/W B W a
a/W1.000000-0.048381-0.047423-0.0048819319960.
B/W-0.0483811.0000000.929033-0.106963-0.140845
B-0.0474230.9290331.0000000.111798039838-0.
W-0.004881-0.1069630.1117981.0000000.219458
a0.931996-0.140845-0.0398380.2194581.000000
), ArticleFig(id=1241838646794457554, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, language=EN, label=Table 3, caption=

Comparison of the fitting coefficients r2 of the four algorithms

, figureFileSmall=null, figureFileBig=null, tableContent=
Model r2
RE0.96495
KNN0.48469
KR-0.003487
LR0.71528
), ArticleFig(id=1241838646857372118, tenantId=1146029695717560320, journalId=1241755870837649424, articleId=1241838628876390410, language=CN, label=表3, caption=

四种算法拟合系数r2对比

, figureFileSmall=null, figureFileBig=null, tableContent=
Model r2
RE0.96495
KNN0.48469
KR-0.003487
LR0.71528
)], 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/o3.2024.044, detailUrlEn=https://castjournals.cast.org.cn/joweb/gtlxxb/EN/10.19636/j.cnki.cjsm42-1250/o3.2024.044, pdfUrlCn=https://castjournals.cast.org.cn/joweb/gtlxxb/CN/PDF/10.19636/j.cnki.cjsm42-1250/o3.2024.044, pdfUrlEn=https://castjournals.cast.org.cn/joweb/gtlxxb/EN/PDF/10.19636/j.cnki.cjsm42-1250/o3.2024.044, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于随机森林算法和数据增强策略的拘束相关断裂韧性预测研究
收藏切换
PDF下载
单康中 1 , 王骁晓 2 , 刘芳 3 , 崔元元 3 , 杨杰 1, **
固体力学学报 | 研究论文 2025,46(1): 105-116
收起
收藏切换
固体力学学报 | 研究论文 2025, 46(1): 105-116
基于随机森林算法和数据增强策略的拘束相关断裂韧性预测研究
全屏
单康中1, 王骁晓2, 刘芳3, 崔元元3, 杨杰1, **
作者信息
  • 1上海理工大学能源与动力工程学院，上海市动力工程多相流动与传热重点实验室，上海，200093
  • 2华东理工大学承压系统与安全教育部重点实验室，上海，200237
  • 3上海理工大学机械工程学院，上海，200093

通讯作者:

A Study on Constraint-Related Fracture Toughness Prediction Based on Random Forest Algorithm and Data Enhancement Strategies
Kangzhong Shan1, Xiaoxiao Wang2, Fang Liu3, Yuanyuan Cui3, Jie Yang1, **
Affiliations
  • 1Shanghai Key Laboratory of Multiphase Flow and Heat Transfer in Power Engineering, School of Energy and Power Engineering, University of Shanghai for Science and Technology, Shanghai, 200093
  • 2Key Laboratory of Pressure Systems and Safety, Ministry of Education, East China University of Science and Technology, Shanghai, 200237
  • 3School of Mechanical Engineering, University of Shanghai for Science and Technology, Shanghai, 200093
出版时间: 2025-02-28 doi: 10.19636/j.cnki.cjsm42-1250/o3.2024.044
文章导航
收藏切换
摘要
收起

选用核电用钢A508为研究对象，对K近邻回归（KNN）、核回归（KR）、线性回归（LR）和随机森林回归（RE）四种算法拘束相关断裂韧性的预测能力进行了考察，发现四种算法对拘束相关断裂韧性的预测效果为RE>LR>KNN>KR. 进一步，基于RE算法，在数据中加入了平面应变状态下的数据进行数据增强，对单边缺口弯曲（SENB）试样的拘束相关断裂韧性进行了预测与验证. 并基于验证过的模型，向单边裂纹拉伸（SENT）、紧凑拉伸（CT）和中心裂纹拉伸（CCT）试样进行了移植. 结果表明：通过添加数据增强策略，试样在边界点处的断裂韧性预测能力得到有效提高，预测结果更加准确，基于RE算法并添加数据增强策略的模型具有较好的泛化能力. 最后，在基于RE算法和数据增强的基础上，加入试样类别这一特征，构建了准确度较高的统一预测模型.

拘束  /  断裂韧性  /  机器学习  /  随机森林算法  /  数据增强

The study of data-driven predictions for constraint-related fracture toughness is an interdisciplinary scientific problem relevant to mechanics, mechanical engineering, as well as computer science and technology, and is of great significance for accurate structural integrity assessment. This research focused on nuclear power steel A508. The predictive capabilities of four algorithms, namely the K-nearest neighbors (KNN) regression, kernel regression (KR), linear regression (LR), and random forest (RF) regression, for constraint-related fracture toughness predictions were investigated. The RF algorithm outperformed the others, while the KR algorithm had the least effective predictions. The prediction accuracy ranked as follows: RF>LR>KNN>KR. Furthermore, based on the RF algorithm, data under plane strain conditions were added for data enhancement, enabling the prediction and verification of constraint-related fracture toughness for single-edge notch bending (SENB) specimens. The validated model was successfully transplanted to single-edge notch tension (SENT), compact tension (CT), and central crack tension (CCT) specimens. Results indicated that the RF algorithm with data augmentation improved prediction accuracy and capability, particularly at boundary points. The RF-based model, enhanced with additional data strategies, demonstrated strong generalization across different specimen types. For SENB and CT specimens, bending loads dominate at the crack tip; thus, altering a/W and B/W enhances restraint. For SENT and CCT specimens, where shear loads predominate at the crack tip, adjusting a and B proves more effective. Finally, a unified, high-accuracy prediction model was developed by incorporating sample category features using the RF algorithm and data enhancement strategies.

constraint  /  fracture toughness  /  machine learning  /  random forest algorithm  /  data enhancement
单康中, 王骁晓, 刘芳, 崔元元, 杨杰. 基于随机森林算法和数据增强策略的拘束相关断裂韧性预测研究. 固体力学学报, 2025 , 46 (1) : 105 -116 . DOI: 10.19636/j.cnki.cjsm42-1250/o3.2024.044
Kangzhong Shan, Xiaoxiao Wang, Fang Liu, Yuanyuan Cui, Jie Yang. A Study on Constraint-Related Fracture Toughness Prediction Based on Random Forest Algorithm and Data Enhancement Strategies[J]. Chinese Journal of Solid Mechanics, 2025 , 46 (1) : 105 -116 . DOI: 10.19636/j.cnki.cjsm42-1250/o3.2024.044
正文
收起
0　引言
收起
拘束可以看作结构对裂纹尖端区域材料塑性变形的阻碍，包括面内拘束和面外拘束. 面内拘束受裂纹扩展方向上结构尺寸的影响，面外拘束则受与裂尖平面相平行方向上结构尺寸的影响. 拘束显著影响着材料的断裂行为，拘束的丧失会导致材料断裂韧性的增加[1]. 为进行准确的结构完整性评定，需要考虑拘束对材料断裂韧性的影响.
在过去的几十年里，针对拘束对断裂韧性的影响已进行了很多研究. 近几年，张经伟等[2]对紧凑拉伸（CT）试样在不同厚度及裂纹长度下的断裂韧性进行了试验研究，并通过有限元分析了上述试样的拘束水平，建立了表观断裂韧度与拘束参数Q的关联方程. 张宏等[3]基于细观损伤力学理论，采用数值模拟方法建立了环焊缝裂纹扩展阻力数值计算模型，针对低强、等强以及高强3种焊缝强度匹配条件，分别计算了面内、面外拘束耦合下以裂纹尖端张开位移（CTOD）为表征的环焊缝断裂韧性，并比较了使用不同拘束参数来描述断裂韧性与拘束关联的合理性. 孙彤等[4]采用理论分析、宏观试验、数值模拟相结合的方法，探究了面内、面外拘束对G20Mn5QT铸钢断裂韧性的影响，并建立了拘束与该材料断裂韧性之间的关联. Huang等[5]建立了一个利用弹塑性相场模型和改进的边界层公式预测拘束效应对断裂韧性影响的新框架.
随着科学的发展，科学研究在历经经验科学、理论科学、计算科学三个范式后，如今已迈入数据驱动科学范式[6,7]. 以机器学习为主的数据驱动方法正在被广泛应用于各个领域[8,9]. 在断裂韧性预测领域，Ma等[10]基于采集的Nb-Si基合金数据，利用机器学习模型分析了Nb-Si基合金室温断裂韧性与合金元素的相关性. Ibrahim等[11]基于中心直切口巴西圆盘（CSNBD）测试生成的420个数据集，提出了15种有监督和无监督学习算法，对混凝土的断裂韧性进行了估算. 并通过与试验结果的对比，评估了所应用模型的性能和准确性. Hu等[12]使用了六种机器学习模型（支持向量机（SVM）、随机森林（RE）、反向传播神经网络（BPNN）、反向传播-粒子群优化（BP-PSO）、卷积神经网络（CNN）和径向基函数神经网络（RBE））预测了岩石在不同温度下的断裂韧性. 可以发现，机器学习在断裂韧性预测中的应用研究还不多，且在研究中并没有考虑拘束的影响.
此外，虽然数据驱动方法正在被广泛应用，但囿于决策的透明度和结果的可解释性，数据驱动机器学习模型尚难以部署到一些性能要求高的关键领域[13]. 在最近的研究中，一些学者将数据驱动与机理驱动相结合，通过增加边界条件对模型参数进行约束，以达到增强数据驱动可解释性、提高泛化能力、得到符合物理规律预测结果的效果[14-16]. 然而，目前结合机理驱动的方法仍处于探究阶段，且对边界条件的要求较为苛刻，数据机理双驱动下的融合建模和合理解释仍然是学者们面临的一个难题.
鉴于此，本文选用核电用钢A508为研究对象，首先考察了K邻近回归（KNN）、核回归（KR）、线性回归（LR）和RE回归四种算法对拘束相关断裂韧性的预测能力，在筛选出预测结果最好的算法后，基于该算法，对不同试样的拘束相关断裂韧性进行了预测. 进一步，通过添加数据增强策略，对单边缺口弯曲（SENB）试样的拘束相关断裂韧性进行了预测与验证，并将验证过的模型向单边裂纹拉伸（SENT）、CT和中心裂纹拉伸（CCT）试样进行了移植. 最后，在基于RE算法和数据增强的基础上，加入试样类别特征，构建了准确度较高的统一模型，实现了不同试样准确的拘束相关断裂韧性预测.
1　数据来源及机器学习算法
收起
1.1　不同试样的拘束相关断裂韧性
本文从文献[17-19]中获取了A508钢在不同拘束下的断裂韧性. 这些断裂韧性分别在不同试样中获得，包括CT、SENB、SENT及CCT试样. 针对每一种试样，通过改变裂纹尺寸（裂纹长度a、裂纹长度与试样宽度的比值a/W）达到改变面内拘束的目的，通过改变试样厚度（试样厚度B、试样厚度与试样宽度的比值B/W、平面应变状态）达到改变面外拘束的目的. 四种试样的示意图如图1所示，不同试样数据集的数量如表1所示.
1.2　四种机器学习算法
1.2.1　KNN算法
KNN具有简便性和易实现性，因受数据点噪声的影响较小，因此被广泛应用. 该算法假设输入的新数据对应的输出值在各个样本对应的输出值空间中相似，最相似的K个数据点及其各个特征具有相同权重. 故输入新数据后，KNN提取样本中与新数据最相似的K个数据，通过取K个数据对应输出值的均值作为新数据的输出值.
KNN通常采用欧式距离对数据点和新数据点进行距离度量，新数据点x0=[x0，1，x0，2，…，x0，j，…，x0，n]和样本点xi=[xi，1，xi，2，…，xi，j，…，xi，n]之间的距离为：
式中：xi，j和x0，j分别为第i个数据点与新数据点的第j个特征属性值.
1.2.2　KR算法
KR算法是一种为建立随机变量X和Y之间的非线性关系而存在的利用非参数的随机变量条件期望进行预测的回归方法. 对于所有的非参数回归，在变量X的情况下，变量Y的条件期望数学表达式可以写成：
其中，r是回归函数. 常用的核函数包括高斯核函数（Gaussian Kernel）、多项式核函数（Polynomial Kernel）和线性核函数（Linear Kernel）等.
1.2.3　LR算法
LR算法是在给定的训练集上学习得到一个线性函数，在损失函数的约束下，求解相关系数，最终在测试集上测试模型的回归效果. 若回归分析中仅包括一个自变量x和一个因变量y，且二者的关系可用一条直线近似表示，这种回归分析称为一元线性回归分析：
式中a和b为回归系数；若回归分析中包括2个或2个以上的自变量，且因变量和自变量之间是线性关系，这种回归分析称为多元线性回归分析：
式中：x1，x2为自变量；y为因变量；a为截距；b为回归系数；e为误差项.
1.2.4　RE算法
RE算法由多个个体决策树构成，并利用投票机制进行决策分类及回归预测. 其中每棵决策树的分割节点数目均根据样本特征数随机确定，这种随机性也使得集合决策树具备更优的预测性能. 一个包含K棵决策树的RE算法模型如图2所示.
在图2中，首先对原始样本集进行抽样以获得K个样本，并将其建模成决策树，即弱分类器；接着每个弱分类器均会产生相应的决策结果，再选择相应的变量建模成决策树，以此获得具有K棵决策树的随机森林；最后利用投票机制寻得最高分的树，且将其作为最终结果输出. RE算法模型RE可表示为：
式中，Si是第i个样本集；Ck是第k棵决策树；η（Ck，Si）是Ck对Si的决策值；是投票机制的函数式.
1.3　数据增强策略
数据增强是一种通过让有限的数据产生更多的等价数据来人工扩展数据集的技术. 在对比学习中，数据增强不仅可以生成正样本，也能改善对比学习在源领域与目标领域间的迁移能力. 在传统对比学习方法中，数据增强除拥有数据增强的基本特性（如增加训练样本数量）外，主要用于生成锚点样本的正样本.
本文中，采用平面应变状态下的数据进行数据增强.
2　结果与讨论
收起
2.1　不同机器学习算法的对比
首先对所有试样进行特征工程，所有试样输入特征（a/W，B/W，B，W和a）之间的相关性矩阵如表2所示. 从表中可以发现，a/W与a、B/W与B间相关性较强，其余各特征之间相关性较弱，不存在明显强相关性，而a/W与a、B/W与B是后期需要进行对比的对象.
为了探索更适合拘束相关断裂韧性预测的算法，针对不同面内拘束下的SENB试样，对节1.2中所介绍四种机器学习算法的预测结果进行了对比，如图3所示.
由图可见，随着面内拘束（a/W）的增加，SENB试样的拘束相关断裂韧性逐渐降低，符合其变化规律. 四种算法中，RE算法的预测结果与实际结果最接近，预测效果最好，KR算法的预测效果最差. 四种算法的拟合系数r2如表3所示，从表中可以更加清晰的发现四种算法对SENB试样拘束相关断裂韧性的预测效果为RE>LR>KNN>KR.
进一步，针对SENT、CT和CCT试样，均进行了四种算法预测效果的对比，如图4所示. 由图可见，四种算法的预测效果中均为RE最好，故后文中将选取RE算法进行进一步的研究.
2.2　数据增强对预测结果的影响
在预测过程中，发现对于试样边界点的预测效果较差（如图5（a）中a/W=0.1时），为提高预测的准确性，针对不同面内拘束下的SENB试样，在使用RE算法进行预测的同时在数据中加入平面应变状态下的数据以进行数据增强，数据增强前后其预测结果对比如图5所示. 由图可见，进行数据增强后，预测结果更加准确，预测效果更好. 尤其是在a/W=0.1边界点处，预测结果得到了改善. 图5（a）的拟合系数r2为0.96495，图5（b）的拟合系数r2为0.98375，数据增强后预测准确度进一步提高.
针对不同面外拘束下的SENB试样，同样使用RE算法进行预测，并加入平面应变时的数据进行数据增强，数据增强前后其预测结果对比如图6所示. 由图可见，进行数据增强后，预测效果得到明显改善，尤其是在B=16 mm边界点处. 图6（a）的拟合系数r2为0.89373，图6（b）的拟合系数r2为0.93841，数据增强后预测准确度显著提高.
使用训练好的模型，对面内、面外拘束同时变化时的4个试样进行预测结果验证，如图7所示. 由图可见，预测结果与实际结果吻合良好，r2为0.98036，说明使用RE算法并添加数据增强策略后的模型具有较好的泛化能力.
在进行试样设计时，笔者发现一些学者通过改变a和B来改变拘束，还有一些学者通过改变a/W和B/W来改变拘束，故基于使用RE算法并添加数据增强策略后的模型，对这4个拘束变化关键特征量进行提取并进行重要性排序，如图8所示. 由图可见，对于SENB试样，4个关键特征量的重要性排序为a/W、a、B/W、B，当设计试样来研究拘束变化的影响时，通过改变a/W和B/W来改变拘束所达到的效果会更加明显.
2.3　基于RE算法和数据增强的拘束相关断裂韧性预测
2.3.1　SENT试样
为进一步考察模型的泛化能力，针对面内、面外拘束同时变化的SENT试样，使用RE算法和数据增强后的模型进行预测，并与数据增强前的结果进行对比，如图9所示. 由图可见，进行数据增强后，在之前预测效果略差的B=4 mm边界点处，预测结果得到了进一步改善. 数据增强前的拟合系数r2为0.97045，数据增强后的拟合系数r2为0.97596，略有增加，这主要是因为数据增强前对SENT试样的预测结果较好.
基于使用RE算法并添加数据增强策略后的模型，对SENT试样进行拘束变化关键特征量重要性排序，如图10所示. 由图可见，对于SENT试样，4个关键特征量的重要性排序为a、a/W、B、B/W，与SENB试样不同. 这与其加载方式有关，将在后续统一进行讨论.
2.3.2　CT试样
同样，针对面内、面外拘束同时变化的CT试样，使用RE算法并添加数据增强策略后的模型进行预测，数据增强前后预测结果对比如图11所示. 由图可见，进行数据增强后，B=4和32 mm边界点处的预测效果得到明显改善. 数据增强前的拟合系数r2为0.97370，数据增强后的拟合系数r2为0.98679.
基于使用RE算法并添加数据增强策略后的模型，CT试样拘束变化关键特征量重要性排序如图12所示. 由图可见，对于CT试样，4个关键特征量的重要性排序为B/W、B、a/W、a，且B/W、B与a/W、a相差较大. 这主要是因为所使用的CT试样数据中仅包含了两组a/W的变化（a/W=0.5和a/W=0.7），且这两组试样拘束接近，拘束相关断裂韧性相差不大.
2.3.3　CCT试样
针对面内、面外拘束同时变化的CCT试样，数据增强前后预测结果对比如图13所示. 由图可见，进行数据增强后，预测效果同样得到明显改善. 数据增强前的拟合系数r2为0.90673，数据增强后的拟合系数r2为0.93388. 综合SENT、CT和CCT试样的预测对比结果可以进一步说明，基于RE算法和数据增强策略的模型具有较好的泛化能力，且数据增强策略的加入有效提高了试样在边界点处的预测能力.
同样可以得到CCT试样拘束变化关键特征量重要性排序如图14所示，CCT试样4个关键特征量的重要性排序为B、B/W、a、a/W. 综合对比可以发现，对于SENB和CT试样，裂尖主要承受弯曲载荷，4个关键特征量中a/W和B/W重要性更大，当设计试样来研究拘束变化的影响时，通过改变a/W和B/W来改变拘束所达到的效果更好；对于SENT和CCT试样，裂尖主要承受剪切载荷，4个关键特征量中a和B重要性更大，通过改变a和B来改变拘束所达到的效果更好.
2.4　考虑试样类别的统一预测模型
进一步，同时考虑四个试样，在基于RE算法和添加数据增强策略的基础上，加入试样类别这一特征，构建统一模型，进一步对所有试样的拘束相关断裂韧性进行预测，如图15所示. 由图可见，该模型具有很高的预测精度，其r2达到了0.98221，后续可使用该模型对不同试样的拘束相关断裂韧性进行预测.
3　结论
收起
选用核电用钢A508为研究对象，考察了KNN、KR、LR和RE四种算法对拘束相关断裂韧性的预测能力，在筛选出预测结果最好的算法后，基于该算法，对不同试样的拘束相关断裂韧性进行了预测. 进一步，通过添加数据增强策略，实现了更加精准的拘束相关断裂韧性预测，并最终建立了一个统一预测模型. 所得主要结论如下：
（1）四种算法相比，RE算法的预测效果最好，KR算法的预测效果最差. 四种算法对拘束相关断裂韧性的预测效果为RE>LR>KNN>KR.
（2）使用RE算法进行预测的同时在数据中进行数据增强，将使预测结果变得更加准确、预测效果更好. 数据增强策略的加入有效提高了试样在边界点处的预测能力，且该模型具有较好的泛化能力，可以从SENB试样成功移植到SENT、CT和CCT试样. 进一步，在基于RE算法和添加数据增强策略的基础上，加入试样类别特征，构建了统一预测模型.
（3）对于SENB和CT试样，裂尖主要承受弯曲载荷，当设计试样来研究拘束变化的影响时，通过改变a/W和B/W来改变拘束所达到的效果更好；对于SENT和CCT试样，裂尖主要承受剪切载荷，通过改变a和B来改变拘束所达到的效果更好.
基金
收起
  • 国家自然科学基金项目(52375154; 52311530067)
文献
收起
参考文献 引证文献
排序方式：
[1]
Brocks W, Schmitt W. Second parameter in J-R curves: constraint or triaxiality in: Proceedings of the 1993 Conference on Constraint Effects in Fracture: Theory and Applications[C], ASTM, Dallas, TX, USA, 1993.
[2]
张经伟, 林嘉铭, 谈建平, 郭子键, 刘康林. 试样几何尺寸对347L材料断裂性能的影响[J]. 压力容器, 2023, 40(01): 30-37.
(Zhang J W, Lin J M, Tan J P, Guo Z J, Lin K L. Effect of specimen geometries on fracture toughness of 347L materials[J]. Pressure Vessel Technology, 2023, 40(01): 30-37. (in Chinese))
[3]
张宏, 吴锴, 冯庆善, 隋永莉, 刘啸奔, 杨悦, 杨叠, 戴联双, 王东营, 王冲. 高钢级管道环焊缝断裂韧性与裂尖拘束关系[J]. 石油学报, 2023, 44(02): 385-393.
(Zhang H, Wu K, Feng Q S, Sui Y L, Liu X B, Yang Y, Yang D, Dai L S, Wang D Y, Wang C. Relationship between fracture toughness and crack tip constraint of high-strength pipe girth welds[J]. Acta Petrolei Sinica, 2023, 44(02): 385-393. (in Chinese))
[4]
孙彤. 考虑面内/面外拘束的G20Mn5QT铸钢材料断裂韧性研究[D]. 天津大学, 2021.
(Sun T. Research on Fracture Toughness of G20Mn5QT Cast Steel ConsideringIn-plane and Out-of-plane Constrain[D]. Tianjin University, 2021. (in Chinese))
[5]
Huang X, Xie Q, Li S L, Qi H Y, Yang X G, Shi D Q. Novel framework for predicting constraint effects on fracture toughness using an elastic-plastic phase field model and modified boundary layer formulations[J]. Theoretical and Applied Fracture Mechanics, 2024, 130: 104279.
[6]
Agrawal A, Choudhary A. Perspective: Materials informatics and big data: Realization of the “fourth paradigm” of science in materials science[J]. APL Materials, 2016, 4(5): 053208.
[7]
Schleder G R, Padilha A C M, Acosta C M, Costa M, Fazzio A. From DFT to machine learning: recent approaches to materials science - a review[J]. Journal of Physics: Materials, 2019, 2: 032001.
[8]
赵申坤, 姜潮, 龙湘云. 一种基于数据驱动和贝叶斯理论的机械系统剩余寿命预测方法[J]. 机械工程学报, 2018, 54(12): 115-124.
(Zhao S K, Jiang C, Long X Y. Remaining useful life estimation of mechanical systems based on the data-driven method and bayesian theory[J]. Journal of Mechanical Engineering, 2018, 54(12): 115-124. (in Chinese))
[9]
Liu Y L, Niu C, Wang Z, Wang Z, Gan Y, Zhu Y, Sun S H, Shen T. Machine learning in materials genome initiative: A review[J]. Journal of Materials Science & Technology, 2020, 57: 113-122.
[10]
Ma E H, Shin S H, Choi W J, Byun J M, Hwang B C. Machine learning approach for predicting the fracture toughness of Nb-Si based alloys[J]. International Journal of Refractory Metals and Hard Materials, 2023, 117: 106420.
[11]
Albaijan I, Samadi H, Mahmood Z M F, Mahmoodzadeh A, Fakhri D, Ibrahim H H, Ouni E H M. Evaluation of concrete's fracture toughness under an acidic environment condition using advanced machine learning algorithms[J]. Engineering Fracture Mechanics, 2024, 298: 109948.
[12]
Hu X J, Liao D, Ma D D, Xie S L, Xie N, Hu H B, Gong X N. Machine learning models for predicting rock fracture toughness at different temperature conditions[J]. Case Studies in Construction Materials, 2023, 19: e02622.
[13]
肖立志. 机器学习数据驱动与机理模型融合及可解释性问题[J]. 石油物探, 2022, 61(2): 205-212.
(Xiao L Z. The fusion of data-driven machine learning with mechanism models and interpretability issues[J]. Geophysical Prospecting for Petroleum, 2022, 61(2): 205-212. (in Chinese))
[14]
Karniadakis G E, Kevrekidis I G, Lu L, Perdikaris P, Wang S, Yang L. Physics-informed machine learning[J]. Nature Reviews Physics, 2021, 3: 422-440.
[15]
Karpatne A, Atluri G, Faghmous J H, Steinbach M, Banerjee A, Ganguly A, Shekhar S, Samatova N, Kumar V. Theory-guided data science: A new paradigm for scientific discovery from data[J]. IEEE Transactions on Knowledge and Data Engineering, 2017, 29(10): 2318-2331.
[16]
Yang J Y, Kang G Z, Kan Q H. Rate-dependent multiaxial life prediction for polyamide-6 considering ratchetting: Semi-empirical and physics-informed machine learning models[J]. International Journal of Fatigue, 2022, 163: 107086.
[17]
杨杰. 面内/面外统一拘束参数及其与材料及焊接接头断裂韧性的关联[D]. 华东理工大学, 2014.
(Yang J. Unified Characterization Parameter of In-plane and Out-of Plane Constraint and Its Correlation with Fracture Toughness of Materials and Welded Joints[D]. East China University of Science and Technology, 2014. (in Chinese))
[18]
Yang J, Wang G Z, Xuan F Z, Tu S T. Unified characterisation of in-plane and out-of-plane constraint based on crack-tip equivalent plastic strain[J]. Fatigue & Fracture of Engineering Materials & Structures, 2013, 36(6): 504-514.
[19]
Yang J, Wang G Z, Xuan F Z, Tu S T. Unified correlation of in-plane and out-of-plane constraints with fracture toughness[J]. Fatigue & Fracture of Engineering Materials & Structures, 2014, 37(2): 132-145.
2025年第46卷第1期
PDF下载
47
22
引用本文
BibTeX
文章信息
doi: 10.19636/j.cnki.cjsm42-1250/o3.2024.044
  • 接收时间：2024-09-15
  • 首发时间：2026-03-20
  • 出版时间：2025-02-28
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期：2024-09-15
基金
国家自然科学基金项目(52375154; 52311530067)
作者信息
    1上海理工大学能源与动力工程学院，上海市动力工程多相流动与传热重点实验室，上海，200093
    2华东理工大学承压系统与安全教育部重点实验室，上海，200237
    3上海理工大学机械工程学院，上海，200093

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/o3.2024.044
分享至
全文二维码

扫描看全文

引用本文
BibTeX
本文的引用情况
2种不同金属材料的力学参数
科
Family		 属数
Number of
genus		 种数
Number of
species		 占总种数比例
Percentage of
total species (%)		 属
Genus		 种数
Number of
species		 占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏
相关链接
论文
最新文章
热读文章
热点专题
内参
蓝皮书
产业发展报告
传播力报告
期刊分级目录
资讯
学术新闻
行业新闻
学术会议
行业会议
关于
关于我们
联系我们
北京市海淀区学院南路86号
100081
010-62199257
qkjq@cast.org.cn

中国科学技术协会版权所有 京ICP 备10216604号-4 海淀分局备案 1101084647
科技导报社主办 中国科协信息中心技术支持