Article(id=1244316352664682686, tenantId=1146029695717560320, journalId=1244215477623373855, issueId=1244316342938087728, articleNumber=null, orderNo=null, doi=10.16285/j.rsm.2024.1483, pmid=null, cstr=32223.14.j.rsm.2024.1483, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1732982400000, receivedDateStr=2024-12-01, revisedDate=null, revisedDateStr=null, acceptedDate=1742659200000, acceptedDateStr=2025-03-23, onlineDate=1774597736754, onlineDateStr=2026-03-27, pubDate=1763049600000, pubDateStr=2025-11-14, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1774597736754, onlineIssueDateStr=2026-03-27, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1774597736754, creator=13701087609, updateTime=1774597736754, updator=13701087609, issue=Issue{id=1244316342938087728, tenantId=1146029695717560320, journalId=1244215477623373855, year='2025', volume='46', issue='11', pageStart='3329', pageEnd='3672', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=1, specialIssue=null, createTime=1774597734436, creator=13701087609, updateTime=1774597825220, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1244316723801862468, tenantId=1146029695717560320, journalId=1244215477623373855, issueId=1244316342938087728, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1244316723806056773, tenantId=1146029695717560320, journalId=1244215477623373855, issueId=1244316342938087728, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=3615, endPage=3625, ext={EN=ArticleExt(id=1244316353046364368, articleId=1244316352664682686, tenantId=1146029695717560320, journalId=1244215477623373855, language=EN, title=Intelligent geological condition recognition in shield tunneling via time-series clustering and online learning, columnId=1244316346998174029, journalTitle=Rock and Soil Mechanics, columnName=Geotechnical Engineering, runingTitle=null, highlight=null, articleAbstract=

Current machine learning models for recognizing geological conditions during shield tunneling heavily rely on precise geological data labelling, limiting their applicability in complex geological environments. To address this, we propose a continuous dynamic time warping (CDTW)-based agglomerative hierarchical clustering model (CDTW-Agglomerative), which integrates a linear interpolation framework to overcome DTW's discretization issues. An online learning mechanism is implemented for dynamic strata recognition. The model's accuracy and reliability are validated using Xiamen Metro Line 3 data, with generalization tested on Line 6 data. Results show recognition accuracies of 85% and 73% on the two datasets, demonstrating robust generalization. CDTW-Agglomerative outperforms DTW-Agglomerative, SoftDTW-Agglomerative, and CDTW-based models (K-means, K-medoids, Spectral clustering). Notably, it identifies cutterhead stratigraphy without requiring pre-labelled geological data, supporting intelligent decision-making for tunnelling parameters.

, correspAuthors=null, authorNote=null, correspAuthorsNote=null, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=null, magXml=null, pdfUrl=null, pdf=null, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=null, mapNumber=null, authorCompany=null, fund=null, authors=null, authorsList=Jia-jie ZHEN, Feng-wen LAI, Ming HUANG, Qing-xiang LIAO, Shuang LI, Yue-qiang DUAN), CN=ArticleExt(id=1244316361946677809, articleId=1244316352664682686, tenantId=1146029695717560320, journalId=1244215477623373855, language=CN, title=基于时序聚类和在线学习的盾构掘进地层智能识别方法, columnId=1244316347161751894, journalTitle=岩土力学, columnName=岩土工程研究, runingTitle=null, highlight=null, articleAbstract=

已有盾构掘进地层识别机器学习模型高度依赖准确的地层信息作为模型标签输入,使其在复杂地层适用性较差。通过引入线性插值模型克服传统动态时间规整(dynamic time warping,简称DTW)的离散化问题,提出了基于连续动态时间规整(continuous dynamic time warping,简称CDTW)的凝聚型层次聚类模型(CDTW-Agglomerative),构建了能够动态识别地层的在线学习机制。基于厦门地铁3号线盾构掘进数据集验证了所提模型的准确性和可靠性,并通过厦门地铁6号线盾构掘进数据集对模型泛化性进行测试。结果表明,CDTW-Agglomerative在两个不同地质条件数据集下的预测准确率分别约为85%和73%,具有良好的泛化性。CDTW-Agglomerative性能优于基于DTW、软动态时间规整(soft dynamic time warping,简称SoftDTW)的凝聚型层次聚类模型和CDTW-K-means、CDTW-K-medoids、CDTW-Spectral等聚类模型。所提模型无需地层信息作为标签输入,即可有效识别盾构刀盘处地层信息,为盾构掘进参数智能决策提供参考。

, correspAuthors=null, authorNote=null, correspAuthorsNote=
赖丰文,男,1992年生,博士,副研究员,硕士生导师,主要从事土-结构相互作用、岩土原位测试方面的研究工作。E-mail:
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=zbilWfq5WpIEQZf/Az49xw==, magXml=nUofF1xH65YZN7Jg0DjQRw==, pdfUrl=null, pdf=sLZNcnx780q8rOkHU35bbA==, pdfFileSize=5132170, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=uANgDLE0vB/mXsAdtZqarw==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=JHeUEqvxTHOCukSr/ybqkQ==, mapNumber=null, authorCompany=null, fund=null, authors=

真嘉捷,男,1996年生,博士研究生,主要从事盾构法隧道智能化掘进方面的研究工作。E-mail:

, authorsList=真嘉捷, 赖丰文, 黄明, 廖清香, 李爽, 段岳强)}, authors=[Author(id=1244316362722624123, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=Ternuraa148@163.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1244316362819093124, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, authorId=1244316362722624123, language=EN, stringName=Jia-jie ZHEN, firstName=Jia-jie, middleName=null, lastName=ZHEN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1.College of Civil Engineering, Fuzhou University, Fuzhou, Fujian 350108, China
2.College of Transportation and Civil Engineering, Fujian Agriculture and Forestry University, Fuzhou, Fujian 350108, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1244316362965893776, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, authorId=1244316362722624123, language=CN, stringName=真嘉捷, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1.福州大学 土木工程学院,福建 福州 350108
2.福建农林大学 交通与土木工程学院,福建 福州 350108, bio={"content":"

真嘉捷,男,1996年生,博士研究生,主要从事盾构法隧道智能化掘进方面的研究工作。E-mail:

"}, bioImg=null, bioContent=

真嘉捷,男,1996年生,博士研究生,主要从事盾构法隧道智能化掘进方面的研究工作。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1244316362269639249, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, xref=1., ext=[AuthorCompanyExt(id=1244316362278027858, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, companyId=1244316362269639249, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.College of Civil Engineering, Fuzhou University, Fuzhou, Fujian 350108, China), AuthorCompanyExt(id=1244316362290610771, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, companyId=1244316362269639249, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.福州大学 土木工程学院,福建 福州 350108)]), AuthorCompany(id=1244316362370302557, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, xref=2., ext=[AuthorCompanyExt(id=1244316362378691166, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, companyId=1244316362370302557, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.College of Transportation and Civil Engineering, Fujian Agriculture and Forestry University, Fuzhou, Fujian 350108, China), AuthorCompanyExt(id=1244316362382885471, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, companyId=1244316362370302557, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.福建农林大学 交通与土木工程学院,福建 福州 350108)])]), Author(id=1244316363137860262, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=laifengwen@fzu.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1244316363242717871, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, authorId=1244316363137860262, language=EN, stringName=Feng-wen LAI, firstName=Feng-wen, middleName=null, lastName=LAI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.College of Civil Engineering, Fuzhou University, Fuzhou, Fujian 350108, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1244316364811387573, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, authorId=1244316363137860262, language=CN, stringName=赖丰文, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.福州大学 土木工程学院,福建 福州 350108, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1244316362269639249, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, xref=1., ext=[AuthorCompanyExt(id=1244316362278027858, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, companyId=1244316362269639249, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.College of Civil Engineering, Fuzhou University, Fuzhou, Fujian 350108, China), AuthorCompanyExt(id=1244316362290610771, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, companyId=1244316362269639249, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.福州大学 土木工程学院,福建 福州 350108)])]), Author(id=1244316364958188227, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, 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=1244316365176292049, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, authorId=1244316364958188227, language=EN, stringName=Ming HUANG, firstName=Ming, middleName=null, lastName=HUANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.College of Civil Engineering, Fuzhou University, Fuzhou, Fujian 350108, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1244316365331481309, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, authorId=1244316364958188227, language=CN, stringName=黄明, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.福州大学 土木工程学院,福建 福州 350108, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1244316362269639249, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, xref=1., ext=[AuthorCompanyExt(id=1244316362278027858, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, companyId=1244316362269639249, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.College of Civil Engineering, Fuzhou University, Fuzhou, Fujian 350108, China), AuthorCompanyExt(id=1244316362290610771, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, companyId=1244316362269639249, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.福州大学 土木工程学院,福建 福州 350108)])]), Author(id=1244316365440533221, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, 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=1244316365566362349, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, authorId=1244316365440533221, language=EN, stringName=Qing-xiang LIAO, firstName=Qing-xiang, middleName=null, lastName=LIAO, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3.Fujian Fuzhou Construction Development Group Co. Ltd., Fuzhou, Fujian 350009, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1244316365729940216, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, authorId=1244316365440533221, language=CN, stringName=廖清香, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3.福州市建设发展集团有限公司,福建 福州 350009, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1244316362470965861, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, xref=3., ext=[AuthorCompanyExt(id=1244316362479354470, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, companyId=1244316362470965861, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3.Fujian Fuzhou Construction Development Group Co. Ltd., Fuzhou, Fujian 350009, China), AuthorCompanyExt(id=1244316362487743079, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, companyId=1244316362470965861, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3.福州市建设发展集团有限公司,福建 福州 350009)])]), Author(id=1244316365855769347, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, 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=1244316366006764305, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, authorId=1244316365855769347, language=EN, stringName=Shuang LI, firstName=Shuang, middleName=null, lastName=LI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.College of Civil Engineering, Fuzhou University, Fuzhou, Fujian 350108, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1244316366124204825, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, authorId=1244316365855769347, language=CN, stringName=李爽, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.福州大学 土木工程学院,福建 福州 350108, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1244316362269639249, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, xref=1., ext=[AuthorCompanyExt(id=1244316362278027858, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, companyId=1244316362269639249, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.College of Civil Engineering, Fuzhou University, Fuzhou, Fujian 350108, China), AuthorCompanyExt(id=1244316362290610771, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, companyId=1244316362269639249, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.福州大学 土木工程学院,福建 福州 350108)])]), Author(id=1244316366287782696, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, orderNo=5, 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=1244316366434583352, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, authorId=1244316366287782696, language=EN, stringName=Yue-qiang DUAN, firstName=Yue-qiang, middleName=null, lastName=DUAN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=4, address=4.Xiamen Engineering Co. Ltd. of CCCC First Highway Engineering Co. Ltd., Xiamen, Fujian 361021, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1244316366585578309, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, authorId=1244316366287782696, language=CN, stringName=段岳强, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=4, address=4.中交一公局厦门工程有限公司,福建 厦门 361021, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1244316362592600685, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, xref=4., ext=[AuthorCompanyExt(id=1244316362605183599, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, companyId=1244316362592600685, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=4.Xiamen Engineering Co. Ltd. of CCCC First Highway Engineering Co. Ltd., Xiamen, Fujian 361021, China), AuthorCompanyExt(id=1244316362613572208, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, companyId=1244316362592600685, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=4.中交一公局厦门工程有限公司,福建 厦门 361021)])])], keywords=[Keyword(id=1244316366757544786, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, language=EN, orderNo=1, keyword=shield tunnel), Keyword(id=1244316366895956832, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, language=EN, orderNo=2, keyword=machine learning), Keyword(id=1244316366979842919, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, language=EN, orderNo=3, keyword=geological condition prediction), Keyword(id=1244316367076311921, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, language=EN, orderNo=4, keyword=time series clustering), Keyword(id=1244316367181169530, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, language=EN, orderNo=5, keyword=online learning), Keyword(id=1244316367265055617, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, language=CN, orderNo=1, keyword=盾构隧道), Keyword(id=1244316367369913223, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, language=CN, orderNo=2, keyword=机器学习), Keyword(id=1244316367483159440, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, language=CN, orderNo=3, keyword=地层识别), Keyword(id=1244316367588017049, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, language=CN, orderNo=4, keyword=时间序列聚类), Keyword(id=1244316367768372132, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, language=CN, orderNo=5, keyword=在线学习)], refs=[Reference(id=1244316375762714820, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, doi=null, pmid=null, pmcid=null, year=2020, volume=39, issue=9, pageStart=1860, pageEnd=71, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=朱梦琦, 朱合华, 王昕, journalName=岩石力学与工程学报, refType=null, unstructuredReference=朱梦琦, 朱合华, 王昕, . 基于集成CART算法的TBM掘进参数与围岩等级预测[J]. 岩石力学与工程学报, 2020, 39(9): 1860-71., articleTitle=基于集成CART算法的TBM掘进参数与围岩等级预测, refAbstract=null), Reference(id=1244316375875961034, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, doi=null, pmid=null, pmcid=null, year=2020, volume=39, issue=9, pageStart=1860, pageEnd=71, url=null, language=null, rfNumber=[1], rfOrder=1, authorNames=ZHU Meng-qi, ZHU He-hua, WANG Xin, journalName=Chinese Journal of Rock Mechanics and Engineering, refType=null, unstructuredReference=ZHU Meng-qi, ZHU He-hua, WANG Xin, et al. Study on CART-based ensemble learning algorithms for predicting TBM tunneling parameters and classing surrounding rockmasses[J]. Chinese Journal of Rock Mechanics and Engineering, 2020, 39(9): 1860-71., articleTitle=Study on CART-based ensemble learning algorithms for predicting TBM tunneling parameters and classing surrounding rockmasses, refAbstract=null), Reference(id=1244316375989207249, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, doi=null, pmid=null, pmcid=null, year=2024, volume=45, issue=12, pageStart=3791, pageEnd=3801, url=null, language=null, rfNumber=[2], rfOrder=2, authorNames=真嘉捷, 赖丰文, 黄明, journalName=岩土力学, refType=null, unstructuredReference=真嘉捷, 赖丰文, 黄明, . 基于LightGBM-Informer的盾构隧道管片上浮长时间序列预测模型[J]. 岩土力学, 2024, 45(12): 3791-3801., articleTitle=基于LightGBM-Informer的盾构隧道管片上浮长时间序列预测模型, refAbstract=null), Reference(id=1244316376077287637, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, doi=null, pmid=null, pmcid=null, year=2024, volume=45, issue=12, pageStart=3791, pageEnd=3801, url=null, language=null, rfNumber=[2], rfOrder=3, authorNames=ZHEN Jia-jie, LAI Feng-wen, HUANG Ming, journalName=Rock and Soil Mechanics, refType=null, unstructuredReference=ZHEN Jia-jie, LAI Feng-wen, HUANG Ming, et al. Long sequence time series model to predict uplift of segmental lining in shield tunnel based on LightGBM-Informer[J]. Rock and Soil Mechanics, 2024, 45(12): 3791-3801., articleTitle=Long sequence time series model to predict uplift of segmental lining in shield tunnel based on LightGBM-Informer, refAbstract=null), Reference(id=1244316376182145244, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, doi=null, pmid=null, pmcid=null, year=2023, volume=135, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[3], rfOrder=4, authorNames=HUANG M, LU Y, ZHEN J J, journalName=Tunnelling and Underground Space Technology, refType=null, unstructuredReference=HUANG M, LU Y, ZHEN J J, et al. Analysis of face stability at the launch stage of shield or TBM tunnelling using a concrete box in complex urban environments[J]. Tunnelling and Underground Space Technology, 2023, 135: 105067., articleTitle=Analysis of face stability at the launch stage of shield or TBM tunnelling using a concrete box in complex urban environments, refAbstract=null), Reference(id=1244316376295391459, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, doi=null, pmid=null, pmcid=null, year=2024, volume=45, issue=2, pageStart=539, pageEnd=551, url=null, language=null, rfNumber=[4], rfOrder=5, authorNames=潘秋景, 吴洪涛, 张子龙, journalName=岩土力学, refType=null, unstructuredReference=潘秋景, 吴洪涛, 张子龙, . 基于多域物理信息神经网络的复合地层隧道掘进地表沉降预测[J]. 岩土力学, 2024, 45(2): 539-551., articleTitle=基于多域物理信息神经网络的复合地层隧道掘进地表沉降预测, refAbstract=null), Reference(id=1244316376450580714, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, doi=null, pmid=null, pmcid=null, year=2024, volume=45, issue=2, pageStart=539, pageEnd=551, url=null, language=null, rfNumber=[4], rfOrder=6, authorNames=PAN Qiu-jing, WU Hong-tao, ZHANG Zi-long, journalName=Rock and Soil Mechanics, refType=null, unstructuredReference=PAN Qiu-jing, WU Hong-tao, ZHANG Zi-long, et al. Prediction of tunneling-induced ground surface settlement within composite strata using multi-physics-informed neural network[J]. Rock and Soil Mechanics, 2024, 45(2): 539-551., articleTitle=Prediction of tunneling-induced ground surface settlement within composite strata using multi-physics-informed neural network, refAbstract=null), Reference(id=1244316376580604143, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, doi=null, pmid=null, pmcid=null, year=2023, volume=44, issue=10, pageStart=2997, pageEnd=3010, url=null, language=null, rfNumber=[5], rfOrder=7, authorNames=张东明, 周烨璐, 黄宏伟, journalName=岩土力学, refType=null, unstructuredReference=张东明, 周烨璐, 黄宏伟, . 物理信息双驱动的长距离盾构隧道结构纵向力学性态智能诊断方法[J]. 岩土力学, 2023, 44(10): 2997-3010., articleTitle=物理信息双驱动的长距离盾构隧道结构纵向力学性态智能诊断方法, refAbstract=null), Reference(id=1244316376660295928, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, doi=null, pmid=null, pmcid=null, year=2023, volume=44, issue=10, pageStart=2997, pageEnd=3010, url=null, language=null, rfNumber=[5], rfOrder=8, authorNames=ZHANG Dong-ming, ZHOU Ye-lu, HUANG Hong-wei, journalName=Rock and Soil Mechanics, refType=null, unstructuredReference=ZHANG Dong-ming, ZHOU Ye-lu, HUANG Hong-wei, et al. A physics and information dual-driven intelligent diagnosis method for longitudinal mechanical behavior of long-distance shield tunnels[J]. Rock and Soil Mechanics, 2023, 44(10): 2997-3010., articleTitle=A physics and information dual-driven intelligent diagnosis method for longitudinal mechanical behavior of long-distance shield tunnels, refAbstract=null), Reference(id=1244316376752570620, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, doi=null, pmid=null, pmcid=null, year=2025, volume=62, issue=null, pageStart=1, pageEnd=23, url=null, language=null, rfNumber=[6], rfOrder=9, authorNames=LAI F W, TSCHUCHNIGG F, SCHWEIGER F H, journalName=Canadian Geotechnical Journal, refType=null, unstructuredReference=LAI F W, TSCHUCHNIGG F, SCHWEIGER F H, et al. A numerical study of deep excavations adjacent to existing tunnels: Integrating CPTU and SDMT to calibrate soil constitutive model[J]. Canadian Geotechnical Journal, 2025, 62: 1-23., articleTitle=A numerical study of deep excavations adjacent to existing tunnels: Integrating CPTU and SDMT to calibrate soil constitutive model, refAbstract=null), Reference(id=1244316378283491585, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, doi=null, pmid=null, pmcid=null, year=2024, volume=16, issue=null, pageStart=164, pageEnd=182, url=null, language=null, rfNumber=[7], rfOrder=10, authorNames=WANG S Y, LU T Y, ZHENG X C, journalName=Underground Space, refType=null, unstructuredReference=WANG S Y, LU T Y, ZHENG X C, et al. Dynamic collapse characteristics of the tunnel face induced by the shutdown of earth pressure balance shields (EPB): a 3D material point method study[J]. Underground Space, 2024, 16: 164-182., articleTitle=Dynamic collapse characteristics of the tunnel face induced by the shutdown of earth pressure balance shields (EPB): a 3D material point method study, refAbstract=null), Reference(id=1244316378438680841, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, doi=null, pmid=null, pmcid=null, year=2024, volume=244, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[8], rfOrder=11, authorNames=TAN X Y, PALAIAHNAKOTE S, CHEN W Z, journalName=Expert Systems with Applications, refType=null, unstructuredReference=TAN X Y, PALAIAHNAKOTE S, CHEN W Z, et al. A novel autoencoder for structural anomalies detection in river tunnel operation[J]. Expert Systems with Applications, 2024, 244: 122906., articleTitle=A novel autoencoder for structural anomalies detection in river tunnel operation, refAbstract=null), Reference(id=1244316378556121364, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, doi=null, pmid=null, pmcid=null, year=2020, volume=41, issue=1, pageStart=285, pageEnd=294, url=null, language=null, rfNumber=[9], rfOrder=12, authorNames=王忠凯, 徐光黎, journalName=岩土力学, refType=null, unstructuredReference=王忠凯, 徐光黎. 盾构掘进、离开施工阶段对地表变形的影响范围及量化预测[J]. 岩土力学, 2020, 41(1): 285-294., articleTitle=盾构掘进、离开施工阶段对地表变形的影响范围及量化预测, refAbstract=null), Reference(id=1244316378681950492, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, doi=null, pmid=null, pmcid=null, year=2018, volume=18, issue=6, pageStart=37, pageEnd=49, url=null, language=null, rfNumber=[9], rfOrder=13, authorNames=WANG Zhong-kai, XU Guang-li, journalName=Rock and Soil Mechanics, refType=null, unstructuredReference=WANG Zhong-kai, XU Guang-li. Influence range and quantitative prediction of surface deformation during shield tunnelling and exiting stages[J]. Rock and Soil Mechanics, 2018, 18(6): 37-49., articleTitle=Influence range and quantitative prediction of surface deformation during shield tunnelling and exiting stages, refAbstract=null), Reference(id=1244316378803585317, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, doi=null, pmid=null, pmcid=null, year=2014, volume=33, issue=6, pageStart=1090, pageEnd=1113, url=null, language=null, rfNumber=[10], rfOrder=14, authorNames=李术才, 刘斌, 孙怀凤, journalName=岩石力学与工程学报, refType=null, unstructuredReference=李术才, 刘斌, 孙怀凤, . 隧道施工超前地质预报研究现状及发展趋势[J]. 岩石力学与工程学报, 2014, 33(6): 1090-1113., articleTitle=隧道施工超前地质预报研究现状及发展趋势, refAbstract=null), Reference(id=1244316378933608749, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, doi=null, pmid=null, pmcid=null, year=2014, volume=33, issue=6, pageStart=1090, pageEnd=1113, url=null, language=null, rfNumber=[10], rfOrder=15, authorNames=LI Shu-cai, LIU Bin, SUN Huai-feng, journalName=Chinese Journal of Rock Mechanics and Engineering, refType=null, unstructuredReference=LI Shu-cai, LIU Bin, SUN Huai-feng, et al. State of art and trends of adcanced geological prediction in tunnel construction[J]. Chinese Journal of Rock Mechanics and Engineering, 2014, 33(6): 1090-1113., articleTitle=State of art and trends of adcanced geological prediction in tunnel construction, refAbstract=null), Reference(id=1244316379046854964, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, doi=null, pmid=null, pmcid=null, year=2023, volume=153, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[11], rfOrder=16, authorNames=PAN Y, WU M Z, ZHANG L M, journalName=Automation in Construction, refType=null, unstructuredReference=PAN Y, WU M Z, ZHANG L M, et al. Time series clustering-enabled geological condition perception in tunnel boring machine excavation[J]. Automation in Construction, 2023, 153: 104954., articleTitle=Time series clustering-enabled geological condition perception in tunnel boring machine excavation, refAbstract=null), Reference(id=1244316379168489789, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, doi=null, pmid=null, pmcid=null, year=2018, volume=96, issue=null, pageStart=378, pageEnd=97, url=null, language=null, rfNumber=[12], rfOrder=17, authorNames=KIM J I, FISCHER M, KAM C, journalName=Automation in Construction, refType=null, unstructuredReference=KIM J I, FISCHER M, KAM C. Generation and evaluation of excavation schedules for hard rock tunnels in preconstruction and construction[J]. Automation in Construction, 2018, 96: 378-97., articleTitle=Generation and evaluation of excavation schedules for hard rock tunnels in preconstruction and construction, refAbstract=null), Reference(id=1244316379298513216, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, doi=null, pmid=null, pmcid=null, year=2020, volume=39, issue=增刊1, pageStart=2733, pageEnd=40, url=null, language=null, rfNumber=[13], rfOrder=18, authorNames=娄国充, 孙志涛, 满令聪, journalName=岩石力学与工程学报, refType=null, unstructuredReference=娄国充, 孙志涛, 满令聪. 三维地震波定向超前地质预报技术试验研究[J]. 岩石力学与工程学报, 2020, 39(增刊1): 2733-40., articleTitle=三维地震波定向超前地质预报技术试验研究, refAbstract=null), Reference(id=1244316379453702471, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, doi=null, pmid=null, pmcid=null, year=2020, volume=39, issue=Suppl.1, pageStart=2733, pageEnd=40, url=null, language=null, rfNumber=[13], rfOrder=19, authorNames=LOU Guo-chong, SUN Zhi-tao, MAN Ling-cong, journalName=Chinese Journal of Rock Mechanics and Engineering, refType=null, unstructuredReference=LOU Guo-chong, SUN Zhi-tao, MAN Ling-cong, Experimental research on 3D geological directional seismic prediction during tunnel construction[J]. Chinese Journal of Rock Mechanics and Engineering, 2020, 39(Suppl.1): 2733-40., articleTitle=Experimental research on 3D geological directional seismic prediction during tunnel construction, refAbstract=null), Reference(id=1244316379596308812, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, doi=null, pmid=null, pmcid=null, year=2016, volume=37, issue=12, pageStart=3618, pageEnd=3626, url=null, language=null, rfNumber=[14], rfOrder=20, authorNames=刘成禹, 余世为, journalName=岩土力学, refType=null, unstructuredReference=刘成禹, 余世为. 基于探地雷达单道信号处理的岩溶分析方法[J]. 岩土力学, 2016, 37(12): 3618-3626., articleTitle=基于探地雷达单道信号处理的岩溶分析方法, refAbstract=null), Reference(id=1244316379705360718, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, doi=null, pmid=null, pmcid=null, year=2016, volume=37, issue=12, pageStart=3618, pageEnd=3626, url=null, language=null, rfNumber=[14], rfOrder=21, authorNames=LIU Cheng-yu, YU Shi-wei, journalName=Rock and Soil Mechanics, refType=null, unstructuredReference=LIU Cheng-yu, YU Shi-wei. Analysis method of karst based on single channel signal processing by ground penetrating radar[J]. Rock and Soil Mechanics, 2016, 37(12): 3618-3626., articleTitle=Analysis method of karst based on single channel signal processing by ground penetrating radar, refAbstract=null), Reference(id=1244316379801829715, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, doi=null, pmid=null, pmcid=null, year=2021, volume=125, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[15], rfOrder=22, authorNames=LIU Z B, LI L, FANG X L, journalName=Automation in Construction, refType=null, unstructuredReference=LIU Z B, LI L, FANG X L, et al. Hard-rock tunnel lithology prediction with TBM construction big data using a global-attention-mechanism-based LSTM network[J]. Automation in Construction, 2021, 125: 103647., articleTitle=Hard-rock tunnel lithology prediction with TBM construction big data using a global-attention-mechanism-based LSTM network, refAbstract=null), Reference(id=1244316379948630363, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, doi=null, pmid=null, pmcid=null, year=2023, volume=44, issue=4, pageStart=941, pageEnd=951, url=null, language=null, rfNumber=[16], rfOrder=23, authorNames=刘勇, 周怡晟, 索晓明, journalName=岩土力学, refType=null, unstructuredReference=刘勇, 周怡晟, 索晓明, . 盾构下穿高铁路基变形规律模型试验研究[J]. 岩土力学, 2023, 44(4): 941-951., articleTitle=盾构下穿高铁路基变形规律模型试验研究, refAbstract=null), Reference(id=1244316380095431010, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, doi=null, pmid=null, pmcid=null, year=2023, volume=23, issue=4, pageStart=248, pageEnd=57, url=null, language=null, rfNumber=[16], rfOrder=24, authorNames=LIU Yong, ZHOU Yi-sheng, SUO Xiao-ming, journalName=Rock and Soil Mechanics, refType=null, unstructuredReference=LIU Yong, ZHOU Yi-sheng, SUO Xiao-ming, et al. Model test on the deformation law of shield tunnel underpassing high speed railway roadbed[J]. Rock and Soil Mechanics, 2023, 23(4): 248-57., articleTitle=Model test on the deformation law of shield tunnel underpassing high speed railway roadbed, refAbstract=null), Reference(id=1244316380242231654, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, doi=null, pmid=null, pmcid=null, year=2023, volume=15, issue=5, pageStart=1248, pageEnd=62, url=null, language=null, rfNumber=[17], rfOrder=25, authorNames=LAI F W, SHIAU J, KEAWSAWASVONG S, journalName=Journal of Rock Mechanics and Geotechnical Engineering, refType=null, unstructuredReference=LAI F W, SHIAU J, KEAWSAWASVONG S, et al. Physics-based and data-driven modeling for stability evaluation of buried structures in natural clays[J]. Journal of Rock Mechanics and Geotechnical Engineering, 2023, 15(5): 1248-62., articleTitle=Physics-based and data-driven modeling for stability evaluation of buried structures in natural clays, refAbstract=null), Reference(id=1244316380347089261, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, doi=null, pmid=null, pmcid=null, year=2025, volume=24, issue=null, pageStart=162, pageEnd=179, url=null, language=null, rfNumber=[18], rfOrder=26, authorNames=LAI F W, LIU S Y, SHIAU J, journalName=Underground Space, refType=null, unstructuredReference=LAI F W, LIU S Y, SHIAU J, et al. Data-driven modeling for evaluating deformation of a deep excavation near existing tunnels[J]. Underground Space, 2025, 24: 162-179., articleTitle=Data-driven modeling for evaluating deformation of a deep excavation near existing tunnels, refAbstract=null), Reference(id=1244316380435169651, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, doi=null, pmid=null, pmcid=null, year=2025, volume=15, issue=null, pageStart=1337, pageEnd=1348, url=null, language=null, rfNumber=[19], rfOrder=27, authorNames=TAN X Y, CHEN W Z, FAN C K, journalName=Journal of Civil Structural Health Monitoring, refType=null, unstructuredReference=TAN X Y, CHEN W Z, FAN C K, et al. Missing data imputation in tunnel monitoring with a spatio-temporal correlation fused machine learning model[J]. Journal of Civil Structural Health Monitoring, 2025, 15: 1337-1348., articleTitle=Missing data imputation in tunnel monitoring with a spatio-temporal correlation fused machine learning model, refAbstract=null), Reference(id=1244316380531638646, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, doi=null, pmid=null, pmcid=null, year=2019, volume=91, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[20], rfOrder=28, authorNames=LIU B, WANG R R, GUAN Z D, journalName=Tunnnelling Undergrround Space Technology, refType=null, unstructuredReference=LIU B, WANG R R, GUAN Z D, et al. Improved support vector regression models for predicting rock mass parameters using tunnel boring machine driving data[J]. Tunnnelling Undergrround Space Technology, 2019, 91: 102958., articleTitle=Improved support vector regression models for predicting rock mass parameters using tunnel boring machine driving data, refAbstract=null), Reference(id=1244316380644884861, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, doi=null, pmid=null, pmcid=null, year=2019, volume=100, issue=null, pageStart=73, pageEnd=83, url=null, language=null, rfNumber=[21], rfOrder=29, authorNames=ZHANG Q L, LIU Z Y, TAN J R, journalName=Automation in Construction, refType=null, unstructuredReference=ZHANG Q L, LIU Z Y, TAN J R. Prediction of geological conditions for a tunnel boring machine using big operational data[J]. Automation in Construction, 2019, 100: 73-83., articleTitle=Prediction of geological conditions for a tunnel boring machine using big operational data, refAbstract=null), Reference(id=1244316380774908290, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, doi=null, pmid=null, pmcid=null, year=2020, volume=106, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[22], rfOrder=30, authorNames=LIU Q S, WANG X Y, HUANG X, journalName=Tunnelling and Underground Space Technology, refType=null, unstructuredReference=LIU Q S, WANG X Y, HUANG X, et al. Prediction model of rock mass class using classification and regression tree integrated AdaBoost algorithm based on TBM driving data[J]. Tunnelling and Underground Space Technology, 2020, 106: 103595., articleTitle=Prediction model of rock mass class using classification and regression tree integrated AdaBoost algorithm based on TBM driving data, refAbstract=null), Reference(id=1244316380913320328, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, doi=null, pmid=null, pmcid=null, year=2021, volume=13, issue=6, pageStart=1311, pageEnd=25, url=null, language=null, rfNumber=[23], rfOrder=31, authorNames=WU Z J, WEI R L, CHU Z F, journalName=Journal of Rock Mechanics and Geotechnical Engineering, refType=null, unstructuredReference=WU Z J, WEI R L, CHU Z F, et al. Real-time rock mass condition prediction with TBM tunneling big data using a novel rock-machine mutual feedback perception method[J]. Journal of Rock Mechanics and Geotechnical Engineering, 2021, 13(6): 1311-25., articleTitle=Real-time rock mass condition prediction with TBM tunneling big data using a novel rock-machine mutual feedback perception method, refAbstract=null), Reference(id=1244316381039149455, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, doi=null, pmid=null, pmcid=null, year=2019, volume=107, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[24], rfOrder=32, authorNames=ZHOU C, KONG T, ZHOU Y, journalName=Automation in Construction, refType=null, unstructuredReference=ZHOU C, KONG T, ZHOU Y, et al. Unsupervised spectral clustering for shield tunneling machine monitoring data with complex network theory[J]. Automation in Construction, 2019, 107: 102924., articleTitle=Unsupervised spectral clustering for shield tunneling machine monitoring data with complex network theory, refAbstract=null), Reference(id=1244316381173367190, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, doi=null, pmid=null, pmcid=null, year=2018, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[25], rfOrder=33, authorNames=SAI MADIRAJU N, journalName=null, refType=null, unstructuredReference=SAI MADIRAJU N. Deep temporal clustering: fully unsupervised learning of time-domain features[D]. Phoenix: Arizona State University, 2018., articleTitle=Deep temporal clustering: fully unsupervised learning of time-domain features, refAbstract=null), Reference(id=1244316382737842591, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, doi=null, pmid=null, pmcid=null, year=2017, volume=30, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[26], rfOrder=34, authorNames=LUNDBERG S M, LEE S I, journalName=Advances in Neural Information Processing Systems, refType=null, unstructuredReference=LUNDBERG S M, LEE S I. A unified approach to interpreting model predictions[J]. Advances in Neural Information Processing Systems, 2017, 30., articleTitle=A unified approach to interpreting model predictions, refAbstract=null), Reference(id=1244316382851088802, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, doi=null, pmid=null, pmcid=null, year=2021, volume=108, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[27], rfOrder=35, authorNames=CHEN Z Y, ZHANG Y P, LI J B, journalName=Tunnelling and Underground Space Technology, refType=null, unstructuredReference=CHEN Z Y, ZHANG Y P, LI J B, et al. Diagnosing tunnel collapse sections based on TBM tunneling big data and deep learning: a case study on the Yinsong Project, China[J]. Tunnelling and Underground Space Technology, 2021, 108: 103700., articleTitle=Diagnosing tunnel collapse sections based on TBM tunneling big data and deep learning: a case study on the Yinsong Project, China, refAbstract=null), Reference(id=1244316382985306534, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, doi=null, pmid=null, pmcid=null, year=2023, volume=139, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[28], rfOrder=36, authorNames=FANG Y R, LI X G, LIU H Z, journalName=Tunnelling and Underground Space Technology, refType=null, unstructuredReference=FANG Y R, LI X G, LIU H Z, et al. Intelligent real-time identification technology of stratum characteristics during slurry TBM tunneling[J]. Tunnelling and Underground Space Technology, 2023, 139., articleTitle=Intelligent real-time identification technology of stratum characteristics during slurry TBM tunneling, refAbstract=null), Reference(id=1244316383106941357, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, doi=null, pmid=null, pmcid=null, year=2022, volume=37, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[29], rfOrder=37, authorNames=XIAO H H, CHEN Z Y, CAO R L, journalName=Transportation Geotechnics, refType=null, unstructuredReference=XIAO H H, CHEN Z Y, CAO R L, et al. Prediction of shield machine posture using the GRU algorithm with adaptive boosting: a case study of Chengdu subway project[J]. Transportation Geotechnics, 2022, 37: 100837., articleTitle=Prediction of shield machine posture using the GRU algorithm with adaptive boosting: a case study of Chengdu subway project, refAbstract=null), Reference(id=1244316383228576175, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, doi=null, pmid=null, pmcid=null, year=2015, volume=53, issue=null, pageStart=16, pageEnd=38, url=null, language=null, rfNumber=[30], rfOrder=38, authorNames=AGHABOZORGI S, SHIRKHORSHIDI A S, WAH T Y, journalName=Information Systems, refType=null, unstructuredReference=AGHABOZORGI S, SHIRKHORSHIDI A S, WAH T Y. Time-series clustering—a decade review[J]. Information Systems, 2015, 53: 16-38., articleTitle=Time-series clustering—a decade review, refAbstract=null), Reference(id=1244316383337628087, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, doi=null, pmid=null, pmcid=null, year=2022, volume=51, issue=3, pageStart=416, pageEnd=424, url=null, language=null, rfNumber=[31], rfOrder=39, authorNames=李海林, 张丽萍, journalName=电子科技大学学报, refType=null, unstructuredReference=李海林, 张丽萍. 时间序列数据挖掘中的聚类研究综述[J]. 电子科技大学学报, 2022, 51(3): 416-424., articleTitle=时间序列数据挖掘中的聚类研究综述, refAbstract=null), Reference(id=1244316383471845818, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, doi=null, pmid=null, pmcid=null, year=2022, volume=51, issue=3, pageStart=416, pageEnd=424, url=null, language=null, rfNumber=[31], rfOrder=40, authorNames=LI Hai-lin, ZHANG Li-ping, journalName=Journal of University of Electronic Science and Technology of China, refType=null, unstructuredReference=LI Hai-lin, ZHANG Li-ping. Summary of clustering research in time series data mining[J]. Journal of University of Electronic Science and Technology of China, 2022, 51(3): 416-424., articleTitle=Summary of clustering research in time series data mining, refAbstract=null)], funds=[Fund(id=1244316375217455262, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, awardId=52378392; 52408356, language=EN, fundingSource=National Natural Science Foundation of China(52378392; 52408356), fundOrder=null, country=null), Fund(id=1244316375334895783, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, awardId=52378392; 52408356, language=CN, fundingSource=国家自然科学基金(52378392; 52408356), fundOrder=null, country=null), Fund(id=1244316375439753394, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, awardId=00387088, language=EN, fundingSource=“Foal Eagle Program” Youth Top-notch Talent Project of Fujian Province, China(00387088), fundOrder=null, country=null), Fund(id=1244316375573971126, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, awardId=00387088, language=CN, fundingSource=福建省“雏鹰计划”青年拔尖人才项目(00387088), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1244316362269639249, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, xref=1., ext=[AuthorCompanyExt(id=1244316362278027858, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, companyId=1244316362269639249, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.College of Civil Engineering, Fuzhou University, Fuzhou, Fujian 350108, China), AuthorCompanyExt(id=1244316362290610771, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, companyId=1244316362269639249, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.福州大学 土木工程学院,福建 福州 350108)]), AuthorCompany(id=1244316362370302557, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, xref=2., ext=[AuthorCompanyExt(id=1244316362378691166, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, companyId=1244316362370302557, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.College of Transportation and Civil Engineering, Fujian Agriculture and Forestry University, Fuzhou, Fujian 350108, China), AuthorCompanyExt(id=1244316362382885471, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, companyId=1244316362370302557, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.福建农林大学 交通与土木工程学院,福建 福州 350108)]), AuthorCompany(id=1244316362470965861, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, xref=3., ext=[AuthorCompanyExt(id=1244316362479354470, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, companyId=1244316362470965861, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3.Fujian Fuzhou Construction Development Group Co. Ltd., Fuzhou, Fujian 350009, China), AuthorCompanyExt(id=1244316362487743079, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, companyId=1244316362470965861, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3.福州市建设发展集团有限公司,福建 福州 350009)]), AuthorCompany(id=1244316362592600685, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, xref=4., ext=[AuthorCompanyExt(id=1244316362605183599, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, companyId=1244316362592600685, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=4.Xiamen Engineering Co. Ltd. of CCCC First Highway Engineering Co. Ltd., Xiamen, Fujian 361021, China), AuthorCompanyExt(id=1244316362613572208, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, companyId=1244316362592600685, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=4.中交一公局厦门工程有限公司,福建 厦门 361021)])], figs=[ArticleFig(id=1244316369420927921, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, language=EN, label=Fig.1, caption=Comparison of path matching rule between DTW and CDTW, figureFileSmall=T+oiuU37OFWwNFtfzoVpSQ==, figureFileBig=uANgDLE0vB/mXsAdtZqarw==, tableContent=null), ArticleFig(id=1244316369534174135, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, language=CN, label=图1, caption=DTW与CDTW路径匹配规则对比, figureFileSmall=T+oiuU37OFWwNFtfzoVpSQ==, figureFileBig=uANgDLE0vB/mXsAdtZqarw==, tableContent=null), ArticleFig(id=1244316369831969734, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, language=EN, label=Fig.2, caption=Example of applying linear interpolation in DTW, figureFileSmall=3uvYxSWJWXqGn0nDcXWmTQ==, figureFileBig=a8TWe8k/cWEGDSmmgx5N2Q==, tableContent=null), ArticleFig(id=1244316369949410253, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, language=CN, label=图2, caption=在DTW中应用线性插值的示例, figureFileSmall=3uvYxSWJWXqGn0nDcXWmTQ==, figureFileBig=a8TWe8k/cWEGDSmmgx5N2Q==, tableContent=null), ArticleFig(id=1244316370045879254, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, language=EN, label=Fig.3, caption=SHAP method predictor loss curve, figureFileSmall=YeWDDRIJ7j+hjkmGtptfYw==, figureFileBig=Z7RcZ9d6c/uJr3mfyR4nxA==, tableContent=null), ArticleFig(id=1244316370125571038, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, language=CN, label=图3, caption=SHAP方法预测器损失曲线, figureFileSmall=YeWDDRIJ7j+hjkmGtptfYw==, figureFileBig=Z7RcZ9d6c/uJr3mfyR4nxA==, tableContent=null), ArticleFig(id=1244316370234622948, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, language=EN, label=Fig.4, caption=Results of SHAP feature importance analysis, figureFileSmall=sNVXyvYMSUKwhW46FroM6Q==, figureFileBig=couAddnCW7R70iPfMfnHVA==, tableContent=null), ArticleFig(id=1244316370368840681, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, language=CN, label=图4, caption=SHAP特征重要性分析结果

注:PT-A、PT-B、PT-C、PT-D分别为A~D组千斤顶压力,SPC-A、SPC-B、SPC-C、SPC-D分别为A~D组千斤顶行程,CL-CP、UL-CP、LL-CP、LR-CP、CR-CP分别为左中、左上、左下、右下、右中土舱压力,SCP为螺旋机压力,SCRS为螺旋机转速,SCT为螺旋机扭矩,AS为推进速度,TTF为总推力,P为贯入度,CT为刀盘扭矩,CRS为刀盘转速,CP为刀盘压力,GV为注浆量,HDSH为盾构头部水平偏差,VDSH为盾构尾部垂直偏差,VDST为盾构尾部垂直偏差,VDSH为盾构头部垂直偏差,HA为倾斜角,RA为旋转角。

, figureFileSmall=sNVXyvYMSUKwhW46FroM6Q==, figureFileBig=couAddnCW7R70iPfMfnHVA==, tableContent=null), ArticleFig(id=1244316370532418546, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, language=EN, label=Fig.5, caption=Performance of CDTW-Agglomerative under different input sequence lengths, figureFileSmall=oZDbMBGIoZ6/jLknuERrNg==, figureFileBig=JIlZbeEFa78N54THsUngrQ==, tableContent=null), ArticleFig(id=1244316370754716667, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, language=CN, label=图5, caption=不同输入序列长度下的CDTW-Agglomerative性能, figureFileSmall=oZDbMBGIoZ6/jLknuERrNg==, figureFileBig=JIlZbeEFa78N54THsUngrQ==, tableContent=null), ArticleFig(id=1244316370863768576, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, language=EN, label=Fig.6, caption=Confusion matrix of DTW- Agglomerative model, figureFileSmall=XEnEN2do2RF+OrsrAY/zcg==, figureFileBig=zv1sE1CdBCnTPqzsjZ2jZQ==, tableContent=null), ArticleFig(id=1244316370989596682, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, language=CN, label=图6, caption=DTW-Agglomerative混淆矩阵, figureFileSmall=XEnEN2do2RF+OrsrAY/zcg==, figureFileBig=zv1sE1CdBCnTPqzsjZ2jZQ==, tableContent=null), ArticleFig(id=1244316371073482769, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, language=EN, label=Fig.7, caption=Confusion matrix of CDTW-Agglomerative model, figureFileSmall=dnpUWO1/t6SSdJddwz54Vg==, figureFileBig=RfaVjVjK+UkPeKAjlBz03A==, tableContent=null), ArticleFig(id=1244316371211894809, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, language=CN, label=图7, caption=CDTW-Agglomerative混淆矩阵, figureFileSmall=dnpUWO1/t6SSdJddwz54Vg==, figureFileBig=RfaVjVjK+UkPeKAjlBz03A==, tableContent=null), ArticleFig(id=1244316371346112546, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, language=EN, label=Fig.8, caption=CDTW-Agglomerative-based temporal clustering results for advance speed (AS), figureFileSmall=lLz6KAoB8lg+aoqVAcrIYA==, figureFileBig=1uG/dXllbnNp9zeEC76R0g==, tableContent=null), ArticleFig(id=1244316371564216358, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, language=CN, label=图8, caption=基于CDTW-Agglomerative模型的推进速度(AS)时序聚类结果, figureFileSmall=lLz6KAoB8lg+aoqVAcrIYA==, figureFileBig=1uG/dXllbnNp9zeEC76R0g==, tableContent=null), ArticleFig(id=1244316371690045484, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, language=EN, label=Fig.9, caption=Robustness test results with data noise, figureFileSmall=qrg3K6bI7RcLanRLTbLa8A==, figureFileBig=nGQd9fsPl3zj/JCFlhA2dQ==, tableContent=null), ArticleFig(id=1244316371920732209, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, language=CN, label=图9, caption=数据噪声鲁棒性测试结果, figureFileSmall=qrg3K6bI7RcLanRLTbLa8A==, figureFileBig=nGQd9fsPl3zj/JCFlhA2dQ==, tableContent=null), ArticleFig(id=1244316372063338553, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, language=EN, label=Fig.10, caption=Robustness test results with missing data, figureFileSmall=vy0baoSpU8vDO8PMx12Lkw==, figureFileBig=WQyIgYw9Ko4W/jXCDH7yCA==, tableContent=null), ArticleFig(id=1244316372159807554, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, language=CN, label=图10, caption=数据缺失鲁棒性测试结果, figureFileSmall=vy0baoSpU8vDO8PMx12Lkw==, figureFileBig=WQyIgYw9Ko4W/jXCDH7yCA==, tableContent=null), ArticleFig(id=1244316372264665161, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, language=EN, label=Fig.11, caption=Confusion matrix of DTW- Agglomerative model generalizability text, figureFileSmall=XOjmwTJSOezIgWH8u9Gi5Q==, figureFileBig=2kpx0eWcJhT89VvAuZApCg==, tableContent=null), ArticleFig(id=1244316373791391822, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, language=CN, label=图11, caption=CDTW-Agglomerative泛化性测试混淆矩阵, figureFileSmall=XOjmwTJSOezIgWH8u9Gi5Q==, figureFileBig=2kpx0eWcJhT89VvAuZApCg==, tableContent=null), ArticleFig(id=1244316373913026649, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, language=EN, label=Fig.12, caption=Result of online learning, figureFileSmall=KQF3RcYFHGVekckb1TNHmQ==, figureFileBig=JF3x6/WGgwkckAPg02HGuQ==, tableContent=null), ArticleFig(id=1244316374026272863, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, language=CN, label=图12, caption=在线学习结果, figureFileSmall=KQF3RcYFHGVekckb1TNHmQ==, figureFileBig=JF3x6/WGgwkckAPg02HGuQ==, tableContent=null), ArticleFig(id=1244316374181462118, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, language=EN, label=Table 1, caption=

Geological condition of the dataset

, figureFileSmall=null, figureFileBig=null, tableContent=
环号276~360459~579960~1 1211 490~1 601
地层砾质黏性土中风化花岗岩粉质黏土、全风化花岗岩混合地层粉质黏土
), ArticleFig(id=1244316374353428585, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, language=CN, label=表1, caption=

研究数据集的地层信息

, figureFileSmall=null, figureFileBig=null, tableContent=
环号276~360459~579960~1 1211 490~1 601
地层砾质黏性土中风化花岗岩粉质黏土、全风化花岗岩混合地层粉质黏土
), ArticleFig(id=1244316374441508974, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, language=EN, label=Table 2, caption=

Model input feature statistics

, figureFileSmall=null, figureFileBig=null, tableContent=
取值PT-A/kNPT-B/kNPT-C/kNPT-D/kNUL-CP/kPaLL-CP/kPaCL-CP/kPaLR-CP/kPa
最大值248.26308.53326.93328.08303182460278
最小值24.0248.0513.0214.71212130
平均值111.34193.52104.3998.32147142265200
中位数109.41195.1694.5890.08172147208201
取值CR-CP/kPaSCP/kPaSCRS/(r·min−1SCT/(kN·m)AS/(mm·min−1TTF/kNP/(mm·r−1CT/(kN·m)
最大值18380099.9849.3975.8931 458.3361.894 188.55
最小值224760.020.011.768 616.511.70801.78
平均值11633186.3720.8939.1715 097.5828.302 075.13
中位数13443116.4720.4141.2514 576.8129.022 018.61
取值CRS/(r·min−1CP/kPaHDSH/mmVDSH/mmHDST/mmVDST/mmHA/(°)RA/(°)
最大值1.8219 093.2427.8843.9527.8427.260.14−0.53
最小值0.7866.19−157.425.78−164.22−22.66−0.72−1.01
平均值1.313 024.21−2.5122.82−2.951.64−0.18−0.72
中位数1.352 932.89−0.8624.292.073.84−0.19−0.72
), ArticleFig(id=1244316374546366580, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, language=CN, label=表2, caption=

模型输入特征统计信息

, figureFileSmall=null, figureFileBig=null, tableContent=
取值PT-A/kNPT-B/kNPT-C/kNPT-D/kNUL-CP/kPaLL-CP/kPaCL-CP/kPaLR-CP/kPa
最大值248.26308.53326.93328.08303182460278
最小值24.0248.0513.0214.71212130
平均值111.34193.52104.3998.32147142265200
中位数109.41195.1694.5890.08172147208201
取值CR-CP/kPaSCP/kPaSCRS/(r·min−1SCT/(kN·m)AS/(mm·min−1TTF/kNP/(mm·r−1CT/(kN·m)
最大值18380099.9849.3975.8931 458.3361.894 188.55
最小值224760.020.011.768 616.511.70801.78
平均值11633186.3720.8939.1715 097.5828.302 075.13
中位数13443116.4720.4141.2514 576.8129.022 018.61
取值CRS/(r·min−1CP/kPaHDSH/mmVDSH/mmHDST/mmVDST/mmHA/(°)RA/(°)
最大值1.8219 093.2427.8843.9527.8427.260.14−0.53
最小值0.7866.19−157.425.78−164.22−22.66−0.72−1.01
平均值1.313 024.21−2.5122.82−2.951.64−0.18−0.72
中位数1.352 932.89−0.8624.292.073.84−0.19−0.72
), ArticleFig(id=1244316374659612794, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, language=EN, label=Table 3, caption=

Results of ablation experiment

, figureFileSmall=null, figureFileBig=null, tableContent=
模型/评价指标ACCARINMI
CDTW-Agglomerative 0.851 4 0.830 5 0.782 8
DTW-Agglomerative0.756 80.828 20.776 5
SoftDTW-Agglomerative0.695 20.518 10.446 3
), ArticleFig(id=1244316374781247616, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, language=CN, label=表3, caption=

消融试验结果

, figureFileSmall=null, figureFileBig=null, tableContent=
模型/评价指标ACCARINMI
CDTW-Agglomerative 0.851 4 0.830 5 0.782 8
DTW-Agglomerative0.756 80.828 20.776 5
SoftDTW-Agglomerative0.695 20.518 10.446 3
), ArticleFig(id=1244316374940631181, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, language=EN, label=Table 4, caption=

Results of comparison experiment

, figureFileSmall=null, figureFileBig=null, tableContent=
模型评价指标聚类数
23456
CDTW-AgglomerativeACC0.488 40.609 6 0.851 40.561 00.476 7
ARI0.231 80.491 6 0.830 50.370 80.170 0
NMI0.214 30.322 0 0.782 80.320 60.145 9
CDTW-KmeansACC0.441 80.539 00.412 30.487 00.495 2
ARI0.129 00.371 70.128 50.203 10.320 1
NMI0.126 50.263 40.124 00.209 40.256 0
CDTW-KmedoidsACC0.529 50.478 10.457 50.396 60.368 5
ARI0.321 90.185 00.152 00.116 30.112 7
NMI0.259 10.186 40.129 10.076 80.072 3
CDTW-SpectralACC0.708 20.723 30.701 40.732 90.726 0
ARI0.633 50.672 90.564 40.778 10.748 0
NMI0.400 90.478 60.392 70.578 20.513 6
), ArticleFig(id=1244316375053877394, tenantId=1146029695717560320, journalId=1244215477623373855, articleId=1244316352664682686, language=CN, label=表4, caption=

对比试验结果

, figureFileSmall=null, figureFileBig=null, tableContent=
模型评价指标聚类数
23456
CDTW-AgglomerativeACC0.488 40.609 6 0.851 40.561 00.476 7
ARI0.231 80.491 6 0.830 50.370 80.170 0
NMI0.214 30.322 0 0.782 80.320 60.145 9
CDTW-KmeansACC0.441 80.539 00.412 30.487 00.495 2
ARI0.129 00.371 70.128 50.203 10.320 1
NMI0.126 50.263 40.124 00.209 40.256 0
CDTW-KmedoidsACC0.529 50.478 10.457 50.396 60.368 5
ARI0.321 90.185 00.152 00.116 30.112 7
NMI0.259 10.186 40.129 10.076 80.072 3
CDTW-SpectralACC0.708 20.723 30.701 40.732 90.726 0
ARI0.633 50.672 90.564 40.778 10.748 0
NMI0.400 90.478 60.392 70.578 20.513 6
)], attaches=null, journal=Journal(id=1244215370232414238, delFlag=0, nameCn=岩土力学, nameEn=Rock and Soil Mechanics, nameHistory1=null, nameHistory2=null, issn=1000-7598, eissn=null, cn=42-1199/O3, 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=duqIXvnPSuSRfuUz6Avf1Q==, journalPrice=null, startedYear=null, abbrevIsoEn=Rock and Soil Mechanics, journalRemark=null, publicationField=null, createdTime=1774573660669, updatedTime=1774573816307, createdBy=18614031015, updatedBy=13701087609, firstLetterCn=R, firstLetterEn=R, subjectCode=Engineering, subjectName=null, subjectCodeEn=Engineering, subjectNameEn=null, picCn=duqIXvnPSuSRfuUz6Avf1Q==, picEn=tD48Z76zrNgyHe8rRYQqtQ==, jcr=null, cjcr=null, exts=[JournalExt(id=1244216023155590113, language=CN, name=岩土力学, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1774573816336, updatedTime=1774573816336, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=https://ytlx.whrsm.ac.cn/journalx/authorLogOn.action, submissionEditorUrl=https://ytlx.whrsm.ac.cn/journalx/editorLogOn.action, submissionReviewUrl=https://ytlx.whrsm.ac.cn/journalx/expertLogOn.action, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1244216023205921762, language=EN, name=Rock and Soil Mechanics, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1774573816348, updatedTime=1774573816348, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=https://ytlx.whrsm.ac.cn/journalx/authorLogOn.action, submissionEditorUrl=https://ytlx.whrsm.ac.cn/journalx/editorLogOn.action, submissionReviewUrl=https://ytlx.whrsm.ac.cn/journalx/expertLogOn.action, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1244215477623373855, websiteList=[Website(id=1244216089618531299, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1244215477623373855, 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/ytlx/CN, language=CN, createTime=1774573832182, createBy=18614031015, updateTime=1774573849833, updateBy=18614031015, name=岩土力学-中文, tplId=1146099689490845704, title=岩土力学, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1244216395047748596, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1244216089618531299, code=articleTextType, value=kx, createTime=1774573905002, updateTime=1774573905002, creator=18614031015, updator=18614031015), WebsiteProps(id=1244216395018388465, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1244216089618531299, code=banner, value=null, createTime=1774573904995, updateTime=1774573904995, creator=18614031015, updator=18614031015), WebsiteProps(id=1244216395064525815, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1244216089618531299, code=grayFlag, value=0, createTime=1774573905006, updateTime=1774573905006, creator=18614031015, updator=18614031015), WebsiteProps(id=1244216395009999856, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1244216089618531299, code=logo, value=https://castjournals.cast.org.cn/joweb/ytlx/CN/file/pic?fileId=5lAZSqrRQoha9OEvB6fTZg==, createTime=1774573904993, updateTime=1774573904993, creator=18614031015, updator=18614031015), WebsiteProps(id=1244216395077108729, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1244216089618531299, code=minRunFlag, value=0, createTime=1774573905009, updateTime=1774573905009, creator=18614031015, updator=18614031015), WebsiteProps(id=1244216395039359987, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1244216089618531299, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/ytlx/CN/file/pic, createTime=1774573905000, updateTime=1774573905000, creator=18614031015, updator=18614031015), WebsiteProps(id=1244216395072914424, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1244216089618531299, code=silenceFlag, value=0, createTime=1774573905008, updateTime=1774573905008, creator=18614031015, updator=18614031015), WebsiteProps(id=1244216395030971378, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1244216089618531299, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1774573904998, updateTime=1774573904998, creator=18614031015, updator=18614031015), WebsiteProps(id=1244216395056137205, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1244216089618531299, code=themeColor, value=null, createTime=1774573905004, updateTime=1774573905004, creator=18614031015, updator=18614031015), WebsiteProps(id=1244216395060331510, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1244216089618531299, code=themeStyle, value=null, createTime=1774573905005, updateTime=1774573905005, creator=18614031015, updator=18614031015)]), Website(id=1244216089685640164, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1244215477623373855, 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/ytlx/EN, language=EN, createTime=1774573832199, createBy=18614031015, updateTime=1774573872997, updateBy=18614031015, name=岩土力学-英文, tplId=1146101810881728533, title=Rock and Soil Mechanics, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1244216425120903885, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1244216089685640164, code=articleTextType, value=kx, createTime=1774573912172, updateTime=1774573912172, creator=18614031015, updator=18614031015), WebsiteProps(id=1244216425095738058, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1244216089685640164, code=banner, value=null, createTime=1774573912166, updateTime=1774573912166, creator=18614031015, updator=18614031015), WebsiteProps(id=1244216425146069712, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1244216089685640164, code=grayFlag, value=0, createTime=1774573912178, updateTime=1774573912178, creator=18614031015, updator=18614031015), WebsiteProps(id=1244216425087349449, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1244216089685640164, code=logo, value=https://castjournals.cast.org.cn/joweb/ytlx/EN/file/pic?fileId=5lAZSqrRQoha9OEvB6fTZg==, createTime=1774573912164, updateTime=1774573912164, creator=18614031015, updator=18614031015), WebsiteProps(id=1244216425167041234, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1244216089685640164, code=minRunFlag, value=0, createTime=1774573912183, updateTime=1774573912183, creator=18614031015, updator=18614031015), WebsiteProps(id=1244216425112515276, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1244216089685640164, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/ytlx/EN/file/pic, createTime=1774573912170, updateTime=1774573912170, creator=18614031015, updator=18614031015), WebsiteProps(id=1244216425150264017, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1244216089685640164, code=silenceFlag, value=0, createTime=1774573912179, updateTime=1774573912179, creator=18614031015, updator=18614031015), WebsiteProps(id=1244216425104126667, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1244216089685640164, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_en_623/, createTime=1774573912168, updateTime=1774573912168, creator=18614031015, updator=18614031015), WebsiteProps(id=1244216425129292494, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1244216089685640164, code=themeColor, value=null, createTime=1774573912174, updateTime=1774573912174, creator=18614031015, updator=18614031015), WebsiteProps(id=1244216425137681103, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1244216089685640164, code=themeStyle, value=null, createTime=1774573912176, updateTime=1774573912176, creator=18614031015, updator=18614031015)])], journalTitle=岩土力学, weixinUrl=null, journalUrl=https://ytlx.whrsm.ac.cn/, iacademicId=null, status=1, seqNo=null, journalTitleEn=Rock and Soil Mechanics, journalPhotoCn=duqIXvnPSuSRfuUz6Avf1Q==, journalPhotoEn=tD48Z76zrNgyHe8rRYQqtQ==, journalFirstLetter=R, journalRecommend=null, journalNew=null, journalCollection=null, jcrJf=null, cjcrJf=null, jcrJfStr=null, cjcrJfStr=null, submissionFirstDecision=null, sciSubjectClassification=null, casSubjectClassification=null, citeScore=null, totalCitationFrequency=null, icpCode=null, psCode=null, advertisingLicenseCode=null, copyrightInformation=null, country=null, option=, provinceCode=null, provinceName=null, collectFlag=false), detailUrlCn=https://castjournals.cast.org.cn/joweb/ytlx/CN/10.16285/j.rsm.2024.1483, detailUrlEn=https://castjournals.cast.org.cn/joweb/ytlx/EN/10.16285/j.rsm.2024.1483, pdfUrlCn=https://castjournals.cast.org.cn/joweb/ytlx/CN/PDF/10.16285/j.rsm.2024.1483, pdfUrlEn=https://castjournals.cast.org.cn/joweb/ytlx/EN/PDF/10.16285/j.rsm.2024.1483, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于时序聚类和在线学习的盾构掘进地层智能识别方法
收藏切换
PDF下载
真嘉捷 1, 2 , 赖丰文 1 , 黄明 1 , 廖清香 3 , 李爽 1 , 段岳强 4
岩土力学 | 岩土工程研究 2025,46(11): 3615-3625
收起
收藏切换
岩土力学 | 岩土工程研究 2025, 46(11): 3615-3625
基于时序聚类和在线学习的盾构掘进地层智能识别方法
全屏
真嘉捷1, 2 , 赖丰文1 , 黄明1, 廖清香3, 李爽1, 段岳强4
作者信息
  • 1.福州大学 土木工程学院,福建 福州 350108
  • 2.福建农林大学 交通与土木工程学院,福建 福州 350108
  • 3.福州市建设发展集团有限公司,福建 福州 350009
  • 4.中交一公局厦门工程有限公司,福建 厦门 361021
  • 真嘉捷,男,1996年生,博士研究生,主要从事盾构法隧道智能化掘进方面的研究工作。E-mail:

通讯作者:

赖丰文,男,1992年生,博士,副研究员,硕士生导师,主要从事土-结构相互作用、岩土原位测试方面的研究工作。E-mail:
Intelligent geological condition recognition in shield tunneling via time-series clustering and online learning
Jia-jie ZHEN1, 2 , Feng-wen LAI1 , Ming HUANG1, Qing-xiang LIAO3, Shuang LI1, Yue-qiang DUAN4
Affiliations
  • 1.College of Civil Engineering, Fuzhou University, Fuzhou, Fujian 350108, China
  • 2.College of Transportation and Civil Engineering, Fujian Agriculture and Forestry University, Fuzhou, Fujian 350108, China
  • 3.Fujian Fuzhou Construction Development Group Co. Ltd., Fuzhou, Fujian 350009, China
  • 4.Xiamen Engineering Co. Ltd. of CCCC First Highway Engineering Co. Ltd., Xiamen, Fujian 361021, China
出版时间: 2025-11-14 doi: 10.16285/j.rsm.2024.1483
文章导航
收藏切换

已有盾构掘进地层识别机器学习模型高度依赖准确的地层信息作为模型标签输入,使其在复杂地层适用性较差。通过引入线性插值模型克服传统动态时间规整(dynamic time warping,简称DTW)的离散化问题,提出了基于连续动态时间规整(continuous dynamic time warping,简称CDTW)的凝聚型层次聚类模型(CDTW-Agglomerative),构建了能够动态识别地层的在线学习机制。基于厦门地铁3号线盾构掘进数据集验证了所提模型的准确性和可靠性,并通过厦门地铁6号线盾构掘进数据集对模型泛化性进行测试。结果表明,CDTW-Agglomerative在两个不同地质条件数据集下的预测准确率分别约为85%和73%,具有良好的泛化性。CDTW-Agglomerative性能优于基于DTW、软动态时间规整(soft dynamic time warping,简称SoftDTW)的凝聚型层次聚类模型和CDTW-K-means、CDTW-K-medoids、CDTW-Spectral等聚类模型。所提模型无需地层信息作为标签输入,即可有效识别盾构刀盘处地层信息,为盾构掘进参数智能决策提供参考。

盾构隧道  /  机器学习  /  地层识别  /  时间序列聚类  /  在线学习

Current machine learning models for recognizing geological conditions during shield tunneling heavily rely on precise geological data labelling, limiting their applicability in complex geological environments. To address this, we propose a continuous dynamic time warping (CDTW)-based agglomerative hierarchical clustering model (CDTW-Agglomerative), which integrates a linear interpolation framework to overcome DTW's discretization issues. An online learning mechanism is implemented for dynamic strata recognition. The model's accuracy and reliability are validated using Xiamen Metro Line 3 data, with generalization tested on Line 6 data. Results show recognition accuracies of 85% and 73% on the two datasets, demonstrating robust generalization. CDTW-Agglomerative outperforms DTW-Agglomerative, SoftDTW-Agglomerative, and CDTW-based models (K-means, K-medoids, Spectral clustering). Notably, it identifies cutterhead stratigraphy without requiring pre-labelled geological data, supporting intelligent decision-making for tunnelling parameters.

shield tunnel  /  machine learning  /  geological condition prediction  /  time series clustering  /  online learning
真嘉捷, 赖丰文, 黄明, 廖清香, 李爽, 段岳强. 基于时序聚类和在线学习的盾构掘进地层智能识别方法. 岩土力学, 2025 , 46 (11) : 3615 -3625 . DOI: 10.16285/j.rsm.2024.1483
Jia-jie ZHEN, Feng-wen LAI, Ming HUANG, Qing-xiang LIAO, Shuang LI, Yue-qiang DUAN. Intelligent geological condition recognition in shield tunneling via time-series clustering and online learning[J]. Rock and Soil Mechanics, 2025 , 46 (11) : 3615 -3625 . DOI: 10.16285/j.rsm.2024.1483
我国城市轨道交通建设进入高速发展阶段,运营里程已跃居全球第一[1]。盾构法因其施工速度快、对地层扰动较小、安全系数高等优点被广泛应用于城市地铁隧道建设[2-8]。由于盾构刀盘对地质条件较为敏感,施工中需根据刀盘所处地层情况,合理调整盾构掘进参数,以保证盾构机安全高效掘进[9]。及时、可靠地预测盾构掘进过程中的地层信息是保证隧道安全高效施工的关键。
由于刀盘和隧道掌子面之间空间狭窄且施工环境复杂,通过传统勘探和原位测试方法获取地层、围岩参数具有一定难度[10]。尽管钻孔取样法是了解盾构隧道沿线工程地质信息的主要方法之一,但由于钻孔分布及数量原因,导致其无法准确反映相邻钻孔之间的地质异常[11]。超前钻孔[12]、地震波检测[13]、地质雷达[14]等地质预报手段,均需耗费额外人力物力,且难以实时解译盾构掘进过程中的地层信息。地层响应与掘进参数变化是岩土体环境系统与盾构机系统中各要素相互作用的结果[15-16],即地层状态可通过盾构掘进参数反映。这使得以盾构控制、姿态等参数为输入特征,建立机器学习模型并准确预测地层信息成为可能。
随着人工智能和大数据技术的蓬勃发展[17-19],已有学者通过支持向量回归[20]、支持向量分类[21]、AdaBoost[22]、AdaCost[1]、深度神经网络[23]等算法,构建有监督机器学习模型,以准确预测盾构隧道的地层信息、围岩等级。上述模型需将真实准确的地层信息作为数据标签,并反复训练模型达到较高的预测精度。然而,为大规模盾构掘进数据集添加地层信息标签需要耗费大量时间和成本。对于水下隧道、深层隧道或复杂地层隧道等挑战性工程,精确获取地层信息难度较大。将不准确地层信息作为有监督模型的数据标签,易降低模型预测结果的真实性和可信度。因此,如何在准确识别盾构隧道地层信息的基础上,减少模型对数据标签依赖是亟待解决的关键问题。
无需数据标签的聚类算法可能是预测盾构隧道地层信息的有效替代方法[11]。Zhang等[21]利用隧道掘进机(tunnel boring machine,简称TBM)运行参数在不同岩体条件下的不同响应,通过聚类的方法建立了新的岩体分级体系。Wu等[23]基于谱聚类算法,从掘进大数据中挖掘岩体信息。Zhou等[24]通过谱聚类和复杂网络理论从盾构隧道监测数据集中提取潜在的数据相关性。然而,上述研究仅通过聚类算法将数据集中的样本点分配到不同自然组,而未考虑盾构掘进数据中潜在的时间相关性。掘进速度、刀盘扭矩等盾构掘进参数是随时间变化数据点的有序集合,可被视为时序数据。时序聚类算法能揭示数据在时间上的潜在模式和变化趋势,将具有相似时间动态特性的序列分为同一组[25]。因此,通过时序聚类算法揭示盾构掘进数据中潜在的时间相关性,能更准确地识别盾构隧道掘进过程中的地层信息。此外,构建时序聚类模型的在线学习框架,可实现盾构隧道施工期地层实时预测,进一步提高模型的工程适用性。
鉴于此,拟提出基于连续动态时间规整(continuous dynamic time warping,简称CDTW)的凝聚型层次聚类模型(CDTW-Agglomerative)。通过线性插值模型改进传统动态时间规整(dynamic time warping,简称DTW)的离散化问题,实现时间序列的连续化规整。构建CDTW-Agglomerative模型的在线学习框架,以自动更新模型聚类中心,实现盾构刀盘处地层信息的实时动态识别。通过厦门地铁3号线盾构掘进数据集对模型有效性和可靠性进行验证,并基于厦门地铁6号线盾构掘进数据集对模型泛化性进行测试。
动态时间规整是一种用于测量两个时间序列之间相似度的方法,其目的是找到一种“路径”将这两个序列对齐,使得序列之间总距离或差异最小。
定义两个离散时间序列X=[x1x2,…,xm]和Y=[y1y2,…,yn]。两个序列之间点xiyi之间的距离通过下式计算:
可建立两个时间序列间所有点的距离矩阵:
通过确定距离矩阵中的规整路径,最小化下式中XY间的累计距离:
式中:π为满足以下约束的规整路径。
(1)边界约束:规整路径要从点(xm,yn)开始到点(x1,y1)结束。
(2)单调连续性:规整路径从点(xm,yn)开始只能去往(xm,yn−1),(xm−1,yn)和(xm−1,yn−1)中的一个点。
规整路径可通过回溯法得到。映射离散化是DTW算法应用在时间序列数据上的主要局限之一。盾构掘进参数变化轨迹本质上是连续的,但由于传感器采样率限制,记录数据通常是离散的。在离散数据上应用DTW算法只能将时间序列变化轨迹映射到已有数据点上,会导致匹配精度降低和一对多匹配情况。
提出基于线性插值模型的CDTW,其规整路径不受已有离散点限制,可映射到两个连续数据点间的插值点。通过观察研究数据集发现,各参数值在连续采样点之间的变化较为缓慢,甚至在多个连续时间步内保持相同值,表明数据集采样频率高于数据实际变化频率。因此,使用简单高效的线性插值模型即可有效增加时间序列的匹配精度,减少计算成本。CDTW路径匹配规则如图1所示,DTW算法的规整路径只能选取3个边界点,而CDTW算法可以到达下方网格线的插值点,使得匹配路径不再局限于离散采样点,可更精确地反映时间序列的真实轨迹。
通过DTW方法得到两个离散时间序列的最佳规整路径。当算法进行回溯时,如果相似性度量矩阵中出现多点映射一点的情况,就通过线性插值模型在一对多映射数据点间进行插值,直到数据点间实现一一映射。具体流程如下:
使用DTW算法计算相似性度量矩阵D。通过D,找到查询序列Q和参考序列R的初步规整路径P。遍历规整路径P,识别出查询序列中单个点与参考序列中多个连续点匹配的区域。然后,从一对多匹配区域中,确定开始和结束的关键点。在这些关键点之间进行线性插值,生成新的、更密集的点序列,如图2所示。图中,a1a3为输入序列上的任意3个点。插值结束后,基于新的插值序列按照上述DTW算法流程,重新计算两个序列之间的距离,从而找到最优规整路径。
凝聚型层次聚类算法是先将数据中的每一个样本作为一个聚类,然后每一次合并距离最近的两个聚类,直至达到终止条件或最终化为一类为止。算法的主要步骤如下:
(1)将每个时间序列作为一个独立的聚类;
(2)计算所有可能聚类对之间的距离,使用CDTW距离作为聚类间的相似度度量;
(3)将距离度量最小的两个聚类合并成一个新的聚类;
(4)更新距离矩阵,重复合并过程,直到所有序列被合并为一个聚类或达到终止条件。
相较于K-means、K-medoids等聚类算法,Agglomerative算法支持不直接指定聚类数,自动将输入数据分为若干聚类,使其增加了在地层信息较难获取的盾构隧道工程中的适用性,无需人为提前预判数据集中的地层数量,降低试错和计算成本。
为了确定影响结果的关键输入变量,采用沙普利加和解释(Shapley additive explanations,简称SHAP)方法进行特征重要性分析[26]。SHAP方法通过沙普利(Shapley)值来计算特征的重要性,其数学表达式如下:
式中:ϕif)为特征i的SHAP值;fxS)为模型在只考虑特征子集S时的输出值;fxS∪{i})是考虑特征子集并且加上特征时模型的预测值;N为特征全集。
数据集来自厦门地铁3号线DK33+914.833-36+290.697段,主要穿越吹填淤泥混砂、粉质黏土、残积砾质黏土和全风化花岗岩等地层,埋深为11.2~12.0 m。采用土压平衡盾构机进行施工,开挖直径为6 480 mm,刀盘转速为0~3.7 r/m,扭矩为5 631 kN·m,最大推力为40 042.8 kN,最大推进速度为80 mm/min。
所研究数据集分别通过线性插值和K-近邻算法进行缺失值填补和离群值检测,确保模型输入数据质量。数据集包含476环管片的389 280个样本点,分别位于砾质黏性土地层、中风化花岗岩地层、粉质黏土及全风化花岗岩混合地层、粉质黏土地层等4种地层中,见表1
由于数据不同维度间存在显著差异,可通过最小-最大缩放方法对数据进行归一化处理:
式中:x*为归一化后的数据;x为原始数据中的某个样本点;max(x)和min(x)分别是某特征数据中的最大值和最小值。
参考已有研究[21, 27-29],选择与识别地层有较强相关性的盾构掘进参数作为模型输入特征,再通过SHAP方法输出特征重要性,删除贡献较小的特征。SHAP方法预测器为长短时记忆(long and short-term memory,简称LSTM)网络,其损失曲线如图3所示。可见,模型损失曲线平稳下降,趋于稳定,未发生过拟合现象。LSTM模型预测准确度为88.92%,表明其有效拟合了数据,其特征重要性结果具有一定参考性。
图4为SHAP方法的特征重要性分析结果。由图可见,4组推进千斤顶压力(PT-A,PT-B,PT-C,PT-D)的特征重要性最高。这是因为推进千斤顶压力是控制盾构掘进位置的主要参数,不同地层中千斤顶压力的数据分布和值域具有显著差异,因而其对模型预测地层影响较大。4组千斤顶行程(SPC-A,SPC-B,SPC-C,SPC-D)及注浆量GV的特征重要性显著小于其他特征。这是因为盾构在掘进每一环管片时,千斤顶行程均是由600 mm增加至1 800 mm左右(一环管片宽为1 200 mm),在不同地层中该特征的变化趋势相似。同时,由于传感器故障,导致GV在不同地层的数值变化幅度较小。因此,从输入特征中删除SPC-A、SPC-B、SPC-C、SPC-D和GV。模型输入特征的统计信息如表2所示。
研究数据集中包含了4种不同地层,若模型能够将数据集分成代表不同地层的4个聚类,表明模型准确有效地识别了地层。通过输入数据的管片号确定该输入时间序列所处的真实地层,以此判断模型聚类结果的准确度。参考已有研究[30-31],选择使用广泛的调整兰德指数ARI(adjusted Rand index)、归一化互信息(normalized mutual information,简称NMI)和准确率ACC(accuracy)评价模型性能。
ACC是模型正确预测样本数与总样本数之比。
ARI用于评估两个聚类间的相似性,取值范围为[−1,1]。ARI的值越接近1,表明聚类性能越好。
式中:为随机聚类条件下兰德指数RI(rand index)的期望值;Max(RI)表示兰德指数的最大值。RI的计算公式为
式中:真阳性TP是指模型预测为阳性,实际情况也为阳性;真阴性TN是指模型预测为阴性,实际情况也为阴性;假阳性FP是指模型预测为阳性,但实际情况为阴性;假阴性FN是指模型预测为阴性,但实际情况为阳性。
NMI是基于信息论的聚类结果评价指标,用于衡量聚类结果与真实标签之间的信息共享程度,取值范围为[0,1]。NMI越接近1表示聚类性能越好。
式中:U为真实的聚类标签;V为模型生成的聚类标签;MI(U,V)是U和V之间的互信息(mutual information);H(U)是U的熵;H(V)是V的熵。
输入序列长度显著影响时序聚类模型性能。预试验表明,当模型输入序列长度为60~336时,模型性能较为优异。在聚类数为4的情况下,分别设置CDTW-Agglomerative模型的输入序列长度为60、84、112、120、140、168、224、240、280和336。
图5所示,输入序列长度为240时,模型性能最佳。输入序列长度过短可能导致一条时间序列中蕴含较少的时间信息。输入序列长度过长可能导致一条时间序列中数据的时间相关性较弱,这是因为盾构平均掘进一环管片约20.5 min,即掘进一环管片约记录246个数据点(采样频率为5 s/次)。若输入序列长度超过246,表明单条输入序列中可能包含了两环管片的掘进数据。由于拼装阶段的存在,连续两环管片数据在时间上不连续。因此,后续实验均在输入序列长度为240的情况下进行。
分别使用CDTW、DTW及SoftDTW作为Agglomerative的距离度量方法,结果如表3所示。CDTW-Agglomerative取得了最高的ACC、ARI和NMI。CDTW通过插值点提高了DTW规整序列的连续性,更好地捕捉时间序列间相似性。SoftDTW仍是基于离散点进行计算,无法解决离散化导致的轨迹失真问题。
表4所示,CDTW-Agglomerative在聚类数为4时,取得了最高的ACC、ARI和NMI,其性能显著高于其他聚类数,且性能优于对比模型。这表明该模型倾向于将数据集分为4个聚类,与真实地层数量一致。CDTW-Spectral模型在各个聚类数下的预测准确率变化较为平缓,其在聚类数由3增加到4时,ACC、ARI和NMI均发生下降,表明其更偏向于将数据集分为3个聚类。
图67分别给出了聚类数为4时DTW-Agglomerative和CDTW-Agglomerative的混淆矩阵。可以发现,两个模型识别砾质黏性土和中风化花岗岩地层的准确率都接近100%。但在预测粉质黏土、全风化花岗岩混合地层与粉质黏土地层时,两种模型的预测准确度均发生下降。如图6所示,DTW-Agglomerative将约50%的混合地层时间序列识别为粉质黏土地层,将超过70%的粉质黏土地层识别为混合地层。因为粉质黏土地层和粉质黏土、全风化花岗岩混合地层的盾构掘进数据分布和值域较为相似,导致DTW-Agglomerative难以有效区分两种地层的时间序列。
图7所示,CDTW-Agglomerative在识别粉质黏土、全风化花岗岩混合地层与粉质黏土地层时准确率高于DTW-Agglomerative。近75%的混合地层被正确识别。近30%被DTW-Agglomerative错误识别为混合地层的粉质黏土地层被该模型正确识别。3条中风化花岗岩地层的时间序列被CDTW-Agglomerative错误识别为了砾质黏性土地层,这些序列被DTW-Agglomerative正确识别,这可能是因为CDTW过度捕捉局部相关性导致的。DTW-Agglomerative错误地将2条混合地层和4条粉质黏土地层时间序列识别为中风化花岗岩地层,CDTW-Agglomerative纠正了这个错误。
图8为CDTW-Agglomerative在聚类数为4的特征推进速度AS(advance speed)时间序列聚类情况。其中,每个子图都代表模型的一个聚类,同一个聚类内的时间序列具有较高的相似度。线条颜色表示该时间序列真实的地层情况。可见,除了聚类4之外,其他集群均表现出良好的聚类效果。
综上所述,CDTW-Agglomerative在无需数据标签的情况下,仍能准确识别盾构刀盘处地层,但其在识别相似地层方面具有一定的局限性。其原因可能是①相似地层中土舱压力、螺旋机转速等参数的值域分布与变化趋势相似;②盾构驾驶员在相似地层中调控千斤顶压力、刀盘转速、总推力等参数的思路相似。另外,动态时间规整重点关注时间序列中的局部对齐,可能忽略时间序列的整体趋势。例如,刀盘扭矩在两种不同地层中分别呈现出整体上升趋势和整体平稳波动,CDTW通过局部对齐使得两者距离较小,但忽略了两者的全局特性。
模型鲁棒性测试过程将高斯噪声生成正态分布扰动添加至原始数据集中。高斯噪声标准差分别为0.05,0.10,0.15,0.20,0.25。标准差越高说明原始数据获得扰动越大。通过均匀随机缺失构造缺失数据,缺失率设置为10%、20%、30%、40%和50%。
图9给出了数据噪声鲁棒性测试结果。可以发现,CDTW-Agglomerative对数据噪声较为敏感,高斯噪声标准差由0.05增加至0.10时,模型性能大幅下降;随着标准差进一步增大,模型性能下降幅度变平缓。这是因为初始噪声增加会导致时间序列中的关键点(如峰值、谷值)发生显著变化,从而影响CDTW路径匹配。随着噪声标准差达到一定程度时,数据噪声已饱和,进一步增加噪声不会显著改变时间序列的整体形态。
图10绘制了数据缺失鲁棒性测试结果。可见,模型对数据缺失具有较强鲁棒性,当数据缺失率为50%时,预测准确度仍能达到73%。这是因为即使数据存在缺失,CDTW也能通过寻找两条时间序列之间的最佳对齐路径,跳过缺失数据点,而不显著影响模型整体性能。
采用厦门地铁6号线某区间盾构隧道掘进数据集对所提模型泛化性进行测试。由于两个项目盾构机为同一型号,故数据集记录参数和采样频率一致。泛化性测试数据集的地层情况主要为残积砂质黏性土、微风化花岗岩、散体状强风化花岗岩、中风化花岗岩。模型训练相关参数与厦门地铁3号线数据集保持一致。
CDTW-Agglomerative的ACC、ARI及NMI分别为0.725 2、0.468 9、0.552 9。图11给出了CDTW-Agglomerative泛化性测试混淆矩阵。可以看出,由于散体状花岗岩地层的松散颗粒特性与砂质黏性土较为接近,有23%的残积砂质黏性土时间序列被预测为散体状强风化花岗岩。同时,有35%的散体状强风化花岗岩时间序列被预测为残积砂质黏性土。中风化和微风化花岗岩是较为完整的岩体,其刀盘扭矩、土舱压力分布相似,模型较难区分两种地层间的差别。因此,所提模型在厦门地铁3号线及6号线数据集上均取得了较准确的预测精度,表明其泛化性良好,但在区分相似地层上仍有一定局限性。
盾构掘进监测数据是随施工时间逐步搜集的。但CDTW-Agglomerative是一种离线聚类算法,在整个数据到达之前无法完成预测,这可能导致实际应用中的分析滞后和决策延迟。为此,基于厦门地铁3号线数据集,通过构建CDTW-Agglomerative在线学习框架,使模型能一边接收数据一边更新参数,从而实现盾构掘进地层实时识别。
首先,提取离线训练后CDTW-Agglomerative的聚类中心。然后,按照每次6条时间序列输入模型,共进行27次在线学习训练;基于CDTW计算新时间序列与现有簇的距离,判断归属,再动态更新聚类中心。图12为CDTW-Agglomerative在线学习结果。由图可知,虽然评价指标出现一定程度波动,但随着在线学习次数增加,ACC、ARI及NMI呈上升趋势。这是因为每次输入的时序数据可能随机分布在不同聚类中,也可能分布在同一聚类附近;当新数据分布偏离现有聚类中心时,模型需要显著调整聚类中心,短期内部分错误的分配也可能导致模型性能波动。此外,所提模型应用于相似地层的局限性会导致模型性能波动。但模型性能总体呈上升趋势,表明随着在线更新,模型聚类中心逐步靠近最优聚类中心,可实现盾构掘进过程中的实时动态识别。
所提模型在无需数据标签的条件下,较为准确地识别了盾构掘进地层信息,在非复合地层或地层情况变化较大的盾构隧道工程中适应性较强,但其识别相似地层精确度仍有待改善。尽管通过线性插值模型改进了DTW区分相似地层的能力,但所使用线性插值模型对于复杂非线性时间序列适用性较差,比如在盾构掘进过程中地质条件突变导致的数据震荡。
后续研究可引入3次样条插值和高斯过程插值等方法,改善模型对复杂非线性时间序列的适用性。进一步可构建动态插值模型选择方法,根据数据特性选择适合的插值模型,平稳段使用线性插值、非平稳段使用高阶插值,降低模型计算成本。此外,通过神经网络、注意力机制等深度学习方法对时序数据进行特征提取,探究其潜在的特征表示;结合聚类算法对地层进行无监督预测,增强模型对时间序列的全局探索能力。
本文提出了基于CDTW-Agglomerative模型的盾构掘进地层智能识别方法,所提模型无需真实地层信息作为数据标签,适用于地层信息难以获取的盾构掘进工程,主要结论如下:
(1)提出的连续动态时间规整(CDTW)方法有效捕捉了数据的时间相关性,显著提高了模型预测准确度,其性能优于基于动态时间规整(DTW)和软动态时间规整(SoftDTW)的凝聚型层次聚类模型,且优于CDTW-K-means、CDTW-K-medoids等对比模型。同时,该模型在两个不同地质条件的盾构掘进数据集中均表现出优异的预测精度,表明该模型泛化性良好。
(2)所提模型识别差异较大地层的准确率较高,但对于识别相似地层或混合地层的准确度有待改善。所提模型识别中风化花岗岩地层和砾质黏性土地层时的准确率接近100%,但较难区分粉质黏土地层和粉质黏土、全风化花岗岩混合地层之间的区别。
(3)所提模型对数据缺失具有强鲁棒性,缺失率为50%时,预测准确率仍能达到73%;所提模型对数据噪声的鲁棒性较弱,对地层突变导致的盾构掘进参数变化较为敏感。
后续研究可利用深度学习模型的特征提取能力,结合时序聚类模型,更有效地表征数据的时间和空间相关性,增加模型在相似地层上的识别准确率,进一步改善模型在复杂地质条件下的工程适用性。
  • 国家自然科学基金(52378392; 52408356)
  • 福建省“雏鹰计划”青年拔尖人才项目(00387088)
参考文献 引证文献
排序方式:
[1]
朱梦琦, 朱合华, 王昕, . 基于集成CART算法的TBM掘进参数与围岩等级预测[J]. 岩石力学与工程学报, 2020, 39(9): 1860-71.
ZHU Meng-qi, ZHU He-hua, WANG Xin, et al. Study on CART-based ensemble learning algorithms for predicting TBM tunneling parameters and classing surrounding rockmasses[J]. Chinese Journal of Rock Mechanics and Engineering, 2020, 39(9): 1860-71.
[2]
真嘉捷, 赖丰文, 黄明, . 基于LightGBM-Informer的盾构隧道管片上浮长时间序列预测模型[J]. 岩土力学, 2024, 45(12): 3791-3801.
ZHEN Jia-jie, LAI Feng-wen, HUANG Ming, et al. Long sequence time series model to predict uplift of segmental lining in shield tunnel based on LightGBM-Informer[J]. Rock and Soil Mechanics, 2024, 45(12): 3791-3801.
[3]
HUANG M, LU Y, ZHEN J J, et al. Analysis of face stability at the launch stage of shield or TBM tunnelling using a concrete box in complex urban environments[J]. Tunnelling and Underground Space Technology, 2023, 135: 105067.
[4]
潘秋景, 吴洪涛, 张子龙, . 基于多域物理信息神经网络的复合地层隧道掘进地表沉降预测[J]. 岩土力学, 2024, 45(2): 539-551.
PAN Qiu-jing, WU Hong-tao, ZHANG Zi-long, et al. Prediction of tunneling-induced ground surface settlement within composite strata using multi-physics-informed neural network[J]. Rock and Soil Mechanics, 2024, 45(2): 539-551.
[5]
张东明, 周烨璐, 黄宏伟, . 物理信息双驱动的长距离盾构隧道结构纵向力学性态智能诊断方法[J]. 岩土力学, 2023, 44(10): 2997-3010.
ZHANG Dong-ming, ZHOU Ye-lu, HUANG Hong-wei, et al. A physics and information dual-driven intelligent diagnosis method for longitudinal mechanical behavior of long-distance shield tunnels[J]. Rock and Soil Mechanics, 2023, 44(10): 2997-3010.
[6]
LAI F W, TSCHUCHNIGG F, SCHWEIGER F H, et al. A numerical study of deep excavations adjacent to existing tunnels: Integrating CPTU and SDMT to calibrate soil constitutive model[J]. Canadian Geotechnical Journal, 2025, 62: 1-23.
[7]
WANG S Y, LU T Y, ZHENG X C, et al. Dynamic collapse characteristics of the tunnel face induced by the shutdown of earth pressure balance shields (EPB): a 3D material point method study[J]. Underground Space, 2024, 16: 164-182.
[8]
TAN X Y, PALAIAHNAKOTE S, CHEN W Z, et al. A novel autoencoder for structural anomalies detection in river tunnel operation[J]. Expert Systems with Applications, 2024, 244: 122906.
[9]
王忠凯, 徐光黎. 盾构掘进、离开施工阶段对地表变形的影响范围及量化预测[J]. 岩土力学, 2020, 41(1): 285-294.
WANG Zhong-kai, XU Guang-li. Influence range and quantitative prediction of surface deformation during shield tunnelling and exiting stages[J]. Rock and Soil Mechanics, 2018, 18(6): 37-49.
[10]
李术才, 刘斌, 孙怀凤, . 隧道施工超前地质预报研究现状及发展趋势[J]. 岩石力学与工程学报, 2014, 33(6): 1090-1113.
LI Shu-cai, LIU Bin, SUN Huai-feng, et al. State of art and trends of adcanced geological prediction in tunnel construction[J]. Chinese Journal of Rock Mechanics and Engineering, 2014, 33(6): 1090-1113.
[11]
PAN Y, WU M Z, ZHANG L M, et al. Time series clustering-enabled geological condition perception in tunnel boring machine excavation[J]. Automation in Construction, 2023, 153: 104954.
[12]
KIM J I, FISCHER M, KAM C. Generation and evaluation of excavation schedules for hard rock tunnels in preconstruction and construction[J]. Automation in Construction, 2018, 96: 378-97.
[13]
娄国充, 孙志涛, 满令聪. 三维地震波定向超前地质预报技术试验研究[J]. 岩石力学与工程学报, 2020, 39(增刊1): 2733-40.
LOU Guo-chong, SUN Zhi-tao, MAN Ling-cong, Experimental research on 3D geological directional seismic prediction during tunnel construction[J]. Chinese Journal of Rock Mechanics and Engineering, 2020, 39(Suppl.1): 2733-40.
[14]
刘成禹, 余世为. 基于探地雷达单道信号处理的岩溶分析方法[J]. 岩土力学, 2016, 37(12): 3618-3626.
LIU Cheng-yu, YU Shi-wei. Analysis method of karst based on single channel signal processing by ground penetrating radar[J]. Rock and Soil Mechanics, 2016, 37(12): 3618-3626.
[15]
LIU Z B, LI L, FANG X L, et al. Hard-rock tunnel lithology prediction with TBM construction big data using a global-attention-mechanism-based LSTM network[J]. Automation in Construction, 2021, 125: 103647.
[16]
刘勇, 周怡晟, 索晓明, . 盾构下穿高铁路基变形规律模型试验研究[J]. 岩土力学, 2023, 44(4): 941-951.
LIU Yong, ZHOU Yi-sheng, SUO Xiao-ming, et al. Model test on the deformation law of shield tunnel underpassing high speed railway roadbed[J]. Rock and Soil Mechanics, 2023, 23(4): 248-57.
[17]
LAI F W, SHIAU J, KEAWSAWASVONG S, et al. Physics-based and data-driven modeling for stability evaluation of buried structures in natural clays[J]. Journal of Rock Mechanics and Geotechnical Engineering, 2023, 15(5): 1248-62.
[18]
LAI F W, LIU S Y, SHIAU J, et al. Data-driven modeling for evaluating deformation of a deep excavation near existing tunnels[J]. Underground Space, 2025, 24: 162-179.
[19]
TAN X Y, CHEN W Z, FAN C K, et al. Missing data imputation in tunnel monitoring with a spatio-temporal correlation fused machine learning model[J]. Journal of Civil Structural Health Monitoring, 2025, 15: 1337-1348.
[20]
LIU B, WANG R R, GUAN Z D, et al. Improved support vector regression models for predicting rock mass parameters using tunnel boring machine driving data[J]. Tunnnelling Undergrround Space Technology, 2019, 91: 102958.
[21]
ZHANG Q L, LIU Z Y, TAN J R. Prediction of geological conditions for a tunnel boring machine using big operational data[J]. Automation in Construction, 2019, 100: 73-83.
[22]
LIU Q S, WANG X Y, HUANG X, et al. Prediction model of rock mass class using classification and regression tree integrated AdaBoost algorithm based on TBM driving data[J]. Tunnelling and Underground Space Technology, 2020, 106: 103595.
[23]
WU Z J, WEI R L, CHU Z F, et al. Real-time rock mass condition prediction with TBM tunneling big data using a novel rock-machine mutual feedback perception method[J]. Journal of Rock Mechanics and Geotechnical Engineering, 2021, 13(6): 1311-25.
[24]
ZHOU C, KONG T, ZHOU Y, et al. Unsupervised spectral clustering for shield tunneling machine monitoring data with complex network theory[J]. Automation in Construction, 2019, 107: 102924.
[25]
SAI MADIRAJU N. Deep temporal clustering: fully unsupervised learning of time-domain features[D]. Phoenix: Arizona State University, 2018.
[26]
LUNDBERG S M, LEE S I. A unified approach to interpreting model predictions[J]. Advances in Neural Information Processing Systems, 2017, 30.
[27]
CHEN Z Y, ZHANG Y P, LI J B, et al. Diagnosing tunnel collapse sections based on TBM tunneling big data and deep learning: a case study on the Yinsong Project, China[J]. Tunnelling and Underground Space Technology, 2021, 108: 103700.
[28]
FANG Y R, LI X G, LIU H Z, et al. Intelligent real-time identification technology of stratum characteristics during slurry TBM tunneling[J]. Tunnelling and Underground Space Technology, 2023, 139.
[29]
XIAO H H, CHEN Z Y, CAO R L, et al. Prediction of shield machine posture using the GRU algorithm with adaptive boosting: a case study of Chengdu subway project[J]. Transportation Geotechnics, 2022, 37: 100837.
[30]
AGHABOZORGI S, SHIRKHORSHIDI A S, WAH T Y. Time-series clustering—a decade review[J]. Information Systems, 2015, 53: 16-38.
[31]
李海林, 张丽萍. 时间序列数据挖掘中的聚类研究综述[J]. 电子科技大学学报, 2022, 51(3): 416-424.
LI Hai-lin, ZHANG Li-ping. Summary of clustering research in time series data mining[J]. Journal of University of Electronic Science and Technology of China, 2022, 51(3): 416-424.
2025年第46卷第11期
PDF下载
76
35
引用本文
BibTeX
文章信息
doi: 10.16285/j.rsm.2024.1483
  • 接收时间:2024-12-01
  • 首发时间:2026-03-27
  • 出版时间:2025-11-14
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2024-12-01
  • 录用日期:2025-03-23
基金
National Natural Science Foundation of China(52378392; 52408356)
国家自然科学基金(52378392; 52408356)
“Foal Eagle Program” Youth Top-notch Talent Project of Fujian Province, China(00387088)
福建省“雏鹰计划”青年拔尖人才项目(00387088)
作者信息
    1.福州大学 土木工程学院,福建 福州 350108
    2.福建农林大学 交通与土木工程学院,福建 福州 350108
    3.福州市建设发展集团有限公司,福建 福州 350009
    4.中交一公局厦门工程有限公司,福建 厦门 361021

通讯作者:

赖丰文,男,1992年生,博士,副研究员,硕士生导师,主要从事土-结构相互作用、岩土原位测试方面的研究工作。E-mail:
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/ytlx/CN/10.16285/j.rsm.2024.1483
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