首页 期刊 论文 学科刊群 资讯 加盟 关于
EN
image
Article(id=1320423035543339311, tenantId=1146029695717560320, journalId=1319355204128309394, issueId=1320423027695792874, articleNumber=null, orderNo=null, doi=10.3969/j.issn.1001-4837.2026.02.005, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1749398400000, receivedDateStr=2025-06-09, revisedDate=1768579200000, revisedDateStr=2026-01-17, acceptedDate=null, acceptedDateStr=null, onlineDate=1792742983947, onlineDateStr=2026-10-23, pubDate=1772208000000, pubDateStr=2026-02-28, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1792742983947, onlineIssueDateStr=2026-10-23, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1792742983947, creator=13701087609, updateTime=1792742983947, updator=13701087609, issue=Issue{id=1320423027695792874, tenantId=1146029695717560320, journalId=1319355204128309394, year='2026', volume='43', issue='2', pageStart='1', pageEnd='86', issueExtLink='null', onlineDate='null', pubDate='1772208000000', pubDateStr='2026-02-28', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1792742982076, creator='13701087609', updateTime=1792745307038, updator='13701087609', preIssue=null, nextIssue=null, articleTotal=null, ext={EN=IssueExt(id=1320432779335156588, tenantId=1146029695717560320, journalId=1319355204128309394, issueId=1320423027695792874, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1320432779335156589, tenantId=1146029695717560320, journalId=1319355204128309394, issueId=1320423027695792874, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null, downloadFileDto=null}, startPage=50, endPage=60, ext={EN=ArticleExt(id=1320423035971158320, articleId=1320423035543339311, tenantId=1146029695717560320, journalId=1319355204128309394, language=EN, title=Research on prediction method of prestress loss in concrete tank based on measured data and machine learning, columnId=1320422992044217077, journalTitle=Pressure Vessel Technology, columnName=Designs & Analyses, runingTitle=null, highlight=null, articleAbstract=

To address the difficulty in accurately monitoring and predicting the prestress loss of long‑distance prestressing strands in large‑scale structures due to duct friction，anchor deformation，and stress relaxation，a comprehensive prediction method integrating fiber optic sensing measurement data and machine learning is proposed，based on a liquefied natural gas storage tank project.This method uses fiber optic sensing technology to conduct long‑term monitoring of long‑distance prestressing strands in actual engineering，obtaining prestress loss data.Based on the measured data，a numerical simulation dataset of long‑term prestress loss is established.Multiple machine learning algorithms are used to construct prediction models，and the SHAP interpretability algorithm is further introduced to analyze the prediction basis and key influencing factors of the models.Experimental and simulation results show that the total losses of the circumferential and vertical prestressing strands of the storage tank are approximately 390 MPa and 320 MPa，respectively.The average percentage errors of the six established machine learning models in both the training set and the test set are below 3.5%，among which the XGBoost model has the smallest error，achieving 1.19% on the test set.Through SHAP analysis of multiple influencing factors，the length of the prestressing strand has the most significant effect on long‑term loss，followed by the elastic modulus of concrete，the elastic modulus of the prestressing strand，and the tensioning control stress.The research shows that machine learning models can accurately predict prestress loss and analyze the important factors causing prestress loss.This study is of great significance for the accurate evaluation of the service performance of prestressed structures.

, authors=Bocheng LI1, Jian YANG1, Decheng CAI1, Juan SU1, Qiyong CUI1, Wenwei WANG2, authorsList=Bocheng LI, Jian YANG, Decheng CAI, Juan SU, Qiyong CUI, Wenwei WANG, authorCompany=null, correspAuthors=Wenwei WANG, 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, fund=null), CN=ArticleExt(id=1320423039196578118, articleId=1320423035543339311, tenantId=1146029695717560320, journalId=1319355204128309394, language=CN, title=基于实测数据与机器学习的混凝土罐体预应力损失预测方法研究, columnId=1320422992211989239, journalTitle=压力容器, columnName=设计计算, runingTitle=null, highlight=null, articleAbstract=

针对大尺寸结构中长距离预应力钢绞线因孔道摩擦、锚具变形及应力松弛导致的预应力损失难以精准监测与预测的问题，以某液化天然气储罐项目为背景，提出一种融合光纤传感实测数据与机器学习的综合预测方法。该方法利用光纤传感技术对实际工程中的长距离预应力钢绞线进行长期监测，获取其预应力损失数据；基于实测数据建立预应力长期损失的数值仿真数据集，采用多种机器学习算法构建预测模型，并进一步引入SHAP可解释性算法对模型的预测依据与关键影响因素进行分析。试验与模拟结果表明，储罐环向与竖向预应力钢绞线的总损失分别约为390 MPa和320 MPa；所建立的6种机器学习模型在训练集和测试集中的预测平均百分比误差均低于3.5%，其中XGBoost模型误差最小，在测试集表现上1.19%。通过SHAP分析多项影响因素，其中，钢绞线长度对长期损失的影响最为显著，其次为混凝土弹性模量、钢绞线弹性模量和张拉控制应力。研究表明，采用机器学习模型可准确预测预应力损失，并分析造成预应力损失的重要因素。该研究对于预应力结构服役性能的准确评估具有重要意义。

, authors=李博成1, 杨健1, 蔡德成1, 苏娟1, 崔启勇1, 王文炜2, authorsList=李博成, 杨健, 蔡德成, 苏娟, 崔启勇, 王文炜, authorCompany=null, correspAuthors=王文炜, authorNote=

李博成（1989），男，高级工程师，主要研究方向为新材料组合结构，通信地址：300461天津市滨海新区保税区海滨十五路199号海工大厦海洋石油工程股份有限公司，E-mail：。

, correspAuthorsNote=
王文炜（1971），男，教授，博导，主要研究方向为新材料在工程中的应用，通信地址：211189江苏省南京市江宁区东南大学交通学院桥梁工程系，E-mail：。
, copyrightStatement=作者向本刊所投稿件一经本刊录用，则该论文的复制权、发行权、信息网络传播权、翻译权、汇编权等权利视为自动转让给本刊。本刊为国内各主要数据库收录期刊，本刊所发表的稿件将同时通过因特网进行网络出版或提供信息服务（包括印刷版、光盘版和网络版等各种使用方式）。, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=B9WphCfp48PpZLkk+O/vZg==, magXml=/GSK5bONDYMcmBPfy8tCYQ==, pdfUrl=null, pdf=Ca+NztDow8uu8XYxKOgtyQ==, pdfFileSize=5856952, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=QstqN7tt7G0VlHXeHQodVA==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=ZnBfcs+RbemW/TTy8UHFlA==, mapNumber=null, fund=null)}, authors=[Author(id=1320423039867666766, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=liboc@cooec.com.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1320423040039633232, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, authorId=1320423039867666766, language=EN, stringName=Bocheng LI, firstName=Bocheng, middleName=null, lastName=LI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1Offshore Oil Engineering Co.，Ltd.，Tianjin 300461，China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1320423040127713617, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, authorId=1320423039867666766, language=CN, stringName=李博成, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1海洋石油工程股份有限公司，天津 300461, bio={"content":"

李博成（1989），男，高级工程师，主要研究方向为新材料组合结构，通信地址：300461天津市滨海新区保税区海滨十五路199号海工大厦海洋石油工程股份有限公司，E-mail：。

"}, bioImg=null, bioContent=

李博成（1989），男，高级工程师，主要研究方向为新材料组合结构，通信地址：300461天津市滨海新区保税区海滨十五路199号海工大厦海洋石油工程股份有限公司，E-mail：。

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1320423039662145863, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, xref=1, ext=[AuthorCompanyExt(id=1320423039670534472, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, companyId=1320423039662145863, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1Offshore Oil Engineering Co.，Ltd.，Tianjin 300461，China), AuthorCompanyExt(id=1320423039683117385, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, companyId=1320423039662145863, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1海洋石油工程股份有限公司，天津 300461)])]), Author(id=1320423040228376915, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, 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=1320423040438092117, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, authorId=1320423040228376915, language=EN, stringName=Jian YANG, firstName=Jian, middleName=null, lastName=YANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1Offshore Oil Engineering Co.，Ltd.，Tianjin 300461，China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1320423040513589590, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, authorId=1320423040228376915, language=CN, stringName=杨健, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1海洋石油工程股份有限公司，天津 300461, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1320423039662145863, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, xref=1, ext=[AuthorCompanyExt(id=1320423039670534472, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, companyId=1320423039662145863, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1Offshore Oil Engineering Co.，Ltd.，Tianjin 300461，China), AuthorCompanyExt(id=1320423039683117385, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, companyId=1320423039662145863, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1海洋石油工程股份有限公司，天津 300461)])]), Author(id=1320423040597475672, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, 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=1320423040677167450, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, authorId=1320423040597475672, language=EN, stringName=Decheng CAI, firstName=Decheng, middleName=null, lastName=CAI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1Offshore Oil Engineering Co.，Ltd.，Tianjin 300461，China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1320423040861716827, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, authorId=1320423040597475672, language=CN, stringName=蔡德成, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1海洋石油工程股份有限公司，天津 300461, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1320423039662145863, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, xref=1, ext=[AuthorCompanyExt(id=1320423039670534472, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, companyId=1320423039662145863, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1Offshore Oil Engineering Co.，Ltd.，Tianjin 300461，China), AuthorCompanyExt(id=1320423039683117385, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, companyId=1320423039662145863, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1海洋石油工程股份有限公司，天津 300461)])]), Author(id=1320423040949797213, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, 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=1320423041025294687, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, authorId=1320423040949797213, language=EN, stringName=Juan SU, firstName=Juan, middleName=null, lastName=SU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1Offshore Oil Engineering Co.，Ltd.，Tianjin 300461，China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1320423041402782048, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, authorId=1320423040949797213, language=CN, stringName=苏娟, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1海洋石油工程股份有限公司，天津 300461, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1320423039662145863, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, xref=1, ext=[AuthorCompanyExt(id=1320423039670534472, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, companyId=1320423039662145863, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1Offshore Oil Engineering Co.，Ltd.，Tianjin 300461，China), AuthorCompanyExt(id=1320423039683117385, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, companyId=1320423039662145863, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1海洋石油工程股份有限公司，天津 300461)])]), Author(id=1320423041457308002, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, orderNo=4, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1320423041528611172, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, authorId=1320423041457308002, language=EN, stringName=Qiyong CUI, firstName=Qiyong, middleName=null, lastName=CUI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1Offshore Oil Engineering Co.，Ltd.，Tianjin 300461，China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1320423041729937765, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, authorId=1320423041457308002, language=CN, stringName=崔启勇, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1海洋石油工程股份有限公司，天津 300461, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1320423039662145863, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, xref=1, ext=[AuthorCompanyExt(id=1320423039670534472, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, companyId=1320423039662145863, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1Offshore Oil Engineering Co.，Ltd.，Tianjin 300461，China), AuthorCompanyExt(id=1320423039683117385, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, companyId=1320423039662145863, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1海洋石油工程股份有限公司，天津 300461)])]), Author(id=1320423041826406759, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, orderNo=5, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=wangwenwei@seu.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1320423042136785257, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, authorId=1320423041826406759, language=EN, stringName=Wenwei WANG, firstName=Wenwei, middleName=null, lastName=WANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2School of Transportation，Southeast University，Nanjing 211189，China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1320423042224865642, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, authorId=1320423041826406759, language=CN, stringName=王文炜, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2东南大学 交通学院，南京 211189, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1320423039758614858, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, xref=2, ext=[AuthorCompanyExt(id=1320423039767003467, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, companyId=1320423039758614858, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2School of Transportation，Southeast University，Nanjing 211189，China), AuthorCompanyExt(id=1320423039771197772, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, companyId=1320423039758614858, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2东南大学 交通学院，南京 211189)])])], keywords=[Keyword(id=1320423042623324523, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, language=EN, orderNo=1, keyword=prestress strand), Keyword(id=1320423042975646060, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, language=EN, orderNo=2, keyword=prestress loss), Keyword(id=1320423043386687853, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, language=EN, orderNo=3, keyword=prestress monitoring), Keyword(id=1320423043462185326, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, language=EN, orderNo=4, keyword=machine learning), Keyword(id=1320423043852255599, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, language=EN, orderNo=5, keyword=loss prediction), Keyword(id=1320423044242325872, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, language=CN, orderNo=1, keyword=预应力钢绞线), Keyword(id=1320423045936824689, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, language=CN, orderNo=2, keyword=预应力损失), Keyword(id=1320423046037487986, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, language=CN, orderNo=3, keyword=预应力监测), Keyword(id=1320423046112985459, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, language=CN, orderNo=4, keyword=机器学习), Keyword(id=1320423046326894964, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, language=CN, orderNo=5, keyword=损失预测)], refs=[Reference(id=1320423050722525586, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, doi=null, pmid=null, pmcid=null, year=2023, volume=20, issue=7, pageStart=2740, pageEnd=2750, url=null, language=null, rfNumber=1, rfOrder=0, authorNames=覃荷瑛, 雷静, 汤鹏飞, journalName=铁道科学与工程学报, refType=null, unstructuredReference=覃荷瑛，雷静，汤鹏飞，等.准分布FBG钢绞线对混凝土梁预应力损失的监测［J］.铁道科学与工程学报，2023，20（7）：2740-2750., articleTitle=准分布FBG钢绞线对混凝土梁预应力损失的监测, refAbstract=null), Reference(id=1320423050802217363, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, doi=null, pmid=null, pmcid=null, year=2023, volume=20, issue=7, pageStart=2740, pageEnd=2750, url=null, language=null, rfNumber=1, rfOrder=1, authorNames=QIN H Y, LEI J, TANG P F, journalName=Journal of Railway Science and Engineering, refType=null, unstructuredReference=QIN H Y，LEI J，TANG P F，et al.Prestress loss monitoring in concrete beams using quasi‑distributed FBG sensors steel strands［J］.Journal of Railway Science and Engineering，2023，20（7）：2740-2750., articleTitle=Prestress loss monitoring in concrete beams using quasi‑distributed FBG sensors steel strands, refAbstract=null), Reference(id=1320423050877714836, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, doi=null, pmid=null, pmcid=null, year=2021, volume=38, issue=10, pageStart=1, pageEnd=15, url=null, language=null, rfNumber=2, rfOrder=2, authorNames=陈学东, 范志超, 崔军, journalName=压力容器, refType=null, unstructuredReference=陈学东，范志超，崔军，等.我国压力容器高性能制造技术进展［J］.压力容器，2021，38（10）：1-15., articleTitle=我国压力容器高性能制造技术进展, refAbstract=null), Reference(id=1320423050953212309, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, doi=null, pmid=null, pmcid=null, year=2021, volume=38, issue=10, pageStart=1, pageEnd=15, url=null, language=null, rfNumber=2, rfOrder=3, authorNames=CHEN X D, FAN Z C, CUI J, journalName=Pressure Vessel Technology, refType=null, unstructuredReference=CHEN X D，FAN Z C，CUI J，et al.Progress in high‑performance manufacturing technology for pressure vessels in China［J］.Pressure Vessel Technology，2021，38（10）：1-15., articleTitle=Progress in high‑performance manufacturing technology for pressure vessels in China, refAbstract=null), Reference(id=1320423051020321174, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, doi=null, pmid=null, pmcid=null, year=2014, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=3, rfOrder=4, authorNames=李松海, journalName=null, refType=null, unstructuredReference=李松海.LNG预应力混凝土储罐极限承载力分析［D］.哈尔滨：哈尔滨工程大学，2014., articleTitle=LNG预应力混凝土储罐极限承载力分析, refAbstract=null), Reference(id=1320423051083235735, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, doi=null, pmid=null, pmcid=null, year=2014, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=3, rfOrder=5, authorNames=LI S H, journalName=null, refType=null, unstructuredReference=LI S H.Ultimate bearing capacity analysis of prestressed concrete LNG storage tank［D］.Harbin：Harbin Engineering University，2014., articleTitle=Ultimate bearing capacity analysis of prestressed concrete LNG storage tank, refAbstract=null), Reference(id=1320423051150344600, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, doi=null, pmid=null, pmcid=null, year=2025, volume=42, issue=1, pageStart=34, pageEnd=42, url=null, language=null, rfNumber=4, rfOrder=6, authorNames=袁朝庆, 房宽光, 张证柱, journalName=压力容器, refType=null, unstructuredReference=袁朝庆，房宽光，张证柱，等.新型双钢板-混凝土LNG外罐静力性能分析［J］.压力容器，2025，42（1）：34-42., articleTitle=新型双钢板-混凝土LNG外罐静力性能分析, refAbstract=null), Reference(id=1320423051213259161, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, doi=null, pmid=null, pmcid=null, year=2025, volume=42, issue=1, pageStart=34, pageEnd=42, url=null, language=null, rfNumber=4, rfOrder=7, authorNames=YUAN C Q, FANG K G, ZHANG Z Z, journalName=Pressure Vessel Technology, refType=null, unstructuredReference=YUAN C Q，FANG K G，ZHANG Z Z，et al.Static performance analysis of new double steel plate-concrete LNG outer tank［J］.Pressure Vessel Technology，2025，42（1）：34-42., articleTitle=Static performance analysis of new double steel plate-concrete LNG outer tank, refAbstract=null), Reference(id=1320423051284562330, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, doi=null, pmid=null, pmcid=null, year=2012, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=5, rfOrder=8, authorNames=毛鑫, journalName=null, refType=null, unstructuredReference=毛鑫.预制T梁有效预应力静力试验检测评估技术［D］.西安：长安大学，2012., articleTitle=预制T梁有效预应力静力试验检测评估技术, refAbstract=null), Reference(id=1320423051347476891, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, doi=null, pmid=null, pmcid=null, year=2012, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=5, rfOrder=9, authorNames=MAO X, journalName=null, refType=null, unstructuredReference=MAO X.Effective prestressed static test detection evaluation technology for precast T beam［D］.Xi’an：Chang’an University，2012., articleTitle=Effective prestressed static test detection evaluation technology for precast T beam, refAbstract=null), Reference(id=1320423051422974364, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, doi=null, pmid=null, pmcid=null, year=2021, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=6, rfOrder=10, authorNames=宁健, journalName=null, refType=null, unstructuredReference=宁健.预应力结构中FBG自感知钢绞线监测技术的应用［D］.桂林：桂林理工大学，2021., articleTitle=预应力结构中FBG自感知钢绞线监测技术的应用, refAbstract=null), Reference(id=1320423051494277533, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, doi=null, pmid=null, pmcid=null, year=2021, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=6, rfOrder=11, authorNames=NING J, journalName=null, refType=null, unstructuredReference=NING J.Research on the application of FBG self‑sening steel strand in monitoring technology of post tensioned bonded prestressed structure［D］.Guilin：Guilin University of Technology，2021., articleTitle=Research on the application of FBG self‑sening steel strand in monitoring technology of post tensioned bonded prestressed structure, refAbstract=null), Reference(id=1320423051586552222, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, doi=null, pmid=null, pmcid=null, year=2006, volume=null, issue=1, pageStart=73, pageEnd=75, url=null, language=null, rfNumber=7, rfOrder=12, authorNames=胡志坚, 胡钊芳, journalName=桥梁建设, refType=null, unstructuredReference=胡志坚，胡钊芳.实用体外预应力结构预应力损失估算方法［J］.桥梁建设，2006（1）：73-75., articleTitle=实用体外预应力结构预应力损失估算方法, refAbstract=null), Reference(id=1320423051636883871, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, doi=null, pmid=null, pmcid=null, year=2006, volume=null, issue=1, pageStart=73, pageEnd=75, url=null, language=null, rfNumber=7, rfOrder=13, authorNames=HU Z J, HU Z F, journalName=Bridge Construction, refType=null, unstructuredReference=HU Z J，HU Z F.Pactical estimation method for prestress loss of externally prestressed structures［J］.Bridge Construction，2006（1）：73-75., articleTitle=Pactical estimation method for prestress loss of externally prestressed structures, refAbstract=null), Reference(id=1320423051771101600, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, doi=null, pmid=null, pmcid=null, year=2016, volume=37, issue=11, pageStart=1510, pageEnd=1513, url=null, language=null, rfNumber=8, rfOrder=14, authorNames=刘寒冰, 罗国宝, 吴春利, journalName=哈尔滨工程大学学报, refType=null, unstructuredReference=刘寒冰，罗国宝，吴春利.简支桥梁预应力损失计算方法［J］.哈尔滨工程大学学报，2016，37（11）：1510-1513., articleTitle=简支桥梁预应力损失计算方法, refAbstract=null), Reference(id=1320423051846599073, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, doi=null, pmid=null, pmcid=null, year=2016, volume=37, issue=11, pageStart=1510, pageEnd=1513, url=null, language=null, rfNumber=8, rfOrder=15, authorNames=LIU H B, LUO G B, WU C L, journalName=Journal of Harbin Engineering University, refType=null, unstructuredReference=LIU H B，LUO G B，WU C L.Calculation method for the prestress loss of a simply‑supported bridge［J］.Journal of Harbin Engineering University，2016，37（11）：1510-1513., articleTitle=Calculation method for the prestress loss of a simply‑supported bridge, refAbstract=null), Reference(id=1320423051917902242, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, doi=null, pmid=null, pmcid=null, year=2020, volume=243, issue=null, pageStart=112172, pageEnd=null, url=null, language=null, rfNumber=9, rfOrder=16, authorNames=ATUTIS M, KAWASHIMA S, journalName=Composite Structures, refType=null, unstructuredReference=ATUTIS M，KAWASHIMA S.Analysis of flexural concrete beams prestressed with basalt composite bars.Analytical‑experimental approach［J］.Composite Structures，2020，243：112172., articleTitle=Analysis of flexural concrete beams prestressed with basalt composite bars.Analytical‑experimental approach, refAbstract=null), Reference(id=1320423051997594020, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, doi=null, pmid=null, pmcid=null, year=2020, volume=510, issue=5, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=10, rfOrder=17, authorNames=SHI H B, GUO Q, journalName=IOP Conference Series：Earth and Environmental Science, refType=null, unstructuredReference=SHI H B，GUO Q.Study of simplified calculating model on friction correlated prestress loss for PC bridges［J］.IOP Conference Series：Earth and Environmental Science，2020，510（5）：052066., articleTitle=Study of simplified calculating model on friction correlated prestress loss for PC bridges, refAbstract=null), Reference(id=1320423052098257317, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, doi=null, pmid=null, pmcid=null, year=2018, volume=38, issue=11, pageStart=97, pageEnd=105, url=null, language=null, rfNumber=11, rfOrder=18, authorNames=程旭东, 王子栋, 马川, journalName=天然气工业, refType=null, unstructuredReference=程旭东，王子栋，马川，等.大型LNG储罐外罐长期预应力损失分析［J］.天然气工业，2018，38（11）：97-105., articleTitle=大型LNG储罐外罐长期预应力损失分析, refAbstract=null), Reference(id=1320423052245057958, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, doi=null, pmid=null, pmcid=null, year=2018, volume=38, issue=11, pageStart=97, pageEnd=105, url=null, language=null, rfNumber=11, rfOrder=19, authorNames=CHENG X D, WANG Z D, MA C, journalName=Natural Gas Industry, refType=null, unstructuredReference=CHENG X D，WANG Z D，MA C，et al.Analysis on the long-term prestress loss of the external walls of large LNG tanks［J］.Natural Gas Industry，2018，38（11）：97-105., articleTitle=Analysis on the long-term prestress loss of the external walls of large LNG tanks, refAbstract=null), Reference(id=1320423052320555431, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, doi=null, pmid=null, pmcid=null, year=2017, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=12, rfOrder=20, authorNames=李小军, journalName=null, refType=null, unstructuredReference=李小军.大直径筒仓预应力损失监测与数据分析［D］.邯郸：河北工程大学，2017., articleTitle=大直径筒仓预应力损失监测与数据分析, refAbstract=null), Reference(id=1320423052400247208, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, doi=null, pmid=null, pmcid=null, year=2017, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=12, rfOrder=21, authorNames=LI X J, journalName=null, refType=null, unstructuredReference=LI X J.Prestress loss monitoring and dataanalysis of large diameter silo［D］.Handan：Hebei University of Engineering，2017., articleTitle=Prestress loss monitoring and dataanalysis of large diameter silo, refAbstract=null), Reference(id=1320423052479938985, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, doi=null, pmid=null, pmcid=null, year=1986, volume=1, issue=1, pageStart=81, pageEnd=106, url=null, language=null, rfNumber=13, rfOrder=22, authorNames=QUINLAN J R, journalName=Machine Learning, refType=null, unstructuredReference=QUINLAN J R.Induction of decision trees［J］.Machine Learning，1986，1（1）：81-106., articleTitle=Induction of decision trees, refAbstract=null), Reference(id=1320423052609962410, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, doi=null, pmid=null, pmcid=null, year=2002, volume=38, issue=4, pageStart=367, pageEnd=378, url=null, language=null, rfNumber=14, rfOrder=23, authorNames=FRIEDMAN J H, journalName=Computational Statistics & Data Analysis, refType=null, unstructuredReference=FRIEDMAN J H.Stochastic gradient boosting［J］.Computational Statistics & Data Analysis，2002，38（4）：367-378., articleTitle=Stochastic gradient boosting, refAbstract=null), Reference(id=1320423052677071275, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, doi=null, pmid=null, pmcid=null, year=2023, volume=278, issue=null, pageStart=115290, pageEnd=null, url=null, language=null, rfNumber=15, rfOrder=24, authorNames=YAZDANPANAH O, DOLATSHAHI K M, MOAMMER O, journalName=Engineering Structures, refType=null, unstructuredReference=YAZDANPANAH O，DOLATSHAHI K M，MOAMMER O.Rapid seismic fragility curves assessment of eccentrically braced frames through an output‑only nonmodel‑based procedure and machine learning techniques［J］.Engineering Structures，2023，278：115290., articleTitle=Rapid seismic fragility curves assessment of eccentrically braced frames through an output‑only nonmodel‑based procedure and machine learning techniques, refAbstract=null), Reference(id=1320423052752568748, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, doi=null, pmid=null, pmcid=null, year=2019, volume=12, issue=2, pageStart=193, pageEnd=207, url=null, language=null, rfNumber=16, rfOrder=25, authorNames=CHAKRABORTY D, ELZARKA H, journalName=Journal of Building Performance Simulation, refType=null, unstructuredReference=CHAKRABORTY D，ELZARKA H.Advanced machine learning techniques for building performance simulation：A comparative analysis［J］.Journal of Building Performance Simulation，2019，12（2）：193-207., articleTitle=Advanced machine learning techniques for building performance simulation：A comparative analysis, refAbstract=null), Reference(id=1320423052844843437, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, doi=null, pmid=null, pmcid=null, year=2003, volume=16, issue=7/8, pageStart=657, pageEnd=665, url=null, language=null, rfNumber=17, rfOrder=26, authorNames=SAMANTA B, AL-BALUSHI K R, AL-ARAIMI S A, journalName=Engineering Applications of Artificial Intelligence, refType=null, unstructuredReference=SAMANTA B，AL-BALUSHI K R，AL-ARAIMI S A.Artificial neural networks and support vector machines with genetic algorithm for bearing fault detection［J］.Engineering Applications of Artificial Intelligence，2003，16（7/8）：657-665., articleTitle=Artificial neural networks and support vector machines with genetic algorithm for bearing fault detection, refAbstract=null), Reference(id=1320423052945506734, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, doi=null, pmid=null, pmcid=null, year=2022, volume=251, issue=null, pageStart=113497, pageEnd=null, url=null, language=null, rfNumber=18, rfOrder=27, authorNames=SAROTHI S Z, AHMED K S, KHAN N I, journalName=Engineering Structures, refType=null, unstructuredReference=SAROTHI S Z，AHMED K S，KHAN N I，et al.Predicting bearing capacity of double shear bolted connections using machine learning［J］.Engineering Structures，2022，251（Part A）：113497., articleTitle=Predicting bearing capacity of double shear bolted connections using machine learning, refAbstract=null), Reference(id=1320423053016809903, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, doi=null, pmid=null, pmcid=null, year=2017, volume=null, issue=null, pageStart=4768, pageEnd=4777, url=null, language=null, rfNumber=19, rfOrder=28, authorNames=LUNDBERG S M, LEE S I, journalName=null, refType=null, unstructuredReference=LUNDBERG S M，LEE S I.A unified approach to interpreting model predictions［C］//Proceedings of the 31st International Conference on Neural Information Processing Systems.La Jolla：Neural Information Processing Systems，2017：4768-4777., articleTitle=A unified approach to interpreting model predictions, refAbstract=null)], funds=null, companyList=[AuthorCompany(id=1320423039662145863, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, xref=1, ext=[AuthorCompanyExt(id=1320423039670534472, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, companyId=1320423039662145863, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1Offshore Oil Engineering Co.，Ltd.，Tianjin 300461，China), AuthorCompanyExt(id=1320423039683117385, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, companyId=1320423039662145863, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1海洋石油工程股份有限公司，天津 300461)]), AuthorCompany(id=1320423039758614858, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, xref=2, ext=[AuthorCompanyExt(id=1320423039767003467, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, companyId=1320423039758614858, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2School of Transportation，Southeast University，Nanjing 211189，China), AuthorCompanyExt(id=1320423039771197772, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, companyId=1320423039758614858, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2东南大学 交通学院，南京 211189)])], figs=[ArticleFig(id=1320423046477889909, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, language=EN, label=Fig.1, caption=Schematic of LNG storage tank outer tank andprestress monitoring points, figureFileSmall=+qRrODYW5gkmOlWyXz3phQ==, figureFileBig=QstqN7tt7G0VlHXeHQodVA==, tableContent=null), ArticleFig(id=1320423046557581686, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, language=CN, label=图1, caption=液化天然气储罐外罐与预应力监测点示意, figureFileSmall=+qRrODYW5gkmOlWyXz3phQ==, figureFileBig=QstqN7tt7G0VlHXeHQodVA==, tableContent=null), ArticleFig(id=1320423046842794359, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, language=EN, label=Fig.2, caption=Layout of storage tank monitoring points, figureFileSmall=5sn+BkFL1DsX6l7my4tojA==, figureFileBig=3bfPjKb+q7iqfkIhbm3mxQ==, tableContent=null), ArticleFig(id=1320423046905708920, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, language=CN, label=图2, caption=储罐监测点布置, figureFileSmall=5sn+BkFL1DsX6l7my4tojA==, figureFileBig=3bfPjKb+q7iqfkIhbm3mxQ==, tableContent=null), ArticleFig(id=1320423046977012089, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, language=EN, label=Fig.3, caption=Schematic diagram of fiber bragg grating sensor embedment, figureFileSmall=EyCYxXj2f9z6SFZF84Ny2Q==, figureFileBig=1/LyXplH6d+EDugjiQtcGA==, tableContent=null), ArticleFig(id=1320423047182532986, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, language=CN, label=图3, caption=光纤光栅传感器埋设示意, figureFileSmall=EyCYxXj2f9z6SFZF84Ny2Q==, figureFileBig=1/LyXplH6d+EDugjiQtcGA==, tableContent=null), ArticleFig(id=1320423047245447547, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, language=EN, label=Fig.4, caption=Numerical attenuation curve of prestress of circumferential prestressing strands in LNG storage tank, figureFileSmall=+6pUaw99a+XQYGL7iwgNQw==, figureFileBig=/sVgHBwxWTeCp0ZXL7YAcg==, tableContent=null), ArticleFig(id=1320423047312556412, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, language=CN, label=图4, caption=LNG储罐环向预应力钢绞线预应力数值衰减曲线, figureFileSmall=+6pUaw99a+XQYGL7iwgNQw==, figureFileBig=/sVgHBwxWTeCp0ZXL7YAcg==, tableContent=null), ArticleFig(id=1320423047388053885, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, language=EN, label=Fig.5, caption=Numerical attenuation curve of prestress of vertical prestressing strands in LNG storage tank, figureFileSmall=zu77zy10hQMUWl3HgjhMXw==, figureFileBig=qhuWtb4vy7tRQ9NR9A/nzw==, tableContent=null), ArticleFig(id=1320423047576797566, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, language=CN, label=图5, caption=LNG储罐竖向预应力钢绞线预应力数值衰减曲线, figureFileSmall=zu77zy10hQMUWl3HgjhMXw==, figureFileBig=qhuWtb4vy7tRQ9NR9A/nzw==, tableContent=null), ArticleFig(id=1320423047685849472, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, language=EN, label=Fig.6, caption=Performance of six machine learning models on the training set, figureFileSmall=yf/VgpjdSXjJM7Jz/xMf4Q==, figureFileBig=j5Q9IYrmaGgqaUFFINcFiQ==, tableContent=null), ArticleFig(id=1320423047761346945, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, language=CN, label=图6, caption=6种机器学习模型在训练集上的表现, figureFileSmall=yf/VgpjdSXjJM7Jz/xMf4Q==, figureFileBig=j5Q9IYrmaGgqaUFFINcFiQ==, tableContent=null), ArticleFig(id=1320423047862010242, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, language=EN, label=Fig.7, caption=Performance of six machine learning models on the test set, figureFileSmall=CkViHlnmtVQG4tuAiZHgUg==, figureFileBig=CoWumWtk7LKTkXF/AkVsrA==, tableContent=null), ArticleFig(id=1320423047950090627, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, language=CN, label=图7, caption=6种机器学习模型在测试集上的表现, figureFileSmall=CkViHlnmtVQG4tuAiZHgUg==, figureFileBig=CoWumWtk7LKTkXF/AkVsrA==, tableContent=null), ArticleFig(id=1320423048017199492, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, language=EN, label=Fig.8, caption=Schematic diagram of the influence of various parameters on the long‑term prestress loss of long‑distance steel strands, figureFileSmall=V8AB8+Ocoh6s5jVqXUZhKg==, figureFileBig=JlsLER66zJ76yXCgBIsGfw==, tableContent=null), ArticleFig(id=1320423048092696965, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, language=CN, label=图8, caption=各参数对长距离钢绞线预应力长期损失影响示意, figureFileSmall=V8AB8+Ocoh6s5jVqXUZhKg==, figureFileBig=JlsLER66zJ76yXCgBIsGfw==, tableContent=null), ArticleFig(id=1320423048168194438, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, language=EN, label=Fig.9, caption=Schematic diagram of the contribution of various variables to the long‑term prestress loss of long‑distance steel strands, figureFileSmall=E0Tz0e3sOFNr+dyufcMrLw==, figureFileBig=+xaL/bCVX9fxYgqlfsTFcw==, tableContent=null), ArticleFig(id=1320423048243691911, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, language=CN, label=图9, caption=各变量对长距离钢绞线预应力长期损失的贡献示意, figureFileSmall=E0Tz0e3sOFNr+dyufcMrLw==, figureFileBig=+xaL/bCVX9fxYgqlfsTFcw==, tableContent=null), ArticleFig(id=1320423048314995080, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, language=EN, label=Fig.10, caption=SHAP values of each parameter in the XGBoost model, figureFileSmall=2f40LZKJZos2ga+JlfgUMg==, figureFileBig=s+wfJ+1H0Kp6Nur/R13cIw==, tableContent=null), ArticleFig(id=1320423048377909641, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, language=CN, label=图10, caption=XGBoost模型中各参数SHAP值, figureFileSmall=2f40LZKJZos2ga+JlfgUMg==, figureFileBig=s+wfJ+1H0Kp6Nur/R13cIw==, tableContent=null), ArticleFig(id=1320423048457601418, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, language=EN, label=Tab.1, caption=

Circumferential prestress loss value of storage tanks

, figureFileSmall=null, figureFileBig=null, tableContent=
时间/d预应力损失值/MPa
监测点1监测点2监测点4监测点5
1100.3285.3192.8195.31
2130.90128.24129.57135.15
3182.65188.10185.38192.99
5200.71195.85198.28203.31
8221.12228.31224.72232.76
11246.48250.86248.67256.01
14263.39265.68264.53271.36
21289.11282.16285.63290.15
28312.60301.77307.19310.73
35334.78320.53327.65330.34
42341.55354.19347.87357.28
49356.90360.32358.61365.71
56350.70365.23357.97367.85
63365.66380.00372.83382.66
70382.60384.00383.30389.90
77384.33377.73381.03385.63
84391.58389.66390.62396.39
98389.12385.73387.42392.82
112392.01379.52394.52393.27
126392.10379.57390.73391.40
140401.24383.39392.31394.10
160401.25388.49394.87397.93
180391.50384.74388.12392.68
200389.31381.20385.25389.47
), ArticleFig(id=1320423048541487499, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, language=CN, label=表1, caption=

储罐环向预应力损失值

, figureFileSmall=null, figureFileBig=null, tableContent=
时间/d预应力损失值/MPa
监测点1监测点2监测点4监测点5
1100.3285.3192.8195.31
2130.90128.24129.57135.15
3182.65188.10185.38192.99
5200.71195.85198.28203.31
8221.12228.31224.72232.76
11246.48250.86248.67256.01
14263.39265.68264.53271.36
21289.11282.16285.63290.15
28312.60301.77307.19310.73
35334.78320.53327.65330.34
42341.55354.19347.87357.28
49356.90360.32358.61365.71
56350.70365.23357.97367.85
63365.66380.00372.83382.66
70382.60384.00383.30389.90
77384.33377.73381.03385.63
84391.58389.66390.62396.39
98389.12385.73387.42392.82
112392.01379.52394.52393.27
126392.10379.57390.73391.40
140401.24383.39392.31394.10
160401.25388.49394.87397.93
180391.50384.74388.12392.68
200389.31381.20385.25389.47
), ArticleFig(id=1320423048612790668, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, language=EN, label=Tab.2, caption=

Vertical prestress loss value of the storage tank

, figureFileSmall=null, figureFileBig=null, tableContent=
时间/d预应力损失值/MPa
监测点1监测点2监测点4监测点5
1124.67128.56128.25134.65
3219.00194.11208.20207.40
4221.50196.72210.75209.99
5245.00240.94244.61249.03
6248.89242.94247.56251.50
7252.13241.50248.46251.23
8258.33240.83251.22252.28
10259.83242.83252.97254.15
11261.56243.50254.17255.08
12267.83246.72258.92259.07
13272.17250.44262.95262.95
14270.89252.89263.53264.46
18288.39274.50283.08268.49
20276.50264.89272.33274.86
24301.56291.22298.03300.88
28297.50290.44295.61299.28
32300.83297.28300.70305.24
36310.06301.50307.42310.71
40310.16296.39304.91306.90
47304.00297.06302.17305.86
53308.39304.06307.86312.21
60314.89316.50317.33323.17
67324.44308.17325.16322.91
74327.44314.33322.53320.48
82321.50312.39318.58321.74
90319.00312.28317.28328.54
98325.00316.22322.25325.49
108317.39309.67322.51322.34
120324.83311.83319.97322.15
133320.28310.50317.03320.01
149327.50314.56322.67324.86
161322.28311.94318.75325.43
175325.78311.44320.25322.10
187326.21308.72319.11320.16
200326.00312.61320.95319.42
), ArticleFig(id=1320423048692482445, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, language=CN, label=表2, caption=

储罐竖向预应力损失值

, figureFileSmall=null, figureFileBig=null, tableContent=
时间/d预应力损失值/MPa
监测点1监测点2监测点4监测点5
1124.67128.56128.25134.65
3219.00194.11208.20207.40
4221.50196.72210.75209.99
5245.00240.94244.61249.03
6248.89242.94247.56251.50
7252.13241.50248.46251.23
8258.33240.83251.22252.28
10259.83242.83252.97254.15
11261.56243.50254.17255.08
12267.83246.72258.92259.07
13272.17250.44262.95262.95
14270.89252.89263.53264.46
18288.39274.50283.08268.49
20276.50264.89272.33274.86
24301.56291.22298.03300.88
28297.50290.44295.61299.28
32300.83297.28300.70305.24
36310.06301.50307.42310.71
40310.16296.39304.91306.90
47304.00297.06302.17305.86
53308.39304.06307.86312.21
60314.89316.50317.33323.17
67324.44308.17325.16322.91
74327.44314.33322.53320.48
82321.50312.39318.58321.74
90319.00312.28317.28328.54
98325.00316.22322.25325.49
108317.39309.67322.51322.34
120324.83311.83319.97322.15
133320.28310.50317.03320.01
149327.50314.56322.67324.86
161322.28311.94318.75325.43
175325.78311.44320.25322.10
187326.21308.72319.11320.16
200326.00312.61320.95319.42
), ArticleFig(id=1320423050340843918, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, language=EN, label=Tab.3, caption=

Hyperparameter values of machine learning algorithms obtained by grid search optimization

, figureFileSmall=null, figureFileBig=null, tableContent=
算法超参数解释
DT dmax=7决策树最大深度
nmax=26决策树最大叶节点个数
nf=4用于数据划分的最大特征数
Criterion=Friedman-mse采用Friedman-mse系数作为叶节点划分准则
RF ner=60随机森林中决策树的棵树
dmax=6决策树最大深度
nmax=25决策树最大叶节点个数
nf=6用于数据划分的最大特征数
Criterion=Absolute-error采用Absolute-error系数作为叶节点划分准则
ERT ner=100极端随机树中决策树的棵树
dmax=8决策树最大深度
nmax=30决策树最大叶节点个数
nf=4用于数据划分的最大特征数
Criterion=Poisson采用Poisson系数作为叶节点划分准则
GBDT ner=100梯度提升树中决策树的棵树
lr=0.1用于权重更新的学习率
Loss=Squared-error损失函数
dmax=4决策树最大深度
nmax=10决策树最大叶节点个数
nf=4用于数据划分的最大特征数
Criterion=Friedman-mse采用Friedman-mse系数作为叶节点划分准则
XGBoost ner=80极限梯度提升树中决策树的棵树
lr=0.5用于权重更新的学习率
γ=0.001控制叶节点分裂的最小收益
α=0L1正则化系数
λ=1L2正则化系数
Objective:reg:squarederror使用reg:squarederror进行回归任务
ANN α=0.01L2正则化强度
nhl=10隐藏层层数
lr=0.01用于权重更新的学习率
itermax=20 000主循环的最大迭代次数
Activation function:logistic使用logistic函数作为激活函数
), ArticleFig(id=1320423050441507215, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, language=CN, label=表3, caption=

网格搜索优化获得的机器学习算法超参数数值

, figureFileSmall=null, figureFileBig=null, tableContent=
算法超参数解释
DT dmax=7决策树最大深度
nmax=26决策树最大叶节点个数
nf=4用于数据划分的最大特征数
Criterion=Friedman-mse采用Friedman-mse系数作为叶节点划分准则
RF ner=60随机森林中决策树的棵树
dmax=6决策树最大深度
nmax=25决策树最大叶节点个数
nf=6用于数据划分的最大特征数
Criterion=Absolute-error采用Absolute-error系数作为叶节点划分准则
ERT ner=100极端随机树中决策树的棵树
dmax=8决策树最大深度
nmax=30决策树最大叶节点个数
nf=4用于数据划分的最大特征数
Criterion=Poisson采用Poisson系数作为叶节点划分准则
GBDT ner=100梯度提升树中决策树的棵树
lr=0.1用于权重更新的学习率
Loss=Squared-error损失函数
dmax=4决策树最大深度
nmax=10决策树最大叶节点个数
nf=4用于数据划分的最大特征数
Criterion=Friedman-mse采用Friedman-mse系数作为叶节点划分准则
XGBoost ner=80极限梯度提升树中决策树的棵树
lr=0.5用于权重更新的学习率
γ=0.001控制叶节点分裂的最小收益
α=0L1正则化系数
λ=1L2正则化系数
Objective:reg:squarederror使用reg:squarederror进行回归任务
ANN α=0.01L2正则化强度
nhl=10隐藏层层数
lr=0.01用于权重更新的学习率
itermax=20 000主循环的最大迭代次数
Activation function:logistic使用logistic函数作为激活函数
), ArticleFig(id=1320423050542170512, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, language=EN, label=Tab.4, caption=

Baseline values，predicted values and actual valuesof four machine learning models

, figureFileSmall=null, figureFileBig=null, tableContent=
项目RF模型ERT模型

GBDT

模型

XGBoost模型
基线值/MPa236.33236.40234.60235.19
预测值/MPa249.64252.42250.21248.35
实际值/MPa248248248248
预测值与实际值的误差/%0.661.780.890.14
), ArticleFig(id=1320423050621862289, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, language=CN, label=表4, caption=

4种机器学习模型基线值、预测值与实际值

, figureFileSmall=null, figureFileBig=null, tableContent=
项目RF模型ERT模型

GBDT

模型

XGBoost模型
基线值/MPa236.33236.40234.60235.19
预测值/MPa249.64252.42250.21248.35
实际值/MPa248248248248
预测值与实际值的误差/%0.661.780.890.14
)], attaches=null, journal=Journal(id=1319354845020389520, delFlag=0, nameCn=压力容器, nameEn=Pressure Vessel Technology, nameHistory1=null, nameHistory2=null, issn=1001-4837, eissn=null, cn=34-1058/TH, coden=null, periodic=0, language=CN, oaType=null, ccby=null, superviseOffice=null, ownerOffice=null, pubOffice=null, editorOffice=null, officeType=null, aims=null, clcCode=null, officeProv=null, officeCity=null, officeAddr=null, officeZip=null, officeEmail=null, officePhone=null, editDirector=null, officeDirector=null, officeDirectorPhone=null, officeStaffNum=null, officeEmpNum=null, coverPicUrl=jxjNdnQvHSQ8b9q0zS7Bgw==, journalPrice=null, startedYear=null, abbrevIsoEn=Pressure Vessel Technology, journalRemark=null, publicationField=null, createdTime=1792488307482, updatedTime=1792488496537, createdBy=18614031015, updatedBy=13701087609, firstLetterCn=Y, firstLetterEn=Y, subjectCode=Engineering, subjectName=null, subjectCodeEn=Engineering, subjectNameEn=null, picCn=jxjNdnQvHSQ8b9q0zS7Bgw==, picEn=4fVBwqRFt4uCO8g42aXObg==, jcr=null, cjcr=null, exts=[JournalExt(id=1319355638048740090, language=CN, name=压力容器, 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=1792488496553, updatedTime=1792488496553, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=https://ylrq.portal.founderss.cn, submissionEditorUrl=https://journal.ids.fzyun.cn, submissionReviewUrl=https://ylrq.portal.founderss.cn, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1319355638103266043, language=EN, name=Pressure Vessel Technology, 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=1792488496566, updatedTime=1792488496566, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=https://ylrq.portal.founderss.cn, submissionEditorUrl=https://journal.ids.fzyun.cn, submissionReviewUrl=https://ylrq.portal.founderss.cn, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1319355204128309394, websiteList=[Website(id=1319376331645764504, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1319355204128309394, 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/ylrq/CN, language=CN, createTime=1792493430291, createBy=18614031015, updateTime=1792493471510, updateBy=18614031015, name=压力容器-中文, tplId=1146099689490845704, title=压力容器, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1319376610952856568, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1319376331645764504, code=articleTextType, value=kx, createTime=1792493496883, updateTime=1792493496883, creator=18614031015, updator=18614031015), WebsiteProps(id=1319376610923496437, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1319376331645764504, code=banner, value=null, createTime=1792493496876, updateTime=1792493496876, creator=18614031015, updator=18614031015), WebsiteProps(id=1319376610969633787, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1319376331645764504, code=grayFlag, value=0, createTime=1792493496887, updateTime=1792493496887, creator=18614031015, updator=18614031015), WebsiteProps(id=1319376610910913524, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1319376331645764504, code=logo, value=https://castjournals.cast.org.cn/joweb/ylrq/CN/file/pic?fileId=jTQ3ULyAlxRu0s8fI4nfng==, createTime=1792493496873, updateTime=1792493496873, creator=18614031015, updator=18614031015), WebsiteProps(id=1319376610986411005, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1319376331645764504, code=minRunFlag, value=0, createTime=1792493496891, updateTime=1792493496891, creator=18614031015, updator=18614031015), WebsiteProps(id=1319376610944467959, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1319376331645764504, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/ylrq/CN/file/pic, createTime=1792493496881, updateTime=1792493496881, creator=18614031015, updator=18614031015), WebsiteProps(id=1319376610978022396, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1319376331645764504, code=silenceFlag, value=0, createTime=1792493496889, updateTime=1792493496889, creator=18614031015, updator=18614031015), WebsiteProps(id=1319376610936079350, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1319376331645764504, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1792493496879, updateTime=1792493496879, creator=18614031015, updator=18614031015), WebsiteProps(id=1319376610957050873, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1319376331645764504, code=themeColor, value=null, createTime=1792493496884, updateTime=1792493496884, creator=18614031015, updator=18614031015), WebsiteProps(id=1319376610965439482, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1319376331645764504, code=themeStyle, value=null, createTime=1792493496886, updateTime=1792493496886, creator=18614031015, updator=18614031015)]), Website(id=1319376331893228450, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1319355204128309394, 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/ylrq/EN, language=EN, createTime=1792493430350, createBy=18614031015, updateTime=1792493467616, updateBy=18614031015, name=压力容器-英文, tplId=1146101810881728533, title=Pressure Vessel Technology, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1319376586462315499, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1319376331893228450, code=articleTextType, value=kx, createTime=1792493491044, updateTime=1792493491044, creator=18614031015, updator=18614031015), WebsiteProps(id=1319376586432955368, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1319376331893228450, code=banner, value=null, createTime=1792493491037, updateTime=1792493491037, creator=18614031015, updator=18614031015), WebsiteProps(id=1319376586500064238, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1319376331893228450, code=grayFlag, value=0, createTime=1792493491053, updateTime=1792493491053, creator=18614031015, updator=18614031015), WebsiteProps(id=1319376586420372455, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1319376331893228450, code=logo, value=https://castjournals.cast.org.cn/joweb/ylrq/EN/file/pic?fileId=jTQ3ULyAlxRu0s8fI4nfng==, createTime=1792493491034, updateTime=1792493491034, creator=18614031015, updator=18614031015), WebsiteProps(id=1319376586521035760, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1319376331893228450, code=minRunFlag, value=0, createTime=1792493491058, updateTime=1792493491058, creator=18614031015, updator=18614031015), WebsiteProps(id=1319376586453926890, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1319376331893228450, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/ylrq/EN/file/pic, createTime=1792493491042, updateTime=1792493491042, creator=18614031015, updator=18614031015), WebsiteProps(id=1319376586512647151, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1319376331893228450, code=silenceFlag, value=0, createTime=1792493491056, updateTime=1792493491056, creator=18614031015, updator=18614031015), WebsiteProps(id=1319376586441343977, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1319376331893228450, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_en_623/, createTime=1792493491039, updateTime=1792493491039, creator=18614031015, updator=18614031015), WebsiteProps(id=1319376586474898412, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1319376331893228450, code=themeColor, value=null, createTime=1792493491047, updateTime=1792493491047, creator=18614031015, updator=18614031015), WebsiteProps(id=1319376586487481325, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1319376331893228450, code=themeStyle, value=null, createTime=1792493491050, updateTime=1792493491050, creator=18614031015, updator=18614031015)])], journalTitle=压力容器, weixinUrl=null, journalUrl=https://www.pvtjournal.com/, iacademicId=null, status=1, seqNo=null, journalTitleEn=Pressure Vessel Technology, journalPhotoCn=jxjNdnQvHSQ8b9q0zS7Bgw==, journalPhotoEn=4fVBwqRFt4uCO8g42aXObg==, journalFirstLetter=Y, 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, interPubPlatform=, interPubPlatformUrl=null), detailUrlCn=https://castjournals.cast.org.cn/joweb/ylrq/CN/10.3969/j.issn.1001-4837.2026.02.005, detailUrlEn=https://castjournals.cast.org.cn/joweb/ylrq/EN/10.3969/j.issn.1001-4837.2026.02.005, pdfUrlCn=https://castjournals.cast.org.cn/joweb/ylrq/CN/PDF/10.3969/j.issn.1001-4837.2026.02.005, pdfUrlEn=https://castjournals.cast.org.cn/joweb/ylrq/EN/PDF/10.3969/j.issn.1001-4837.2026.02.005, aliStartDate=0, aliEndDate=0, collectionFlag=false, citedCount=null, citedUrl=null, previewStatus=0, delFlag=0, hasFullText=1, orderTime=1772208000000, fullTextJson=null, articleText=null, reference=null)
收藏切换
基于实测数据与机器学习的混凝土罐体预应力损失预测方法研究
收藏切换
PDF下载
李博成 1 , 杨健 1 , 蔡德成 1 , 苏娟 1 , 崔启勇 1 , 王文炜 2
压力容器 | 设计计算 2026,43(2): 50-60
收起
收藏切换
压力容器 |设计计算 2026 , 43 (2) : 50 -60
基于实测数据与机器学习的混凝土罐体预应力损失预测方法研究
全屏
[Author(id=1320423039867666766, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=liboc@cooec.com.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1320423040039633232, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, authorId=1320423039867666766, language=EN, stringName=Bocheng LI, firstName=Bocheng, middleName=null, lastName=LI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1Offshore Oil Engineering Co.，Ltd.，Tianjin 300461，China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1320423040127713617, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, authorId=1320423039867666766, language=CN, stringName=李博成, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1海洋石油工程股份有限公司，天津 300461, bio={"content":"

李博成（1989），男，高级工程师，主要研究方向为新材料组合结构，通信地址：300461天津市滨海新区保税区海滨十五路199号海工大厦海洋石油工程股份有限公司，E-mail：。

"}, bioImg=null, bioContent=

李博成（1989），男，高级工程师，主要研究方向为新材料组合结构，通信地址：300461天津市滨海新区保税区海滨十五路199号海工大厦海洋石油工程股份有限公司，E-mail：。

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1320423039662145863, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, xref=1, ext=[AuthorCompanyExt(id=1320423039670534472, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, companyId=1320423039662145863, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1Offshore Oil Engineering Co.，Ltd.，Tianjin 300461，China), AuthorCompanyExt(id=1320423039683117385, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, companyId=1320423039662145863, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1海洋石油工程股份有限公司，天津 300461)])]), Author(id=1320423040228376915, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, 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=1320423040438092117, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, authorId=1320423040228376915, language=EN, stringName=Jian YANG, firstName=Jian, middleName=null, lastName=YANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1Offshore Oil Engineering Co.，Ltd.，Tianjin 300461，China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1320423040513589590, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, authorId=1320423040228376915, language=CN, stringName=杨健, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1海洋石油工程股份有限公司，天津 300461, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1320423039662145863, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, xref=1, ext=[AuthorCompanyExt(id=1320423039670534472, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, companyId=1320423039662145863, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1Offshore Oil Engineering Co.，Ltd.，Tianjin 300461，China), AuthorCompanyExt(id=1320423039683117385, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, companyId=1320423039662145863, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1海洋石油工程股份有限公司，天津 300461)])]), Author(id=1320423040597475672, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, 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=1320423040677167450, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, authorId=1320423040597475672, language=EN, stringName=Decheng CAI, firstName=Decheng, middleName=null, lastName=CAI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1Offshore Oil Engineering Co.，Ltd.，Tianjin 300461，China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1320423040861716827, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, authorId=1320423040597475672, language=CN, stringName=蔡德成, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1海洋石油工程股份有限公司，天津 300461, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1320423039662145863, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, xref=1, ext=[AuthorCompanyExt(id=1320423039670534472, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, companyId=1320423039662145863, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1Offshore Oil Engineering Co.，Ltd.，Tianjin 300461，China), AuthorCompanyExt(id=1320423039683117385, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, companyId=1320423039662145863, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1海洋石油工程股份有限公司，天津 300461)])]), Author(id=1320423040949797213, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, 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=1320423041025294687, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, authorId=1320423040949797213, language=EN, stringName=Juan SU, firstName=Juan, middleName=null, lastName=SU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1Offshore Oil Engineering Co.，Ltd.，Tianjin 300461，China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1320423041402782048, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, authorId=1320423040949797213, language=CN, stringName=苏娟, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1海洋石油工程股份有限公司，天津 300461, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1320423039662145863, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, xref=1, ext=[AuthorCompanyExt(id=1320423039670534472, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, companyId=1320423039662145863, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1Offshore Oil Engineering Co.，Ltd.，Tianjin 300461，China), AuthorCompanyExt(id=1320423039683117385, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, companyId=1320423039662145863, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1海洋石油工程股份有限公司，天津 300461)])]), Author(id=1320423041457308002, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, orderNo=4, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1320423041528611172, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, authorId=1320423041457308002, language=EN, stringName=Qiyong CUI, firstName=Qiyong, middleName=null, lastName=CUI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1Offshore Oil Engineering Co.，Ltd.，Tianjin 300461，China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1320423041729937765, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, authorId=1320423041457308002, language=CN, stringName=崔启勇, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1海洋石油工程股份有限公司，天津 300461, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1320423039662145863, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, xref=1, ext=[AuthorCompanyExt(id=1320423039670534472, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, companyId=1320423039662145863, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1Offshore Oil Engineering Co.，Ltd.，Tianjin 300461，China), AuthorCompanyExt(id=1320423039683117385, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, companyId=1320423039662145863, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1海洋石油工程股份有限公司，天津 300461)])]), Author(id=1320423041826406759, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, orderNo=5, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=wangwenwei@seu.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1320423042136785257, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, authorId=1320423041826406759, language=EN, stringName=Wenwei WANG, firstName=Wenwei, middleName=null, lastName=WANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2School of Transportation，Southeast University，Nanjing 211189，China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1320423042224865642, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, authorId=1320423041826406759, language=CN, stringName=王文炜, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2东南大学 交通学院，南京 211189, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1320423039758614858, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, xref=2, ext=[AuthorCompanyExt(id=1320423039767003467, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, companyId=1320423039758614858, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2School of Transportation，Southeast University，Nanjing 211189，China), AuthorCompanyExt(id=1320423039771197772, tenantId=1146029695717560320, journalId=1319355204128309394, articleId=1320423035543339311, companyId=1320423039758614858, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2东南大学 交通学院，南京 211189)])])]
李博成1 , 杨健1, 蔡德成1, 苏娟1, 崔启勇1, 王文炜2
作者信息
  • 1海洋石油工程股份有限公司，天津 300461
  • 2东南大学 交通学院，南京 211189
通讯作者:
王文炜（1971），男，教授，博导，主要研究方向为新材料在工程中的应用，通信地址：211189江苏省南京市江宁区东南大学交通学院桥梁工程系，E-mail：。
作者简介:

李博成（1989），男，高级工程师，主要研究方向为新材料组合结构，通信地址：300461天津市滨海新区保税区海滨十五路199号海工大厦海洋石油工程股份有限公司，E-mail：。

Research on prediction method of prestress loss in concrete tank based on measured data and machine learning
Bocheng LI1 , Jian YANG1, Decheng CAI1, Juan SU1, Qiyong CUI1, Wenwei WANG2
Affiliations
  • 1Offshore Oil Engineering Co.，Ltd.，Tianjin 300461，China
  • 2School of Transportation，Southeast University，Nanjing 211189，China
出版时间: 2026-02-28 doi: 10.3969/j.issn.1001-4837.2026.02.005
文章导航
收藏切换
摘要
收起

针对大尺寸结构中长距离预应力钢绞线因孔道摩擦、锚具变形及应力松弛导致的预应力损失难以精准监测与预测的问题，以某液化天然气储罐项目为背景，提出一种融合光纤传感实测数据与机器学习的综合预测方法。该方法利用光纤传感技术对实际工程中的长距离预应力钢绞线进行长期监测，获取其预应力损失数据；基于实测数据建立预应力长期损失的数值仿真数据集，采用多种机器学习算法构建预测模型，并进一步引入SHAP可解释性算法对模型的预测依据与关键影响因素进行分析。试验与模拟结果表明，储罐环向与竖向预应力钢绞线的总损失分别约为390 MPa和320 MPa；所建立的6种机器学习模型在训练集和测试集中的预测平均百分比误差均低于3.5%，其中XGBoost模型误差最小，在测试集表现上1.19%。通过SHAP分析多项影响因素，其中，钢绞线长度对长期损失的影响最为显著，其次为混凝土弹性模量、钢绞线弹性模量和张拉控制应力。研究表明，采用机器学习模型可准确预测预应力损失，并分析造成预应力损失的重要因素。该研究对于预应力结构服役性能的准确评估具有重要意义。

预应力钢绞线  /  预应力损失  /  预应力监测  /  机器学习  /  损失预测

To address the difficulty in accurately monitoring and predicting the prestress loss of long‑distance prestressing strands in large‑scale structures due to duct friction，anchor deformation，and stress relaxation，a comprehensive prediction method integrating fiber optic sensing measurement data and machine learning is proposed，based on a liquefied natural gas storage tank project.This method uses fiber optic sensing technology to conduct long‑term monitoring of long‑distance prestressing strands in actual engineering，obtaining prestress loss data.Based on the measured data，a numerical simulation dataset of long‑term prestress loss is established.Multiple machine learning algorithms are used to construct prediction models，and the SHAP interpretability algorithm is further introduced to analyze the prediction basis and key influencing factors of the models.Experimental and simulation results show that the total losses of the circumferential and vertical prestressing strands of the storage tank are approximately 390 MPa and 320 MPa，respectively.The average percentage errors of the six established machine learning models in both the training set and the test set are below 3.5%，among which the XGBoost model has the smallest error，achieving 1.19% on the test set.Through SHAP analysis of multiple influencing factors，the length of the prestressing strand has the most significant effect on long‑term loss，followed by the elastic modulus of concrete，the elastic modulus of the prestressing strand，and the tensioning control stress.The research shows that machine learning models can accurately predict prestress loss and analyze the important factors causing prestress loss.This study is of great significance for the accurate evaluation of the service performance of prestressed structures.

prestress strand  /  prestress loss  /  prestress monitoring  /  machine learning  /  loss prediction
李博成, 杨健, 蔡德成, 苏娟, 崔启勇, 王文炜. 基于实测数据与机器学习的混凝土罐体预应力损失预测方法研究. 压力容器, 2026 , 43 (2) : 50 -60 . DOI: 10.3969/j.issn.1001-4837.2026.02.005
Bocheng LI, Jian YANG, Decheng CAI, Juan SU, Qiyong CUI, Wenwei WANG. Research on prediction method of prestress loss in concrete tank based on measured data and machine learning[J]. Pressure Vessel Technology, 2026 , 43 (2) : 50 -60 . DOI: 10.3969/j.issn.1001-4837.2026.02.005
正文
收起
0　引言
收起
随着预应力技术在土木工程领域中的快速发展，预应力混凝土结构为大跨、超长、重载、防裂等工程难题提供了新的思路和技术方案，解决了传统钢筋混凝土结构自重和截面较大、裂缝和挠度控制性差、经济性和美观性不足等问题，同时还相对提高了结构刚度和耐久性，在近几十年间得到了广泛的工程应用［1-2］。由于以上特点，液化天然气（LNG）储罐外罐多采用预应力混凝土结构以容纳和保护内罐，预应力混凝土结构全容式LNG储罐已已成为世界上应用最多的LNG储罐形式［3-4］。然而，在预应力混凝土外罐施工及长期服役过程中，钢绞线与孔道的摩擦、锚固装置的变形、钢绞线的应力松弛、混凝土的徐变收缩等因素都会导致预应力的损失。随着预应力损失值的逐步增加，结构的安全度逐渐降低，可能存在一定的安全隐患和服役风险，甚至会引发事故［5］。因此，判断预应力混凝土外罐的安全状态，需要对预应力损失进行预测。
预应力钢绞线是预应力混凝土结构中的关键受力单元，服役期间处于较高应力状态，其预应力值的大小是否能够符合要求，关系到整个预应力结构的安全［6］。因此，关于预应力混凝土结构应力状态的分析与研究重点应为预应力损失的评价判断。基于预应力的损失，国内外学者展开了广泛的研究。胡志坚等［7］分别对预应力摩阻损失、锚具变形损失、混凝土收缩徐变损失和时效损失进行分项估算，提出了偏转块处体外束偏角误差等参数，并通过实际工程项目数据进行了验证。刘寒冰等［8］利用等效思想和力学分析，推导出预应力简支梁跨中截面预应力损失的近似计算公式，并以实际工程为依托，进行参数标定和对比分析，验证了该方法的有效性和可靠性。ATUTIS等［9］研究发现，瞬时和时变预应力损失、截面应力与应变、挠度、开裂行为是一个相互关联的过程，且应力松弛占有很重要的比重。SHI等［10］为了量化预应力摩擦的相关损失，在现行规范的基础上，提出了一种通用且与摩擦相关的预应力损失简化计算模型，该方法在衰减曲线上与当前代码的匹配度较高，具有较高精度。现有研究表明导致预应力损失是由多种因素叠加产生的。然而，目前施工过程中使用的控制张拉设备无法测量钢绞线的实际应力状态，难以具体分析预应力损失产生原因。因此，如何实现较为准确的预应力钢绞线应力状态监测具有重大意义。
本文依托实际储罐结构，采用光纤传感技术采集长距离预应力损失数据，并利用机器学习模型和SHAP可解释方法分析损失原因。参考国内外研究和工程实际，将影响预应力损失的因素总结为钢绞线长度、混凝土弹性模量、钢绞线弹性模量、张拉控制应力、损失时间、钢绞线公称直径共6组相关参数。基于现场实测数据，建立长距离钢绞线预应力长期损失的数据集；通过机器学习算法建立精确的长距离钢绞线预应力长期损失机器学习预测模型，并使用SHAP算法对机器学习模型的预测过程进行分析，得到长距离钢绞线长期损失的重要性因素排序，最终实现基于机器学习的预应力损失预测分析方法。研究为混凝土罐体预应力损失预测方法提供了新的思路。
1　工程概况
收起
龙口南山液化天然气（LNG）接收站一期工程规模为4台22万 m3混凝土储罐，混凝土储罐外罐采用后张法有粘结预应力结构，混凝土外罐内直径88 m，墙体高度50.4 m。为确保罐体结构的稳定性，罐体墙的四周布设4个扶壁柱。在罐体墙和扶壁柱内部布置预应力钢绞线束，这些钢绞线束由环向水平钢绞线束和竖向钢绞线束组成，构成了储罐预应力体系的核心部分。环向水平预应力钢绞线束共有96层，合计192束。每束钢绞线包含25根，长度约145 m，环绕罐体半圈布置，每两束对应形成一周圈，水平地嵌入在罐体壁内。环向和竖向预应力采用⌀s15.2的预应力钢绞线，钢绞线抗拉标准强度fpk=1 860 MPa，设计锚下张拉控制应力均为fcon=0.8fpk=1 488 MPa。环向预应力钢绞线采用两端对称张拉，竖向预应力钢绞线在储罐顶部横梁上采用单端张拉。储罐外罐及其预应力监测点布置如图1所示。
2　实测数据分析
收起
2.1　监测方案
预应力监测采用光纤光栅埋入式应变计传感器，其量程为±2 000 με，光栅数量为1，光栅中心波长为1 528~1 563 nm。将光纤光栅贴在预应力钢绞线表面，之后进行钢绞线张拉，在预应力张拉施工过程中，做好对钢绞线伸长量的测量和记录。监测所用的光纤光栅高速解调仪为SuperHawk8000series型，其测量模式为应变模式，通道数为8，扫描频率1 000 Hz，通过现场测定，初始波长设为1 533.987 nm。
预应力混凝土外罐墙体上部的混凝土及钢绞线在施工及运行过程中应力水平较高，因此，在高42 m处（第12层墙体，距罐顶7 m处）两束钢绞线的4个端点和其中一束钢绞线中间，共设置5个环向钢绞线监测点，着重考虑此处预应力损失；竖向预应力钢绞136束，每束12根钢绞线，顶端锚固在罐壁顶部的环梁上，底端锚固在承台下面，每束长约50 m，总长约6 854 m。在对称的4个扶壁柱处钢绞线的顶端和其中一束钢绞线的底部，共设置5个监测点，如图2所示。相关光栅现场布置如图3所示。
2.2　监测结果及分析
在监测过程中，由于浇筑混凝土时与光纤传感器之间存在拉伸、摩擦，导致光纤传感器的失效（测试过程中LNG环向监测点3、竖向监测点4失效）。因此，仅针对没有失效传感器获取的数据进行数据分析。将采集到的预应力钢绞线波长信息转换为应力数据，对LNG储罐环向预应力钢绞线（4个监测点）和竖向预应力钢绞线（4个监测点）数据进行汇总，结果见表1、表2。
对储罐环向预应力钢绞线进行为期200 d的预应力监测，结果如图4所示。监测点1，2，4，5的预应力损失值变化趋势相同，前期增大较快，在70 d后增长速率逐渐降低，预应力损失值趋于稳定。综合监测点1，2，4，5的监测数据，可以得到环向预应力钢绞线张拉完成后的瞬时损失约为125 MPa，长期预应力损失值约为265 MPa，故预应力钢绞线总损失值约为390 MPa。
对储罐竖向预应力钢绞线进行为期200 d的预应力监测，结果如图5所示。监测点1，2的预应力损失值变化趋势相同，前期增大较快，在70 d后增长速率逐渐降低，预应力损失值趋于稳定。监测点1，5的监测值较为接近，在预应力损失开始前期（1~2 d），应力损失约125 MPa，随着监测时间增加，预应力损失值逐渐增加，且变化趋势渐趋平缓，得到钢绞线的长期预应力损失值为205 MPa，预应力钢绞线总损失值约330 MPa；监测点2，4的监测值较为接近，在预应力损失开始前期（1~2 d），应力损失约125 MPa，随着监测时间增加，预应力损失值逐渐增加，且变化趋势渐趋平缓，得到钢绞线的长期预应力损失值为185 MPa，预应力钢绞线总损失值约310 MPa；综合监测点1，2，4，5的监测数据，可以得到竖向预应力钢绞线张拉完成后瞬时损失约为125 MPa，长期预应力损失值约为195 MPa，故预应力钢绞线总损失值约为320 MPa。
3　机器学习预测方法
收起
3.1　数据集的建立与计算模型
为保证机器学习测试集数据的可靠性，建模所使用的数据来源于3个方面：（1）已有文献［11-12］，共15组；（2）基于上述现场实测储罐预应力损失的数值模拟结果，共126组；（3）基于以往实践工程的预应力损失数值模拟结果，共135组。
根据GB 50010—2010《混凝土结构设计规范》规定，后张法构件的预应力损失计算分为张拉端锚具变形和预应力筋内缩、预应力筋的摩擦、预应力筋的应力松弛、混凝土的收缩徐变，以及螺旋式预应力筋在直径不大于3 m时混凝土的局部挤压。结合现场测量和文献［11-12］中可收集的数据格式，选择预应力钢绞线长度l、混凝土弹性模量Ec、钢绞线弹性模量Es、张拉控制应力、损失时间t、钢绞线公称直径d共6个参数为主要研究对象。一共采集267组数据，组成本次钢绞线预应力损失研究的数据集。
采用以下6种机器学习计算模型，并比较其有效性：决策树（DT）、随机森林（RF）、极端随机树（ERT）、梯度提升树（GBDT）、限梯度提升树（XGBoost）和人工神经网络（ANN）。决策树模型基本算法是采用一种自上向下的递归方式构造一棵决策树［13］，通过决策树不同的枝干划分不同的结果空间；随机森林是一种基于决策树的集成学习算法，通过建立多个决策树来提高分类或回归的精度；极端随机树的每棵决策树都是由原始训练样本构建的，在每个测试节点上，每棵树随机分配特征与特征值，使得减小不同树之间的相关性。梯度提升决策树是基于Boosting算法的一种改进［14］；XGBoost算法具有极高的预测准确度，相对于传统统计模型有优越的预测能力，由于该算法不预设自变量和因变量之间的线性关系，因此可以更好地探测可能存在的非线性关系；人工神经网络是在现代神经生物学研究基础上提出的模拟生物过程以反映人脑某些特性的计算结构，可用于分类、回归、聚类等任务的算法。
3.2　超参数寻优
超参数寻优即为机器学习算法的超参数选择最优值，寻优算法决定机器学习的过程并深刻影响模型的性能［15］。网格搜索结合交叉验证算法（GridSearch Cross-validation）［16］是常用的超参数寻优算法，本次寻优采用GridSearch CV与10折交叉验证，生成的6个机器学习模型的超参数及其对应值见表3。
3.3　机器学习预测预应力损失
3.3.1　评价指标
选取上述6种机器学习算法，通过将样本中每个特征的值除以所有样本中该特征的最大值，同时将每个自变量缩放到0~1之间〔见式（1）〕，完成输入特征数据的归一化［17］，并将归一化数据集用于模型的训练和测试［18］，训练集与测试集的占比分别为80%与20%。
x'=xi-xi,minxi,max-xi,min
采用以下5个指标评价算法的性能：均方根误差（RMSE）、平均绝对百分比误差（MAPE）、平均绝对误差（MAE）、决定系数（R2）、皮尔逊相关系数（Pearson Correlation Coefficient，Rs）。
RMSE=1n∑i=1n(y^i-yi)2
MAPE=1n∑i=1ny^i-yiyi×100%
MAE=1n∑i=1ny^i-yiyi
R2=1-∑i=1n(yi-y^i)2∑i=1n(yi-y¯)2
Rs=∑i=1n(y^i-y^¯)(yi-y¯)∑i=1n(y^i-y^¯)2∑i=1n(yi-y¯)2
式中，n为数据点的数量；yi为实际值；y^i为模型预测值；y¯为所有实际值的平均值；y^¯为所有模型预测值的平均值。
3.3.2　性能表现及评价
图6示出6种机器学习模型在训练集上的性能表现。可以看出，6种机器学习模型的训练集中百分比误差均小于3.5%，DT，RF，ERT三种模型的5个性能评价指标值较接近，三种模型的长距离钢绞线长期应力损失预测效果差异不大；ANN模型的RMSE，MAPE，MAE指标数值和其他模型相比较大，R2和Rs指标值与其他模型相比较小；GBDT模型与XGBoost模型的RMSE，MAPE，MAE指标数值和其他模型相比较小，R2和Rs指标值与其他模型相比差异不明显。整体结果表明，GBDT模型与XGBoost模型的预测精度相对较高，ANN模型的预测精度相对较低。
图7示出了6种机器学习模型在测试集上的性能表现。可以看出，相比之下，GBDT模型与XGBoost模型的预测精度相对较高，DT模型与ANN模型的预测精度相对较低。
与训练集相比，6种机器学习模型在测试集上的整体预测精度较低，这说明了拥有足够的样本数对机器学习模型的精度具有重要意义。
3.4　基于SHAP的可解释分析
3.4.1　SHAP机器学习模型解释算法
SHAP（Shapley additive explanations）机器学习模型解释算法［19］可对具体样本生成局部解释，可以明确揭示机器学习模型预测过程的机器学习模型解释算法，比较“有”和“无”某一特征的模型输出值来确定每个输入特征的贡献，基于该贡献确定不同特征的重要性。在此基础上，可对比分析不同机器学习模型对特征贡献的分配差异，进而直观揭示各特征值对预测结果的定向影响，从而为制定针对性的特征调控范围提供依据。
3.4.2　机器学习模型具体解释
图8示出所有样本的每个特征对长距离钢绞线预应力长期损失的平均SHAP值。图中，左侧6个参数为本次数据集中每个样本数据包含的参数，右侧表示每个特征值高低的颜色柱，数据点对应的底部SHAP值即为此数据对长距离钢绞线预应力长期损失的影响。以图8（a）为例，在RF机器学习模型中，较大的预应力钢绞线张拉控制应力σcon、钢绞线长度l、混凝土弹性模量Ec、钢绞线弹性模量Es对长距离钢绞线的预应力长期损失产生正面影响，即增大了长距离钢绞线的预应力长期损失。
为了进一步解释机器学习模型的预测过程，从数据集中选取一条具体的数据。模拟结果显示，在预应力钢绞线长度145 m、混凝土弹性模量30 MPa、钢绞线弹性模量195 GPa、张拉控制应力1 488 MPa、张拉后时间233 d、钢绞线公称直径15.2mm时，钢绞线产生的的预应力长期损失为248 MPa。4种机器学习模型特征贡献案例的结果如图9所示，其中，基线值（base value）表示训练集中目标变量拟合值的均值，红色条带和蓝色条带分别显示了特征的正SHAP值和负SHAP值。4种机器学习模型的基线值、预测值与实际值见表4。
进一步分析可知，4种机器学习模型RF，ERT，GBDT，XGBoost输出预测结果时，主要影响特征都是预应力钢绞线的张拉控制应力和钢绞线长度，表示预应力钢绞线的张拉控制应力和钢绞线长度是研究长距离钢绞线预应力长期损失的关键设计参数。两个特征对长距离钢绞线的预应力长期损失产生了正面影响，即增加了长距离钢绞线的预应力长期损失。
将每个特征的SHAP值（见图8）与基线值相加，即为相应机器学习模型的预测值（见表4）。由表4可知，该4种机器学习模型的预测值与实际值的误差均未超过2%，其中，XGBoost模型的误差最小，仅为0.14%，在4种机器学习模型中精度最高。因此，进一步采用XGBoost机器学习模型分析数据集中的6个参数，得到其SHAP值见图10。可以看出，混凝土弹性模量Ec、钢绞线弹性模量Es和张拉控制应力σcon的SHAP值随参数值增加而增大，即产生的预应力长期损失增大。
从图10（a）可以看出，当预应力钢绞线的长度由40 m增大至160 m时，SHAP值由-50提高至20，变化量为70，表示长距离钢绞线的预应力长期损失受钢绞线长度的影响较大，且当钢绞线长度l<100 m时，有利于降低长距离钢绞线的预应力长期损失。同理可得，当混凝土弹性模量Ec≤32.5 MPa、钢绞线弹性模量Es≤200 GPa、张拉控制应力σcon≤1 350 MPa时〔见图10（b）~（d）〕，有利于降低长距离钢绞线的预应力长期损失。
4　结论
收起
（1）利用光纤传感技术对液化天然气储罐环向、竖向钢绞线进行预应力损失监测，储罐环向预应力钢绞线瞬时损失约为125 MPa，长期预应力损失值约为265 MPa，预应力钢绞线总损失值约为390 MPa；储罐竖向预应力钢绞线瞬时损失约为125 MPa，长期预应力损失值约为195 MPa，预应力钢绞线总损失值约为320 MPa。
（2）利用DT，RF，ERT，GBDT，XGBoost和ANN共6种机器学习算法，通过网格搜索算法进行超参数寻优，并对样本中的特征数据归一化，得到了用于预测长距离钢绞线预应力长期损失的机器学习模型。6种机器学习算法在训练集和测试集的预测准确率均较高，平均百分比误差均小于3.5%。
（3）采用SHAP解释模型对RF，ERT，GBDT和XGBoost四种机器学习模型进行了解释，结果表明，该4种机器学习模型预测值与实际值的误差均未超过2%，其中，XGBoost模型的误差值最小，仅为0.14%，在4种机器学习模型中精度最高。
（4）采用SHAP解释模型对XGBoost模型分析后结果显示，在分析的6个参数中，钢绞线长度l对预应力长期损失的影响最大，混凝土弹性模量Ec、钢绞线弹性模量Es和张拉控制应力σcon对预应力长期损失的影响较大。综合分析结果和现场施工，在满足工程需求下，建议钢绞线长度小于100 m、混凝土弹性模量控制在32.5 MPa以下、张拉控制应力σcon在1 350 MPa以下。

文献
收起
参考文献 引证文献
排序方式：
1
覃荷瑛，雷静，汤鹏飞，等.准分布FBG钢绞线对混凝土梁预应力损失的监测［J］.铁道科学与工程学报，2023，20（7）：2740-2750.
QIN H Y，LEI J，TANG P F，et al.Prestress loss monitoring in concrete beams using quasi‑distributed FBG sensors steel strands［J］.Journal of Railway Science and Engineering，2023，20（7）：2740-2750.
2
陈学东，范志超，崔军，等.我国压力容器高性能制造技术进展［J］.压力容器，2021，38（10）：1-15.
CHEN X D，FAN Z C，CUI J，et al.Progress in high‑performance manufacturing technology for pressure vessels in China［J］.Pressure Vessel Technology，2021，38（10）：1-15.
3
李松海.LNG预应力混凝土储罐极限承载力分析［D］.哈尔滨：哈尔滨工程大学，2014.
LI S H.Ultimate bearing capacity analysis of prestressed concrete LNG storage tank［D］.Harbin：Harbin Engineering University，2014.
4
袁朝庆，房宽光，张证柱，等.新型双钢板-混凝土LNG外罐静力性能分析［J］.压力容器，2025，42（1）：34-42.
YUAN C Q，FANG K G，ZHANG Z Z，et al.Static performance analysis of new double steel plate-concrete LNG outer tank［J］.Pressure Vessel Technology，2025，42（1）：34-42.
5
毛鑫.预制T梁有效预应力静力试验检测评估技术［D］.西安：长安大学，2012.
MAO X.Effective prestressed static test detection evaluation technology for precast T beam［D］.Xi’an：Chang’an University，2012.
6
宁健.预应力结构中FBG自感知钢绞线监测技术的应用［D］.桂林：桂林理工大学，2021.
NING J.Research on the application of FBG self‑sening steel strand in monitoring technology of post tensioned bonded prestressed structure［D］.Guilin：Guilin University of Technology，2021.
7
胡志坚，胡钊芳.实用体外预应力结构预应力损失估算方法［J］.桥梁建设，2006（1）：73-75.
HU Z J，HU Z F.Pactical estimation method for prestress loss of externally prestressed structures［J］.Bridge Construction，2006（1）：73-75.
8
刘寒冰，罗国宝，吴春利.简支桥梁预应力损失计算方法［J］.哈尔滨工程大学学报，2016，37（11）：1510-1513.
LIU H B，LUO G B，WU C L.Calculation method for the prestress loss of a simply‑supported bridge［J］.Journal of Harbin Engineering University，2016，37（11）：1510-1513.
9
ATUTIS M，KAWASHIMA S.Analysis of flexural concrete beams prestressed with basalt composite bars.Analytical‑experimental approach［J］.Composite Structures，2020，243：112172.
10
SHI H B，GUO Q.Study of simplified calculating model on friction correlated prestress loss for PC bridges［J］.IOP Conference Series：Earth and Environmental Science，2020，510（5）：052066.
11
程旭东，王子栋，马川，等.大型LNG储罐外罐长期预应力损失分析［J］.天然气工业，2018，38（11）：97-105.
CHENG X D，WANG Z D，MA C，et al.Analysis on the long-term prestress loss of the external walls of large LNG tanks［J］.Natural Gas Industry，2018，38（11）：97-105.
12
李小军.大直径筒仓预应力损失监测与数据分析［D］.邯郸：河北工程大学，2017.
LI X J.Prestress loss monitoring and dataanalysis of large diameter silo［D］.Handan：Hebei University of Engineering，2017.
13
QUINLAN J R.Induction of decision trees［J］.Machine Learning，1986，1（1）：81-106.
14
FRIEDMAN J H.Stochastic gradient boosting［J］.Computational Statistics & Data Analysis，2002，38（4）：367-378.
15
YAZDANPANAH O，DOLATSHAHI K M，MOAMMER O.Rapid seismic fragility curves assessment of eccentrically braced frames through an output‑only nonmodel‑based procedure and machine learning techniques［J］.Engineering Structures，2023，278：115290.
16
CHAKRABORTY D，ELZARKA H.Advanced machine learning techniques for building performance simulation：A comparative analysis［J］.Journal of Building Performance Simulation，2019，12（2）：193-207.
17
SAMANTA B，AL-BALUSHI K R，AL-ARAIMI S A.Artificial neural networks and support vector machines with genetic algorithm for bearing fault detection［J］.Engineering Applications of Artificial Intelligence，2003，16（7/8）：657-665.
18
SAROTHI S Z，AHMED K S，KHAN N I，et al.Predicting bearing capacity of double shear bolted connections using machine learning［J］.Engineering Structures，2022，251（Part A）：113497.
19
LUNDBERG S M，LEE S I.A unified approach to interpreting model predictions［C］//Proceedings of the 31st International Conference on Neural Information Processing Systems.La Jolla：Neural Information Processing Systems，2017：4768-4777.
2026年第43卷第2期
PDF下载
74
28
引用本文
BibTeX
文章信息
doi: 10.3969/j.issn.1001-4837.2026.02.005
  • 接收时间：2025-06-09
  • 首发时间：2026-10-23
  • 出版时间：2026-02-28
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期：2025-06-09
  • 修回日期：2026-01-17
基金
作者信息
    1海洋石油工程股份有限公司，天津 300461
    2东南大学 交通学院，南京 211189

通讯作者:

王文炜（1971），男，教授，博导，主要研究方向为新材料在工程中的应用，通信地址：211189江苏省南京市江宁区东南大学交通学院桥梁工程系，E-mail：。
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/ylrq/CN/10.3969/j.issn.1001-4837.2026.02.005
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
010-62662699（运营及技术支持）
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