Article(id=1148106715125510624, tenantId=1146029695717560320, journalId=1146031787341344770, issueId=1148106709542892487, articleNumber=1003-3033(2025)04-0110-10, orderNo=null, doi=10.16265/j.cnki.issn1003-3033.2025.04.0893, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1735488000000, receivedDateStr=2024-12-30, revisedDate=1739894400000, revisedDateStr=2025-02-19, acceptedDate=null, acceptedDateStr=null, onlineDate=1751659571677, onlineDateStr=2025-07-05, pubDate=1745769600000, pubDateStr=2025-04-28, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1751659571677, onlineIssueDateStr=2025-07-05, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1751659571677, creator=13701087609, updateTime=1751659571677, updator=13701087609, issue=Issue{id=1148106709542892487, tenantId=1146029695717560320, journalId=1146031787341344770, year='2025', volume='35', issue='4', pageStart='1', pageEnd='264', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=1, specialIssue=0, createTime=1751659570346, creator=13701087609, updateTime=1757560692417, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1172857809499730113, tenantId=1146029695717560320, journalId=1146031787341344770, issueId=1148106709542892487, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1172857809499730114, tenantId=1146029695717560320, journalId=1146031787341344770, issueId=1148106709542892487, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=110, endPage=119, ext={EN=ArticleExt(id=1149757846134371261, articleId=1148106715125510624, tenantId=1146029695717560320, journalId=1146031787341344770, language=EN, title=Analysis of feature importance to retaining wall deformation of excavation using interpretable machine learning model, columnId=1149733269173878863, journalTitle=China Safety Science Journal, columnName=Safety engineering technology, runingTitle=null, highlight=null, articleAbstract=

In order to improve the interpretability of excavation deformation prediction,this study developed an interpretable machine-learning model aimed at predicting the deformation of excavation retaining walls. A comprehensive analysis was conducted to evaluate the influence of different feature variables on the prediction outcomes. Firstly,a large number of excavation support structure parameters were used as a dataset,and 80% of the dataset was used to build a prediction model for the maximum lateral deflection of the retaining wall using the XGBoost (eXtreme Gradient Boosting)model. Then,the model was tested based on the remaining 20% of the dataset,and the accuracy of the model was evaluated by four indicators,i.e.,the coefficient of determination,bias factor,mean absolute percentage error,and root mean square error. Finally,combined with the XGBoost model,the SHAP(SHapley Additive exPlanations) method was applied to complete the global explanation of the excavation feature variables,the partial analysis of individual samples,and the analysis of interaction effects of feature variables. The results show that the proposed method can provide both global and local explanations for the deformation prediction of excavation. At the global level,it not only provides the importance ranking of feature variables,but also gives the distribution of SHAP values. At the local level,the deformation prediction results of individual samples are decomposed into the base value and the contribution of each feature variable,which can quantify the impact of individual feature variables.

, correspAuthors=Hesong HU, 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=Yadong LIU, Xian LIU, Hesong HU, Hang CHEN, Shengfang QIAO), CN=ArticleExt(id=1148106720649408565, articleId=1148106715125510624, tenantId=1146029695717560320, journalId=1146031787341344770, language=CN, title=基于可解释机器学习模型的基坑围护墙变形影响因素分析, columnId=1149733269727526997, journalTitle=中国安全科学学报, columnName=安全工程技术, runingTitle=null, highlight=null, articleAbstract=

为了提高基坑变形预测的可解释性,构建一种基于可解释机器学习的基坑围护墙变形预测模型,并详细分析各特征变量对预测结果的影响。首先,将大量的基坑支护结构参数作为数据集,利用80%的数据集和极限梯度提升(XGBoost)模型构建基坑围护墙最大侧移的预测模型;然后,基于20%的数据集对模型进行测试,利用决定系数、偏差系数、平均绝对百分差和均方根误差4种指标评估模型精度;最后,基于XGBoost模型,运用沙普利加和解释(SHAP)方法完成基坑特征变量的全局解释、单个样本的局部分析和特征变量的交互作用分析。结果表明:所提方法能够对基坑的变形预测进行全局和局部解释。在全局层面,不仅能提供基坑特征变量的重要性排序,还可以给出SHAP值的分布;在局部层面,能够将单个样本的变形预测结果分解为基值和每个特征变量的贡献,从而量化单个特征变量的影响。

, correspAuthors=胡贺松 教授级高级工程师, authorNote=null, correspAuthorsNote=
**胡贺松(1979—),男,河南驻马店人,博士,教授级高级工程师,主要从事岩土工程检测、安全监测与建筑施工等方面的研究。E-mail:
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=pV8DYIGatSE0/iodEf8uBw==, magXml=AJKqRqBoeJQPKLseueVigg==, pdfUrl=null, pdf=CKYK/Y1TuTxQAhcJYBLZig==, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=BpNwgjCEZgH71FA6p1YlNQ==, mapNumber=null, authorCompany=null, fund=null, authors=

刘亚栋 (1991—),男,河南信阳人,博士,主要从事岩土工程安全评估、机器学习及大数据分析等方面的研究。E-mail:

, authorsList=刘亚栋, 刘贤, 胡贺松 教授级高级工程师, 陈航 正高级工程师, 乔升访 高级工程师)}, authors=[Author(id=1165198259250274560, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=liuyd27@mail3.sysu.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1165198259376103684, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, authorId=1165198259250274560, language=EN, stringName=Yadong LIU, firstName=Yadong, middleName=null, lastName=LIU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, 3, address=1 Guangzhou Institute of Building Science Group Co.,Ltd.,Guangzhou Guangdong 510440,China
2 Guangzhou Construction Engineering Co.,Ltd.,Guangzhou Guangdong 510030,China
3 School of Civil Engineering and Transportation,South China University of Technology,Guangzhou Guangdong 510641,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1165198259455795461, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, authorId=1165198259250274560, language=CN, stringName=刘亚栋, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, 3, address=1 广州市建筑科学研究院集团有限公司,广东 广州 510440
2 广州建筑股份有限公司,广东 广州 510030
3 华南理工大学 土木与交通学院,广东 广州 510641, bio={"img":"a/NQGKYTtn6ADGyevBgJXw==","content":"

刘亚栋 (1991—),男,河南信阳人,博士,主要从事岩土工程安全评估、机器学习及大数据分析等方面的研究。E-mail:

"}, bioImg=a/NQGKYTtn6ADGyevBgJXw==, bioContent=

刘亚栋 (1991—),男,河南信阳人,博士,主要从事岩土工程安全评估、机器学习及大数据分析等方面的研究。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1165198258923118835, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, xref=1, ext=[AuthorCompanyExt(id=1165198258931507444, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, companyId=1165198258923118835, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 Guangzhou Institute of Building Science Group Co.,Ltd.,Guangzhou Guangdong 510440,China), AuthorCompanyExt(id=1165198258935701749, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, companyId=1165198258923118835, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 广州市建筑科学研究院集团有限公司,广东 广州 510440)]), AuthorCompany(id=1165198258990227702, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, xref=2, ext=[AuthorCompanyExt(id=1165198258994422007, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, companyId=1165198258990227702, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 Guangzhou Construction Engineering Co.,Ltd.,Guangzhou Guangdong 510030,China), AuthorCompanyExt(id=1165198259002810616, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, companyId=1165198258990227702, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 广州建筑股份有限公司,广东 广州 510030)]), AuthorCompany(id=1165198259065725177, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, xref=3, ext=[AuthorCompanyExt(id=1165198259074113786, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, companyId=1165198259065725177, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 School of Civil Engineering and Transportation,South China University of Technology,Guangzhou Guangdong 510641,China), AuthorCompanyExt(id=1165198259078308091, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, companyId=1165198259065725177, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 华南理工大学 土木与交通学院,广东 广州 510641)])]), Author(id=1165198259506127111, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, 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=1165198259627761929, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, authorId=1165198259506127111, language=EN, stringName=Xian LIU, firstName=Xian, middleName=null, lastName=LIU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=4, address=4 School of Civil Engineering,Sun Yat-sen University,Guangzhou Guangdong 510275,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1165198259682287882, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, authorId=1165198259506127111, language=CN, stringName=刘贤, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=4, address=4 中山大学 土木工程学院,广东 广州 510275, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1165198259187359996, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, xref=4, ext=[AuthorCompanyExt(id=1165198259191554301, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, companyId=1165198259187359996, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=4 School of Civil Engineering,Sun Yat-sen University,Guangzhou Guangdong 510275,China), AuthorCompanyExt(id=1165198259195748606, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, companyId=1165198259187359996, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=4 中山大学 土木工程学院,广东 广州 510275)])]), Author(id=1165198259795534092, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=hesonghu79@126.com, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1165198259883614478, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, authorId=1165198259795534092, language=EN, stringName=Hesong HU, firstName=Hesong, middleName=null, lastName=HU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, **, address=2 Guangzhou Construction Engineering Co.,Ltd.,Guangzhou Guangdong 510030,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1165198259980083471, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, authorId=1165198259795534092, language=CN, stringName=胡贺松 教授级高级工程师, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, **, address=2 广州建筑股份有限公司,广东 广州 510030, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1165198258990227702, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, xref=2, ext=[AuthorCompanyExt(id=1165198258994422007, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, companyId=1165198258990227702, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 Guangzhou Construction Engineering Co.,Ltd.,Guangzhou Guangdong 510030,China), AuthorCompanyExt(id=1165198259002810616, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, companyId=1165198258990227702, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 广州建筑股份有限公司,广东 广州 510030)])]), Author(id=1165198260059775249, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, 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=1165198260126884115, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, authorId=1165198260059775249, language=EN, stringName=Hang CHEN, firstName=Hang, middleName=null, lastName=CHEN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 Guangzhou Institute of Building Science Group Co.,Ltd.,Guangzhou Guangdong 510440,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1165198260198187284, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, authorId=1165198260059775249, language=CN, stringName=陈航 正高级工程师, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 广州市建筑科学研究院集团有限公司,广东 广州 510440, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1165198258923118835, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, xref=1, ext=[AuthorCompanyExt(id=1165198258931507444, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, companyId=1165198258923118835, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 Guangzhou Institute of Building Science Group Co.,Ltd.,Guangzhou Guangdong 510440,China), AuthorCompanyExt(id=1165198258935701749, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, companyId=1165198258923118835, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 广州市建筑科学研究院集团有限公司,广东 广州 510440)])]), Author(id=1165198260273684758, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, 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=1165198260328210712, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, authorId=1165198260273684758, language=EN, stringName=Shengfang QIAO, firstName=Shengfang, middleName=null, lastName=QIAO, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 Guangzhou Institute of Building Science Group Co.,Ltd.,Guangzhou Guangdong 510440,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1165198260391125273, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, authorId=1165198260273684758, language=CN, stringName=乔升访 高级工程师, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 广州市建筑科学研究院集团有限公司,广东 广州 510440, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1165198258923118835, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, xref=1, ext=[AuthorCompanyExt(id=1165198258931507444, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, companyId=1165198258923118835, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 Guangzhou Institute of Building Science Group Co.,Ltd.,Guangzhou Guangdong 510440,China), AuthorCompanyExt(id=1165198258935701749, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, companyId=1165198258923118835, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 广州市建筑科学研究院集团有限公司,广东 广州 510440)])])], keywords=[Keyword(id=1165198260554703130, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, language=EN, orderNo=1, keyword=interpretability), Keyword(id=1165198260605034779, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, language=EN, orderNo=2, keyword=machine learning model), Keyword(id=1165198260667949340, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, language=EN, orderNo=3, keyword=excavation), Keyword(id=1165198260718280989, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, language=EN, orderNo=4, keyword=retaining wall deformation), Keyword(id=1165198260844110110, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, language=EN, orderNo=5, keyword=influence factor), Keyword(id=1165198260907024671, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, language=EN, orderNo=6, keyword=feature variable), Keyword(id=1165198260990910752, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, language=CN, orderNo=1, keyword=可解释性), Keyword(id=1165198261062213921, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, language=CN, orderNo=2, keyword=机器学习模型), Keyword(id=1165198261129322786, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, language=CN, orderNo=3, keyword=基坑), Keyword(id=1165198261179654435, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, language=CN, orderNo=4, keyword=围护墙变形), Keyword(id=1165198261225791780, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, language=CN, orderNo=5, keyword=影响因素), Keyword(id=1165198261330649381, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, language=CN, orderNo=6, keyword=特征变量)], refs=[Reference(id=1165198263645905216, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, doi=null, pmid=null, pmcid=null, year=2023, volume=33, issue=3, pageStart=68, pageEnd=74, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=张仲宇, 李兆平, 杨航, journalName=中国安全科学学报, refType=null, unstructuredReference=张仲宇, 李兆平, 杨航, 等. 并行基坑施工对邻近桥梁影响及保护措施[J]. 中国安全科学学报, 2023, 33(3): 68-74., articleTitle=并行基坑施工对邻近桥梁影响及保护措施, refAbstract=null), Reference(id=1165198263704625473, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, doi=null, pmid=null, pmcid=null, year=2023, volume=33, issue=3, pageStart=68, pageEnd=74, url=null, language=null, rfNumber=[1], rfOrder=1, authorNames=ZHANG Zhongyu, LI Zhaoping, YANG Hang, journalName=China Safety Science Journal, refType=null, unstructuredReference=ZHANG Zhongyu, LI Zhaoping, YANG Hang, et al. Study on influence of parallel foundation pit construction on adjacent bridge and protection measures[J]. China Safety Science Journal, 2023, 33(3): 68-74., articleTitle=Study on influence of parallel foundation pit construction on adjacent bridge and protection measures, refAbstract=null), Reference(id=1165198263792705858, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, doi=null, pmid=null, pmcid=null, year=2013, volume=35, issue=12, pageStart=2153, pageEnd=2163, url=null, language=null, rfNumber=[2], rfOrder=2, authorNames=郑刚, 曾超峰, journalName=岩土工程学报, refType=null, unstructuredReference=郑刚, 曾超峰. 基坑开挖前潜水降水引起的地下连续墙侧移研究[J]. 岩土工程学报, 2013, 35(12): 2153-2163., articleTitle=基坑开挖前潜水降水引起的地下连续墙侧移研究, refAbstract=null), Reference(id=1165198263872397635, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, doi=null, pmid=null, pmcid=null, year=2013, volume=35, issue=12, pageStart=2153, pageEnd=2163, url=null, language=null, rfNumber=[2], rfOrder=3, authorNames=ZHENG Gang, ZENG Chaofeng, journalName=Chinese Journal of Geotechnical Engineering, refType=null, unstructuredReference=ZHENG Gang, ZENG Chaofeng. Lateral displacement of diaphragm wall by dewatering of phreatic water before excavation[J]. Chinese Journal of Geotechnical Engineering, 2013, 35(12): 2153-2163., articleTitle=Lateral displacement of diaphragm wall by dewatering of phreatic water before excavation, refAbstract=null), Reference(id=1165198263939506500, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, doi=null, pmid=null, pmcid=null, year=2023, volume=51, issue=4, pageStart=37, pageEnd=40, url=null, language=null, rfNumber=[3], rfOrder=4, authorNames=李岩, 陶金国, 任红霞, journalName=广州建筑, refType=null, unstructuredReference=李岩, 陶金国, 任红霞, 等. 深基坑支护结构形变影响因素分析[J]. 广州建筑, 2023, 51(4): 37-40., articleTitle=深基坑支护结构形变影响因素分析, refAbstract=null), Reference(id=1165198264073724229, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, doi=null, pmid=null, pmcid=null, year=2023, volume=51, issue=4, pageStart=37, pageEnd=40, url=null, language=null, rfNumber=[3], rfOrder=5, authorNames=LI Yan, TAO Jinguo, REN Hongxia, journalName=Guangzhou Architecture, refType=null, unstructuredReference=LI Yan, TAO Jinguo, REN Hongxia, et al. Analysis on influencing factors of deformation of deep foundation pit supporting structure[J]. Guangzhou Architecture, 2023, 51(4): 37-40., articleTitle=Analysis on influencing factors of deformation of deep foundation pit supporting structure, refAbstract=null), Reference(id=1165198264132444486, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, doi=null, pmid=null, pmcid=null, year=2007, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[4], rfOrder=6, authorNames=徐中华, journalName=上海地区支护结构与主体地下结构相结合的深基坑变形性状研究, refType=null, unstructuredReference=徐中华. 上海地区支护结构与主体地下结构相结合的深基坑变形性状研究[D]. 上海: 上海交通大学, 2007., articleTitle=null, refAbstract=null), Reference(id=1165198264191164743, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, doi=null, pmid=null, pmcid=null, year=2007, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[4], rfOrder=7, authorNames=XU Zhonghua, journalName=Deformation behavior of deep excavations supported by permanent structure in Shanghai soft deposit, refType=null, unstructuredReference=XU Zhonghua. Deformation behavior of deep excavations supported by permanent structure in Shanghai soft deposit[D]. Shanghai: Shanghai Jiao Tong University, 2007., articleTitle=null, refAbstract=null), Reference(id=1165198264254079304, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, doi=null, pmid=null, pmcid=null, year=2023, volume=54, issue=5, pageStart=1851, pageEnd=1862, url=null, language=null, rfNumber=[5], rfOrder=8, authorNames=程康, 徐日庆, 应宏伟, journalName=中南大学学报:自然科学版, refType=null, unstructuredReference=程康, 徐日庆, 应宏伟, 等. 考虑开挖全过程的基坑坑外任意地表沉降实用计算方法[J]. 中南大学学报:自然科学版, 2023, 54(5): 1851-1862., articleTitle=考虑开挖全过程的基坑坑外任意地表沉降实用计算方法, refAbstract=null), Reference(id=1165198264308605257, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, doi=null, pmid=null, pmcid=null, year=2023, volume=54, issue=5, pageStart=1851, pageEnd=1862, url=null, language=null, rfNumber=[5], rfOrder=9, authorNames=CHENG Kang, XU Riqing, YING Hongwei, journalName=Journal of Central South University: Science and Technology, refType=null, unstructuredReference=CHENG Kang, XU Riqing, YING Hongwei, et al. Practical calculation method of arbitrary ground surface settlement outside basement considering the whole process of excavation[J]. Journal of Central South University: Science and Technology, 2023, 54(5): 1851-1862., articleTitle=Practical calculation method of arbitrary ground surface settlement outside basement considering the whole process of excavation, refAbstract=null), Reference(id=1165198264363131210, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, doi=null, pmid=null, pmcid=null, year=2024, volume=46, issue=1, pageStart=1, pageEnd=25, url=null, language=null, rfNumber=[6], rfOrder=10, authorNames=王卫东, journalName=岩土工程学报, refType=null, unstructuredReference=王卫东. 软土深基坑变形及环境影响分析方法与控制技术[J]. 岩土工程学报, 2024, 46(1): 1-25., articleTitle=软土深基坑变形及环境影响分析方法与控制技术, refAbstract=null), Reference(id=1165198264413462859, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, doi=null, pmid=null, pmcid=null, year=2024, volume=46, issue=1, pageStart=1, pageEnd=25, url=null, language=null, rfNumber=[6], rfOrder=11, authorNames=WANG Weidong, journalName=Chinese Journal of Geotechnical Engineering, refType=null, unstructuredReference=WANG Weidong. Analytical methods and controlling techniques for deformation and environmental influence of deep excavations in soft soils[J]. Chinese Journal of Geotechnical Engineering, 2024, 46(1): 1-25., articleTitle=Analytical methods and controlling techniques for deformation and environmental influence of deep excavations in soft soils, refAbstract=null), Reference(id=1165198264467988812, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, doi=null, pmid=null, pmcid=null, year=2020, volume=16, issue=7, pageStart=145, pageEnd=151, url=null, language=null, rfNumber=[7], rfOrder=12, authorNames=蒙国往, 农忠建, 吴波, journalName=中国安全生产科学技术, refType=null, unstructuredReference=蒙国往, 农忠建, 吴波, 等. 地铁车站深基坑开挖变形及数值模拟分析[J]. 中国安全生产科学技术, 2020, 16(7): 145-151., articleTitle=地铁车站深基坑开挖变形及数值模拟分析, refAbstract=null), Reference(id=1165198264522514765, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, doi=null, pmid=null, pmcid=null, year=2020, volume=16, issue=7, pageStart=145, pageEnd=151, url=null, language=null, rfNumber=[7], rfOrder=13, authorNames=MENG Guowang, NONG Zhongjian, WU Bo, journalName=Journal of Safety Science and Technology, refType=null, unstructuredReference=MENG Guowang, NONG Zhongjian, WU Bo, et al. Excavation deformation and numerical simulation analysis of deep foundation pit in subway station[J]. Journal of Safety Science and Technology, 2020, 16(7): 145-151., articleTitle=Excavation deformation and numerical simulation analysis of deep foundation pit in subway station, refAbstract=null), Reference(id=1165198264585429326, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, doi=null, pmid=null, pmcid=null, year=2023, volume=19, issue=3, pageStart=992, pageEnd=1000, url=null, language=null, rfNumber=[8], rfOrder=14, authorNames=李尚明, 洪成雨, 姬凤玲, journalName=地下空间与工程学报, refType=null, unstructuredReference=李尚明, 洪成雨, 姬凤玲, 等. 深基坑的机器视觉监测与变形预测研究[J]. 地下空间与工程学报, 2023, 19(3): 992-1000., articleTitle=深基坑的机器视觉监测与变形预测研究, refAbstract=null), Reference(id=1165198264639955279, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, doi=null, pmid=null, pmcid=null, year=2023, volume=19, issue=3, pageStart=992, pageEnd=1000, url=null, language=null, rfNumber=[8], rfOrder=15, authorNames=LI Shangming, HONG Chengyu, JI Fengling, journalName=Chinese Journal of Underground Space and Engineering, refType=null, unstructuredReference=LI Shangming, HONG Chengyu, JI Fengling, et al. Study on machine vision monitoring and deformation prediction of deep foundation pit[J]. Chinese Journal of Underground Space and Engineering, 2023, 19(3): 992-1000., articleTitle=Study on machine vision monitoring and deformation prediction of deep foundation pit, refAbstract=null), Reference(id=1165198264698675536, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, doi=null, pmid=null, pmcid=null, year=2023, volume=33, issue=9, pageStart=41, pageEnd=48, url=null, language=null, rfNumber=[9], rfOrder=16, authorNames=靳春玲, 姬照泰, 贡力, journalName=中国安全科学学报, refType=null, unstructuredReference=靳春玲, 姬照泰, 贡力, 等. 基于WOA-SVM的引水隧洞岩爆烈度评估模型[J]. 中国安全科学学报, 2023, 33(9): 41-48., articleTitle=基于WOA-SVM的引水隧洞岩爆烈度评估模型, refAbstract=null), Reference(id=1165198264749007185, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, doi=null, pmid=null, pmcid=null, year=2023, volume=33, issue=9, pageStart=41, pageEnd=48, url=null, language=null, rfNumber=[9], rfOrder=17, authorNames=JIN Chunling, JI Zhaotai, GONG Li, journalName=China Safety Science Journal, refType=null, unstructuredReference=JIN Chunling, JI Zhaotai, GONG Li, et al. Evaluation model of rockburst intensity of diversion tunnel based on WOA-SVM[J]. China Safety Science Journal, 2023, 33(9): 41-48., articleTitle=Evaluation model of rockburst intensity of diversion tunnel based on WOA-SVM, refAbstract=null), Reference(id=1165198264803533138, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, doi=null, pmid=null, pmcid=null, year=2022, volume=59, issue=增2, pageStart=77, pageEnd=85, url=null, language=null, rfNumber=[10], rfOrder=18, authorNames=薛艳杰, journalName=现代隧道技术, refType=null, unstructuredReference=薛艳杰. 基于机器学习算法的土岩复合地层深基坑变形时序预测[J]. 现代隧道技术, 2022, 59(增2): 77-85., articleTitle=基于机器学习算法的土岩复合地层深基坑变形时序预测, refAbstract=null), Reference(id=1165198264853864787, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, doi=null, pmid=null, pmcid=null, year=2022, volume=59, issue=S2, pageStart=77, pageEnd=85, url=null, language=null, rfNumber=[10], rfOrder=19, authorNames=XUE Yanjie, journalName=Modern Tunnelling Technology, refType=null, unstructuredReference=XUE Yanjie. Time series prediction of deep foundation pit deformation in soil-rock composite stratum based on machine learning algorithm[J]. Modern Tunnelling Technology, 2022, 59(S2): 77-85., articleTitle=Time series prediction of deep foundation pit deformation in soil-rock composite stratum based on machine learning algorithm, refAbstract=null), Reference(id=1165198264929362260, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, doi=null, pmid=null, pmcid=null, year=2019, volume=47, issue=1, pageStart=19, pageEnd=23, url=null, language=null, rfNumber=[11], rfOrder=20, authorNames=刘永辉, 黄立, 刘炳凯, journalName=广州建筑, refType=null, unstructuredReference=刘永辉, 黄立, 刘炳凯, 等. BP神经网络在深基坑监测预报中的应用与精度分析[J]. 广州建筑, 2019, 47(1): 19-23., articleTitle=BP神经网络在深基坑监测预报中的应用与精度分析, refAbstract=null), Reference(id=1165198264979693909, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, doi=null, pmid=null, pmcid=null, year=2019, volume=47, issue=1, pageStart=19, pageEnd=23, url=null, language=null, rfNumber=[11], rfOrder=21, authorNames=LIU Yonghui, HUANG Li, LIU Bingkai, journalName=Guangzhou Architecture, refType=null, unstructuredReference=LIU Yonghui, HUANG Li, LIU Bingkai, et al. Application and accuracy analysis of BP neural network in monitoring and forecasting of deep foundation pit[J]. Guangzhou Architecture, 2019, 47(1): 19-23., articleTitle=Application and accuracy analysis of BP neural network in monitoring and forecasting of deep foundation pit, refAbstract=null), Reference(id=1165198265063579990, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, doi=null, pmid=null, pmcid=null, year=1998, volume=19, issue=4, pageStart=63, pageEnd=68, url=null, language=null, rfNumber=[12], rfOrder=22, authorNames=孙海涛, 吴限, journalName=岩土力学, refType=null, unstructuredReference=孙海涛, 吴限. 深基坑工程变形预报神经网络法的初步研究[J]. 岩土力学, 1998, 19(4): 63-68., articleTitle=深基坑工程变形预报神经网络法的初步研究, refAbstract=null), Reference(id=1165198265168437591, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, doi=null, pmid=null, pmcid=null, year=1998, volume=19, issue=4, pageStart=63, pageEnd=68, url=null, language=null, rfNumber=[12], rfOrder=23, authorNames=SUN Haitao, WU Xian, journalName=Rock and Soil Mechanics, refType=null, unstructuredReference=SUN Haitao, WU Xian. Study on neural networks method of deformation prediction of foundation pit based on artificial[J]. Rock and Soil Mechanics, 1998, 19(4): 63-68., articleTitle=Study on neural networks method of deformation prediction of foundation pit based on artificial, refAbstract=null), Reference(id=1165198265231352152, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, doi=null, pmid=null, pmcid=null, year=2003, volume=22, issue=增1, pageStart=2284, pageEnd=2288, url=null, language=null, rfNumber=[13], rfOrder=24, authorNames=曲霞, 刘新宇, 华瑞平, journalName=岩石力学与工程学报, refType=null, unstructuredReference=曲霞, 刘新宇, 华瑞平. 基于时间效应的反演分析方法在深基坑工程中的应用[J]. 岩石力学与工程学报, 2003, 22(增1): 2284-2288., articleTitle=基于时间效应的反演分析方法在深基坑工程中的应用, refAbstract=null), Reference(id=1165198265290072409, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, doi=null, pmid=null, pmcid=null, year=2003, volume=22, issue=S1, pageStart=2284, pageEnd=2288, url=null, language=null, rfNumber=[13], rfOrder=25, authorNames=QU Xia, LIU Xinyu, HUA Ruiping, journalName=Chinese Journal of Rock Mechanics and Engineering, refType=null, unstructuredReference=QU Xia, LIU Xinyu, HUA Ruiping. Back analysis method based on time effect and its application to deep foundation[J]. Chinese Journal of Rock Mechanics and Engineering, 2003, 22(S1): 2284-2288., articleTitle=Back analysis method based on time effect and its application to deep foundation, refAbstract=null), Reference(id=1165198265344598362, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, doi=null, pmid=null, pmcid=null, year=2021, volume=12, issue=1, pageStart=365, pageEnd=373, url=null, language=null, rfNumber=[14], rfOrder=26, authorNames=ZHANG Runhong, WU Chongzhi, GOH A T C, journalName=Geoscience Frontiers, refType=null, unstructuredReference=ZHANG Runhong, WU Chongzhi, GOH A T C, et al. Estimation of diaphragm wall deflections for deep braced excavation in anisotropic clays using ensemble learning[J]. Geoscience Frontiers, 2021, 12(1): 365-373., articleTitle=Estimation of diaphragm wall deflections for deep braced excavation in anisotropic clays using ensemble learning, refAbstract=null), Reference(id=1165198265394930011, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, doi=null, pmid=null, pmcid=null, year=2017, volume=null, issue=null, pageStart=4768, pageEnd=4777, url=null, language=null, rfNumber=[15], rfOrder=27, authorNames=LUNDBERG S M, LEE S, journalName=Proceedings of the 31st International Conference on Neural Information Processing Systems, refType=null, unstructuredReference=LUNDBERG S M, LEE S. A unified approach to interpreting model predictions[C]. Proceedings of the 31st International Conference on Neural Information Processing Systems, 2017: 4768-4777., articleTitle=A unified approach to interpreting model predictions, refAbstract=null), Reference(id=1165198265462038876, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, doi=null, pmid=null, pmcid=null, year=2022, volume=14, issue=4, pageStart=1052, pageEnd=1063, url=null, language=null, rfNumber=[16], rfOrder=28, authorNames=KANNANGARA K K P M, ZHOU Wanhuan, DING Zhi, journalName=Journal of Rock Mechanics and Geotechnical Engineering, refType=null, unstructuredReference=KANNANGARA K K P M, ZHOU Wanhuan, DING Zhi, et al. Investigation of feature contribution to shield tunneling-induced settlement using Shapley additive explanations method[J]. Journal of Rock Mechanics and Geotechnical Engineering, 2022, 14(4): 1052-1063., articleTitle=Investigation of feature contribution to shield tunneling-induced settlement using Shapley additive explanations method, refAbstract=null), Reference(id=1165198265520759133, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, doi=null, pmid=null, pmcid=null, year=2023, volume=25, issue=4, pageStart=852, pageEnd=865, url=null, language=null, rfNumber=[17], rfOrder=29, authorNames=李心雨, 闫浩文, 王卓, journalName=地球信息科学学报, refType=null, unstructuredReference=李心雨, 闫浩文, 王卓, 等. 街景图像与机器学习相结合的道路环境安全感知评价与影响因素分析[J]. 地球信息科学学报, 2023, 25(4): 852-865., articleTitle=街景图像与机器学习相结合的道路环境安全感知评价与影响因素分析, refAbstract=null), Reference(id=1165198265621422430, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, doi=null, pmid=null, pmcid=null, year=2023, volume=25, issue=4, pageStart=852, pageEnd=865, url=null, language=null, rfNumber=[17], rfOrder=30, authorNames=LI Xinyu, YAN Haowen, WANG Zhuo, journalName=Journal of Geo-information Science, refType=null, unstructuredReference=LI Xinyu, YAN Haowen, WANG Zhuo, et al. Evaluation of road environment safety perception and analysis of influencing factors combining street view imagery and machine learning[J]. Journal of Geo-information Science, 2023, 25(4): 852-865., articleTitle=Evaluation of road environment safety perception and analysis of influencing factors combining street view imagery and machine learning, refAbstract=null), Reference(id=1165198265671754079, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, doi=null, pmid=null, pmcid=null, year=2023, volume=39, issue=13, pageStart=113, pageEnd=122, url=null, language=null, rfNumber=[18], rfOrder=31, authorNames=葛建坤, 雷国相, 陈皓锐, journalName=农业工程学报, refType=null, unstructuredReference=葛建坤, 雷国相, 陈皓锐, 等. 基于SHAP重要性排序和机器学习算法的灌区渠道调度流量预测[J]. 农业工程学报, 2023, 39(13): 113-122., articleTitle=基于SHAP重要性排序和机器学习算法的灌区渠道调度流量预测, refAbstract=null), Reference(id=1165198265726280032, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, doi=null, pmid=null, pmcid=null, year=2023, volume=39, issue=13, pageStart=113, pageEnd=122, url=null, language=null, rfNumber=[18], rfOrder=32, authorNames=GE Jiankun, LEI Guoxiang, CHEN Haorui, journalName=Transactions of the Chinese Society of Agricultural Engineering, refType=null, unstructuredReference=GE Jiankun, LEI Guoxiang, CHEN Haorui, et al. Irrigation district channel dispatch flow prediction based on SHAP importance ranking and machine learning algorithm[J]. Transactions of the Chinese Society of Agricultural Engineering, 2023, 39(13): 113-122., articleTitle=Irrigation district channel dispatch flow prediction based on SHAP importance ranking and machine learning algorithm, refAbstract=null), Reference(id=1165198265780805985, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, doi=null, pmid=null, pmcid=null, year=2021, volume=147, issue=11, pageStart=1, pageEnd=13, url=null, language=null, rfNumber=[19], rfOrder=33, authorNames=FENG Decheng, WANG Wenjie, MANGALATHU S, journalName=Journal of Structural Engineering, refType=null, unstructuredReference=FENG Decheng, WANG Wenjie, MANGALATHU S, et al. Interpretable XGBoost-SHAP machine-learning model for shear strength prediction of squat RC walls[J]. Journal of Structural Engineering, 2021, 147(11): 1-13., articleTitle=Interpretable XGBoost-SHAP machine-learning model for shear strength prediction of squat RC walls, refAbstract=null), Reference(id=1165198265839526242, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, doi=null, pmid=null, pmcid=null, year=2024, volume=32, issue=3, pageStart=627, pageEnd=642, url=null, language=null, rfNumber=[20], rfOrder=34, authorNames=赵靖, 侯超凡, 丰明洁, journalName=应用基础与工程科学学报, refType=null, unstructuredReference=赵靖, 侯超凡, 丰明洁, 等. 信号交叉口右转交通安全的影响因素研究[J]. 应用基础与工程科学学报, 2024, 32(3): 627-642., articleTitle=信号交叉口右转交通安全的影响因素研究, refAbstract=null), Reference(id=1165198265894052195, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, doi=null, pmid=null, pmcid=null, year=2024, volume=32, issue=3, pageStart=627, pageEnd=642, url=null, language=null, rfNumber=[20], rfOrder=35, authorNames=ZHAO Jing, HOU Chaofan, FENG Mingjie, journalName=Journal of Basic Science and Engineering, refType=null, unstructuredReference=ZHAO Jing, HOU Chaofan, FENG Mingjie, et al. Research on influencing factors of right-turn traffic safety at signalized intersections[J]. Journal of Basic Science and Engineering, 2024, 32(3): 627-642., articleTitle=Research on influencing factors of right-turn traffic safety at signalized intersections, refAbstract=null), Reference(id=1165198265965355364, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, doi=null, pmid=null, pmcid=null, year=2016, volume=null, issue=null, pageStart=785, pageEnd=794, url=null, language=null, rfNumber=[21], rfOrder=36, authorNames=CHEN T, GUESTRIN C, journalName=Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, refType=null, unstructuredReference=CHEN T, GUESTRIN C. XGBoost: a scalable tree boosting system[C]. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2016: 785-794., articleTitle=XGBoost: a scalable tree boosting system, refAbstract=null), Reference(id=1165198266011492709, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, doi=null, pmid=null, pmcid=null, year=2020, volume=11, issue=4, pageStart=1095, pageEnd=1106, url=null, language=null, rfNumber=[22], rfOrder=37, authorNames=ZHANG Wengang, ZHANG Runhong, WU Chongzhi, journalName=Geoscience Frontiers, refType=null, unstructuredReference=ZHANG Wengang, ZHANG Runhong, WU Chongzhi, et al. State-of-the-art review of soft computing applications in underground excavations[J]. Geoscience Frontiers, 2020, 11(4): 1095-1106., articleTitle=State-of-the-art review of soft computing applications in underground excavations, refAbstract=null), Reference(id=1165198266166681958, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, doi=null, pmid=null, pmcid=null, year=2015, volume=63, issue=null, pageStart=67, pageEnd=72, url=null, language=null, rfNumber=[23], rfOrder=38, authorNames=ZHANG Wengang, GOH A T C, XUAN Feng, journalName=Computers and Geotechnics, refType=null, unstructuredReference=ZHANG Wengang, GOH A T C, XUAN Feng. A simple prediction model for wall deflection caused by braced excavation in clays[J]. Computers and Geotechnics, 2015, 63: 67-72., articleTitle=A simple prediction model for wall deflection caused by braced excavation in clays, refAbstract=null)], funds=[Fund(id=1165198263281000764, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, awardId=2024B03J1389, language=CN, fundingSource=广州市科技计划项目(2024B03J1389), fundOrder=null, country=null), Fund(id=1165198263335526717, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, awardId=2024KJ033, language=CN, fundingSource=广州市建筑集团有限公司科技计划项目(2024KJ033), fundOrder=null, country=null), Fund(id=1165198263411024190, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, awardId=2024KJ030, language=CN, fundingSource=广州市建筑集团有限公司科技计划项目(2024KJ030), fundOrder=null, country=null), Fund(id=1165198263473938751, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, awardId=创新中心-2024-D011, language=CN, fundingSource=广州市院士专家工作站建设项目(创新中心-2024-D011), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1165198258923118835, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, xref=1, ext=[AuthorCompanyExt(id=1165198258931507444, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, companyId=1165198258923118835, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 Guangzhou Institute of Building Science Group Co.,Ltd.,Guangzhou Guangdong 510440,China), AuthorCompanyExt(id=1165198258935701749, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, companyId=1165198258923118835, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 广州市建筑科学研究院集团有限公司,广东 广州 510440)]), AuthorCompany(id=1165198258990227702, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, xref=2, ext=[AuthorCompanyExt(id=1165198258994422007, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, companyId=1165198258990227702, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 Guangzhou Construction Engineering Co.,Ltd.,Guangzhou Guangdong 510030,China), AuthorCompanyExt(id=1165198259002810616, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, companyId=1165198258990227702, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 广州建筑股份有限公司,广东 广州 510030)]), AuthorCompany(id=1165198259065725177, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, xref=3, ext=[AuthorCompanyExt(id=1165198259074113786, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, companyId=1165198259065725177, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 School of Civil Engineering and Transportation,South China University of Technology,Guangzhou Guangdong 510641,China), AuthorCompanyExt(id=1165198259078308091, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, companyId=1165198259065725177, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 华南理工大学 土木与交通学院,广东 广州 510641)]), AuthorCompany(id=1165198259187359996, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, xref=4, ext=[AuthorCompanyExt(id=1165198259191554301, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, companyId=1165198259187359996, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=4 School of Civil Engineering,Sun Yat-sen University,Guangzhou Guangdong 510275,China), AuthorCompanyExt(id=1165198259195748606, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, companyId=1165198259187359996, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=4 中山大学 土木工程学院,广东 广州 510275)])], figs=[ArticleFig(id=1165198261561336102, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, language=EN, label=Fig.1, caption=Profile of excavation, figureFileSmall=lXPZ9w8+iBKoqD3s1DLFLg==, figureFileBig=NCM3kX8T6XKvgnPvT97KLg==, tableContent=null), ArticleFig(id=1165198261628444967, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, language=CN, label=图1, caption=基坑剖面, figureFileSmall=lXPZ9w8+iBKoqD3s1DLFLg==, figureFileBig=NCM3kX8T6XKvgnPvT97KLg==, tableContent=null), ArticleFig(id=1165198261682970920, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, language=EN, label=Fig.2, caption=Accuracy validation of XGBoost model, figureFileSmall=pnTW5VfO9Hhz7LmtHasd2g==, figureFileBig=pWB5XtLtEjmMri+4M0smQQ==, tableContent=null), ArticleFig(id=1165198261750079785, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, language=CN, label=图2, caption=XGBoost模型的预测精度验证, figureFileSmall=pnTW5VfO9Hhz7LmtHasd2g==, figureFileBig=pWB5XtLtEjmMri+4M0smQQ==, tableContent=null), ArticleFig(id=1165198261804605738, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, language=EN, label=Fig.3, caption=Global interpretations of XGBoost model by SHAP values, figureFileSmall=muTCxAW3iCE1tlvhuovauw==, figureFileBig=JBle4Ruacwh6Wg9XHNfQiw==, tableContent=null), ArticleFig(id=1165198261854937387, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, language=CN, label=图3, caption=基于SHAP值的XGBoost模型全局解释, figureFileSmall=muTCxAW3iCE1tlvhuovauw==, figureFileBig=JBle4Ruacwh6Wg9XHNfQiw==, tableContent=null), ArticleFig(id=1165198261943017772, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, language=EN, label=Fig.4, caption=Feature importance based on XGBoost model[22], figureFileSmall=FkTUZFDOEWdBiRZyV9sjkw==, figureFileBig=CXVSZSZtLiduTcGg5ycCyA==, tableContent=null), ArticleFig(id=1165198262010126637, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, language=CN, label=图4, caption=基于XGBoost模型的特征重要性[22], figureFileSmall=FkTUZFDOEWdBiRZyV9sjkw==, figureFileBig=CXVSZSZtLiduTcGg5ycCyA==, tableContent=null), ArticleFig(id=1165198262077235502, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, language=EN, label=Fig.5, caption=Local interpretations of XGBoost model by SHAP values, figureFileSmall=7kQ3DWIPEOTPJ5h5bV+00A==, figureFileBig=gbIig7iCQZRAARFak7uO1w==, tableContent=null), ArticleFig(id=1165198262131761455, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, language=CN, label=图5, caption=基于SHAP值的XGBoost模型局部解释, figureFileSmall=7kQ3DWIPEOTPJ5h5bV+00A==, figureFileBig=gbIig7iCQZRAARFak7uO1w==, tableContent=null), ArticleFig(id=1165198262207258928, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, language=EN, label=Fig.6, caption=Interaction between different features, figureFileSmall=ms8Y1e/qkxkTCJO+rDbIPg==, figureFileBig=3iE4I1l7ZOKlgd39aJGyHw==, tableContent=null), ArticleFig(id=1165198262265979185, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, language=CN, label=图6, caption=不同特征变量间的交互作用, figureFileSmall=ms8Y1e/qkxkTCJO+rDbIPg==, figureFileBig=3iE4I1l7ZOKlgd39aJGyHw==, tableContent=null), ArticleFig(id=1165198262328893746, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, language=EN, label=Fig.7, caption=Global interpretations of XGBoost model by SHAP values, figureFileSmall=m74PN+7lXlLJ4Txkq0Y2bw==, figureFileBig=kxXx6KTzEdEzueZkhIpgNw==, tableContent=null), ArticleFig(id=1165198262404391219, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, language=CN, label=图7, caption=基于SHAP值的XGBoost模型全局解释, figureFileSmall=m74PN+7lXlLJ4Txkq0Y2bw==, figureFileBig=kxXx6KTzEdEzueZkhIpgNw==, tableContent=null), ArticleFig(id=1165198262463111476, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, language=EN, label=Fig.8, caption=Interaction between different features, figureFileSmall=91nV20utIQW8YVYwNeZ1DQ==, figureFileBig=M4aV+w5WLTRtcYR/kKAAPg==, tableContent=null), ArticleFig(id=1165198262546997557, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, language=CN, label=图8, caption=不同特征变量间的交互作用, figureFileSmall=91nV20utIQW8YVYwNeZ1DQ==, figureFileBig=M4aV+w5WLTRtcYR/kKAAPg==, tableContent=null), ArticleFig(id=1165198262706381110, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, language=EN, label=Table 1, caption=

Features of excavation and range of values[23]

, figureFileSmall=null, figureFileBig=null, tableContent=
符号 特征变量 取值
x1 cu/σ'v 0.21、0.25、0.29、0.34
x2 E50/cu 100、200、300
x3 γs/(kN·m-3) 15、17、19
x4 Ts/m 25、30、35
x5 B/m 20、30、40、50、60
x6 He/m 11、14、17、20
x7 ln(EI/γw h a v g 4) 6.097、7.313、8.176、8.846
), ArticleFig(id=1165198262781878583, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, language=CN, label=表1, caption=

基坑特征变量及其取值[23]

, figureFileSmall=null, figureFileBig=null, tableContent=
符号 特征变量 取值
x1 cu/σ'v 0.21、0.25、0.29、0.34
x2 E50/cu 100、200、300
x3 γs/(kN·m-3) 15、17、19
x4 Ts/m 25、30、35
x5 B/m 20、30、40、50、60
x6 He/m 11、14、17、20
x7 ln(EI/γw h a v g 4) 6.097、7.313、8.176、8.846
), ArticleFig(id=1165198262857376056, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, language=EN, label=Table 2, caption=

Prediction accuracy of XGBoost model under different combination of features

, figureFileSmall=null, figureFileBig=null, tableContent=
序号 变量组合 训练集 测试集
R2 SBF SMAPE SRMSE/mm R2 SBF SMAPE SRMSE/mm
1 x7 + x2 + x1 + x6 + x3 + x4 + x5 1.000 1.000 0.006 1.322 0.993 0.996 0.034 6.062
2 x7 + x2 + x1 + x6 + x3 + x4 0.988 1.000 0.044 7.545 0.967 0.996 0.086 12.906
3 x7 + x2 + x1 + x6 + x3 0.915 0.998 0.101 20.039 0.824 0.993 0.144 29.983
4 x7 + x2 + x1 + x6 0.740 1.000 0.173 35.098 0.713 0.981 0.202 38.330
5 x7 + x2 + x1 0.598 1.003 0.243 43.599 0.584 0.967 0.282 46.190
6 x7 + x2 0.457 0.999 0.297 50.665 0.432 0.985 0.324 53.931
7 x7 0.285 1.004 0.367 58.156 0.265 1.002 0.398 61.364
), ArticleFig(id=1165198262991593785, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, language=CN, label=表2, caption=

不同特征变量组合下XGBoost模型的预测精度

, figureFileSmall=null, figureFileBig=null, tableContent=
序号 变量组合 训练集 测试集
R2 SBF SMAPE SRMSE/mm R2 SBF SMAPE SRMSE/mm
1 x7 + x2 + x1 + x6 + x3 + x4 + x5 1.000 1.000 0.006 1.322 0.993 0.996 0.034 6.062
2 x7 + x2 + x1 + x6 + x3 + x4 0.988 1.000 0.044 7.545 0.967 0.996 0.086 12.906
3 x7 + x2 + x1 + x6 + x3 0.915 0.998 0.101 20.039 0.824 0.993 0.144 29.983
4 x7 + x2 + x1 + x6 0.740 1.000 0.173 35.098 0.713 0.981 0.202 38.330
5 x7 + x2 + x1 0.598 1.003 0.243 43.599 0.584 0.967 0.282 46.190
6 x7 + x2 0.457 0.999 0.297 50.665 0.432 0.985 0.324 53.931
7 x7 0.285 1.004 0.367 58.156 0.265 1.002 0.398 61.364
), ArticleFig(id=1165198263075479866, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, language=EN, label=Table 3, caption=

Partial dataset composed of excavation engineering cases

, figureFileSmall=null, figureFileBig=null, tableContent=
编号 z1/m z2/m z3/m z4/(kN·m2) z5/道 z6/m z7 yi/mm
1 22.4 1 35 2 500 000 6 3.73 0 34.59
2 14.6 1 28 2 630 000 3 4.87 0 20.9
54 14 0.8 23.6 1 344 000 5 2.68 1 41.3
55 21.5 0.8 35 1 280 000 5 4.3 1 24.4
56 11.35 0.8 22 1 280 000 2 4.53 1 66.3
108 15 0.6 26 540 000 4 3.38 1 50
109 14.42 0.8 27 1 280 000 4 3.26 1 70
110 15 0.8 28 1 280 000 5 3.29 1 71.22
), ArticleFig(id=1165198263150977339, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106715125510624, language=CN, label=表3, caption=

基坑工程案例组成的部分数据集[4]

, figureFileSmall=null, figureFileBig=null, tableContent=
编号 z1/m z2/m z3/m z4/(kN·m2) z5/道 z6/m z7 yi/mm
1 22.4 1 35 2 500 000 6 3.73 0 34.59
2 14.6 1 28 2 630 000 3 4.87 0 20.9
54 14 0.8 23.6 1 344 000 5 2.68 1 41.3
55 21.5 0.8 35 1 280 000 5 4.3 1 24.4
56 11.35 0.8 22 1 280 000 2 4.53 1 66.3
108 15 0.6 26 540 000 4 3.38 1 50
109 14.42 0.8 27 1 280 000 4 3.26 1 70
110 15 0.8 28 1 280 000 5 3.29 1 71.22
)], attaches=null, journal=Journal(id=1123942128916217864, delFlag=0, nameCn=中国安全科学学报, nameEn=China Safety Science Journal, nameHistory1=null, nameHistory2=null, issn=1003-3033, eissn=, cn=11-2865/X, coden=null, periodic=0, language=CN, oaType=0, 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=fkqsFM6VKlHC4gCtS5XqTw==, journalPrice=null, startedYear=null, abbrevIsoEn=Chin Saf Sci J, journalRemark=null, publicationField=null, createdTime=null, updatedTime=1754269350027, createdBy=null, updatedBy=13701087609, firstLetterCn=C, firstLetterEn=C, subjectCode=Engineering, subjectName=工程, subjectCodeEn=Engineering, subjectNameEn=null, picCn=fkqsFM6VKlHC4gCtS5XqTw==, picEn=SHn9HgqSxtJrOcAxqD++4Q==, jcr=null, cjcr=null, exts=[JournalExt(id=1159052918994595848, language=CN, name=中国安全科学学报, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=null, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=http://www.cssjj.com.cn/, createdTime=1754269350050, updatedTime=1754269350050, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=http://www.cssjj.com.cn/CN/column/item15.shtml, submissionAuthorUrl=https://zgaqkxxbauthor.manuscriptcloud.com/login, submissionEditorUrl=https://zgaqkxxbeditor.manuscriptcloud.com/login, submissionReviewUrl=https://zgaqkxxbauthor.manuscriptcloud.com/login, submissionCeEditorUrl=https://zgaqkxxbeditor.manuscriptcloud.com/login, submissionAeEditorUrl=https://zgaqkxxbeditor.manuscriptcloud.com/login, option={"copyright":""}), JournalExt(id=1159052919040733193, language=EN, name=China Safety Science Journal, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=null, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=http://www.cssjj.com.cn/EN/1003-3033/home.shtml, createdTime=1754269350061, updatedTime=1754269350061, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=https://synbioj.cip.com.cn/EN/column/column3.shtml, submissionAuthorUrl=https://zgaqkxxbauthor.manuscriptcloud.com/login, submissionEditorUrl=https://zgaqkxxbeditor.manuscriptcloud.com/login, submissionReviewUrl=https://zgaqkxxbauthor.manuscriptcloud.com/login, submissionCeEditorUrl=https://zgaqkxxbeditor.manuscriptcloud.com/login, submissionAeEditorUrl=https://zgaqkxxbeditor.manuscriptcloud.com/login, option={"copyright":""})], databaseList=null, tenantJournalId=1146031787341344770, websiteList=[Website(id=1148243202345263519, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146031787341344770, 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/zgaqkxxb/CN, language=CN, createTime=1751692112766, createBy=18614031015, updateTime=1753502583634, updateBy=18614031015, name=《中国安全科学学报》中文站点, tplId=1146099689490845704, title=中国安全科学学报, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1148618794941046792, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202345263519, code=articleTextType, value=kx, createTime=1751781661020, updateTime=1751781661020, creator=18614031015, updator=18614031015), WebsiteProps(id=1148618794911686661, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202345263519, code=banner, value=null, createTime=1751781661012, updateTime=1751781661012, creator=18614031015, updator=18614031015), WebsiteProps(id=1148618794894909444, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202345263519, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=tui0IVO9FMwB61HHtX5scg==, createTime=1751781661008, updateTime=1751781661008, creator=18614031015, updator=18614031015), WebsiteProps(id=1148618794932658183, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202345263519, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1751781661017, updateTime=1751781661017, creator=18614031015, updator=18614031015), WebsiteProps(id=1148618794924269574, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202345263519, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1751781661015, updateTime=1751781661015, creator=18614031015, updator=18614031015)]), Website(id=1155836763751993353, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146031787341344770, 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/zgaqkxxb/EN, language=EN, createTime=1753502558893, createBy=18614031015, updateTime=1753524450387, updateBy=18614031015, name=《中国安全科学学报》英文站点, tplId=1146101810881728533, title=China Safety Science Journal, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1155895925743669425, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155836763751993353, code=articleTextType, value=kx, createTime=1753516664205, updateTime=1753516664205, creator=18614031015, updator=18614031015), WebsiteProps(id=1155895925722697902, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155836763751993353, code=banner, value=null, createTime=1753516664200, updateTime=1753516664200, creator=18614031015, updator=18614031015), WebsiteProps(id=1155895925714309293, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155836763751993353, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=tui0IVO9FMwB61HHtX5scg==, createTime=1753516664198, updateTime=1753516664198, creator=18614031015, updator=18614031015), WebsiteProps(id=1155895925735280816, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155836763751993353, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1753516664203, updateTime=1753516664203, creator=18614031015, updator=18614031015), WebsiteProps(id=1155895925731086511, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155836763751993353, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1753516664202, updateTime=1753516664202, creator=18614031015, updator=18614031015)])], journalTitle=中国安全科学学报, weixinUrl=null, journalUrl=null, iacademicId=null, status=0, seqNo=null, journalTitleEn=China Safety Science Journal, journalPhotoCn=fkqsFM6VKlHC4gCtS5XqTw==, journalPhotoEn=SHn9HgqSxtJrOcAxqD++4Q==, journalFirstLetter=C, journalRecommend=null, journalNew=null, journalCollection=1, 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=null, provinceCode=null, provinceName=null, collectFlag=false), detailUrlCn=https://castjournals.cast.org.cn/joweb/zgaqkxxb/CN/10.16265/j.cnki.issn1003-3033.2025.04.0893, detailUrlEn=https://castjournals.cast.org.cn/joweb/zgaqkxxb/EN/10.16265/j.cnki.issn1003-3033.2025.04.0893, pdfUrlCn=https://castjournals.cast.org.cn/joweb/zgaqkxxb/CN/PDF/10.16265/j.cnki.issn1003-3033.2025.04.0893, pdfUrlEn=https://castjournals.cast.org.cn/joweb/zgaqkxxb/EN/PDF/10.16265/j.cnki.issn1003-3033.2025.04.0893, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于可解释机器学习模型的基坑围护墙变形影响因素分析
收藏切换
PDF下载
刘亚栋 1, 2, 3 , 刘贤 4 , 胡贺松 教授级高级工程师 2, ** , 陈航 正高级工程师 1 , 乔升访 高级工程师 1
中国安全科学学报 | 安全工程技术 2025,35(4): 110-119
收起
收藏切换
中国安全科学学报 | 安全工程技术 2025, 35(4): 110-119
基于可解释机器学习模型的基坑围护墙变形影响因素分析
全屏
刘亚栋1, 2, 3 , 刘贤4, 胡贺松 教授级高级工程师2, ** , 陈航 正高级工程师1, 乔升访 高级工程师1
作者信息
  • 1 广州市建筑科学研究院集团有限公司,广东 广州 510440
  • 2 广州建筑股份有限公司,广东 广州 510030
  • 3 华南理工大学 土木与交通学院,广东 广州 510641
  • 4 中山大学 土木工程学院,广东 广州 510275
  • 刘亚栋 (1991—),男,河南信阳人,博士,主要从事岩土工程安全评估、机器学习及大数据分析等方面的研究。E-mail:

通讯作者:

**胡贺松(1979—),男,河南驻马店人,博士,教授级高级工程师,主要从事岩土工程检测、安全监测与建筑施工等方面的研究。E-mail:
Analysis of feature importance to retaining wall deformation of excavation using interpretable machine learning model
Yadong LIU1, 2, 3 , Xian LIU4, Hesong HU2, ** , Hang CHEN1, Shengfang QIAO1
Affiliations
  • 1 Guangzhou Institute of Building Science Group Co.,Ltd.,Guangzhou Guangdong 510440,China
  • 2 Guangzhou Construction Engineering Co.,Ltd.,Guangzhou Guangdong 510030,China
  • 3 School of Civil Engineering and Transportation,South China University of Technology,Guangzhou Guangdong 510641,China
  • 4 School of Civil Engineering,Sun Yat-sen University,Guangzhou Guangdong 510275,China
出版时间: 2025-04-28 doi: 10.16265/j.cnki.issn1003-3033.2025.04.0893
文章导航
收藏切换

为了提高基坑变形预测的可解释性,构建一种基于可解释机器学习的基坑围护墙变形预测模型,并详细分析各特征变量对预测结果的影响。首先,将大量的基坑支护结构参数作为数据集,利用80%的数据集和极限梯度提升(XGBoost)模型构建基坑围护墙最大侧移的预测模型;然后,基于20%的数据集对模型进行测试,利用决定系数、偏差系数、平均绝对百分差和均方根误差4种指标评估模型精度;最后,基于XGBoost模型,运用沙普利加和解释(SHAP)方法完成基坑特征变量的全局解释、单个样本的局部分析和特征变量的交互作用分析。结果表明:所提方法能够对基坑的变形预测进行全局和局部解释。在全局层面,不仅能提供基坑特征变量的重要性排序,还可以给出SHAP值的分布;在局部层面,能够将单个样本的变形预测结果分解为基值和每个特征变量的贡献,从而量化单个特征变量的影响。

可解释性  /  机器学习模型  /  基坑  /  围护墙变形  /  影响因素  /  特征变量

In order to improve the interpretability of excavation deformation prediction,this study developed an interpretable machine-learning model aimed at predicting the deformation of excavation retaining walls. A comprehensive analysis was conducted to evaluate the influence of different feature variables on the prediction outcomes. Firstly,a large number of excavation support structure parameters were used as a dataset,and 80% of the dataset was used to build a prediction model for the maximum lateral deflection of the retaining wall using the XGBoost (eXtreme Gradient Boosting)model. Then,the model was tested based on the remaining 20% of the dataset,and the accuracy of the model was evaluated by four indicators,i.e.,the coefficient of determination,bias factor,mean absolute percentage error,and root mean square error. Finally,combined with the XGBoost model,the SHAP(SHapley Additive exPlanations) method was applied to complete the global explanation of the excavation feature variables,the partial analysis of individual samples,and the analysis of interaction effects of feature variables. The results show that the proposed method can provide both global and local explanations for the deformation prediction of excavation. At the global level,it not only provides the importance ranking of feature variables,but also gives the distribution of SHAP values. At the local level,the deformation prediction results of individual samples are decomposed into the base value and the contribution of each feature variable,which can quantify the impact of individual feature variables.

interpretability  /  machine learning model  /  excavation  /  retaining wall deformation  /  influence factor  /  feature variable
刘亚栋, 刘贤, 胡贺松 教授级高级工程师, 陈航 正高级工程师, 乔升访 高级工程师. 基于可解释机器学习模型的基坑围护墙变形影响因素分析. 中国安全科学学报, 2025 , 35 (4) : 110 -119 . DOI: 10.16265/j.cnki.issn1003-3033.2025.04.0893
Yadong LIU, Xian LIU, Hesong HU, Hang CHEN, Shengfang QIAO. Analysis of feature importance to retaining wall deformation of excavation using interpretable machine learning model[J]. China Safety Science Journal, 2025 , 35 (4) : 110 -119 . DOI: 10.16265/j.cnki.issn1003-3033.2025.04.0893
随着城市建设的快速发展,地下空间开发项目日渐增多,如地下商场、地下通道、地铁隧道等,这些项目大多涉及基坑工程。然而,基坑开挖过程中,由于土体的力学性质、地下水条件、周边环境等多种因素的作用,支护结构往往会产生变形[1-3]。若变形过大或超过允许范围,不仅会影响基坑的稳定性,还可能对周边建筑物、道路等造成损害,导致安全事故发生[4]。因此,准确预测基坑支护结构变形,对于保障施工安全、控制工程成本以及优化设计方案具有重大意义。
基坑开挖中的变形受地质条件、施工技术等多因素影响,导致实际变形机理远比简化模型复杂[5-6]。特别是地质条件的多样性与不确定性,使围护结构水平变形的精确预测极具挑战。目前,已发展起来的围护结构水平变形计算方法包括:经验公式法、理论解析法、有限元/差分法和机器学习模型等。由于对计算理论的简化,经验公式法和理论解析法难以适用于基坑复杂工况,导致变形计算精度不足。尽管有限元/差分法能够考虑基坑围护结构与土体的相互作用,但岩土材料的理论本构关系难以精确反映工程实际中材料的应力-应变关系,且实际工况远比数值模拟工况复杂,使得数值模拟结果在大多数情况下难以反映真实的基坑变形[7]。近年来,计算机技术的飞速发展极大促进了机器学习技术在岩土工程领域的应用,如人工神经网络、支持向量机和遗传算法等[8-11]。与数值模拟方法相比,这类方法具有学习速度快、计算效率高、预测模型实时更新等优点,为基坑变形预测提供了新途径[12-14]
需要注意的是,以上各类方法在基坑支护结构变形安全控制方面发挥了重要作用,但目前基坑支护结构变形的研究主要集中于模型预测精度的提高,而在对模型内部机制的解释方面稍显不足,为基坑施工安全决策提供的指导作用有限。该缺陷在以数据驱动为基础的机器学习模型上表现尤为突出,因其内部工作机制不透明,传统的机器学习模型通常被视为“黑箱”模型。虽然模型能够给出预测结果,但很难解释为什么给出这样的预测,以及预测结果是如何计算得出的。幸运的是,可解释性机器学习模型能够提供更清晰和可理解的模型解释,帮助人们理解模型的决策依据和原因。沙普利加和解释(SHapley Additive exPlanations,SHAP)[15]是当前广受关注的一种机器学习模型解释工具,它具有识别特征变量之间相互作用的能力,并能够提供详尽的特征变量的重要性排序及其对预测结果的具体贡献[16]。尽管SHAP方法已经在环境监测[17]、灌区水利调度[18]、钢筋混凝土结构[19]和道路交通管理[20]等领域得到了初步应用,但在基坑工程领域的应用及其适用性尚未得到深入的研究和探讨。
为此,笔者将极限梯度提升(eXtreme Gradient Boosting,XGBoost)模型与SHAP方法相结合,构建可解释的机器学习模型,分析基坑围护墙变形影响因素,以期明确量化XGBoost模型中各个特征变量的重要性,为识别基坑支护结构变形控制的关键因素以及优化算法提供有价值的参考和指导。
XGBoost是梯度增强决策树(Gradient Boosted Decision Tree,GBDT)这一集成学习方法的演进版本,它在传统的GBDT框架之上改进后大幅提升了模型的预测性能[21]。作为一种前向叠加的机器学习模型,XGBoost的核心在于通过特定的策略将多个弱学习器(决策树)组合成一个强学习器。具体而言,XGBoost利用多棵决策树进行联合决策,其中每棵树的输出都是目标值与先前所有树预测结果的残差。最终,通过将所有这些树的预测结果进行累加,获得最终的预测输出,进而显著提升整体模型预测性能。
当存在含有n个样本的数据集,即:
D x 1 y 1 x 2 y 2 x n y n,其中,xi为输入变量向量,xi = [x1x2,…,xM],i = 1,2,…,n;x1x2,…,xM分别为相应的特征变量或影响因素,M为影响因素的数量;yi为输出变量,指基坑围护墙最大侧移实际值。XGBoost模型的预测结果可表示为:
y ^ i = ϕ x i = k = 1 K f k x i
式中: y ^ iyi的预测值;ϕ为预测模型;fk为第k个树模型的预测值;K为树模型的总数量。
根据XGBoost模型,将损失函数L定义为样本预测值 y ^ i和样本实际值yi的误差:
L = k = 1 K l y i y ^ i + k = 1 K Ω ( f k )
l y i y ^ i = y i - y ^ i 2
Ω ( f k ) = η G + 1 2 λ w k 2
式中:l为实际值和预测值之间的训练损失;Ω为模型的复杂程度;G为叶节点数量;wk为对应的权重;λη分别为超参数,默认值分别取1和0。当迭代步为t时,L(t)可表示为:
L ( t ) = i = 1 n l y i y ^ i ( t ) + k = 1 t Ω ( f k ) = i = 1 n l y i y ^ i ( t - 1 ) + f t ( x i ) + Ω ( f t ) + C
式中 C = k = 1 t - 1 Ω ( f k ),为常量。当考虑二阶泰勒展开式并忽略常数项,则式(5)中的目标损失函数可进一步表示为:
L ( t ) = i = 1 n l y i y ^ i ( t - 1 ) + g i f t ( x i ) + 1 2 h i f t 2 ( x i ) + Ω ( f t )
其中,
g i = l y i y ^ i ( t - 1 ) y ^ i ( t - 1 )
h i = 2 l y i y ^ i ( t - 1 ) y ^ i ( t - 1 ) 2
式中gihi分别为损失函数的一阶和二阶偏导数。将式(6)最小化,可优化求解得到第t个树模型的相关参数和预测值。重复优化过程,直到达到预设的停止准则,得到最终预测结果。XGBoost模型中决策树模型的数量、树的最大深度和学习率为关键参数,可采用交叉验证和网格搜索法确定。
分别将决定系数R2、偏差系数SBF、平均绝对百分差SMAPE和均方根误差SRMSE作为评价指标,评价基坑围护墙变形的XGBoost模型。R2用于衡量回归模型对数据拟合程度的优劣,SBF反映预测值与实际值之间的平均偏离程度,SMAPE为预测值与实际值之间的平均绝对百分比误差,SRMSE为预测误差的标准差。R2SBF数值越接近1,模型预测精度越高;反之,模型预测精度越低。SMAPESRMSE数值越接近0,模型预测精度越高;反之,模型预测精度越低。各评价指标的表达式分别为:
R 2 = 1 - i = 1 n y i - y ^ i 2 i = 1 n y i - y - 2
S B F = 1 n i = 1 n y i / y ^ i
S M A P E = 1 n i = 1 n y ^ i - y i y i
S R S M E = 1 n i = 1 n y ^ i - y i 2
式中 y -yi的平均值。
SHAP是一种用于解释机器学习模型预测结果的方法,其核心在于量化评估各特征变量或影响因素对模型预测结果的贡献程度。该方法基于博弈论中的Shapley值原理,通过计算并分配每个特征变量在模型预测中的SHAP值,从而得出特征变量的重要性评分。根据文献[15],可解释性模型表示为:
ϕ ( x ) = g ( x ' ) = φ 0 + i = 1 M φ i x i '
式中:x'为x的简化输入变量;M为特征变量的数量;φ0为模型预测结果的均值;φi为第i个特征变量对模型预测结果的贡献值,即SHAP值,其表达式为:
φ i = 1 M ! z ' x ' | z ' | ! M - z ' - 1 ! ϕ ( z ' ) - ϕ ( z ' \ i )
式中:z'为变量x'的子集;z' \iz'i= 0;|z'|为z'中的非0项。
文中采用TreeSHAP方法计算SHAP值。SHAP算法的核心思想是将模型的输出分解为各个特征变量的贡献累加。对于给定的预测值,SHAP算法通过考虑所有特征值的排列组合,计算每个特征变量对预测结果的贡献,以识别每个输入特征的贡献是正值还是负值。
结合XGBoost模型与SHAP方法,分析基坑围护墙变形影响因素,主要流程如下:
1) 借助Python 3.10平台,将基坑数据集分别划分为训练集和测试集,其数量比例为8∶2[22]
2) 将训练集最小化的SRMSE作为目标函数,采用交叉验证和网格搜索法确定XGBoost模型的关键参数,即决策树模型的数量、树的最大深度和学习率,其余参数取默认值。
3) 根据最优参数和训练数据集构建基坑围护墙最大侧移的XGBoost模型,并借助4种评价指标(R2SBFSMAPESRMSE)在测试集上验证模型的预测精度。
4) 在XGBoost模型的基础上,利用SHAP方法分析基坑不同的特征变量x1x2,…,xM对围护墙最大侧移yi的影响。
在工程建设实施前,为了确保基坑支护设计方案的可靠性,常用有限元法模拟基坑开挖引发的支护结构变形、周边地表沉降以及基坑坑底土体的隆起等响应。ZHANG Wengang等[23]的研究表明:有限元分析中硬化小应变模型相较于传统莫尔-库仑模型展现出更高的精度,能够更准确地描述围护墙变形。然而,该研究中与基坑围护墙变形相关的参数(也称为影响因素或特征变量)种类较多,目前对于这些参数如何影响围护墙变形的机制仍缺乏深入且清晰的认识。因此,以文献[23]中的深基坑为例,详细介绍如何采用可解释模型对影响围护墙变形机制的参数进行分析解释。
基坑剖面土层上部为软黏土、下部为硬黏土,为典型的沿海地区土质条件,基坑剖面如图1所示。其中,Ks为水平支撑的轴向刚度,kN;E为围护墙的弹性模量,kN/m2d为围护墙厚度,m;g为下层土体的重度,kN/m3Eu为卸载模量,MPa;cu为软土的不排水强度,kPa;Ts为软土层厚度,m;He为基坑深度,m;B为基坑宽度,m。基坑的特征变量及其取值范围见表1[23]
根据图1的几何参数和表1的变量组合建立基坑二维有限元模型,进行大量有限元分析(Finite Element Analysis,FEA)后,得到基坑围护墙的最大侧移yi,详细数据见文献[22]。将基坑的特征变量或影响因素x1x2,…,x7组成输入变量向量xi = [x1x2,…,x7],围护墙的最大侧移yi作为输出变量,i = 1,2,…,1 119,建立用于训练XGBoost模型的数据集。
由以上流程得到决策树模型的数量、树的最大深度和学习率的取值分别为100、20和0.3。XGBoost模型在训练集和测试集的预测精度验证如图2所示。对于训练集,评价指标R2SBFSMAPESRMSE分别为1.000、1.000、0.006和1.322 mm;对于测试集,评价指标R2SBFSMAPESRMSE分别为0.993、0.996、0.034和6.062 mm。由此可见:XGBoost模型对基坑围护墙最大侧移yi的预测精度较高。
为提高XGBoost模型对基坑围护墙最大侧移预测的可解释性,利用SHAP法分析基坑特征变量的重要性并量化其影响程度。图3给出XGBoost模型预测的全局解释。
图3a为基坑特征变量的重要性排序,表示不同特征变量对变形预测结果的整体影响。由图3a可见:特征变量的重要性程度为:x7 > x2 > x1 > x6 > x3 > x4 > x5,其中围护墙刚度比x7、软土刚度比x2和软土不排水强度比x1对预测结果的影响较大,三者占平均绝对SHAP值总和的57.1%,基坑宽度x5对预测结果的影响最小,仅占平均绝对SHAP值总和的5.2%。
图3b为不同特征变量的SHAP值分布图,其中横轴表示SHAP值,纵轴表示按照重要性排序的基坑特征变量。图中散点表示数据集中的样本,图例表示特征变量的取值大小。散点的水平位置表示该特征变量对预测值 y ^ i的影响是正值或负值,例如左上侧散点表示当围护墙刚度比x7取值较大时,将使围护墙最大侧移的预测值 y ^ i降低约95 mm;同理,右上侧散点表示当围护墙刚度比x7取值较小时,将使围护墙最大侧移的预测值 y ^ i增加约125 mm。由图可知:预测值 y ^ i随基坑特征变量x7x2x1x3取值的增加而降低,而随基坑特征变量x6x4x5取值的增加而增大。因此,SHAP值分布图能够给出基坑特征变量如何影响围护墙最大侧移的全局解释。
文献[22]利用XGBoost模型自身具备的特征重要性分析得到基坑特征变量的重要性排序,如图4所示。其中,变量x7x2的重要性程度较高,变量x4x5的重要性程度较低,其余变量的重要程度处于中间水平。图3a图4整体上一致性较好,验证了本研究中SHAP法的准确性。
为了进一步探究特征变量选择对基坑变形预测结果的影响,根据表1图3建立了7种变量组合,分析模型在训练集和测试集的预测精度,结果见表2。当忽略基坑宽度x5的影响时,对于测试集,模型评价指标R2SBFSMAPESRMSE分别为0.967、0.996、0.086和12.906 mm,预测精度仍然较高,说明基坑宽度对该案例中基坑变形的影响可以忽略。
随着更多其他特征变量的移除,无论对于测试集还是训练集,XGBoost模型的预测精度逐渐下降,因此,将x1 ~ x7作为输入变量,不会导致预测模型出现过拟合现象。以上分析可为基坑围护墙变形预测模型的优化提供合理参考。
SHAP法不但能给出模型预测的全局解释,还能够针对单个样本给出预测结果的局部解释,如图5所示。其中,零轴左侧的条形图表示该样本中x1x2x7x4对变形预测结果的贡献(SHAP值)为负,而零轴右侧的条形图表示该样本中x6x5x3对变形预测结果的贡献(SHAP值)为正。其中,XGBoost模型预测结果的均值为137.32 mm,可得该样本的变形预测值为137.32 + (- 26.78 - 24.25 + 9.3 - 5.33 + 2.76 + 1.46 - 0.39) = 94.09 mm,与FEA得到的94 mm吻合。以上分析从单个样本角度解释了不同特征变量对最终围护墙变形预测的影响。
图6给出不同特征变量交互作用下的SHAP值变化。由图6可知:SHAP值随着特征变量x5x4x6的增加而增加,而随着特征变量x1x2x7x3的增加而降低,表明围护墙最大侧移yi与特征变量x5x4x6具有正相关性,与特征变量x1x2x7x3具有负相关性,该结果与图3b较为一致。此外,当x5小于40 m时,围护墙最大侧移减小;反之,围护墙最大侧移增大。类似地,当x4小于30 m、x6小于14 m、x1大于0.29、x2大于200、x7大于7.3、x3大于17 kN/m3时,围护墙最大侧移减小;反之,围护墙最大侧移增大。此外,当某特征变量取固定值时,在其他特征变量的影响下,SHAP值的变化趋势并不相同。例如:当x1小于0.29时,SHAP值随着x7的增加而减小;反之,SHAP值随着x7的增加而增大。这些结果有助于揭示不同特征变量的交互作用对基坑围护墙变形的影响,解决XGBoost模型的预测结果难以解释的问题,对基坑变形安全控制具有重要参考价值。
为了进一步验证可解释模型在实际工程的适用性,从上海地区基坑工程案例数据库中选取110组工程案例组成数据集[4]。在该数据集中,特征变量为基坑开挖深度z1、围护墙厚度z2、围护墙深度z3、围护墙抗弯刚度z4、支撑数量z5、平均支撑间距z6和支护结构类型z7,因变量为基坑围护墙的最大侧移yi,部分数据集见表3[4]
与上一案例的分析流程相同,利用真实数据集构建XGBoost模型,相应的决策树模型的数量、树的最大深度和学习率的取值分别为200、25和0.2。对于训练集,评价指标R2SBFSMAPESRMSE分别为0.998、0.993、0.019和1.465 mm;对于测试集,评价指标R2SBFSMAPESRMSE分别为0.995、0.985、0.025和1.779 mm。利用SHAP算法得到基坑特征变量的重要性并量化其影响程度,图7给出XGBoost模型预测的全局解释。图7a为基坑特征变量的重要性排序,由图7a可见:特征变量的重要性程度为:z1 > z3 > z6 > z5 > z7 > z2 > z4,其中,基坑开挖深度z1、围护墙深度z3和平均支撑间距z6对围护墙的最大侧移预测值 y ˙ i的影响较大,三者占平均绝对SHAP值总和的70.5%。围护墙厚度x2和围护墙抗弯刚度x4 y ˙ i的影响较小,仅占平均绝对SHAP值总和的5.7%。此外,由图7b中不同特征变量的SHAP值分布图可知:预测值 y ˙ i随基坑特征变量z2z4z5取值的增加而减小,大体上随基坑特征变量z1z3z7取值的增加而增加。此外,预测值 y ˙ i与单个变量z1z3z6的关系并不明显,其主要原因在于单个变量z1z3z6与其他变量共同作用才能与 y ^ i产生明显的相关性。对于类别型特征变量z7,由于支护结构与主体地下结构相结合的形式对围护墙变形的约束能力更强,因此采用该支护形式时墙体最大侧移更小、安全性更高。以上结果表明:当同时含数值型和类别型的基坑特征变量时,本文模型仍然能较好揭示各特征变量对围护墙最大侧移的影响。
类似地,特征变量交互作用下的SHAP值变化如图8所示。由图8a可知:变量z3的SHAP值随z3z1数值的增加而增加,表明基坑开挖深度z1和围护墙深度z3与墙体最大侧移具有正相关性。由图8b可知:变量z5的SHAP值随z5数值的增加而减小,表明支撑数量z5与墙体最大侧移具有负相关性。当z5 > 3时,SHAP值随着z1的增加而减小;反之,SHAP值随着z1的增加而增加。因此,选取适当的支撑数量对基坑变形安全控制具有重要作用。
1) 数值模拟案例和实际工程案例的结果表明:基于XGBoost和SHAP的可解释机器学习模型能够有效分析不同特征变量对基坑围护墙变形的影响。
2) 当选取的基坑特征变量不完全相同时,由于变量间的相互作用,使得其对围护墙变形的影响存在差异。对于数值模拟案例,围护墙刚度比和软土刚度比对基坑围护墙变形的影响较大,而软土厚度和基坑宽度对围护墙变形的影响较小;对于实际工程案例,基坑开挖深度、围护墙深度和平均支撑间距是控制基坑围护墙变形的关键因素,而围护墙厚度和墙体抗弯刚度对基坑围护墙变形的影响较小。
3) SHAP法能够对基坑围护墙变形的预测进行全局和局部解释。在全局层面,它不仅提供了基坑特征变量的重要性排序,还能给出SHAP值的分布。该分布量化了不同的基坑特征变量如何影响围护墙最大侧移预测。在局部层面,SHAP将单个样本的变形预测结果分解为基值和每个特征变量的贡献。可为基坑支护结构变形控制中关键因素的识别以及算法的优化提供重要参考和指导。
  • 广州市科技计划项目(2024B03J1389)
  • 广州市建筑集团有限公司科技计划项目(2024KJ033)
  • 广州市建筑集团有限公司科技计划项目(2024KJ030)
  • 广州市院士专家工作站建设项目(创新中心-2024-D011)
参考文献 引证文献
排序方式:
[1]
张仲宇, 李兆平, 杨航, 等. 并行基坑施工对邻近桥梁影响及保护措施[J]. 中国安全科学学报, 2023, 33(3): 68-74.
ZHANG Zhongyu, LI Zhaoping, YANG Hang, et al. Study on influence of parallel foundation pit construction on adjacent bridge and protection measures[J]. China Safety Science Journal, 2023, 33(3): 68-74.
[2]
郑刚, 曾超峰. 基坑开挖前潜水降水引起的地下连续墙侧移研究[J]. 岩土工程学报, 2013, 35(12): 2153-2163.
ZHENG Gang, ZENG Chaofeng. Lateral displacement of diaphragm wall by dewatering of phreatic water before excavation[J]. Chinese Journal of Geotechnical Engineering, 2013, 35(12): 2153-2163.
[3]
李岩, 陶金国, 任红霞, 等. 深基坑支护结构形变影响因素分析[J]. 广州建筑, 2023, 51(4): 37-40.
LI Yan, TAO Jinguo, REN Hongxia, et al. Analysis on influencing factors of deformation of deep foundation pit supporting structure[J]. Guangzhou Architecture, 2023, 51(4): 37-40.
[4]
徐中华. 上海地区支护结构与主体地下结构相结合的深基坑变形性状研究[D]. 上海: 上海交通大学, 2007.
XU Zhonghua. Deformation behavior of deep excavations supported by permanent structure in Shanghai soft deposit[D]. Shanghai: Shanghai Jiao Tong University, 2007.
[5]
程康, 徐日庆, 应宏伟, 等. 考虑开挖全过程的基坑坑外任意地表沉降实用计算方法[J]. 中南大学学报:自然科学版, 2023, 54(5): 1851-1862.
CHENG Kang, XU Riqing, YING Hongwei, et al. Practical calculation method of arbitrary ground surface settlement outside basement considering the whole process of excavation[J]. Journal of Central South University: Science and Technology, 2023, 54(5): 1851-1862.
[6]
王卫东. 软土深基坑变形及环境影响分析方法与控制技术[J]. 岩土工程学报, 2024, 46(1): 1-25.
WANG Weidong. Analytical methods and controlling techniques for deformation and environmental influence of deep excavations in soft soils[J]. Chinese Journal of Geotechnical Engineering, 2024, 46(1): 1-25.
[7]
蒙国往, 农忠建, 吴波, 等. 地铁车站深基坑开挖变形及数值模拟分析[J]. 中国安全生产科学技术, 2020, 16(7): 145-151.
MENG Guowang, NONG Zhongjian, WU Bo, et al. Excavation deformation and numerical simulation analysis of deep foundation pit in subway station[J]. Journal of Safety Science and Technology, 2020, 16(7): 145-151.
[8]
李尚明, 洪成雨, 姬凤玲, 等. 深基坑的机器视觉监测与变形预测研究[J]. 地下空间与工程学报, 2023, 19(3): 992-1000.
LI Shangming, HONG Chengyu, JI Fengling, et al. Study on machine vision monitoring and deformation prediction of deep foundation pit[J]. Chinese Journal of Underground Space and Engineering, 2023, 19(3): 992-1000.
[9]
靳春玲, 姬照泰, 贡力, 等. 基于WOA-SVM的引水隧洞岩爆烈度评估模型[J]. 中国安全科学学报, 2023, 33(9): 41-48.
JIN Chunling, JI Zhaotai, GONG Li, et al. Evaluation model of rockburst intensity of diversion tunnel based on WOA-SVM[J]. China Safety Science Journal, 2023, 33(9): 41-48.
[10]
薛艳杰. 基于机器学习算法的土岩复合地层深基坑变形时序预测[J]. 现代隧道技术, 2022, 59(增2): 77-85.
XUE Yanjie. Time series prediction of deep foundation pit deformation in soil-rock composite stratum based on machine learning algorithm[J]. Modern Tunnelling Technology, 2022, 59(S2): 77-85.
[11]
刘永辉, 黄立, 刘炳凯, 等. BP神经网络在深基坑监测预报中的应用与精度分析[J]. 广州建筑, 2019, 47(1): 19-23.
LIU Yonghui, HUANG Li, LIU Bingkai, et al. Application and accuracy analysis of BP neural network in monitoring and forecasting of deep foundation pit[J]. Guangzhou Architecture, 2019, 47(1): 19-23.
[12]
孙海涛, 吴限. 深基坑工程变形预报神经网络法的初步研究[J]. 岩土力学, 1998, 19(4): 63-68.
SUN Haitao, WU Xian. Study on neural networks method of deformation prediction of foundation pit based on artificial[J]. Rock and Soil Mechanics, 1998, 19(4): 63-68.
[13]
曲霞, 刘新宇, 华瑞平. 基于时间效应的反演分析方法在深基坑工程中的应用[J]. 岩石力学与工程学报, 2003, 22(增1): 2284-2288.
QU Xia, LIU Xinyu, HUA Ruiping. Back analysis method based on time effect and its application to deep foundation[J]. Chinese Journal of Rock Mechanics and Engineering, 2003, 22(S1): 2284-2288.
[14]
ZHANG Runhong, WU Chongzhi, GOH A T C, et al. Estimation of diaphragm wall deflections for deep braced excavation in anisotropic clays using ensemble learning[J]. Geoscience Frontiers, 2021, 12(1): 365-373.
[15]
LUNDBERG S M, LEE S. A unified approach to interpreting model predictions[C]. Proceedings of the 31st International Conference on Neural Information Processing Systems, 2017: 4768-4777.
[16]
KANNANGARA K K P M, ZHOU Wanhuan, DING Zhi, et al. Investigation of feature contribution to shield tunneling-induced settlement using Shapley additive explanations method[J]. Journal of Rock Mechanics and Geotechnical Engineering, 2022, 14(4): 1052-1063.
[17]
李心雨, 闫浩文, 王卓, 等. 街景图像与机器学习相结合的道路环境安全感知评价与影响因素分析[J]. 地球信息科学学报, 2023, 25(4): 852-865.
LI Xinyu, YAN Haowen, WANG Zhuo, et al. Evaluation of road environment safety perception and analysis of influencing factors combining street view imagery and machine learning[J]. Journal of Geo-information Science, 2023, 25(4): 852-865.
[18]
葛建坤, 雷国相, 陈皓锐, 等. 基于SHAP重要性排序和机器学习算法的灌区渠道调度流量预测[J]. 农业工程学报, 2023, 39(13): 113-122.
GE Jiankun, LEI Guoxiang, CHEN Haorui, et al. Irrigation district channel dispatch flow prediction based on SHAP importance ranking and machine learning algorithm[J]. Transactions of the Chinese Society of Agricultural Engineering, 2023, 39(13): 113-122.
[19]
FENG Decheng, WANG Wenjie, MANGALATHU S, et al. Interpretable XGBoost-SHAP machine-learning model for shear strength prediction of squat RC walls[J]. Journal of Structural Engineering, 2021, 147(11): 1-13.
[20]
赵靖, 侯超凡, 丰明洁, 等. 信号交叉口右转交通安全的影响因素研究[J]. 应用基础与工程科学学报, 2024, 32(3): 627-642.
ZHAO Jing, HOU Chaofan, FENG Mingjie, et al. Research on influencing factors of right-turn traffic safety at signalized intersections[J]. Journal of Basic Science and Engineering, 2024, 32(3): 627-642.
[21]
CHEN T, GUESTRIN C. XGBoost: a scalable tree boosting system[C]. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2016: 785-794.
[22]
ZHANG Wengang, ZHANG Runhong, WU Chongzhi, et al. State-of-the-art review of soft computing applications in underground excavations[J]. Geoscience Frontiers, 2020, 11(4): 1095-1106.
[23]
ZHANG Wengang, GOH A T C, XUAN Feng. A simple prediction model for wall deflection caused by braced excavation in clays[J]. Computers and Geotechnics, 2015, 63: 67-72.
2025年第35卷第4期
PDF下载
481
201
引用本文
BibTeX
文章信息
doi: 10.16265/j.cnki.issn1003-3033.2025.04.0893
  • 接收时间:2024-12-30
  • 首发时间:2025-07-05
  • 出版时间:2025-04-28
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2024-12-30
  • 修回日期:2025-02-19
基金
广州市科技计划项目(2024B03J1389)
广州市建筑集团有限公司科技计划项目(2024KJ033)
广州市建筑集团有限公司科技计划项目(2024KJ030)
广州市院士专家工作站建设项目(创新中心-2024-D011)
作者信息
    1 广州市建筑科学研究院集团有限公司,广东 广州 510440
    2 广州建筑股份有限公司,广东 广州 510030
    3 华南理工大学 土木与交通学院,广东 广州 510641
    4 中山大学 土木工程学院,广东 广州 510275

通讯作者:

**胡贺松(1979—),男,河南驻马店人,博士,教授级高级工程师,主要从事岩土工程检测、安全监测与建筑施工等方面的研究。E-mail:
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/zgaqkxxb/CN/10.16265/j.cnki.issn1003-3033.2025.04.0893
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