Article(id=1243306310943490777, tenantId=1146029695717560320, journalId=1240685776644648972, issueId=1243306309064442584, articleNumber=null, orderNo=null, doi=10.3969/j.issn.1007-7294.2025.05.009, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1732204800000, receivedDateStr=2024-11-22, revisedDate=null, revisedDateStr=null, acceptedDate=null, acceptedDateStr=null, onlineDate=1774356924042, onlineDateStr=2026-03-24, pubDate=1747670400000, pubDateStr=2025-05-20, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1774356924042, onlineIssueDateStr=2026-03-24, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1774356924042, creator=13701087609, updateTime=1774356924042, updator=13701087609, issue=Issue{id=1243306309064442584, tenantId=1146029695717560320, journalId=1240685776644648972, year='2025', volume='29', issue='5', pageStart='681', pageEnd='848', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=0, createTime=1774356923595, creator=13701087609, updateTime=1774357065180, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1243306902965301262, tenantId=1146029695717560320, journalId=1240685776644648972, issueId=1243306309064442584, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1243306902965301263, tenantId=1146029695717560320, journalId=1240685776644648972, issueId=1243306309064442584, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=767, endPage=775, ext={EN=ArticleExt(id=1243306311153205978, articleId=1243306310943490777, tenantId=1146029695717560320, journalId=1240685776644648972, language=EN, title=Structural reliability analysis method based on synthetic minority over-sampling technique algorithm and Bayesian optimization neural network, columnId=1242129251223274417, journalTitle=Journal of Ship Mechanics, columnName=Structural Mechanics, runingTitle=null, highlight=null, articleAbstract=

A structural reliability analysis method based on synthetic minority over-sampling technique (SMOTE) algorithm and Bayesian optimization (BO) neural network was proposed in this paper to improve the calculation accuracy and analysis efficiency of the impact resistance reliability of lubricating oil cooler. Firstly, the uniform design (UD) method and SMOTE algorithm were used to improve the utilization efficiency of the sample points. Secondly, the Bayesian optimization algorithm was used to optimize the hyperparameters, initial weights and initial biases of the BP neural network to improve the fitting accuracy and generalization ability of the model. Finally, the optimized surrogate model was combined with the Monte Carlo (MC) method to calculate the structural reliability. The results show that, compared with the traditional surrogate model method, the proposed method has the advantages of higher accuracy, shorter analysis time and lower calculation cost. The analysis method proposed in this paper has great applicability in the impact resistance reliability analysis of lubricating oil cooler. The analysis results provide technical guidance and theoretical support for the impact resistance design of lubricating oil cooler.

, correspAuthors=null, 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=Fu-lin GE, Zong-hui WU, Jian HE), CN=ArticleExt(id=1243306316203148086, articleId=1243306310943490777, tenantId=1146029695717560320, journalId=1240685776644648972, language=CN, title=基于少数类合成的过采样算法和贝叶斯优化神经网络的结构可靠性分析方法, columnId=1241023038926410098, journalTitle=船舶力学, columnName=结构力学, runingTitle=null, highlight=null, articleAbstract=

为提高滑油冷却器抗冲击可靠性的计算精度和分析效率,本文提出一种基于少数类合成的过采样(SMOTE)算法和贝叶斯优化(BO)神经网络的结构可靠性分析方法。该方法首先采用均匀设计(UD)方法和少数类合成的过采样算法提高样本点的利用效率,其次使用贝叶斯优化算法优化BP神经网络超参数、初始权值和初始偏置,以提高模型的拟合精度和泛化能力,最后利用优化后的代理模型结合Monte Carlo法计算结构可靠度。研究表明:相较于传统的代理模型法,本文的方法具有计算精度高、分析时间短、计算成本低的优势。本文提出的分析方法在滑油冷却器抗冲击可靠性分析中具有良好的适用性,分析结果可为滑油冷却器的抗冲击设计提供技术指导和理论支撑。

, correspAuthors=null, authorNote=null, correspAuthorsNote=
通讯作者,E-mail:
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=zpf8xQe5OVvU27d5ZaUigw==, magXml=LYkbJ8MuOa/h56SS1Rd8bg==, pdfUrl=null, pdf=RERMIFL6nRQrBSpyADEM3g==, pdfFileSize=5854117, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=ino/1wMu7hRmu2F+Xz8c/A==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=7qRZt9tEC0kEW7NaMQKw9w==, mapNumber=null, authorCompany=null, fund=null, authors=

葛福林(1998-),男,硕士

吴宗辉(1999-),男,博士

何建(1972-),男,教授,博士生导师,通讯作者,E-mail:

, authorsList=葛福林, 吴宗辉, 何建)}, authors=[Author(id=1243306316563858245, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306310943490777, 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=1243306316651938633, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306310943490777, authorId=1243306316563858245, language=EN, stringName=Fu-lin GE, firstName=Fu-lin, middleName=null, lastName=GE, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=School of Aerospace and Architectural Engineering, Harbin Engineering University, Harbin 150001, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1243306316748407629, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306310943490777, authorId=1243306316563858245, language=CN, stringName=葛福林, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=哈尔滨工程大学 航天与建筑工程学院,哈尔滨 150001, bio={"content":"

葛福林(1998-),男,硕士

"}, bioImg=null, bioContent=

葛福林(1998-),男,硕士

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1243306316471583550, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306310943490777, xref=null, ext=[AuthorCompanyExt(id=1243306316479972159, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306310943490777, companyId=1243306316471583550, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Aerospace and Architectural Engineering, Harbin Engineering University, Harbin 150001, China), AuthorCompanyExt(id=1243306316492555072, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306310943490777, companyId=1243306316471583550, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=哈尔滨工程大学 航天与建筑工程学院,哈尔滨 150001)])]), Author(id=1243306316828099410, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306310943490777, 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=1243306316937151318, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306310943490777, authorId=1243306316828099410, language=EN, stringName=Zong-hui WU, firstName=Zong-hui, middleName=null, lastName=WU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=School of Aerospace and Architectural Engineering, Harbin Engineering University, Harbin 150001, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1243306317033620315, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306310943490777, authorId=1243306316828099410, language=CN, stringName=吴宗辉, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=哈尔滨工程大学 航天与建筑工程学院,哈尔滨 150001, bio={"content":"

吴宗辉(1999-),男,博士

"}, bioImg=null, bioContent=

吴宗辉(1999-),男,博士

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1243306316471583550, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306310943490777, xref=null, ext=[AuthorCompanyExt(id=1243306316479972159, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306310943490777, companyId=1243306316471583550, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Aerospace and Architectural Engineering, Harbin Engineering University, Harbin 150001, China), AuthorCompanyExt(id=1243306316492555072, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306310943490777, companyId=1243306316471583550, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=哈尔滨工程大学 航天与建筑工程学院,哈尔滨 150001)])]), Author(id=1243306317121700700, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306310943490777, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=hejian@hrbeu.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1243306317213975391, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306310943490777, authorId=1243306317121700700, language=EN, stringName=Jian HE, firstName=Jian, middleName=null, lastName=HE, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=School of Aerospace and Architectural Engineering, Harbin Engineering University, Harbin 150001, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1243306317289472867, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306310943490777, authorId=1243306317121700700, language=CN, stringName=何建, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=哈尔滨工程大学 航天与建筑工程学院,哈尔滨 150001, bio={"content":"

何建(1972-),男,教授,博士生导师,通讯作者,E-mail:

"}, bioImg=null, bioContent=

何建(1972-),男,教授,博士生导师,通讯作者,E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1243306316471583550, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306310943490777, xref=null, ext=[AuthorCompanyExt(id=1243306316479972159, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306310943490777, companyId=1243306316471583550, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Aerospace and Architectural Engineering, Harbin Engineering University, Harbin 150001, China), AuthorCompanyExt(id=1243306316492555072, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306310943490777, companyId=1243306316471583550, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=哈尔滨工程大学 航天与建筑工程学院,哈尔滨 150001)])])], keywords=[Keyword(id=1243306317402719082, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306310943490777, language=EN, orderNo=1, keyword=structural reliability), Keyword(id=1243306317474022255, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306310943490777, language=EN, orderNo=2, keyword=BP neural network), Keyword(id=1243306317545325430, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306310943490777, language=EN, orderNo=3, keyword=Bayesian optimization), Keyword(id=1243306317616628604, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306310943490777, language=EN, orderNo=4, keyword=SMOTE method), Keyword(id=1243306317721486210, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306310943490777, language=EN, orderNo=5, keyword=lubricating oil cooler), Keyword(id=1243306317826343817, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306310943490777, language=CN, orderNo=1, keyword=结构可靠性), Keyword(id=1243306317897646989, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306310943490777, language=CN, orderNo=2, keyword=BP神经网络), Keyword(id=1243306317968950162, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306310943490777, language=CN, orderNo=3, keyword=贝叶斯优化), Keyword(id=1243306318065419157, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306310943490777, language=CN, orderNo=4, keyword=SMOTE算法), Keyword(id=1243306319558591389, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306310943490777, language=CN, orderNo=5, keyword=滑油冷却器)], refs=[Reference(id=1243306329339707488, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306310943490777, doi=null, pmid=null, pmcid=null, year=2014, volume=131, issue=null, pageStart=109, pageEnd=117, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=Cadini F, Santos F, Zio E, journalName=Reliability Engineering & System Safety, refType=null, unstructuredReference=Cadini F, Santos F, Zio E. An improved adaptive Kriging-based importance technique for sampling multiple failure regions of low probability[J]. Reliability Engineering & System Safety, 2014, 131:109-117., articleTitle=An improved adaptive Kriging-based importance technique for sampling multiple failure regions of low probability, refAbstract=null), Reference(id=1243306329440370789, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306310943490777, doi=null, pmid=null, pmcid=null, year=2023, volume=40, issue=3, pageStart=27, pageEnd=35, url=null, language=null, rfNumber=[2], rfOrder=1, authorNames=李宁, 潘慧雨, 李忠献, journalName=工程力学, refType=null, unstructuredReference=李宁,潘慧雨,李忠献. 一种基于自适应集成学习代理模型的结构可靠性分析方法[J]. 工程力学2023, 40(3):27-35., articleTitle=一种基于自适应集成学习代理模型的结构可靠性分析方法, refAbstract=null), Reference(id=1243306329520062571, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306310943490777, doi=null, pmid=null, pmcid=null, year=2023, volume=40, issue=3, pageStart=27, pageEnd=35, url=null, language=null, rfNumber=[2], rfOrder=2, authorNames=Li N, Pan H Y, Li Z X, journalName=Engineering Mechanics, refType=null, unstructuredReference=Li N, Pan H Y, Li Z X. Structural reliability analysis method based on adaptive ensemble learning-surrogate model[J]. Engineering Mechanics, 2023, 40(3): 27-35. (in Chinese), articleTitle=Structural reliability analysis method based on adaptive ensemble learning-surrogate model, refAbstract=null), Reference(id=1243306329645891697, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306310943490777, doi=null, pmid=null, pmcid=null, year=2020, volume=39, issue=3, pageStart=277, pageEnd=283, url=null, language=null, rfNumber=[3], rfOrder=3, authorNames=郑倩, 张宏, 刘啸奔, journalName=油气储运, refType=null, unstructuredReference=郑倩,张宏,刘啸奔. 基于BP-MC方法的断层区管道可靠性分析[J]. 油气储运2020, 39(3):277-283., articleTitle=基于BP-MC方法的断层区管道可靠性分析, refAbstract=null), Reference(id=1243306329771720825, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306310943490777, doi=null, pmid=null, pmcid=null, year=2020, volume=39, issue=3, pageStart=277, pageEnd=283, url=null, language=null, rfNumber=[3], rfOrder=4, authorNames=Zheng Q, Zhang H, Liu X B, journalName=Oil & Gas Storage and Transportation, refType=null, unstructuredReference=Zheng Q, Zhang H, Liu X B. Reliability analysis of pipeline in fault area based on BP-MC method[J]. Oil & Gas Storage and Transportation, 2020, 39(3): 277-283. (in Chinese), articleTitle=Reliability analysis of pipeline in fault area based on BP-MC method, refAbstract=null), Reference(id=1243306329851412605, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306310943490777, doi=null, pmid=null, pmcid=null, year=2019, volume=60, issue=null, pageStart=1, pageEnd=8, url=null, language=null, rfNumber=[4], rfOrder=5, authorNames=Wen K, He L, Liu J, journalName=Journal of Loss Prevention in the Process Industries, refType=null, unstructuredReference=Wen K, He L, Liu J, et al. An optimization of artificial neural network modeling methodology for the reliability assessment of corroding natural gas pipelines[J]. Journal of Loss Prevention in the Process Industries, 2019, 60:1-8., articleTitle=An optimization of artificial neural network modeling methodology for the reliability assessment of corroding natural gas pipelines, refAbstract=null), Reference(id=1243306329947881600, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306310943490777, doi=null, pmid=null, pmcid=null, year=2018, volume=2, issue=null, pageStart=103, pageEnd=109, url=null, language=null, rfNumber=[5], rfOrder=6, authorNames=姜逢源, 董胜, 张鑫, journalName=海洋湖沼通报, refType=null, unstructuredReference=姜逢源,董胜,张鑫. 基于改进神经网络的板桩结构可靠性分析[J]. 海洋湖沼通报2018, 2:103-109., articleTitle=基于改进神经网络的板桩结构可靠性分析, refAbstract=null), Reference(id=1243306330073710727, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306310943490777, doi=null, pmid=null, pmcid=null, year=2018, volume=2, issue=null, pageStart=103, pageEnd=109, url=null, language=null, rfNumber=[5], rfOrder=7, authorNames=Jiang F Y, Dong S, Zhang X, journalName=Transactions of Oceanology and Limnology, refType=null, unstructuredReference=Jiang F Y, Dong S, Zhang X. Reliability analysis of sheet pile structure based on improved neural network[J]. Transactions of Oceanology and Limnology, 2018, 2:103-109. (in Chinese), articleTitle=Reliability analysis of sheet pile structure based on improved neural network, refAbstract=null), Reference(id=1243306330178568331, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306310943490777, doi=null, pmid=null, pmcid=null, year=2021, volume=43, issue=6, pageStart=1359, pageEnd=1365, url=null, language=null, rfNumber=[6], rfOrder=8, authorNames=李永华, 陈鹏, 田宗睿, journalName=机械强度, refType=null, unstructuredReference=李永华,陈鹏,田宗睿,. 基于改进BP神经网络的结构可靠度计算方法[J]. 机械强度2021, 43(6):1359-1365., articleTitle=基于改进BP神经网络的结构可靠度计算方法, refAbstract=null), Reference(id=1243306330270843020, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306310943490777, doi=null, pmid=null, pmcid=null, year=2021, volume=43, issue=6, pageStart=1359, pageEnd=1365, url=null, language=null, rfNumber=[6], rfOrder=9, authorNames=Li Y H, Chen P, Tian Z R, journalName=Journal of Mechanical Strength, refType=null, unstructuredReference=Li Y H, Chen P, Tian Z R, et al. Structure reliability calculation method based on improved neural network[J]. Journal of Mechanical Strength, 2021, 43(6): 1359-1365. (in Chinese), articleTitle=Structure reliability calculation method based on improved neural network, refAbstract=null), Reference(id=1243306330350534800, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306310943490777, doi=null, pmid=null, pmcid=null, year=2018, volume=52, issue=6, pageStart=687, pageEnd=692, url=null, language=null, rfNumber=[7], rfOrder=10, authorNames=陈松坤, 王德禹, journalName=上海交通大学学报, refType=null, unstructuredReference=陈松坤,王德禹. 基于神经网络的蒙特卡罗可靠性分析方法[J]. 上海交通大学学报2018, 52(6):687-692., articleTitle=基于神经网络的蒙特卡罗可靠性分析方法, refAbstract=null), Reference(id=1243306330430226583, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306310943490777, doi=null, pmid=null, pmcid=null, year=2018, volume=52, issue=6, pageStart=687, pageEnd=692, url=null, language=null, rfNumber=[7], rfOrder=11, authorNames=Chen Songkun, Wang Deyu, journalName=Journal of Shanghai Jiaotong University, refType=null, unstructuredReference=Chen Songkun, Wang Deyu. An improved Monte Carlo reliability analysis method based on neural network[J]. Journal of Shanghai Jiaotong University, 2018, 52(6): 687-692. (in Chinese), articleTitle=An improved Monte Carlo reliability analysis method based on neural network, refAbstract=null), Reference(id=1243306330593804440, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306310943490777, doi=null, pmid=null, pmcid=null, year=2019, volume=53, issue=1, pageStart=26, pageEnd=34, url=null, language=null, rfNumber=[8], rfOrder=12, authorNames=龙周, 陈松坤, 王德禹, journalName=上海交通大学学报, refType=null, unstructuredReference=龙周,陈松坤,王德禹. 基于SMOTE算法的船舶结构可靠性优化设计[J]. 上海交通大学学报2019, 53(1):26-34., articleTitle=基于SMOTE算法的船舶结构可靠性优化设计, refAbstract=null), Reference(id=1243306330728022176, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306310943490777, doi=null, pmid=null, pmcid=null, year=2019, volume=53, issue=1, pageStart=26, pageEnd=34, url=null, language=null, rfNumber=[8], rfOrder=13, authorNames=Long Z, Chen S K, Wang D Y, journalName=Journal of Shanghai Jiaotong University, refType=null, unstructuredReference=Long Z, Chen S K, Wang D Y. Reliability-based design optimization of ship structures based on SMOTE algorithm[J]. Journal of Shanghai Jiaotong University, 2019, 53(1): 26-34. (in Chinese), articleTitle=Reliability-based design optimization of ship structures based on SMOTE algorithm, refAbstract=null), Reference(id=1243306330820296870, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306310943490777, doi=null, pmid=null, pmcid=null, year=2020, volume=15, issue=5, pageStart=114, pageEnd=123, url=null, language=null, rfNumber=[9], rfOrder=14, authorNames=刘婧, 王德禹, journalName=中国舰船研究, refType=null, unstructuredReference=刘婧,王德禹. 基于SMOTE算法和动态代理模型的船舶结构可靠性优化[J]. 中国舰船研究2020, 15(5):114-123., articleTitle=基于SMOTE算法和动态代理模型的船舶结构可靠性优化, refAbstract=null), Reference(id=1243306330908377257, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306310943490777, doi=null, pmid=null, pmcid=null, year=2020, volume=15, issue=5, pageStart=114, pageEnd=123, url=null, language=null, rfNumber=[9], rfOrder=15, authorNames=Liu J, Wang D Y, journalName=Chinese Journal of Ship Research, refType=null, unstructuredReference=Liu J, Wang D Y. Reliability-based design optimization of ship structure using SMOTE algorithm and dynamic surrogate model[J]. Chinese Journal of Ship Research, 2020, 15(5): 114-123. (in Chinese), articleTitle=Reliability-based design optimization of ship structure using SMOTE algorithm and dynamic surrogate model, refAbstract=null), Reference(id=1243306331004846253, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306310943490777, doi=null, pmid=null, pmcid=null, year=2011, volume=30, issue=4, pageStart=686, pageEnd=695, url=null, language=null, rfNumber=[10], rfOrder=16, authorNames=汪文俊, 周永道, 方开泰, journalName=数理统计与管理, refType=null, unstructuredReference=汪文俊,周永道,方开泰. 在计算机模拟试验中不同试验设计的比较[J]. 数理统计与管理2011, 30(4):686-695., articleTitle=在计算机模拟试验中不同试验设计的比较, refAbstract=null), Reference(id=1243306331101315248, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306310943490777, doi=null, pmid=null, pmcid=null, year=2011, volume=30, issue=4, pageStart=686, pageEnd=695, url=null, language=null, rfNumber=[10], rfOrder=17, authorNames=Wang W J, Zhou Y D, Fang K T, journalName=Journal of Applied Statistics and Management, refType=null, unstructuredReference=Wang W J, Zhou Y D, Fang K T. Comparisons among different design and modeling methods for computer experiments[J]. Journal of Applied Statistics and Management, 2011, 30(4): 686-695. (in Chinese), articleTitle=Comparisons among different design and modeling methods for computer experiments, refAbstract=null), Reference(id=1243306331197784246, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306310943490777, doi=null, pmid=null, pmcid=null, year=2003, volume=24, issue=1, pageStart=63, pageEnd=65+69, url=null, language=null, rfNumber=[11], rfOrder=18, authorNames=王少波, 柴艳丽, 梁醒培, journalName=郑州大学学报(工学版), refType=null, unstructuredReference=王少波,柴艳丽,梁醒培. 神经网络学习样本点的选取方法比较[J]. 郑州大学学报(工学版)2003, 24(1):63-65+69., articleTitle=神经网络学习样本点的选取方法比较, refAbstract=null), Reference(id=1243306331298447544, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306310943490777, doi=null, pmid=null, pmcid=null, year=2003, volume=24, issue=1, pageStart=63, pageEnd=65+69, url=null, language=null, rfNumber=[11], rfOrder=19, authorNames=Wang S B, Chai Y L, Ling X P, journalName=Journal of Zhengzhou University (Engineering Science), refType=null, unstructuredReference=Wang S B, Chai Y L, Ling X P. Comparison of selection methods of neural network learning sample points[J]. Journal of Zhengzhou University (Engineering Science), 2003, 24(1): 63-65+69. (in Chinese), articleTitle=Comparison of selection methods of neural network learning sample points, refAbstract=null), Reference(id=1243306331378139324, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306310943490777, doi=null, pmid=null, pmcid=null, year=2002, volume=16, issue=null, pageStart=321, pageEnd=357, url=null, language=null, rfNumber=[12], rfOrder=20, authorNames=Chawla N V, Bowyer K W, Hall L O, journalName=AI Access Foundation, refType=null, unstructuredReference=Chawla N V, Bowyer K W, Hall L O, et al. SMOTE: synthetic minority over-sampling technique[J]. AI Access Foundation, 2002, 16:321-357., articleTitle=SMOTE: synthetic minority over-sampling technique, refAbstract=null), Reference(id=1243306331457831105, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306310943490777, doi=null, pmid=null, pmcid=null, year=2021, volume=null, issue=null, pageStart=58, pageEnd=61, url=null, language=null, rfNumber=[13], rfOrder=21, authorNames=魏翼飞, 汪昭颖, 李骏, journalName=深度学习——从神经网络到深度强化学习的演进, refType=null, unstructuredReference=魏翼飞,汪昭颖,李骏. 深度学习——从神经网络到深度强化学习的演进[M]. 北京:清华大学出版社,2021:58-61., articleTitle=null, refAbstract=null), Reference(id=1243306331562688709, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306310943490777, doi=null, pmid=null, pmcid=null, year=2021, volume=null, issue=null, pageStart=58, pageEnd=61, url=null, language=null, rfNumber=[13], rfOrder=22, authorNames=Wei Y F, Wang Z Y, Li J, journalName=Deep Learning—Evolution from neural networks to deep reinforcement learning, refType=null, unstructuredReference=Wei Y F, Wang Z Y, Li J. Deep Learning—Evolution from neural networks to deep reinforcement learning[M]. Beijing: Tsinghua University Publishers, 2021:58-61. (in Chinese), articleTitle=null, refAbstract=null), Reference(id=1243306333089415370, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306310943490777, doi=null, pmid=null, pmcid=null, year=2014, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[14], rfOrder=23, authorNames=Kingma D, Ba J, journalName=Computer Science, refType=null, unstructuredReference=Kingma D, Ba J. Adam: A method for stochastic optimization[J]. Computer Science, 2014., articleTitle=Adam: A method for stochastic optimization, refAbstract=null), Reference(id=1243306333198467277, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306310943490777, doi=null, pmid=null, pmcid=null, year=1999, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[15], rfOrder=24, authorNames=Cantu-Paz E, Goldberg D E, Pelikan M, journalName=null, refType=null, unstructuredReference=Cantu-Paz E, Goldberg D E, Pelikan M. BOA: The Bayesian optimization algorithm[C]//GECCO-99: Proceedings of the Genetic and Evolutionary Computation Conference, 1999., articleTitle=BOA: The Bayesian optimization algorithm, refAbstract=null), Reference(id=1243306333290741971, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306310943490777, doi=null, pmid=null, pmcid=null, year=2018, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[16], rfOrder=25, authorNames=Frazier P, journalName=ArXiv, refType=null, unstructuredReference=Frazier P. A tutorial on Bayesian optimization[M/OL]. ArXiv, 2018,, articleTitle=null, refAbstract=null), Reference(id=1243306333387210967, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306310943490777, doi=null, pmid=null, pmcid=null, year=2022, volume=49, issue=S1, pageStart=86, pageEnd=92, url=null, language=null, rfNumber=[17], rfOrder=26, authorNames=李亚茹, 张宇来, 王佳晨, journalName=计算机科学, refType=null, unstructuredReference=李亚茹,张宇来,王佳晨. 面向超参数估计的贝叶斯优化方法综述[J]. 计算机科学2022, 49(S1):86-92., articleTitle=面向超参数估计的贝叶斯优化方法综述, refAbstract=null), Reference(id=1243306333521428701, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306310943490777, doi=null, pmid=null, pmcid=null, year=2022, volume=49, issue=S1, pageStart=86, pageEnd=92, url=null, language=null, rfNumber=[17], rfOrder=27, authorNames=Li Y R, Zhang Y L, Wang J C, journalName=Computer Science, refType=null, unstructuredReference=Li Y R, Zhang Y L, Wang J C. Survey on Bayesian optimization methods for hyper-parameter tuning[J]. Computer Science, 2022, 49(S1):86-92. (in Chinese), articleTitle=Survey on Bayesian optimization methods for hyper-parameter tuning, refAbstract=null), Reference(id=1243306333626286304, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306310943490777, doi=null, pmid=null, pmcid=null, year=2013, volume=111, issue=null, pageStart=232, pageEnd=240, url=null, language=null, rfNumber=[18], rfOrder=28, authorNames=Echard B, Gayton N, Lemaire M, journalName=Reliability Engineering & System Safety, refType=null, unstructuredReference=Echard B, Gayton N, Lemaire M, et al. A combined importance sampling and Kriging reliability method for small failure probabilities with time-demanding numerical models[J]. Reliability Engineering & System Safety, 2013, 111:232-240., articleTitle=A combined importance sampling and Kriging reliability method for small failure probabilities with time-demanding numerical models, refAbstract=null), Reference(id=1243306333743726818, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306310943490777, doi=null, pmid=null, pmcid=null, year=2022, volume=17, issue=1, pageStart=147, pageEnd=153+165, url=null, language=null, rfNumber=[19], rfOrder=29, authorNames=李雪剑, 秦斌, 肖艺峰, journalName=中国舰船研究, refType=null, unstructuredReference=李雪剑,秦斌,肖艺峰,. 改进随机森林-蒙特卡罗法在A型液舱支座结构可靠性分析中的应用[J]. 中国舰船研究2022, 17(1):147-153+165., articleTitle=改进随机森林-蒙特卡罗法在A型液舱支座结构可靠性分析中的应用, refAbstract=null), Reference(id=1243306333827612901, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306310943490777, doi=null, pmid=null, pmcid=null, year=2022, volume=17, issue=1, pageStart=147, pageEnd=153+165, url=null, language=null, rfNumber=[19], rfOrder=30, authorNames=Li X J, Qin B, Xiao Y F, journalName=Chinese Journal of Ship Research, refType=null, unstructuredReference=Li X J, Qin B, Xiao Y F, et al. An improved random forest-Monte Carlo method and application for structural reliability analysis of A-type independent liquid tank support structure[J]. Chinese Journal of Ship Research, 2022, 17(1): 147-153+165. (in Chinese), articleTitle=An improved random forest-Monte Carlo method and application for structural reliability analysis of A-type independent liquid tank support structure, refAbstract=null), Reference(id=1243306333911498987, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306310943490777, doi=null, pmid=null, pmcid=null, year=2000, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[20], rfOrder=31, authorNames=Nowak A S, Colins K R, journalName=Reliability of structures, refType=null, unstructuredReference=Nowak A S, Colins K R. Reliability of structures[M]. CRC Press, 2000., articleTitle=null, refAbstract=null), Reference(id=1243306334003773678, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306310943490777, doi=null, pmid=null, pmcid=null, year=2012, volume=39, issue=null, pageStart=22, pageEnd=29, url=null, language=null, rfNumber=[21], rfOrder=32, authorNames=Rashki M, Miri M, Moghaddam M A, journalName=Structural Safety, refType=null, unstructuredReference=Rashki M, Miri M, Moghaddam M A. A new efficient simulation method to approximate the probability of failure and most probable point[J]. Structural Safety, 2012, 39:22-29., articleTitle=A new efficient simulation method to approximate the probability of failure and most probable point, refAbstract=null)], funds=[Fund(id=1243306329226461275, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306310943490777, awardId=52278297, language=CN, fundingSource=国家自然科学基金面上项目(52278297), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1243306316471583550, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306310943490777, xref=null, ext=[AuthorCompanyExt(id=1243306316479972159, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306310943490777, companyId=1243306316471583550, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Aerospace and Architectural Engineering, Harbin Engineering University, Harbin 150001, China), AuthorCompanyExt(id=1243306316492555072, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306310943490777, companyId=1243306316471583550, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=哈尔滨工程大学 航天与建筑工程学院,哈尔滨 150001)])], figs=[ArticleFig(id=1243306319701197735, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306310943490777, language=EN, label=Fig.1, caption=Database expansion principle of SMOTE method, figureFileSmall=9VsOFlKZK5Qnv2GWqTD8cw==, figureFileBig=ino/1wMu7hRmu2F+Xz8c/A==, tableContent=null), ArticleFig(id=1243306319789278123, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306310943490777, language=CN, label=图1, caption=SMOTE算法数据库扩充原理, figureFileSmall=9VsOFlKZK5Qnv2GWqTD8cw==, figureFileBig=ino/1wMu7hRmu2F+Xz8c/A==, tableContent=null), ArticleFig(id=1243306319986410422, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306310943490777, language=EN, label=Fig.2, caption=BP neural network structure, figureFileSmall=mJBay1g8qUXKe+Gm13URMw==, figureFileBig=ya6udOpuceVAvfz4Yaqd1g==, tableContent=null), ArticleFig(id=1243306320061907899, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306310943490777, language=CN, label=图2, caption=BP神经网络结构, figureFileSmall=mJBay1g8qUXKe+Gm13URMw==, figureFileBig=ya6udOpuceVAvfz4Yaqd1g==, tableContent=null), ArticleFig(id=1243306320154182593, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306310943490777, language=EN, label=Fig.3, caption=Flow chart of SMOTE-BO-BP-MC algorithm, figureFileSmall=NFIg+IVn/AinSBkUUK1m+g==, figureFileBig=wB8kthGuAPI1TsakAtCL+Q==, tableContent=null), ArticleFig(id=1243306322117116875, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306310943490777, language=CN, label=图3, caption=SMOTE-BO-BP-MC算法流程图, figureFileSmall=NFIg+IVn/AinSBkUUK1m+g==, figureFileBig=wB8kthGuAPI1TsakAtCL+Q==, tableContent=null), ArticleFig(id=1243306322188420047, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306310943490777, language=EN, label=Fig.4, caption=Sample distribution of training set in Case 1, figureFileSmall=CmHZjFMBywyL84ZZiDm8kQ==, figureFileBig=Xl24qPMU/1cLXICCdd+ICQ==, tableContent=null), ArticleFig(id=1243306322314249174, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306310943490777, language=CN, label=图4, caption=算例1训练集样本分布, figureFileSmall=CmHZjFMBywyL84ZZiDm8kQ==, figureFileBig=Xl24qPMU/1cLXICCdd+ICQ==, tableContent=null), ArticleFig(id=1243306322393940957, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306310943490777, language=EN, label=Fig.5, caption=Comparison of training results of surrogate model in Case 1 before and after optimization, figureFileSmall=dNe1jHbfZidqjuxCrMD1tA==, figureFileBig=lJtzXtcL8CLzz3vzYaKRgQ==, tableContent=null), ArticleFig(id=1243306322477827047, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306310943490777, language=CN, label=图5, caption=算例1代理模型优化前后训练结果对比, figureFileSmall=dNe1jHbfZidqjuxCrMD1tA==, figureFileBig=lJtzXtcL8CLzz3vzYaKRgQ==, tableContent=null), ArticleFig(id=1243306322603656173, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306310943490777, language=EN, label=Fig.6, caption=Relative error of different methods in Case 1, figureFileSmall=QRvO4RZf358fXjRqz/ab2Q==, figureFileBig=GcZK8rUoWNzJdk2XUcEYWA==, tableContent=null), ArticleFig(id=1243306324155548663, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306310943490777, language=CN, label=图6, caption=算例1各方法相对误差, figureFileSmall=QRvO4RZf358fXjRqz/ab2Q==, figureFileBig=GcZK8rUoWNzJdk2XUcEYWA==, tableContent=null), ArticleFig(id=1243306324285572093, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306310943490777, language=EN, label=Fig.7, caption=Finite element model of lubricating oil cooler, figureFileSmall=ZoQqInQjCHrzOGLnU1O6dQ==, figureFileBig=DthEbO8FH11h2myK4Zn2wA==, tableContent=null), ArticleFig(id=1243306324377845763, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306310943490777, language=CN, label=图7, caption=滑油冷却器有限元模型, figureFileSmall=ZoQqInQjCHrzOGLnU1O6dQ==, figureFileBig=DthEbO8FH11h2myK4Zn2wA==, tableContent=null), ArticleFig(id=1243306324465926153, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306310943490777, language=EN, label=Fig.8, caption=Triangular course of shock variation of the cooler, figureFileSmall=znermdzp0dzcvThwWtpYzg==, figureFileBig=MZc5TT46nvkI2Xsp/SeGUA==, tableContent=null), ArticleFig(id=1243306324583366671, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306310943490777, language=CN, label=图8, caption=滑油冷却器的三角形变化历程, figureFileSmall=znermdzp0dzcvThwWtpYzg==, figureFileBig=MZc5TT46nvkI2Xsp/SeGUA==, tableContent=null), ArticleFig(id=1243306324692418581, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306310943490777, language=EN, label=Fig.9, caption=Predicted results of test sets, figureFileSmall=OlCH0X4Cz20ta6qAE12hkw==, figureFileBig=pncxXCtOkdIGd42uBPOMdg==, tableContent=null), ArticleFig(id=1243306324839219226, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306310943490777, language=CN, label=图9, caption=测试集预测结果, figureFileSmall=OlCH0X4Cz20ta6qAE12hkw==, figureFileBig=pncxXCtOkdIGd42uBPOMdg==, tableContent=null), ArticleFig(id=1243306324931493922, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306310943490777, language=EN, label=Fig.10, caption=Plot of reliability against impact load, figureFileSmall=fG+Nu/F2SR1wJtKR0Nzraw==, figureFileBig=1ZIhlJsExpGiV59oEorMmw==, tableContent=null), ArticleFig(id=1243306325023768613, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306310943490777, language=CN, label=图10, caption=可靠度随冲击载荷变化曲线, figureFileSmall=fG+Nu/F2SR1wJtKR0Nzraw==, figureFileBig=1ZIhlJsExpGiV59oEorMmw==, tableContent=null), ArticleFig(id=1243306325145403436, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306310943490777, language=EN, label=Tab.1, caption=

Results of Case 1

, figureFileSmall=null, figureFileBig=null, tableContent=
方法NcallPfCov/%e/%
MC[18]5×1072.85×10-5
FORM[18]4.21×10-547.7
IS[18]10 0192.86×10-52.390.35
BP-MC[7]1243.22×10-53.8712.98
改进RF-MC[19]1243.15×10-54.91
传统BP-MC2802.65×10-54.157.18
BO-BP-MC1003.40×10-54.0419.28
本文1002.87×10-54.050.78
), ArticleFig(id=1243306325262843951, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306310943490777, language=CN, label=表1, caption=

算例1分析结果

, figureFileSmall=null, figureFileBig=null, tableContent=
方法NcallPfCov/%e/%
MC[18]5×1072.85×10-5
FORM[18]4.21×10-547.7
IS[18]10 0192.86×10-52.390.35
BP-MC[7]1243.22×10-53.8712.98
改进RF-MC[19]1243.15×10-54.91
传统BP-MC2802.65×10-54.157.18
BO-BP-MC1003.40×10-54.0419.28
本文1002.87×10-54.050.78
), ArticleFig(id=1243306325338341426, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306310943490777, language=EN, label=Tab.2, caption=

Random variables of Case 2

, figureFileSmall=null, figureFileBig=null, tableContent=
随机变量分布类型均值变异系数
Fy正态分布440.105
As正态分布4.080.02
FC正态分布3.120.14
Q正态分布20520.12
), ArticleFig(id=1243306328735727674, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306310943490777, language=CN, label=表2, caption=

算例2随机变量

, figureFileSmall=null, figureFileBig=null, tableContent=
随机变量分布类型均值变异系数
Fy正态分布440.105
As正态分布4.080.02
FC正态分布3.120.14
Q正态分布20520.12
), ArticleFig(id=1243306328823808066, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306310943490777, language=EN, label=Tab.3, caption=

Results of Case 2

, figureFileSmall=null, figureFileBig=null, tableContent=
方法NcallPfCov/%e/%
MC[21]1×1050.011 01
FORM[21]0.009 3914.75
Proposed method[21]50000.010 722.60
传统BP-MC2800.123 302.8311.98
BO-BP-MC900.009 301.8419.28
本文900.011 351.703.06
), ArticleFig(id=1243306328928665672, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306310943490777, language=CN, label=表3, caption=

算例2分析结果

, figureFileSmall=null, figureFileBig=null, tableContent=
方法NcallPfCov/%e/%
MC[21]1×1050.011 01
FORM[21]0.009 3914.75
Proposed method[21]50000.010 722.60
传统BP-MC2800.123 302.8311.98
BO-BP-MC900.009 301.8419.28
本文900.011 351.703.06
), ArticleFig(id=1243306329008357453, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306310943490777, language=EN, label=Tab.4, caption=

Random variables of lubricating oil cooler

, figureFileSmall=null, figureFileBig=null, tableContent=
随机变量物理意义分布类型均值标准差
E/GPa弹性模量正态分布1955.85
thxb/mm支撑结构弧形板厚度正态分布201.00
tdb/mm支撑结构底板厚度正态分布251.25
tbl/mm支撑结构背板和肋板厚度正态分布201.00
tfl/mm法兰板厚度正态分布261.30
ttt/mm筒体结构厚度正态分布120.60
tdg/mm端盖厚度正态分布120.60
P/MPa容器内压正态分布1.00.1
), ArticleFig(id=1243306329083854935, tenantId=1146029695717560320, journalId=1240685776644648972, articleId=1243306310943490777, language=CN, label=表4, caption=

滑油冷却器随机变量

, figureFileSmall=null, figureFileBig=null, tableContent=
随机变量物理意义分布类型均值标准差
E/GPa弹性模量正态分布1955.85
thxb/mm支撑结构弧形板厚度正态分布201.00
tdb/mm支撑结构底板厚度正态分布251.25
tbl/mm支撑结构背板和肋板厚度正态分布201.00
tfl/mm法兰板厚度正态分布261.30
ttt/mm筒体结构厚度正态分布120.60
tdg/mm端盖厚度正态分布120.60
P/MPa容器内压正态分布1.00.1
)], attaches=null, journal=Journal(id=1240685663704625163, delFlag=0, nameCn=船舶力学, nameEn=Journal of Ship Mechanics, nameHistory1=null, nameHistory2=null, issn=1007-7294, eissn=null, cn=32-1468/U, 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=8VABIsgSw5I4HF/4goaIlA==, journalPrice=null, startedYear=null, abbrevIsoEn=Journal of Ship Mechanics, journalRemark=null, publicationField=null, createdTime=1773732113054, updatedTime=1773732336269, createdBy=18614031015, updatedBy=13701087609, firstLetterCn=J, firstLetterEn=J, subjectCode=Engineering, subjectName=null, subjectCodeEn=Engineering, subjectNameEn=null, picCn=8VABIsgSw5I4HF/4goaIlA==, picEn=Ve/8A/FRYceS/z8o7GCJ5g==, jcr=null, cjcr=null, exts=[JournalExt(id=1240686600003318325, language=CN, name=船舶力学, 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=1773732336283, updatedTime=1773732336283, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=https://cblx.cbpt.cnki.net/EditorD3N/index.aspx?t=1, submissionEditorUrl=https://cblx.cbpt.cnki.net/EditorD3N/index.aspx?t=3, submissionReviewUrl=https://cblx.cbpt.cnki.net/EditorD3N/index.aspx?t=2, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1240686600041067062, language=EN, name=Journal of Ship 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=1773732336292, updatedTime=1773732336292, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=https://cblx.cbpt.cnki.net/EditorD3N/index.aspx?t=1, submissionEditorUrl=https://cblx.cbpt.cnki.net/EditorD3N/index.aspx?t=3, submissionReviewUrl=https://cblx.cbpt.cnki.net/EditorD3N/index.aspx?t=2, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1240685776644648972, websiteList=[Website(id=1240686760611607145, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1240685776644648972, 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/cblx/CN, language=CN, createTime=1773732374576, createBy=18614031015, updateTime=1773732394922, updateBy=18614031015, name=船舶力学-中文, tplId=1146099689490845704, title=船舶力学, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1240687166741869216, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1240686760611607145, code=articleTextType, value=kx, createTime=1773732471404, updateTime=1773732471404, creator=18614031015, updator=18614031015), WebsiteProps(id=1240687166725091997, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1240686760611607145, code=banner, value=null, createTime=1773732471400, updateTime=1773732471400, creator=18614031015, updator=18614031015), WebsiteProps(id=1240687166758646435, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1240686760611607145, code=grayFlag, value=0, createTime=1773732471408, updateTime=1773732471408, creator=18614031015, updator=18614031015), WebsiteProps(id=1240687166716703388, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1240686760611607145, code=logo, value=https://castjournals.cast.org.cn/joweb/cblx/CN/file/pic?fileId=/ZVjg3ao2vf5wYxw5Kn1Uw==, createTime=1773732471398, updateTime=1773732471398, creator=18614031015, updator=18614031015), WebsiteProps(id=1240687166771229349, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1240686760611607145, code=minRunFlag, value=0, createTime=1773732471411, updateTime=1773732471411, creator=18614031015, updator=18614031015), WebsiteProps(id=1240687166737674911, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1240686760611607145, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/cblx/CN/file/pic, createTime=1773732471403, updateTime=1773732471403, creator=18614031015, updator=18614031015), WebsiteProps(id=1240687166767035044, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1240686760611607145, code=silenceFlag, value=0, createTime=1773732471410, updateTime=1773732471410, creator=18614031015, updator=18614031015), WebsiteProps(id=1240687166729286302, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1240686760611607145, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1773732471401, updateTime=1773732471401, creator=18614031015, updator=18614031015), WebsiteProps(id=1240687166750257825, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1240686760611607145, code=themeColor, value=null, createTime=1773732471406, updateTime=1773732471406, creator=18614031015, updator=18614031015), WebsiteProps(id=1240687166754452130, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1240686760611607145, code=themeStyle, value=null, createTime=1773732471407, updateTime=1773732471407, creator=18614031015, updator=18614031015)]), Website(id=1240686760674521707, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1240685776644648972, 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/cblx/EN, language=EN, createTime=1773732374590, createBy=18614031015, updateTime=1773732413338, updateBy=18614031015, name=船舶力学-英文, tplId=1146101810881728533, title=Journal of Ship Mechanics, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1240687194269078438, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1240686760674521707, code=articleTextType, value=kx, createTime=1773732477967, updateTime=1773732477967, creator=18614031015, updator=18614031015), WebsiteProps(id=1240687194248106915, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1240686760674521707, code=banner, value=null, createTime=1773732477962, updateTime=1773732477962, creator=18614031015, updator=18614031015), WebsiteProps(id=1240687194285855657, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1240686760674521707, code=grayFlag, value=0, createTime=1773732477971, updateTime=1773732477971, creator=18614031015, updator=18614031015), WebsiteProps(id=1240687194239718306, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1240686760674521707, code=logo, value=https://castjournals.cast.org.cn/joweb/cblx/EN/file/pic?fileId=/ZVjg3ao2vf5wYxw5Kn1Uw==, createTime=1773732477960, updateTime=1773732477960, creator=18614031015, updator=18614031015), WebsiteProps(id=1240687194302632875, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1240686760674521707, code=minRunFlag, value=0, createTime=1773732477975, updateTime=1773732477975, creator=18614031015, updator=18614031015), WebsiteProps(id=1240687194260689829, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1240686760674521707, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/cblx/EN/file/pic, createTime=1773732477965, updateTime=1773732477965, creator=18614031015, updator=18614031015), WebsiteProps(id=1240687194294244266, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1240686760674521707, code=silenceFlag, value=0, createTime=1773732477973, updateTime=1773732477973, creator=18614031015, updator=18614031015), WebsiteProps(id=1240687194256495524, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1240686760674521707, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_en_623/, createTime=1773732477964, updateTime=1773732477964, creator=18614031015, updator=18614031015), WebsiteProps(id=1240687194277467047, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1240686760674521707, code=themeColor, value=null, createTime=1773732477969, updateTime=1773732477969, creator=18614031015, updator=18614031015), WebsiteProps(id=1240687194281661352, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1240686760674521707, code=themeStyle, value=null, createTime=1773732477970, updateTime=1773732477970, creator=18614031015, updator=18614031015)])], journalTitle=船舶力学, weixinUrl=null, journalUrl=https://cblx.cbpt.cnki.net/, iacademicId=null, status=1, seqNo=null, journalTitleEn=Journal of Ship Mechanics, journalPhotoCn=8VABIsgSw5I4HF/4goaIlA==, journalPhotoEn=Ve/8A/FRYceS/z8o7GCJ5g==, 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/cblx/CN/10.3969/j.issn.1007-7294.2025.05.009, detailUrlEn=https://castjournals.cast.org.cn/joweb/cblx/EN/10.3969/j.issn.1007-7294.2025.05.009, pdfUrlCn=https://castjournals.cast.org.cn/joweb/cblx/CN/PDF/10.3969/j.issn.1007-7294.2025.05.009, pdfUrlEn=https://castjournals.cast.org.cn/joweb/cblx/EN/PDF/10.3969/j.issn.1007-7294.2025.05.009, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于少数类合成的过采样算法和贝叶斯优化神经网络的结构可靠性分析方法
收藏切换
PDF下载
葛福林 , 吴宗辉 , 何建
船舶力学 | 结构力学 2025,29(5): 767-775
收起
收藏切换
船舶力学 | 结构力学 2025, 29(5): 767-775
基于少数类合成的过采样算法和贝叶斯优化神经网络的结构可靠性分析方法
全屏
葛福林, 吴宗辉, 何建
作者信息
  • 哈尔滨工程大学 航天与建筑工程学院,哈尔滨 150001
  • 葛福林(1998-),男,硕士

    吴宗辉(1999-),男,博士

    何建(1972-),男,教授,博士生导师,通讯作者,E-mail:

通讯作者:

通讯作者,E-mail:
Structural reliability analysis method based on synthetic minority over-sampling technique algorithm and Bayesian optimization neural network
Fu-lin GE, Zong-hui WU, Jian HE
Affiliations
  • School of Aerospace and Architectural Engineering, Harbin Engineering University, Harbin 150001, China
出版时间: 2025-05-20 doi: 10.3969/j.issn.1007-7294.2025.05.009
文章导航
收藏切换

为提高滑油冷却器抗冲击可靠性的计算精度和分析效率,本文提出一种基于少数类合成的过采样(SMOTE)算法和贝叶斯优化(BO)神经网络的结构可靠性分析方法。该方法首先采用均匀设计(UD)方法和少数类合成的过采样算法提高样本点的利用效率,其次使用贝叶斯优化算法优化BP神经网络超参数、初始权值和初始偏置,以提高模型的拟合精度和泛化能力,最后利用优化后的代理模型结合Monte Carlo法计算结构可靠度。研究表明:相较于传统的代理模型法,本文的方法具有计算精度高、分析时间短、计算成本低的优势。本文提出的分析方法在滑油冷却器抗冲击可靠性分析中具有良好的适用性,分析结果可为滑油冷却器的抗冲击设计提供技术指导和理论支撑。

结构可靠性  /  BP神经网络  /  贝叶斯优化  /  SMOTE算法  /  滑油冷却器

A structural reliability analysis method based on synthetic minority over-sampling technique (SMOTE) algorithm and Bayesian optimization (BO) neural network was proposed in this paper to improve the calculation accuracy and analysis efficiency of the impact resistance reliability of lubricating oil cooler. Firstly, the uniform design (UD) method and SMOTE algorithm were used to improve the utilization efficiency of the sample points. Secondly, the Bayesian optimization algorithm was used to optimize the hyperparameters, initial weights and initial biases of the BP neural network to improve the fitting accuracy and generalization ability of the model. Finally, the optimized surrogate model was combined with the Monte Carlo (MC) method to calculate the structural reliability. The results show that, compared with the traditional surrogate model method, the proposed method has the advantages of higher accuracy, shorter analysis time and lower calculation cost. The analysis method proposed in this paper has great applicability in the impact resistance reliability analysis of lubricating oil cooler. The analysis results provide technical guidance and theoretical support for the impact resistance design of lubricating oil cooler.

structural reliability  /  BP neural network  /  Bayesian optimization  /  SMOTE method  /  lubricating oil cooler
葛福林, 吴宗辉, 何建. 基于少数类合成的过采样算法和贝叶斯优化神经网络的结构可靠性分析方法. 船舶力学, 2025 , 29 (5) : 767 -775 . DOI: 10.3969/j.issn.1007-7294.2025.05.009
Fu-lin GE, Zong-hui WU, Jian HE. Structural reliability analysis method based on synthetic minority over-sampling technique algorithm and Bayesian optimization neural network[J]. Journal of Ship Mechanics, 2025 , 29 (5) : 767 -775 . DOI: 10.3969/j.issn.1007-7294.2025.05.009
滑油冷却器作为舰船动力系统的辅助装置,其在冲击载荷下的可靠性将直接影响舰船的巡航和作战能力。众多实船试验表明,除冲击载荷外,舰船设备在设计制造过程中产生的尺寸误差和材料性能的变化,都会对设备的冲击响应产生显著影响。结构可靠性分析理论正是考虑各种不确定性因素、评估结构安全性的重要方法。
结构可靠性分析方法有三种:近似解法、随机模拟法和代理模型法[1]。其中,近似解法因其适用范围小、计算精度不高等问题难以直接应用于实际工程;随机模拟法因其海量的抽样次数导致计算量过大,也限制了该方法在实际工程中的应用;而代理模型法因其在保证基本精度的前提下,可极大地缩短单个样本点的计算时间而得到广泛应用。目前常用的代理模型有BP(Back Propagation)神经网络、Kriging[2]、随机森林(Random Forest, RF)等,其中,BP神经网络对于高维非线性问题具有较强的拟合能力,得到了大量的工程应用[3]
针对传统BP神经网络模型进行可靠性分析时存在精度不足的问题,诸多学者已开展了大量研究工作。Wen等[4]使用模拟退火优化BP神经网络训练集的输入顺序,采用遗传算法优化BP神经网络的初始权值和偏置,以此提高模型的计算精度和计算速度。姜逢源等[5]采用Adaboost算法优化BP神经网络,结果表明该方法的精度优于传统神经网络。李永华等[6]采用思维进化算法及贝叶斯正则化,对BP神经网络的初始权值、偏置及训练过程进行优化,研究发现优化后的模型在保证精度的同时提高了计算效率。
提高BP神经网络训练集的抽样效率,也是提高可靠性问题计算精度和分析效率的重要途径。陈松坤等[7]以样本点权重因子和其到失效面的距离为筛选准则,将符合要求的样本点加入训练集,以此提高BP神经网络模型在失效面附近的拟合精度。龙周等[8]采用SMOTE(Synthetic Minority Over-Sampling Technique)算法建立改进的BP神经网络,以少量的样本点拟合极限状态函数,克服了以往代理模型不能同时满足精度和效率要求的缺点。刘婧等[9]采用SMOTE算法增加当前最优解周围失效面附近的样本点更新BP神经网络,以此提高模型的拟合精度。
鉴于此,本文综合考虑抽样效率和BP神经网络优化对结构可靠性计算精度和分析效率的影响,提出一种以均匀设计和SMOTE算法为基础,以贝叶斯优化算法(Bayesian Optimization, BO)优化BP神经网络为核心的改进代理模型法,即SMOTE-BO-BP-MC(Monte Carlo, MC)算法。本文将首先利用两个经典算例验证本文方法的可行性和优越性,之后采用该方法构建船用滑油冷却器抗冲击可靠性的代理模型,在此基础上对其抗冲击可靠性进行分析,给出可靠度随冲击载荷的变化规律,为滑油冷却器的设计制造提供理论支撑。
本文首先采用均匀设计方法(Uniform Design, UD)[10]构建初始学习样本数据库。该方法的本质是使样本点在整个样本空间内均匀分布,保证代理模型在小样本量的情况下获得较好的学习效果。诸多学者通过研究已经证明,相较于正交设计法、拉丁超立方设计法、正交拉丁超立方设计等方法,UD方法筛选出的样本点更具代表性,在建立样本数据库方面具有较大的优势[10-11]
实际工程中结构的失效概率一般都很小,因此在使用UD方法构建BP神经网络训练集时,不可避免地会产生失效面附近落入失效域中的样本点过少的问题,而SMOTE算法[12]利用落入失效域中样本点和近邻样本点实现数据库扩充恰好可以解决这个问题,SMOTE算法数据库扩充原理如图1所示。
一般地,BP神经网络结构由输入层、隐藏层和输出层三部分组成,每层之间相互连接。本文采用双隐藏层的BP神经网络作为代理模型对结构的可靠性进行分析,网络结构如图2所示。
本文选择计算效率高、收敛速度快、没有饱和机制、没有“死亡ReLU”问题[13]的Leaky ReLU函数作为BP神经网络的激活函数:
式中,σ可取0.01。
鉴于传统的梯度下降优化算法寻优能力较差,而且容易陷入局部最优解的问题,本文将选用以梯度的移动平均代替负梯度的方向作为参数的更新方向,对不同的参数自适应调整学习率[14],采用自适应动量估计算法(adaptive moment estimation, Adam)作为BP神经网络的优化算法。
BO算法[15]是一种在已知有限样本点的情况下,通过构造黑箱函数输出的后验概率来寻找最优值的算法[16-17]。本文采用BO算法优化BP神经网络的隐藏层神经元个数、迭代优化次数、学习率初值、动态学习率下降间隔、动态学习率下降梯度、初始权值w0和初始偏置b0,以降低初始参数的随机性对训练效果的影响并提高模型的拟合精度。
BP神经网络参数和超参数优化问题,可用式(2)来表示:
式中,x为初始参数和超参数组合,f(⋅)为目标函数,x*为理想的参数和超参数组合,χ为参数和超参数的可行域。
本文选择BP神经网络验证集的平均绝对百分误差(Mean Absolute Percentage Error, MAPE)eMAPE作为BO算法的目标函数f评估模型性能,如式(3)所示;选用计算速度快的TPE(Tree-structured Parzen Estimator)模型作为概率代理模型M对参数和超参数进行迭代寻优;选择期望改善函数作为确定最优样本点位置的采集函数S,如公式(4)所示。
式中,yi为实际值,为预测值。
式中,y*为当前已有样本中的最优值,p(y|x,D)指的是当前的概率代理模型。
综上所述,本文方法的分析流程如图3所示。
本文使用SMOTE-BO-BP-MC法对两个经典可靠性问题进行分析,以此验证本文所提方法的可行性和优越性。
算例1为二维非线性可靠性问题,功能函数如式(5)所示,随机变量U1U2相互独立,且服从标准正态分布。
图4给出了BO-BP模型训练集中样本分布情况,其中采用UD方法生成了50个均匀分布在采样区域内且布满整个采样空间的样本点,以此增加BP神经网络可学习的信息量;再利用SMOTE算法增加20个在失效面附近且落入失效域中的样本点,以此增加BP神经网络在失效曲线附近的拟合精度。
图5给出了算例1中采用BO算法优化BP神经网络的结果,对比发现经BO算法优化后的BP神经网络的验证集和测试集的eMAPE更小,这说明对于该算例,BO-BP模型具有更高的拟合精度和更强的泛化能力。
图6给出了各方法的分析结果的相对误差,表1给出了算例1的分析结果,综合表1图6的结果可知,与其他方法相比,本文提出的方法兼具调用功能函数次数(Ncall)少和计算精度高的优势。此外,通过对比本文方法和BO-BP-MC法的分析结果可知,在调用功能函数次数相同的情况下,本文方法的计算精度远高于BO-BP-MC法,进一步印证了SMOTE算法增加的样本点可提高BP神经网络在失效曲线附近的拟合精度。
算例2是四维非线性可靠性分析问题[20],功能函数如式(6)所示:
式中,As为钢筋截面积,FY为钢筋屈服强度,FC为混凝土抗压强度,Q为荷载作用下的总弯矩,d为混凝土梁截面宽度,其值为12,b为混凝土梁截面高度,其值为19。算例2中随机变量的分布情况如表2所示。
表3给出了算例2的分析结果,其中本文方法仅需调用功能函数90次,且相对误差e仅为3.06%,由此可见本文方法兼具计算速度快和分析精度高的优势。
综合算例1和算例2的分析结果可知,本文方法不仅显著减少计算样本点个数,节省了调整超参数的时间,提高了可靠性分析效率,而且提高了BP神经网络模型的拟合精度,保证了可靠性分析结果的准确性。
算例1和算例2的分析结果验证了本文方法的可行性,现使用该方法对船用滑油冷却器抗冲击可靠性进行分析。
本文使用ABAQUS建立滑油冷却器的有限元模型,如图7所示。模型总长为3.31 m,高度为1.21 m,筒体结构直径为0.8 m,筒体结构总长为2.58 m。模型主要采用S4R薄壳单元和C3D8R实体单元,单元总数为314 985。根据实际工程情况,在滑油冷却器的外接管道处和支撑结构底部施加完全固定约束。此外,根据德国军标BV043-85中的冲击载荷施加方法对滑油冷却器进行加载。图8给出了在确定性分析下滑油冷却器极限冲击谱速度V0=0.65 m/s对应的三角形变化历程。
滑油冷却器模型随机变量的分布参数如表4所示。
滑油冷却器的功能函数如式(7)所示:
式中,σs为材料静态屈服强度,为396 MPa;σmax为冲击载荷作用下滑油冷却器的最大应力。
滑油冷却器抗冲击BP神经网络模型的训练集中UD样本点为150个,SMOTE样本点为18个。BO-BP模型验证集的eMAPE为4.85%,测试集的eMAPE为4.88%,均小于5%,满足精度要求。图9给出测试集的预测结果,其中除15号点以外,其他样本点的预测值与实际值吻合较好,而15号样本点距离失效面较远,对可靠度影响较小。综上可知,优化后的BO-BP模型的拟合精度满足要求,可应用于滑油冷却器抗冲击可靠性分析。
图10给出了可靠度随冲击载荷的变化规律,图中k为当前冲击谱速度与确定性分析情况下的极限冲击谱速度V0的比值。
在实际工程中,一般情况下结构中各部件具备95%的可靠度是可以接受的。由图10可知,滑油冷却器的可靠度为95%时对应的冲击载荷为0.8414V0,这意味着在该标准下考虑了多种不确定性因素的滑油冷却器的极限冲击载荷,大约为确定性分析情况下极限冲击载荷的84.14%。这说明各参数的不确定性降低了滑油冷却器抗冲击能力,与确定性分析相比,该结果更贴近工程实际。此外,相较于传统方法,本文方法在实际工程分析中具有更高的分析效率和更好的适用性。
本文提出了一种准确、高效、适用于实际工程的可靠性分析方法——SMOTE-BO-BP-MC法。本文首先通过两个算例验证了该方法的可行性和优越性,之后将该方法应用于滑油冷却器的抗冲击可靠性分析并得出以下结论:
(1)通过UD方法和SMOTE算法搭建的数据库,不仅使BP神经网络可以在少量样本点情况下学习到更多的信息,而且提高了模型在失效面附近的拟合精度,进而提高模型的预测能力。
(2)本文方法可以在使用少量样本点的情况下得出高精度的可靠性分析结果,而且在实际工程中也具有良好的适用性。
(3)滑油冷却器抗冲击可靠性分析结果表明,设计参数的随机性降低了滑油冷却器的抗冲击能力,以95%可靠度为标准时,降低程度为15.86%。该结果不仅验证了本文方法的可行性,而且为滑油冷却器不同等级的抗冲击设计提供了理论支撑。
  • 国家自然科学基金面上项目(52278297)
参考文献 引证文献
排序方式:
[1]
Cadini F, Santos F, Zio E. An improved adaptive Kriging-based importance technique for sampling multiple failure regions of low probability[J]. Reliability Engineering & System Safety, 2014, 131:109-117.
[2]
李宁,潘慧雨,李忠献. 一种基于自适应集成学习代理模型的结构可靠性分析方法[J]. 工程力学2023, 40(3):27-35.
Li N, Pan H Y, Li Z X. Structural reliability analysis method based on adaptive ensemble learning-surrogate model[J]. Engineering Mechanics, 2023, 40(3): 27-35. (in Chinese)
[3]
郑倩,张宏,刘啸奔. 基于BP-MC方法的断层区管道可靠性分析[J]. 油气储运2020, 39(3):277-283.
Zheng Q, Zhang H, Liu X B. Reliability analysis of pipeline in fault area based on BP-MC method[J]. Oil & Gas Storage and Transportation, 2020, 39(3): 277-283. (in Chinese)
[4]
Wen K, He L, Liu J, et al. An optimization of artificial neural network modeling methodology for the reliability assessment of corroding natural gas pipelines[J]. Journal of Loss Prevention in the Process Industries, 2019, 60:1-8.
[5]
姜逢源,董胜,张鑫. 基于改进神经网络的板桩结构可靠性分析[J]. 海洋湖沼通报2018, 2:103-109.
Jiang F Y, Dong S, Zhang X. Reliability analysis of sheet pile structure based on improved neural network[J]. Transactions of Oceanology and Limnology, 2018, 2:103-109. (in Chinese)
[6]
李永华,陈鹏,田宗睿,. 基于改进BP神经网络的结构可靠度计算方法[J]. 机械强度2021, 43(6):1359-1365.
Li Y H, Chen P, Tian Z R, et al. Structure reliability calculation method based on improved neural network[J]. Journal of Mechanical Strength, 2021, 43(6): 1359-1365. (in Chinese)
[7]
陈松坤,王德禹. 基于神经网络的蒙特卡罗可靠性分析方法[J]. 上海交通大学学报2018, 52(6):687-692.
Chen Songkun, Wang Deyu. An improved Monte Carlo reliability analysis method based on neural network[J]. Journal of Shanghai Jiaotong University, 2018, 52(6): 687-692. (in Chinese)
[8]
龙周,陈松坤,王德禹. 基于SMOTE算法的船舶结构可靠性优化设计[J]. 上海交通大学学报2019, 53(1):26-34.
Long Z, Chen S K, Wang D Y. Reliability-based design optimization of ship structures based on SMOTE algorithm[J]. Journal of Shanghai Jiaotong University, 2019, 53(1): 26-34. (in Chinese)
[9]
刘婧,王德禹. 基于SMOTE算法和动态代理模型的船舶结构可靠性优化[J]. 中国舰船研究2020, 15(5):114-123.
Liu J, Wang D Y. Reliability-based design optimization of ship structure using SMOTE algorithm and dynamic surrogate model[J]. Chinese Journal of Ship Research, 2020, 15(5): 114-123. (in Chinese)
[10]
汪文俊,周永道,方开泰. 在计算机模拟试验中不同试验设计的比较[J]. 数理统计与管理2011, 30(4):686-695.
Wang W J, Zhou Y D, Fang K T. Comparisons among different design and modeling methods for computer experiments[J]. Journal of Applied Statistics and Management, 2011, 30(4): 686-695. (in Chinese)
[11]
王少波,柴艳丽,梁醒培. 神经网络学习样本点的选取方法比较[J]. 郑州大学学报(工学版)2003, 24(1):63-65+69.
Wang S B, Chai Y L, Ling X P. Comparison of selection methods of neural network learning sample points[J]. Journal of Zhengzhou University (Engineering Science), 2003, 24(1): 63-65+69. (in Chinese)
[12]
Chawla N V, Bowyer K W, Hall L O, et al. SMOTE: synthetic minority over-sampling technique[J]. AI Access Foundation, 2002, 16:321-357.
[13]
魏翼飞,汪昭颖,李骏. 深度学习——从神经网络到深度强化学习的演进[M]. 北京:清华大学出版社,2021:58-61.
Wei Y F, Wang Z Y, Li J. Deep Learning—Evolution from neural networks to deep reinforcement learning[M]. Beijing: Tsinghua University Publishers, 2021:58-61. (in Chinese)
[14]
Kingma D, Ba J. Adam: A method for stochastic optimization[J]. Computer Science, 2014.
[15]
Cantu-Paz E, Goldberg D E, Pelikan M. BOA: The Bayesian optimization algorithm[C]//GECCO-99: Proceedings of the Genetic and Evolutionary Computation Conference, 1999.
[16]
Frazier P. A tutorial on Bayesian optimization[M/OL]. ArXiv, 2018,
[17]
李亚茹,张宇来,王佳晨. 面向超参数估计的贝叶斯优化方法综述[J]. 计算机科学2022, 49(S1):86-92.
Li Y R, Zhang Y L, Wang J C. Survey on Bayesian optimization methods for hyper-parameter tuning[J]. Computer Science, 2022, 49(S1):86-92. (in Chinese)
[18]
Echard B, Gayton N, Lemaire M, et al. A combined importance sampling and Kriging reliability method for small failure probabilities with time-demanding numerical models[J]. Reliability Engineering & System Safety, 2013, 111:232-240.
[19]
李雪剑,秦斌,肖艺峰,. 改进随机森林-蒙特卡罗法在A型液舱支座结构可靠性分析中的应用[J]. 中国舰船研究2022, 17(1):147-153+165.
Li X J, Qin B, Xiao Y F, et al. An improved random forest-Monte Carlo method and application for structural reliability analysis of A-type independent liquid tank support structure[J]. Chinese Journal of Ship Research, 2022, 17(1): 147-153+165. (in Chinese)
[20]
Nowak A S, Colins K R. Reliability of structures[M]. CRC Press, 2000.
[21]
Rashki M, Miri M, Moghaddam M A. A new efficient simulation method to approximate the probability of failure and most probable point[J]. Structural Safety, 2012, 39:22-29.
2025年第29卷第5期
PDF下载
76
35
引用本文
BibTeX
文章信息
doi: 10.3969/j.issn.1007-7294.2025.05.009
  • 接收时间:2024-11-22
  • 首发时间:2026-03-24
  • 出版时间:2025-05-20
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2024-11-22
基金
国家自然科学基金面上项目(52278297)
作者信息
    哈尔滨工程大学 航天与建筑工程学院,哈尔滨 150001

通讯作者:

通讯作者,E-mail:
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/cblx/CN/10.3969/j.issn.1007-7294.2025.05.009
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