Article(id=1209816723398725848, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1209811339510411616, articleNumber=null, orderNo=null, doi=10.12404/j.issn.1671-1815.2405717, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=research-article, receivedDate=1722268800000, receivedDateStr=2024-07-30, revisedDate=1734883200000, revisedDateStr=2024-12-23, acceptedDate=null, acceptedDateStr=null, onlineDate=1766372384166, onlineDateStr=2025-12-22, pubDate=1751904000000, pubDateStr=2025-07-08, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1766372384166, onlineIssueDateStr=2025-12-22, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1766372384166, creator=13701087609, updateTime=1766372384166, updator=13701087609, issue=Issue{id=1209811339510411616, tenantId=1146029695717560320, journalId=1146123166801305609, year='2025', volume='25', issue='19', pageStart='7885', pageEnd='8315', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1766371100547, creator=13701087609, updateTime=1766373228996, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1209820266960654935, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1209811339510411616, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1209820266960654936, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1209811339510411616, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=8207, endPage=8217, ext={EN=ArticleExt(id=1209816723897848045, articleId=1209816723398725848, tenantId=1146029695717560320, journalId=1146123166801305609, language=EN, title=Prediction and Uncertainty of Soil Compaction Parameters Based on Explicit Machine Learning Model, columnId=1209816723763630312, journalTitle=Science Technology and Engineering, columnName=Papers∙Architectural Science, runingTitle=null, highlight=null, articleAbstract=

The accurate prediction of soil compaction parameters has practical significance for improving soil bearing capacity and reducing compressibility in geotechnical engineering. The existing models have certain limitations in prediction progress and engineering applicability, and ignore the quantification of model prediction uncertainty. Genetic programming (GP) was used to model and predict two important soil compaction parameters (optimal water content and maximum dry density) for 226 groups of soil compaction test data with extensive and representativeness. The optimal display models of optimal water content and maximum dry density were obtained respectively, and the prediction results were compared with the results of existing prediction models. The GP model was quantified by combining quantile regression method and uncertainty statistics. The results show that the compaction parameters are most affected by fine grain content and plastic limit, while the gravel content and liquid limit have the least influence on them. Therefore, in practical engineering, the optimal compaction effect can be achieved by preferentially adjusting the fine grain content and plastic limit, while the gravel content (CG) and the liquid limit have the least influence on them. Therefore, in practical engineering, the optimal compaction effect can be achieved by preferentially adjusting the fine grain content (CF) and the plastic limit in the soil. In addition, the quantile regression (QR) method provides 90 % confidence and the mean prediction interval (MPI) is less than 0.3.At the same time, most of the data fall within the range of uncertain bands, indicating that the GP algorithm has strong prediction ability and high prediction accuracy. This interpretable display model is more convenient for engineering applications.

, correspAuthors=Ye LIU, 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=Jian-wang LI, Wen-rui QI, Xin-yuan DING, Hang-yu ZHOU, Ye LIU, Su QIN, Liang-fu XIE), CN=ArticleExt(id=1209816727538504099, articleId=1209816723398725848, tenantId=1146029695717560320, journalId=1146123166801305609, language=CN, title=基于显示机器学习模型的土压实参数预测及不确定性, columnId=1209816724011094258, journalTitle=科学技术与工程, columnName=论文∙建筑科学, runingTitle=null, highlight=null, articleAbstract=土压实参数的准确预测对岩土工程中提高土体承载力、降低可压缩性具有实际意义,现有模型在预测进度和工程适用性上存在一定局限性,且忽略了对模型预测不确定性的量化。针对具有广泛性和代表性的226组土击实试验数据,采用遗传编码算法(genetic programming, GP)对两个重要土压实参数(最优含水量和最大干密度)进行了建模预测,分别得到了最优含水量和最大干密度的最优显示模型并将预测结果与现有预测模型所得结果进行了对比分析,结合分位数回归方法和不确定度统计量量化了GP模型。结果表明,压实参数受细粒含量和塑限的影响最大,而碎石量和液限对其影响最小,因此在实际工程中,可通过优先调整土体中的细粒土含量和塑限达到最优击实效果。此外分位数回归方法(quantile regression, QR)提供了90%置信度且平均预测区间值(mean prediction interval, MPI)均小于0.3,同时绝大多数数据均落在不确定带范围内,说明GP算法具有较强的预测能力和较高的预测精度,这种可解释的显示模型更便于工程应用。, correspAuthors=刘烨, authorNote=null, correspAuthorsNote=
*刘烨(2001—),女,汉族,山东高密人,硕士研究生。研究方向:岩土工程。E-mail:
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=Hg7Q6etLNMt6iWKPfKKzfw==, magXml=btkHPqczhB/mIj7ip+dUzQ==, pdfUrl=null, pdf=NdMP+kUFF65YE+JyNvYQeA==, pdfFileSize=9172649, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=uAKG5RBTBkvMPTo45l+Eow==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=jp8lWiz8z3yhhuAJ5ePQLA==, mapNumber=null, authorCompany=null, fund=null, authors=

李建旺(1973—),男,汉族,河北吴桥人,博士,高级工程师。研究方向:轨道交通、盾构施工管理。E-mail:

, authorsList=李建旺, 祁文睿, 丁新渊, 周航宇, 刘烨, 秦溯, 谢良甫)}, authors=[Author(id=1209929300552314933, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=1830408015@qq.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1209929300648783931, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, authorId=1209929300552314933, language=EN, stringName=Jian-wang LI, firstName=Jian-wang, middleName=null, lastName=LI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 Urban Rail Transit Engineering Company Limited of China Railway 15th Bureau, Guangzhou 510400, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1209929300736864319, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, authorId=1209929300552314933, language=CN, stringName=李建旺, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 中铁十五局集团城市轨道交通工程有限公司, 广州 510400, bio={"content":"

李建旺(1973—),男,汉族,河北吴桥人,博士,高级工程师。研究方向:轨道交通、盾构施工管理。E-mail:

"}, bioImg=null, bioContent=

李建旺(1973—),男,汉族,河北吴桥人,博士,高级工程师。研究方向:轨道交通、盾构施工管理。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1209929300288073766, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, xref=1, ext=[AuthorCompanyExt(id=1209929300296462375, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, companyId=1209929300288073766, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 Urban Rail Transit Engineering Company Limited of China Railway 15th Bureau, Guangzhou 510400, China), AuthorCompanyExt(id=1209929300300656680, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, companyId=1209929300288073766, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 中铁十五局集团城市轨道交通工程有限公司, 广州 510400)])]), Author(id=1209929300837527619, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1209929300925608006, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, authorId=1209929300837527619, language=EN, stringName=Wen-rui QI, firstName=Wen-rui, middleName=null, lastName=QI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 Urban Rail Transit Engineering Company Limited of China Railway 15th Bureau, Guangzhou 510400, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1209929301013688394, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, authorId=1209929300837527619, language=CN, stringName=祁文睿, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 中铁十五局集团城市轨道交通工程有限公司, 广州 510400, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1209929300288073766, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, xref=1, ext=[AuthorCompanyExt(id=1209929300296462375, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, companyId=1209929300288073766, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 Urban Rail Transit Engineering Company Limited of China Railway 15th Bureau, Guangzhou 510400, China), AuthorCompanyExt(id=1209929300300656680, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, companyId=1209929300288073766, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 中铁十五局集团城市轨道交通工程有限公司, 广州 510400)])]), Author(id=1209929301131128909, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, 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=1209929301227597907, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, authorId=1209929301131128909, language=EN, stringName=Xin-yuan DING, firstName=Xin-yuan, middleName=null, lastName=DING, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 Urban Rail Transit Engineering Company Limited of China Railway 15th Bureau, Guangzhou 510400, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1209929301328261206, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, authorId=1209929301131128909, language=CN, stringName=丁新渊, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 中铁十五局集团城市轨道交通工程有限公司, 广州 510400, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1209929300288073766, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, xref=1, ext=[AuthorCompanyExt(id=1209929300296462375, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, companyId=1209929300288073766, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 Urban Rail Transit Engineering Company Limited of China Railway 15th Bureau, Guangzhou 510400, China), AuthorCompanyExt(id=1209929300300656680, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, companyId=1209929300288073766, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 中铁十五局集团城市轨道交通工程有限公司, 广州 510400)])]), Author(id=1209929301391175770, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, 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=1209929301462478943, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, authorId=1209929301391175770, language=EN, stringName=Hang-yu ZHOU, firstName=Hang-yu, middleName=null, lastName=ZHOU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 Urban Rail Transit Engineering Company Limited of China Railway 15th Bureau, Guangzhou 510400, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1209929301521199204, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, authorId=1209929301391175770, language=CN, stringName=周航宇, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 中铁十五局集团城市轨道交通工程有限公司, 广州 510400, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1209929300288073766, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, xref=1, ext=[AuthorCompanyExt(id=1209929300296462375, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, companyId=1209929300288073766, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 Urban Rail Transit Engineering Company Limited of China Railway 15th Bureau, Guangzhou 510400, China), AuthorCompanyExt(id=1209929300300656680, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, companyId=1209929300288073766, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 中铁十五局集团城市轨道交通工程有限公司, 广州 510400)])]), Author(id=1209929301609279592, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, orderNo=4, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=Liuye132@outlook.com, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1209929301726720109, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, authorId=1209929301609279592, language=EN, stringName=Ye LIU, firstName=Ye, middleName=null, lastName=LIU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, *, address=2 College of Civil Engineering and Architecture, Xinjiang University, Urumqi 830017, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1209929301810606192, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, authorId=1209929301609279592, language=CN, stringName=刘烨, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, *, address=2 新疆大学建筑工程学院, 乌鲁木齐 830017, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1209929300413902896, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, xref=2, ext=[AuthorCompanyExt(id=1209929300422291503, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, companyId=1209929300413902896, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 College of Civil Engineering and Architecture, Xinjiang University, Urumqi 830017, China), AuthorCompanyExt(id=1209929300426485808, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, companyId=1209929300413902896, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 新疆大学建筑工程学院, 乌鲁木齐 830017)])]), Author(id=1209929301877715059, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, 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=1209929301940629623, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, authorId=1209929301877715059, language=EN, stringName=Su QIN, firstName=Su, middleName=null, lastName=QIN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2 College of Civil Engineering and Architecture, Xinjiang University, Urumqi 830017, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1209929302041292923, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, authorId=1209929301877715059, language=CN, stringName=秦溯, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2 新疆大学建筑工程学院, 乌鲁木齐 830017, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1209929300413902896, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, xref=2, ext=[AuthorCompanyExt(id=1209929300422291503, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, companyId=1209929300413902896, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 College of Civil Engineering and Architecture, Xinjiang University, Urumqi 830017, China), AuthorCompanyExt(id=1209929300426485808, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, companyId=1209929300413902896, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 新疆大学建筑工程学院, 乌鲁木齐 830017)])]), Author(id=1209929302112596095, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, orderNo=6, 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=1209929302213259397, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, authorId=1209929302112596095, language=EN, stringName=Liang-fu XIE, firstName=Liang-fu, middleName=null, lastName=XIE, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2 College of Civil Engineering and Architecture, Xinjiang University, Urumqi 830017, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1209929302297145479, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, authorId=1209929302112596095, language=CN, stringName=谢良甫, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2 新疆大学建筑工程学院, 乌鲁木齐 830017, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1209929300413902896, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, xref=2, ext=[AuthorCompanyExt(id=1209929300422291503, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, companyId=1209929300413902896, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 College of Civil Engineering and Architecture, Xinjiang University, Urumqi 830017, China), AuthorCompanyExt(id=1209929300426485808, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, companyId=1209929300413902896, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 新疆大学建筑工程学院, 乌鲁木齐 830017)])])], keywords=[Keyword(id=1209929302464917644, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, language=EN, orderNo=1, keyword=optimum moisture content), Keyword(id=1209929302548803727, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, language=EN, orderNo=2, keyword=maximum dry density), Keyword(id=1209929302620106899, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, language=EN, orderNo=3, keyword=genetic coding algorithm), Keyword(id=1209929302708187285, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, language=EN, orderNo=4, keyword=prediction), Keyword(id=1209929302834016410, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, language=EN, orderNo=5, keyword=uncertainty analysis), Keyword(id=1209929302917902490, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, language=CN, orderNo=1, keyword=最优含水量), Keyword(id=1209929303001788573, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, language=CN, orderNo=2, keyword=最大干密度), Keyword(id=1209929303102451873, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, language=CN, orderNo=3, keyword=遗传编码算法), Keyword(id=1209929303182143649, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, language=CN, orderNo=4, keyword=预测), Keyword(id=1209929304415269027, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, language=CN, orderNo=5, keyword=不确定性分析)], refs=[Reference(id=1209929309192581378, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=12, pageStart=81, pageEnd=83, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=李宇佳, journalName=西部交通科技, refType=null, unstructuredReference=李宇佳. 湿陷性黄土地基冲击压实处治分析[J]. 西部交通科技, 2023(12): 81-83., articleTitle=湿陷性黄土地基冲击压实处治分析, refAbstract=null), Reference(id=1209929309289050372, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=12, pageStart=81, pageEnd=83, url=null, language=null, rfNumber=[1], rfOrder=1, authorNames=Li Yujia, journalName=Western Communicational Science, refType=null, unstructuredReference=Li Yujia. Analysis of impact compaction treatment of collapsible loess foundation[J]. Western Communicational Science, 2023(12): 81-83., articleTitle=Analysis of impact compaction treatment of collapsible loess foundation, refAbstract=null), Reference(id=1209929309377130757, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=11, pageStart=38, pageEnd=40, url=null, language=null, rfNumber=[2], rfOrder=2, authorNames=王伟伟, journalName=交通世界, refType=null, unstructuredReference=王伟伟. 高填方路基沉降特性及填土参数影响分析[J]. 交通世界, 2023(11): 38-40., articleTitle=高填方路基沉降特性及填土参数影响分析, refAbstract=null), Reference(id=1209929309435851015, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=11, pageStart=38, pageEnd=40, url=null, language=null, rfNumber=[2], rfOrder=3, authorNames=Wang Weiwei, journalName=Transpo World, refType=null, unstructuredReference=Wang Weiwei. Analysis of settlement characteristics of high fill subgrade and influence of filling parameters[J]. Transpo World, 2023(11): 38-40., articleTitle=Analysis of settlement characteristics of high fill subgrade and influence of filling parameters, refAbstract=null), Reference(id=1209929309532320009, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, doi=null, pmid=null, pmcid=null, year=2024, volume=24, issue=23, pageStart=10072, pageEnd=10083, url=null, language=null, rfNumber=[3], rfOrder=4, authorNames=王术剑, 李小勇, 韩沛, journalName=科学技术与工程, refType=null, unstructuredReference=王术剑, 李小勇, 韩沛, 等. 路基振动压实响应特征分析与指标适用性[J]. 科学技术与工程, 2024, 24(23): 10072-10083., articleTitle=路基振动压实响应特征分析与指标适用性, refAbstract=null), Reference(id=1209929309616206091, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, doi=null, pmid=null, pmcid=null, year=2024, volume=24, issue=23, pageStart=10072, pageEnd=10083, url=null, language=null, rfNumber=[3], rfOrder=5, authorNames=Wang Shujian, Li Xiaoyong, Han Pei, journalName=Science Technology and Engineering, refType=null, unstructuredReference=Wang Shujian, Li Xiaoyong, Han Pei, et al. Analysis of subgrade vibration compaction response characteristics and applicability of indicators[J]. Science Technology and Engineering, 2024, 24(23) : 10072-10083., articleTitle=Analysis of subgrade vibration compaction response characteristics and applicability of indicators, refAbstract=null), Reference(id=1209929309674926349, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, doi=null, pmid=null, pmcid=null, year=2019, volume=41, issue=11, pageStart=2142, pageEnd=2148, url=null, language=null, rfNumber=[4], rfOrder=6, authorNames=于际都, 刘斯宏, 王涛, journalName=岩土工程学报, refType=null, unstructuredReference=于际都, 刘斯宏, 王涛, 等. 间断级配粗粒土压实特性试验研究[J]. 岩土工程学报, 2019, 41(11): 2142-2148., articleTitle=间断级配粗粒土压实特性试验研究, refAbstract=null), Reference(id=1209929309763006735, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, doi=null, pmid=null, pmcid=null, year=2019, volume=41, issue=11, pageStart=2142, pageEnd=2148, url=null, language=null, rfNumber=[4], rfOrder=7, authorNames=Yu Jidu, Liu Sihong, Wang Tao, journalName=Chinese Journal of Geotechnical Engineering, refType=null, unstructuredReference=Yu Jidu, Liu Sihong, Wang Tao, et al. Experimental study on compaction characteristics of discontinuous graded coarse-grained soil[J]. Chinese Journal of Geotechnical Engineering, 2019, 41(11): 2142-2148., articleTitle=Experimental study on compaction characteristics of discontinuous graded coarse-grained soil, refAbstract=null), Reference(id=1209929309838504209, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, doi=null, pmid=null, pmcid=null, year=2020, volume=42, issue=5, pageStart=512, pageEnd=518, url=null, language=null, rfNumber=[5], rfOrder=8, authorNames=黄崇伟, 郭丹丹, 王德荣, journalName=上海理工大学学报, refType=null, unstructuredReference=黄崇伟, 郭丹丹, 王德荣, 等. 粗粒土压实特性与高填体沉降规律研究[J]. 上海理工大学学报, 2020, 42(5): 512-518., articleTitle=粗粒土压实特性与高填体沉降规律研究, refAbstract=null), Reference(id=1209929309926584595, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, doi=null, pmid=null, pmcid=null, year=2020, volume=42, issue=5, pageStart=512, pageEnd=518, url=null, language=null, rfNumber=[5], rfOrder=9, authorNames=Huang Chongwei, Guo Dandan, Wang Derong, journalName=Journal of University of Shanghai for Science and Technology, refType=null, unstructuredReference=Huang Chongwei, Guo Dandan, Wang Derong, et al. Study on compaction characteristics of coarse-grained soil and settlement law of high fill[J]. Journal of University of Shanghai for Science and Technology, 2020, 42(5): 512-518., articleTitle=Study on compaction characteristics of coarse-grained soil and settlement law of high fill, refAbstract=null), Reference(id=1209929310035636501, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, doi=null, pmid=null, pmcid=null, year=2020, volume=37, issue=8, pageStart=161, pageEnd=165, url=null, language=null, rfNumber=[6], rfOrder=10, authorNames=耿宏斌, journalName=长江科学院院报, refType=null, unstructuredReference=耿宏斌. 细粒土压实特性与颗粒组成相关性分析[J]. 长江科学院院报, 2020, 37(8): 161-165., articleTitle=细粒土压实特性与颗粒组成相关性分析, refAbstract=null), Reference(id=1209929310127911190, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, doi=null, pmid=null, pmcid=null, year=2020, volume=37, issue=8, pageStart=161, pageEnd=165, url=null, language=null, rfNumber=[6], rfOrder=11, authorNames=Geng Hongbin, journalName=Journal of Changjiang River Scientific Research Institute, refType=null, unstructuredReference=Geng Hongbin. Correlation analysis between compaction characteristics and particle composition of fine-grained soil[J]. Journal of Changjiang River Scientific Research Institute, 2020, 37(8): 161-165., articleTitle=Correlation analysis between compaction characteristics and particle composition of fine-grained soil, refAbstract=null), Reference(id=1209929310228574487, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, doi=null, pmid=null, pmcid=null, year=2010, volume=23, issue=3, pageStart=15, pageEnd=21, url=null, language=null, rfNumber=[7], rfOrder=12, authorNames=陈渊召, 李振霞, 付新元, journalName=中国公路学报, refType=null, unstructuredReference=陈渊召, 李振霞, 付新元. 基于四参数方程的细粒土全压实特性研究[J]. 中国公路学报, 2010, 23(3): 15-21., articleTitle=基于四参数方程的细粒土全压实特性研究, refAbstract=null), Reference(id=1209929310295683352, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, doi=null, pmid=null, pmcid=null, year=2010, volume=23, issue=3, pageStart=15, pageEnd=21, url=null, language=null, rfNumber=[7], rfOrder=13, authorNames=Chen Yuanzhao, Li Zhenxia, Fu Xinyuan, journalName=China Journal of Highway and Transport, refType=null, unstructuredReference=Chen Yuanzhao, Li Zhenxia, Fu Xinyuan. Study on full compaction characteristics of fine-grained soil based on four-parameter equation[J]. China Journal of Highway and Transport, 2010, 23(3): 15-21., articleTitle=Study on full compaction characteristics of fine-grained soil based on four-parameter equation, refAbstract=null), Reference(id=1209929310375375130, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, doi=null, pmid=null, pmcid=null, year=2021, volume=21, issue=33, pageStart=14310, pageEnd=14317, url=null, language=null, rfNumber=[8], rfOrder=14, authorNames=赵乐, 倪万魁, 张镇飞, journalName=科学技术与工程, refType=null, unstructuredReference=赵乐, 倪万魁, 张镇飞, 等. 不同干密度压实黄土垂直积水入渗特性[J]. 科学技术与工程, 2021, 21(33): 14310-14317., articleTitle=不同干密度压实黄土垂直积水入渗特性, refAbstract=null), Reference(id=1209929310476038428, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, doi=null, pmid=null, pmcid=null, year=2021, volume=21, issue=33, pageStart=14310, pageEnd=14317, url=null, language=null, rfNumber=[8], rfOrder=15, authorNames=Zhao Le, Ni Wankui, Zhang Zhenfei, journalName=Science Technology and Engineering, refType=null, unstructuredReference=Zhao Le, Ni Wankui, Zhang Zhenfei, et al. Vertical water infiltration characteristics of compacted loess with different dry densities[J]. Science Technology and Engineering, 2021, 21(33) : 14310-14317., articleTitle=Vertical water infiltration characteristics of compacted loess with different dry densities, refAbstract=null), Reference(id=1209929310551535902, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, doi=null, pmid=null, pmcid=null, year=2015, volume=28, issue=4, pageStart=13, pageEnd=18, url=null, language=null, rfNumber=[9], rfOrder=16, authorNames=吴跃东, 罗如平, 王维春, journalName=中国公路学报, refType=null, unstructuredReference=吴跃东, 罗如平, 王维春. 南京地区砂砾卵石土压实特性的离散元模拟[J]. 中国公路学报, 2015, 28(4): 13-18, 26., articleTitle=南京地区砂砾卵石土压实特性的离散元模拟, refAbstract=null), Reference(id=1209929310656393504, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, doi=null, pmid=null, pmcid=null, year=2015, volume=28, issue=4, pageStart=13, pageEnd=18, url=null, language=null, rfNumber=[9], rfOrder=17, authorNames=Wu Yuedong, Luo Ruping, Wang Weichun, journalName=China Journal of Highway and Transport, refType=null, unstructuredReference=Wu Yuedong, Luo Ruping, Wang Weichun. Discrete element simulation of compaction characteristics of sandy pebble soil in Nanjing area[J]. China Journal of Highway and Transport, 2015, 28(4): 13-18, 26., articleTitle=Discrete element simulation of compaction characteristics of sandy pebble soil in Nanjing area, refAbstract=null), Reference(id=1209929310723502369, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, doi=null, pmid=null, pmcid=null, year=2021, volume=41, issue=S2, pageStart=336, pageEnd=345, url=null, language=null, rfNumber=[10], rfOrder=18, authorNames=白祥瑞, 戎晓力, 文祝, journalName=隧道建设, refType=null, unstructuredReference=白祥瑞, 戎晓力, 文祝, 等. 基于DE-SVR的土压平衡盾构隧道施工阶段地表沉降预测研究[J]. 隧道建设, 2021, 41(S2): 336-345., articleTitle=基于DE-SVR的土压平衡盾构隧道施工阶段地表沉降预测研究, refAbstract=null), Reference(id=1209929310824165667, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, doi=null, pmid=null, pmcid=null, year=2021, volume=41, issue=S2, pageStart=336, pageEnd=345, url=null, language=null, rfNumber=[10], rfOrder=19, authorNames=Bai Xiangrui, Rong Xiaoli, Wen Zhu, journalName=Tunnel Construction, refType=null, unstructuredReference=Bai Xiangrui, Rong Xiaoli, Wen Zhu, et al. Prediction of ground settlement during construction of EPB shield tunnel based on DE-SVR[J]. Tunnel Construction, 2021, 41(S2): 336-345., articleTitle=Prediction of ground settlement during construction of EPB shield tunnel based on DE-SVR, refAbstract=null), Reference(id=1209929310903857443, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, doi=null, pmid=null, pmcid=null, year=2019, volume=59, issue=2, pageStart=284, pageEnd=295, url=null, language=null, rfNumber=[11], rfOrder=20, authorNames=Chen R P, Zhang P, Kang X, journalName=Soils and Foundations, refType=null, unstructuredReference=Chen R P, Zhang P, Kang X, et al. Prediction of maximum surface settlement caused by earth pressure balance (EPB) shield tunneling with ANN methods[J]. Soils and Foundations, 2019, 59(2): 284-295., articleTitle=Prediction of maximum surface settlement caused by earth pressure balance (EPB) shield tunneling with ANN methods, refAbstract=null), Reference(id=1209929310979354917, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, doi=null, pmid=null, pmcid=null, year=2024, volume=24, issue=22, pageStart=9309, pageEnd=9315, url=null, language=null, rfNumber=[12], rfOrder=21, authorNames=何昌春, 赵鹏, 荣耀, journalName=科学技术与工程, refType=null, unstructuredReference=何昌春, 赵鹏, 荣耀, 等. 基于地表沉陷实测数据的覆岩内部移动变形预计方法[J]. 科学技术与工程, 2024, 24(22): 9309-9315., articleTitle=基于地表沉陷实测数据的覆岩内部移动变形预计方法, refAbstract=null), Reference(id=1209929311071629607, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, doi=null, pmid=null, pmcid=null, year=2024, volume=24, issue=22, pageStart=9309, pageEnd=9315, url=null, language=null, rfNumber=[12], rfOrder=22, authorNames=He Changchun, Zhao Peng, Rong Yao, journalName=Science Technology and Engineering, refType=null, unstructuredReference=He Changchun, Zhao Peng, Rong Yao, et al. Method for predicting the internal movement and deformation of overlying strata based on the measured data of surface subsidence[J]. Science Technology and Engineering, 2024, 24(22) : 9309-9315., articleTitle=Method for predicting the internal movement and deformation of overlying strata based on the measured data of surface subsidence, refAbstract=null), Reference(id=1209929311147127080, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, doi=null, pmid=null, pmcid=null, year=2020, volume=268, issue=null, pageStart=105506, pageEnd=null, url=null, language=null, rfNumber=[13], rfOrder=23, authorNames=Cheng Z L, Zhou W H, Garg A, journalName=Engineering Geology, refType=null, unstructuredReference=Cheng Z L, Zhou W H, Garg A. Genetic programming model for estimating soil suction in shallow soil layers in the vicinity of a tree[J]. Engineering Geology, 2020, 268: 105506., articleTitle=Genetic programming model for estimating soil suction in shallow soil layers in the vicinity of a tree, refAbstract=null), Reference(id=1209929311260373289, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, doi=null, pmid=null, pmcid=null, year=2014, volume=18, issue=null, pageStart=45, pageEnd=56, url=null, language=null, rfNumber=[14], rfOrder=24, authorNames=Garg A, Garg A, Tai K, journalName=Computational Geosciences, refType=null, unstructuredReference=Garg A, Garg A, Tai K. A multi-gene genetic programming model for estimating stress-dependent soil water retention curves[J]. Computational Geosciences, 2014, 18: 45-56., articleTitle=A multi-gene genetic programming model for estimating stress-dependent soil water retention curves, refAbstract=null), Reference(id=1209929311327482154, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, doi=null, pmid=null, pmcid=null, year=2009, volume=30, issue=3, pageStart=675, pageEnd=679, url=null, language=null, rfNumber=[15], rfOrder=25, authorNames=苏国韶, 宋咏春, 燕柳斌, journalName=岩土力学, refType=null, unstructuredReference=苏国韶, 宋咏春, 燕柳斌. 高斯过程机器学习在边坡稳定性评价中的应用[J]. 岩土力学, 2009, 30(3): 675-679, 687., articleTitle=高斯过程机器学习在边坡稳定性评价中的应用, refAbstract=null), Reference(id=1209929311382008107, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, doi=null, pmid=null, pmcid=null, year=2009, volume=30, issue=3, pageStart=675, pageEnd=679, url=null, language=null, rfNumber=[15], rfOrder=26, authorNames=Su Guoshao, Song Yongchun, Yan Liubin, journalName=Rock and Soil Mechanics, refType=null, unstructuredReference=Su Guoshao, Song Yongchun, Yan Liubin. Application of Gaussian process machine learning in slope stability evaluation[J]. Rock and Soil Mechanics, 2009, 30(3): 675-679, 687., articleTitle=Application of Gaussian process machine learning in slope stability evaluation, refAbstract=null), Reference(id=1209929311440728364, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, doi=null, pmid=null, pmcid=null, year=2024, volume=24, issue=19, pageStart=7988, pageEnd=7998, url=null, language=null, rfNumber=[16], rfOrder=27, authorNames=冯希尧, 苟俊程, 刘瑞, journalName=科学技术与工程, refType=null, unstructuredReference=冯希尧, 苟俊程, 刘瑞, 等. 基于遗传算法优化机器学习模型的地下水潜在性预测[J]. 科学技术与工程, 2024, 24(19): 7988-7998., articleTitle=基于遗传算法优化机器学习模型的地下水潜在性预测, refAbstract=null), Reference(id=1209929311512031533, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, doi=null, pmid=null, pmcid=null, year=2024, volume=24, issue=19, pageStart=7988, pageEnd=7998, url=null, language=null, rfNumber=[16], rfOrder=28, authorNames=Feng Xiyao, Gou Juncheng, Liu Rui, journalName=Science Technology and Engineering, refType=null, unstructuredReference=Feng Xiyao, Gou Juncheng, Liu Rui, et al. Prediction of groundwater potential based on machine learning model optimized by genetic algorithm[J]. Science Technology and Engineering, 2024, 24(19) : 7988-7998., articleTitle=Prediction of groundwater potential based on machine learning model optimized by genetic algorithm, refAbstract=null), Reference(id=1209929311566557486, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, doi=null, pmid=null, pmcid=null, year=2024, volume=57, issue=1, pageStart=10462, pageEnd=null, url=null, language=null, rfNumber=[17], rfOrder=29, authorNames=Makke N, Chawla S, journalName=Artificial Intelligence Review, refType=null, unstructuredReference=Makke N, Chawla S. Interpretable scientific discovery with symbolic regression: a review[J]. Artificial Intelligence Review, 2024, 57(1): 10462., articleTitle=Interpretable scientific discovery with symbolic regression: a review, refAbstract=null), Reference(id=1209929311642054959, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, doi=null, pmid=null, pmcid=null, year=2014, volume=null, issue=null, pageStart=183, pageEnd=187, url=null, language=null, rfNumber=[18], rfOrder=30, authorNames=Cramer N L, journalName=Proceedings of the First International Conference on Genetic Algorithms and Their Applications, refType=null, unstructuredReference=Cramer N L. A representation for the adaptive generation of simple sequential programs[C]// Proceedings of the First International Conference on Genetic Algorithms and Their Applications. Lundon: Psychology Press, 2014: 183-187., articleTitle=A representation for the adaptive generation of simple sequential programs, refAbstract=null), Reference(id=1209929311700775216, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, doi=null, pmid=null, pmcid=null, year=1994, volume=4, issue=null, pageStart=87, pageEnd=112, url=null, language=null, rfNumber=[19], rfOrder=31, authorNames=Koza J R, journalName=Statistics and Computing, refType=null, unstructuredReference=Koza J R. Genetic programming as a means for programming computers by natural selection[J]. Statistics and Computing, 1994, 4: 87-112., articleTitle=Genetic programming as a means for programming computers by natural selection, refAbstract=null), Reference(id=1209929311788855601, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, doi=null, pmid=null, pmcid=null, year=2022, volume=27, issue=3, pageStart=621, pageEnd=641, url=null, language=null, rfNumber=[20], rfOrder=32, authorNames=Mei Y, Chen Q, Lensen A, journalName=IEEE Transactions on Evolutionary Computation, refType=null, unstructuredReference=Mei Y, Chen Q, Lensen A, et al. Explainable artificial intelligence by genetic programming: a survey[J]. IEEE Transactions on Evolutionary Computation, 2022, 27(3): 621-641., articleTitle=Explainable artificial intelligence by genetic programming: a survey, refAbstract=null), Reference(id=1209929311868547378, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, doi=null, pmid=null, pmcid=null, year=2023, volume=18, issue=4, pageStart=1721, pageEnd=1738, url=null, language=null, rfNumber=[21], rfOrder=33, authorNames=Qin S, Xu T, Cheng Z L, journalName=Acta Geotechnica, refType=null, unstructuredReference=Qin S, Xu T, Cheng Z L, et al. Analysis of spatiotemporal variations of excess pore water pressure during mechanized tunneling using genetic programming[J]. Acta Geotechnica, 2023, 18(4): 1721-1738., articleTitle=Analysis of spatiotemporal variations of excess pore water pressure during mechanized tunneling using genetic programming, refAbstract=null), Reference(id=1209929311923073331, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, doi=null, pmid=null, pmcid=null, year=2020, volume=276, issue=null, pageStart=105758, pageEnd=null, url=null, language=null, rfNumber=[22], rfOrder=34, authorNames=Wang H L, Yin Z Y, journalName=Engineering Geology, refType=null, unstructuredReference=Wang H L, Yin Z Y. High performance prediction of soil compaction parameters using multi expression programming[J]. Engineering Geology, 2020, 276: 105758., articleTitle=High performance prediction of soil compaction parameters using multi expression programming, refAbstract=null), Reference(id=1209929311985987892, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, doi=null, pmid=null, pmcid=null, year=2018, volume=39, issue=8, pageStart=2362, pageEnd=2385, url=null, language=null, rfNumber=[23], rfOrder=35, authorNames=Kalnins A, journalName=Strategic Management Journal, refType=null, unstructuredReference=Kalnins A. Multicollinearity: how common factors cause type 1 errors in multivariate regression[J]. Strategic Management Journal, 2018, 39(8): 2362-2385., articleTitle=Multicollinearity: how common factors cause type 1 errors in multivariate regression, refAbstract=null), Reference(id=1209929312057291061, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, doi=null, pmid=null, pmcid=null, year=2004, volume=44, issue=5, pageStart=27, pageEnd=36, url=null, language=null, rfNumber=[24], rfOrder=36, authorNames=Gurtug Y, Sridharan A, journalName=Soils and Foundations, refType=null, unstructuredReference=Gurtug Y, Sridharan A. Compaction behaviour and prediction of its characteristics of fine grained soils with particular reference to compaction energy[J]. Soils and Foundations, 2004, 44(5): 27-36., articleTitle=Compaction behaviour and prediction of its characteristics of fine grained soils with particular reference to compaction energy, refAbstract=null), Reference(id=1209929312116011318, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, doi=null, pmid=null, pmcid=null, year=2009, volume=57, issue=null, pageStart=203, pageEnd=215, url=null, language=null, rfNumber=[25], rfOrder=37, authorNames=Günaydın O, journalName=Environmental Geology, refType=null, unstructuredReference=Günaydın O. Estimation of soil compaction parameters by using statistical analyses and artificial neural networks[J]. Environmental Geology, 2009, 57: 203-215., articleTitle=Estimation of soil compaction parameters by using statistical analyses and artificial neural networks, refAbstract=null), Reference(id=1209929312183120183, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, doi=null, pmid=null, pmcid=null, year=2015, volume=2, issue=null, pageStart=65, pageEnd=77, url=null, language=null, rfNumber=[26], rfOrder=38, authorNames=Nagaraj H B, Reesha B, Sravan M V, journalName=Transportation Geotechnics, refType=null, unstructuredReference=Nagaraj H B, Reesha B, Sravan M V, et al. Correlation of compaction characteristics of natural soils with modified plastic limit[J]. Transportation Geotechnics, 2015, 2: 65-77., articleTitle=Correlation of compaction characteristics of natural soils with modified plastic limit, refAbstract=null), Reference(id=1209929313412051256, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, doi=null, pmid=null, pmcid=null, year=2016, volume=41, issue=null, pageStart=1319, pageEnd=1328, url=null, language=null, rfNumber=[27], rfOrder=39, authorNames=Farooq K, Khalid U, Mujtaba H, journalName=Arabian Journal for Science and Engineering, refType=null, unstructuredReference=Farooq K, Khalid U, Mujtaba H. Prediction of compaction characteristics of fine-grained soils using consistency limits[J]. Arabian Journal for Science and Engineering, 2016, 41: 1319-1328., articleTitle=Prediction of compaction characteristics of fine-grained soils using consistency limits, refAbstract=null), Reference(id=1209929313495937337, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, doi=null, pmid=null, pmcid=null, year=2019, volume=23, issue=4, pageStart=449, pageEnd=462, url=null, language=null, rfNumber=[28], rfOrder=40, authorNames=Ardakani A, Kordnaeij A, journalName=European Journal of Environmental and Civil Engineering, refType=null, unstructuredReference=Ardakani A, Kordnaeij A. Soil compaction parameters prediction using GMDH-type neural network and genetic algorithm[J]. European Journal of Environmental and Civil Engineering, 2019, 23(4): 449-462., articleTitle=Soil compaction parameters prediction using GMDH-type neural network and genetic algorithm, refAbstract=null), Reference(id=1209929313563046202, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, doi=null, pmid=null, pmcid=null, year=2020, volume=13, issue=null, pageStart=1, pageEnd=13, url=null, language=null, rfNumber=[29], rfOrder=41, authorNames=Kurnaz T F, Kaya Y, journalName=Arabian Journal of Geosciences, refType=null, unstructuredReference=Kurnaz T F, Kaya Y. The performance comparison of the soft computing methods on the prediction of soil compaction parameters[J]. Arabian Journal of Geosciences, 2020, 13: 1-13., articleTitle=The performance comparison of the soft computing methods on the prediction of soil compaction parameters, refAbstract=null), Reference(id=1209929313638543675, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, doi=null, pmid=null, pmcid=null, year=1978, volume=73, issue=363, pageStart=618, pageEnd=622, url=null, language=null, rfNumber=[30], rfOrder=42, authorNames=Koenker R, Basset G, journalName=Journal of the American Statistical Association, refType=null, unstructuredReference=Koenker R, Basset G. Asymptotic theory of least absolute error regression[J]. Journal of the American Statistical Association, 1978, 73(363): 618-622., articleTitle=Asymptotic theory of least absolute error regression, refAbstract=null), Reference(id=1209929313701458236, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, doi=null, pmid=null, pmcid=null, year=2017, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[31], rfOrder=43, authorNames=Rodriguez R N, Yao Y, journalName=Cary: SAS Institute Inc, refType=null, unstructuredReference=Rodriguez R N, Yao Y. Five things you should know about quantile regression[J]. Cary: SAS Institute Inc, 2017., articleTitle=Five things you should know about quantile regression, refAbstract=null), Reference(id=1209929313764372797, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, doi=null, pmid=null, pmcid=null, year=2009, volume=45, issue=12, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[32], rfOrder=44, authorNames=Solomatine D P, Shrestha D L, journalName=Water Resources Research, refType=null, unstructuredReference=Solomatine D P, Shrestha D L. A novel method to estimate model uncertainty using machine learning techniques[J]. Water Resources Research, 2009, 45(12): W00B11., articleTitle=A novel method to estimate model uncertainty using machine learning techniques, refAbstract=null), Reference(id=1209929313818898750, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, doi=null, pmid=null, pmcid=null, year=2019, volume=688, issue=null, pageStart=855, pageEnd=866, url=null, language=null, rfNumber=[33], rfOrder=45, authorNames=Rahmati O, Choubin B, Fathabadi A, journalName=Science of the Total Environment, refType=null, unstructuredReference=Rahmati O, Choubin B, Fathabadi A, et al. Predicting uncertainty of machine learning models for modelling nitrate pollution of groundwater using quantile regression and UNEEC methods[J]. Science of the Total Environment, 2019, 688: 855-866., articleTitle=Predicting uncertainty of machine learning models for modelling nitrate pollution of groundwater using quantile regression and UNEEC methods, refAbstract=null), Reference(id=1209929313877619007, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, doi=null, pmid=null, pmcid=null, year=2024, volume=83, issue=4, pageStart=129, pageEnd=null, url=null, language=null, rfNumber=[34], rfOrder=46, authorNames=Khan M H A, Jafri T H, Ud-Din S, journalName=Environmental Earth Sciences, refType=null, unstructuredReference=Khan M H A, Jafri T H, Ud-Din S, et al. Prediction of soil compaction parameters through the development and experimental validation of Gaussian process regression models[J]. Environmental Earth Sciences, 2024, 83(4): 129., articleTitle=Prediction of soil compaction parameters through the development and experimental validation of Gaussian process regression models, refAbstract=null)], funds=[Fund(id=1209929307678437628, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, awardId=52068066, language=CN, fundingSource=国家自然科学基金地区科学基金(52068066), fundOrder=null, country=null), Fund(id=1209929308907368703, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, awardId=52368052, language=CN, fundingSource=国家自然科学基金地区科学基金(52368052), fundOrder=null, country=null), Fund(id=1209929309003837696, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, awardId=2022D01E32, language=CN, fundingSource=新疆维吾尔自治区自然科学基金杰出青年科学基金(2022D01E32), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1209929300288073766, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, xref=1, ext=[AuthorCompanyExt(id=1209929300296462375, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, companyId=1209929300288073766, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 Urban Rail Transit Engineering Company Limited of China Railway 15th Bureau, Guangzhou 510400, China), AuthorCompanyExt(id=1209929300300656680, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, companyId=1209929300288073766, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 中铁十五局集团城市轨道交通工程有限公司, 广州 510400)]), AuthorCompany(id=1209929300413902896, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, xref=2, ext=[AuthorCompanyExt(id=1209929300422291503, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, companyId=1209929300413902896, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 College of Civil Engineering and Architecture, Xinjiang University, Urumqi 830017, China), AuthorCompanyExt(id=1209929300426485808, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, companyId=1209929300413902896, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 新疆大学建筑工程学院, 乌鲁木齐 830017)])], figs=[ArticleFig(id=1209929304650150054, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, language=EN, label=Fig.1, caption=GP formula: x1+4x2-5, figureFileSmall=0SNZja/jUM9pGMmGJ5y7qA==, figureFileBig=2uZ4JCOv7IjQLQXnxLs1eA==, tableContent=null), ArticleFig(id=1209929304755007658, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, language=CN, label=图1, caption=GP公式:x1+4x2-5, figureFileSmall=0SNZja/jUM9pGMmGJ5y7qA==, figureFileBig=2uZ4JCOv7IjQLQXnxLs1eA==, tableContent=null), ArticleFig(id=1209929304859865261, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, language=EN, label=Fig.2, caption=Genetic operator representation, figureFileSmall=hs9KWSu+V7o1LNtt1NXEkA==, figureFileBig=1SIavr+3CZLnGG4+EQuxAw==, tableContent=null), ArticleFig(id=1209929304939557041, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, language=CN, label=图2, caption=遗传算子表示, figureFileSmall=hs9KWSu+V7o1LNtt1NXEkA==, figureFileBig=1SIavr+3CZLnGG4+EQuxAw==, tableContent=null), ArticleFig(id=1209929305019248821, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, language=EN, label=Fig.3, caption=Genetic coding algorithm flow chart, figureFileSmall=0WfZRXCxWZo1X1ByTukftA==, figureFileBig=kfpbckvK/JNHQH/ZYxI/Vw==, tableContent=null), ArticleFig(id=1209929305103134903, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, language=CN, label=图3, caption=遗传编码算法流程图, figureFileSmall=0WfZRXCxWZo1X1ByTukftA==, figureFileBig=kfpbckvK/JNHQH/ZYxI/Vw==, tableContent=null), ArticleFig(id=1209929305182826682, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, language=EN, label=Fig.4, caption=The characteristic heat map of Pearson correlation analysis, figureFileSmall=CTmG89hEwyLdw9SE0EjOZQ==, figureFileBig=lkqoUJJRCkPOl6ckv2x6aw==, tableContent=null), ArticleFig(id=1209929305308655805, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, language=CN, label=图4, caption=Pearson相关分析的特征热图, figureFileSmall=CTmG89hEwyLdw9SE0EjOZQ==, figureFileBig=lkqoUJJRCkPOl6ckv2x6aw==, tableContent=null), ArticleFig(id=1209929305421902018, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, language=EN, label=Fig.5, caption=The R2, MAPE and RMSE values of the optimal water content, figureFileSmall=FUkAk7fqqG3fFLWHRLV9pw==, figureFileBig=iUwzAtso1KYHLKqeras0WA==, tableContent=null), ArticleFig(id=1209929305505788102, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, language=CN, label=图5, caption=最优含水量的决定系数、平均百分比绝对误差、均方根误差值, figureFileSmall=FUkAk7fqqG3fFLWHRLV9pw==, figureFileBig=iUwzAtso1KYHLKqeras0WA==, tableContent=null), ArticleFig(id=1209929305585479882, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, language=EN, label=Fig.6, caption=The R2, MAPE and RMSE values of the maximum dry density, figureFileSmall=8UN5LrM82dLpnr9y+Ag/pA==, figureFileBig=DRxxtogI9zxj17w0VjWRpg==, tableContent=null), ArticleFig(id=1209929305652588750, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, language=CN, label=图6, caption=最大干密度的决定系数、平均百分比绝对误差、均方根误差值, figureFileSmall=8UN5LrM82dLpnr9y+Ag/pA==, figureFileBig=DRxxtogI9zxj17w0VjWRpg==, tableContent=null), ArticleFig(id=1209929305723891920, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, language=EN, label=Fig.7, caption=Comparison of accuracy of optimal water content of soil obtained by different prediction models, figureFileSmall=zqU/F2g1kHZlMIOacFz0tA==, figureFileBig=mJ+Kauab+6gSbt5Mx9aISA==, tableContent=null), ArticleFig(id=1209929305807778002, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, language=CN, label=图7, caption=不同预测模型所得土最优含水量准确性比较, figureFileSmall=zqU/F2g1kHZlMIOacFz0tA==, figureFileBig=mJ+Kauab+6gSbt5Mx9aISA==, tableContent=null), ArticleFig(id=1209929305883275477, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, language=EN, label=Fig.8, caption=Comparison of accuracy of maximum dry density of soil obtained by different prediction models, figureFileSmall=4NtdQQaboOu8MpBaF5Ed2w==, figureFileBig=Px9Zm0i3DGttRKWqIqjTeg==, tableContent=null), ArticleFig(id=1209929305962967255, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, language=CN, label=图8, caption=不同预测模型所得土最大干密度准确性比较, figureFileSmall=4NtdQQaboOu8MpBaF5Ed2w==, figureFileBig=Px9Zm0i3DGttRKWqIqjTeg==, tableContent=null), ArticleFig(id=1209929306038464728, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, language=EN, label=Fig.9, caption=Linear QR model, figureFileSmall=f3W3J5U6XqT/jzC1lchGhQ==, figureFileBig=eg01oi7B5K7gTImm6lU/NA==, tableContent=null), ArticleFig(id=1209929306101379291, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, language=CN, label=图9, caption=线性QR模型, figureFileSmall=f3W3J5U6XqT/jzC1lchGhQ==, figureFileBig=eg01oi7B5K7gTImm6lU/NA==, tableContent=null), ArticleFig(id=1209929306181071069, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, language=EN, label=Fig.10, caption=The QR method is used to predict the uncertain zone of soil compaction parameters, figureFileSmall=G/zluUQoYqqvxRG6fPOYqg==, figureFileBig=FAGCanMJqm5eQrq4G0HoWw==, tableContent=null), ArticleFig(id=1209929306260762847, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, language=CN, label=图10, caption=使用QR法预测土压实参数的不确定带, figureFileSmall=G/zluUQoYqqvxRG6fPOYqg==, figureFileBig=FAGCanMJqm5eQrq4G0HoWw==, tableContent=null), ArticleFig(id=1209929306357231841, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, language=EN, label=Fig.11, caption=Sensitivity analysis, figureFileSmall=taryX7MXVv780GJK/D9B/A==, figureFileBig=16iSMtIvz4/KvP/9VUnFjQ==, tableContent=null), ArticleFig(id=1209929306415952099, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, language=CN, label=图11, caption=敏感性分析, figureFileSmall=taryX7MXVv780GJK/D9B/A==, figureFileBig=16iSMtIvz4/KvP/9VUnFjQ==, tableContent=null), ArticleFig(id=1209929306491449573, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, language=EN, label=Table 1, caption=

Basic statistical information about variables in a dataset

, figureFileSmall=null, figureFileBig=null, tableContent=
变量 最小值 最大值 平均值 标准差
C G/% 0 67.1 7.5 14.5
C S/% 0 89.0 29.5 23.3
C F/% 8.6 100.0 63.1 29.9
ω L/% 16.0 608.0 108.7 163.9
ω P/% 6.1 48.3 22.0 7.4
E/(kJ·m-3) 154.5 2 755.0 893.8 733.9
ω o p t/% 5.3 43.7 17.5 6.0
ρ d m a x/(mg·m-3) 1.09 2.33 1.75 0.20
), ArticleFig(id=1209929306579529959, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, language=CN, label=表1, caption=

数据集中变量的基本统计信息

, figureFileSmall=null, figureFileBig=null, tableContent=
变量 最小值 最大值 平均值 标准差
C G/% 0 67.1 7.5 14.5
C S/% 0 89.0 29.5 23.3
C F/% 8.6 100.0 63.1 29.9
ω L/% 16.0 608.0 108.7 163.9
ω P/% 6.1 48.3 22.0 7.4
E/(kJ·m-3) 154.5 2 755.0 893.8 733.9
ω o p t/% 5.3 43.7 17.5 6.0
ρ d m a x/(mg·m-3) 1.09 2.33 1.75 0.20
), ArticleFig(id=1209929306646638825, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, language=EN, label=Table 2, caption=

Multicol linearity assessment results

, figureFileSmall=null, figureFileBig=null, tableContent=
输入变量 多重共线性评估
R T VIF
x1 & x2 0.21 0.96 1.05
x1 & x3 0.65 0.58 1.72
x1 & x4 0.22 0.95 1.05
x1 & x5 0.28 0.92 1.09
x1 & x6 0.09 0.99 1.00
x2 & x3 0.88 0.23 4.44
x2 & x4 0.05 0.99 1.00
x2 & x5 0.11 0.99 1.01
x2 & x6 0.11 0.99 1.01
x3 & x4 0.07 0.99 1.00
x3 & x5 0.23 0.95 1.05
x3 & x6 0.13 0.98 1.02
x4 & x5 0.62 0.61 1.62
x4 & x6 0.36 0.87 1.15
x5 & x6 0.09 0.99 1.01
), ArticleFig(id=1209929306764079343, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, language=CN, label=表2, caption=

多重共线性评估结果

, figureFileSmall=null, figureFileBig=null, tableContent=
输入变量 多重共线性评估
R T VIF
x1 & x2 0.21 0.96 1.05
x1 & x3 0.65 0.58 1.72
x1 & x4 0.22 0.95 1.05
x1 & x5 0.28 0.92 1.09
x1 & x6 0.09 0.99 1.00
x2 & x3 0.88 0.23 4.44
x2 & x4 0.05 0.99 1.00
x2 & x5 0.11 0.99 1.01
x2 & x6 0.11 0.99 1.01
x3 & x4 0.07 0.99 1.00
x3 & x5 0.23 0.95 1.05
x3 & x6 0.13 0.98 1.02
x4 & x5 0.62 0.61 1.62
x4 & x6 0.36 0.87 1.15
x5 & x6 0.09 0.99 1.01
), ArticleFig(id=1209929306889908461, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, language=EN, label=Table 3, caption=

The optimal parameter combination setting of GP model

, figureFileSmall=null, figureFileBig=null, tableContent=
参数类别 最优含水量设置值 最大干密度设置值
种群大小 1 000 1 500
运行代数 100 100
最大基因数 6 6
函数集 +、-、×、/ +、-、×、/
复制概率 0.05 0.05
交叉概率 0.85 0.85
变异概率 0.1 0.1
), ArticleFig(id=1209929306973794544, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, language=CN, label=表3, caption=

GP模型最优参数组合设置

, figureFileSmall=null, figureFileBig=null, tableContent=
参数类别 最优含水量设置值 最大干密度设置值
种群大小 1 000 1 500
运行代数 100 100
最大基因数 6 6
函数集 +、-、×、/ +、-、×、/
复制概率 0.05 0.05
交叉概率 0.85 0.85
变异概率 0.1 0.1
), ArticleFig(id=1209929307053486321, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, language=EN, label=Table 4, caption=

The optimal water content prediction model in the literature

, figureFileSmall=null, figureFileBig=null, tableContent=
编号 参考文献 预测模型
(1) [24] ω o p t = ( - 0.344 l g E + 1.880 ) ω P
(2) [26] ω o p t = 0.76 ω P
(3) [27] ω o p t = 0.133 ω L + 0.02 ω P -       5.99 l g E + 28.60
), ArticleFig(id=1209929307133178098, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, language=CN, label=表4, caption=

文献中最优含水量预测模型

, figureFileSmall=null, figureFileBig=null, tableContent=
编号 参考文献 预测模型
(1) [24] ω o p t = ( - 0.344 l g E + 1.880 ) ω P
(2) [26] ω o p t = 0.76 ω P
(3) [27] ω o p t = 0.133 ω L + 0.02 ω P -       5.99 l g E + 28.60
), ArticleFig(id=1209929307204481267, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, language=EN, label=Table 5, caption=

Maximum dry density prediction model in literature

, figureFileSmall=null, figureFileBig=null, tableContent=
编号 参考文献 预测模型
(1) [25] γ d m a x = - 0.100   8 ω L + 21.16
(2) [26] γ d m a x = 20.82 - 0.17 ω P
(3) [27] γ d m a x = - 0.055 ω L + 0.014 ω P +       2.21 l o g E + 12.84
), ArticleFig(id=1209929307305144565, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, language=CN, label=表5, caption=

文献中最大干密度预测模型

, figureFileSmall=null, figureFileBig=null, tableContent=
编号 参考文献 预测模型
(1) [25] γ d m a x = - 0.100   8 ω L + 21.16
(2) [26] γ d m a x = 20.82 - 0.17 ω P
(3) [27] γ d m a x = - 0.055 ω L + 0.014 ω P +       2.21 l o g E + 12.84
), ArticleFig(id=1209929307405807863, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, language=EN, label=Table 6, caption=

Using the uncertainty MPI value of the QR method

, figureFileSmall=null, figureFileBig=null, tableContent=
土压实参数 MPI
训练 测试
最优含水量 0.268 0 0.265 3
最大干密度 0.009 4 0.009 5
), ArticleFig(id=1209929307502276857, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1209816723398725848, language=CN, label=表6, caption=

使用QR法的不确定度MPI值

, figureFileSmall=null, figureFileBig=null, tableContent=
土压实参数 MPI
训练 测试
最优含水量 0.268 0 0.265 3
最大干密度 0.009 4 0.009 5
)], attaches=null, journal=Journal(id=1146119176004939786, delFlag=0, nameCn=科学技术与工程, nameEn=Science Technology and Engineering, nameHistory1=null, nameHistory2=null, issn=1671-1815, eissn=, cn=11-4688/T, coden=null, periodic=4, language=CN, oaType=是, 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=UKU/O7GSka5polgCTkbIIw==, journalPrice=null, startedYear=null, abbrevIsoEn=Sci Technol Eng, journalRemark=null, publicationField=null, createdTime=null, updatedTime=1754445529766, createdBy=null, updatedBy=13701087609, firstLetterCn=S, firstLetterEn=S, subjectCode=Natural Sciences, subjectName=自然科学, subjectCodeEn=Natural Sciences, subjectNameEn=null, picCn=UKU/O7GSka5polgCTkbIIw==, picEn=5hwlULoNwcbj3xUmVi9MAQ==, jcr=null, cjcr=null, exts=[JournalExt(id=1159791870395564357, language=CN, name=科学技术与工程, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=null, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=http://www.stae.com.cn/jsygc/home, createdTime=1754445529793, updatedTime=1754445529793, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=http://www.stae.com.cn/jsygc/site/menus/20090429150146001, submissionAuthorUrl=http://www.stae.com.cn/jsygc/author/login, submissionEditorUrl=http://www.stae.com.cn/jsygc/editor/login, submissionReviewUrl=http://www.stae.com.cn/jsygc/reviewer/login, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1159791870441701702, language=EN, name=Science Technology and Engineering, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=null, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=http://www.stae.com.cn/jsygc/home, createdTime=1754445529804, updatedTime=1754445529804, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=http://www.stae.com.cn/jsygc/author/login, submissionEditorUrl=http://www.stae.com.cn/jsygc/editor/login, submissionReviewUrl=http://www.stae.com.cn/jsygc/reviewer/login, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1146123166801305609, websiteList=[Website(id=1148243202391400884, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146123166801305609, 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/kxjsygc/CN, language=CN, createTime=1751692112777, createBy=18614031015, updateTime=1753520965431, updateBy=18614031015, name=科学技术与工程-中文站点, tplId=1146099689490845704, title=科学技术与工程, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1148622798802673703, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=articleTextType, value=kx, createTime=1751782615614, updateTime=1751782615614, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622798781702180, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=banner, value=null, createTime=1751782615609, updateTime=1751782615609, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622798769119267, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=j86gbwi+p0Idkyl5SzIlmQ==, createTime=1751782615606, updateTime=1751782615606, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622798794285094, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1751782615612, updateTime=1751782615612, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622798790090789, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1751782615611, updateTime=1751782615611, creator=18614031015, updator=18614031015)]), Website(id=1155914124811976731, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146123166801305609, 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/kxjsygc/EN, language=EN, createTime=1753521003206, createBy=18614031015, updateTime=1753521003206, updateBy=18614031015, name=科学技术与工程-英文站点, tplId=1146101810881728533, title=Science Technology and Engineering, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1155914371227308235, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=articleTextType, value=kx, createTime=1753521061952, updateTime=1753521061952, creator=18614031015, updator=18614031015), WebsiteProps(id=1155914371210531016, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=banner, value=null, createTime=1753521061947, updateTime=1753521061947, creator=18614031015, updator=18614031015), WebsiteProps(id=1155914371202142407, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=j86gbwi+p0Idkyl5SzIlmQ==, createTime=1753521061945, updateTime=1753521061945, creator=18614031015, updator=18614031015), WebsiteProps(id=1155914371223113930, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1753521061950, updateTime=1753521061950, creator=18614031015, updator=18614031015), WebsiteProps(id=1155914371218919625, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1753521061949, updateTime=1753521061949, creator=18614031015, updator=18614031015)])], journalTitle=科学技术与工程, weixinUrl=null, journalUrl=null, iacademicId=null, status=0, seqNo=null, journalTitleEn=Science Technology and Engineering, journalPhotoCn=UKU/O7GSka5polgCTkbIIw==, journalPhotoEn=5hwlULoNwcbj3xUmVi9MAQ==, journalFirstLetter=S, 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=null, provinceCode=null, provinceName=null, collectFlag=false), detailUrlCn=https://castjournals.cast.org.cn/joweb/kxjsygc/CN/10.12404/j.issn.1671-1815.2405717, detailUrlEn=https://castjournals.cast.org.cn/joweb/kxjsygc/EN/10.12404/j.issn.1671-1815.2405717, pdfUrlCn=https://castjournals.cast.org.cn/joweb/kxjsygc/CN/PDF/10.12404/j.issn.1671-1815.2405717, pdfUrlEn=https://castjournals.cast.org.cn/joweb/kxjsygc/EN/PDF/10.12404/j.issn.1671-1815.2405717, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于显示机器学习模型的土压实参数预测及不确定性
收藏切换
PDF下载
李建旺 1 , 祁文睿 1 , 丁新渊 1 , 周航宇 1 , 刘烨 2, * , 秦溯 2 , 谢良甫 2
科学技术与工程 | 论文∙建筑科学 2025,25(19): 8207-8217
收起
收藏切换
科学技术与工程 | 论文∙建筑科学 2025, 25(19): 8207-8217
基于显示机器学习模型的土压实参数预测及不确定性
全屏
李建旺1 , 祁文睿1, 丁新渊1, 周航宇1, 刘烨2, * , 秦溯2, 谢良甫2
作者信息
  • 1 中铁十五局集团城市轨道交通工程有限公司, 广州 510400
  • 2 新疆大学建筑工程学院, 乌鲁木齐 830017
  • 李建旺(1973—),男,汉族,河北吴桥人,博士,高级工程师。研究方向:轨道交通、盾构施工管理。E-mail:

通讯作者:

*刘烨(2001—),女,汉族,山东高密人,硕士研究生。研究方向:岩土工程。E-mail:
Prediction and Uncertainty of Soil Compaction Parameters Based on Explicit Machine Learning Model
Jian-wang LI1 , Wen-rui QI1, Xin-yuan DING1, Hang-yu ZHOU1, Ye LIU2, * , Su QIN2, Liang-fu XIE2
Affiliations
  • 1 Urban Rail Transit Engineering Company Limited of China Railway 15th Bureau, Guangzhou 510400, China
  • 2 College of Civil Engineering and Architecture, Xinjiang University, Urumqi 830017, China
出版时间: 2025-07-08 doi: 10.12404/j.issn.1671-1815.2405717
文章导航
收藏切换
土压实参数的准确预测对岩土工程中提高土体承载力、降低可压缩性具有实际意义,现有模型在预测进度和工程适用性上存在一定局限性,且忽略了对模型预测不确定性的量化。针对具有广泛性和代表性的226组土击实试验数据,采用遗传编码算法(genetic programming, GP)对两个重要土压实参数(最优含水量和最大干密度)进行了建模预测,分别得到了最优含水量和最大干密度的最优显示模型并将预测结果与现有预测模型所得结果进行了对比分析,结合分位数回归方法和不确定度统计量量化了GP模型。结果表明,压实参数受细粒含量和塑限的影响最大,而碎石量和液限对其影响最小,因此在实际工程中,可通过优先调整土体中的细粒土含量和塑限达到最优击实效果。此外分位数回归方法(quantile regression, QR)提供了90%置信度且平均预测区间值(mean prediction interval, MPI)均小于0.3,同时绝大多数数据均落在不确定带范围内,说明GP算法具有较强的预测能力和较高的预测精度,这种可解释的显示模型更便于工程应用。
最优含水量  /  最大干密度  /  遗传编码算法  /  预测  /  不确定性分析

The accurate prediction of soil compaction parameters has practical significance for improving soil bearing capacity and reducing compressibility in geotechnical engineering. The existing models have certain limitations in prediction progress and engineering applicability, and ignore the quantification of model prediction uncertainty. Genetic programming (GP) was used to model and predict two important soil compaction parameters (optimal water content and maximum dry density) for 226 groups of soil compaction test data with extensive and representativeness. The optimal display models of optimal water content and maximum dry density were obtained respectively, and the prediction results were compared with the results of existing prediction models. The GP model was quantified by combining quantile regression method and uncertainty statistics. The results show that the compaction parameters are most affected by fine grain content and plastic limit, while the gravel content and liquid limit have the least influence on them. Therefore, in practical engineering, the optimal compaction effect can be achieved by preferentially adjusting the fine grain content and plastic limit, while the gravel content (CG) and the liquid limit have the least influence on them. Therefore, in practical engineering, the optimal compaction effect can be achieved by preferentially adjusting the fine grain content (CF) and the plastic limit in the soil. In addition, the quantile regression (QR) method provides 90 % confidence and the mean prediction interval (MPI) is less than 0.3.At the same time, most of the data fall within the range of uncertain bands, indicating that the GP algorithm has strong prediction ability and high prediction accuracy. This interpretable display model is more convenient for engineering applications.

optimum moisture content  /  maximum dry density  /  genetic coding algorithm  /  prediction  /  uncertainty analysis
李建旺, 祁文睿, 丁新渊, 周航宇, 刘烨, 秦溯, 谢良甫. 基于显示机器学习模型的土压实参数预测及不确定性. 科学技术与工程, 2025 , 25 (19) : 8207 -8217 . DOI: 10.12404/j.issn.1671-1815.2405717
Jian-wang LI, Wen-rui QI, Xin-yuan DING, Hang-yu ZHOU, Ye LIU, Su QIN, Liang-fu XIE. Prediction and Uncertainty of Soil Compaction Parameters Based on Explicit Machine Learning Model[J]. Science Technology and Engineering, 2025 , 25 (19) : 8207 -8217 . DOI: 10.12404/j.issn.1671-1815.2405717
土体压实实质就是将由水包裹的土粒挤压填充到土粒间的空隙中,从而排走空气所占有的空间,使土的孔隙率减小从而增加土的密度和强度,进而最大限度地减小沉降,想要提升和改善土体的技术取决于多种因素,但最终目的都是增加土的强度和密实度,其中压实作为一种常见的施工流程,被广泛应用在地基、路基和隧道的建设中[1-3],因为这些参数会直接影响土体的力学性质、渗透性以及工程的稳定性和安全性。因此,深入了解和预测不同土体压实参数(即最优含水量和最大干密度)对岩土工程实践至关重要。
过往相关研究者们为得到高质量的填土压实效果,通常会在室内开展系列土的击实试验,来确定土的最优含水量和最大干密度。于际都等[4]以级配不连续的粗粒土为研究对象并开展了系列击实试验,研究发现缺少d30以下的粒径不利于土的压实,但若中间粒径缺失则有益于压实,最后建立了间断级配粗粒土干密度的预测模型,这种颗粒分布的不均匀性会影响材料的工程性质,由其得到的研究结果。黄崇伟等[5]开展了粗颗粒土的颗粒分析与重型击实试验,分析了粗粒土的不均匀系数与最大干密度之间的关系,但上述研究未涉及细粒土的颗粒分析及压实特性研究。耿宏斌[6]在收集的123组击实试验数据的基础上,对细粒土的最大干密度、最优含水量与黏粒、粉粒和砂粒数据之间的相关性进行了分析,结果表明颗粒组成是影响细粒土压实特性的主要因素。陈渊召等[7]系统研究了细粒土的密实干密度各饱和度随含水量变化的全压实曲线,并由土的三相比例指标换算推导细粒土全压实曲线四参数方程。赵乐等[8]利用自主研发的一套一维土柱垂直入渗试验装置探究不同干密度变化影响下压实黄土垂直积水入渗特性,结果表明入渗率与压实黄土干密度存在负相关性,由此表明土体干密度变化是土体中水分运移的重要影响因素,所以深入研究土体压实参数对于提高土中水分利用以及确保工程长期稳定具有实际应用意义。然而大多数研究均通过试验得出相应结论,但在估计最大干密度和最优含水量的实验室程序需要足够多时间并付出巨大的努力,为了跳过广泛的实验室程序并且更高效地确定土体压实参数,近年也有学者利用有限元法(finite element method, FEM)和离散元法(discrete element method, DEM)开展相应研究。例如,吴跃东等[9]采用离散元模拟了砂砾卵石土的击实试验,并提出了土石比例区间以达到最佳的压实效果。上述研究虽为确定不同类型土的压实特性提供了基础,但基于试验数据的简单线性回归分析需要进行多次重复试验,而数值模拟的计算方法往往需要对土体颗粒之间的接触和作用力进行简化,从而导致其结果与实际情况存在一定偏差,因此,目前仍需要进一步研究和开发更高效准确的方法确定土的压实特性。
近年来,以数据为驱动的算法已被广泛应用于岩土工程领域,人工智能算法被认为是一个有效的方法,通过自动从大量数据中学习以确定预测模型的结构,如盾构隧道工后沉降预测[10-12],土体性质与变形预测[13-14],边坡稳定性分析[15]等,这些方法能快速、高效地找到参数之间的关系,并获得满意的结果。尽管像支持向量机(support vector machine, SVM)、人工神经网络(artificial neurtal network, ANN)、贝叶斯正则化神经网络(Bayesian regularized neural network, BRNN)等方法在建模复杂关系方面表现良好,但它们是黑箱模型,无法生成实际的预测函数方程,这限制了在实际工程中的实用性,是目前存在于机器学习中的一个缺点,为了克服这一问题,符号回归作为一种正在兴起的机器学习方法,通过遗传编程来处理,可以直接从大量数据中学习后得出一个简洁的可解释数学表达式[16-17]
因而,本文中使用一种进化算法,即遗传编码算法(genetic programming, GP)实现土体击实参数的预测,首先对226组土击实试验数据做最大值-最小值归一化处理,将数据库中奇数行和偶数行数据分别作为训练集和测试集,此外通过分位数回归方法和敏感性分析评估预测模型的准确性和有效性,再利用模型其明确的数学函数能够进一步对预测结果提供良好的可解释性。
遗传编码(GP)作为遗传算法(gennetic algorithm, GA)的扩展,最早是由Cramer[18]和Koza[19]提出并改进的一种进化算法并其本身具有可解释的程序核心,在人工智能和机器学习方面表现突出。GP概念源自于生物进化的理论,特别是达尔文的自然选择原理,能够在可解释空间中通过模拟生物进化的过程来解决复杂的优化和搜索问题。文献[20-21]的一些研究表明,GP能够在不依赖于问题的先验知识的情况下找到解决方案并且可以找到独特的方式来表达预测因子之间的复杂函数关系,而不受传统最小二乘法回归中预测方程具有固定函数形式的限制,所以其成为预测几个变量之间复杂的非线性关系的一种很有前途的方法,该算法能够容易地提取GP中进化的知识,因此,结果模型可以表示为封闭形式方程。
GP是以符号形式发现最能描述输入和输出之间关系的方程,每个树都编码一个数学方程,如图1所示,描绘了遗传规划的树状结构,由分支(功能节点)和叶(终端节点)组成,其中的数学等式被解释为(x1+4x2-5),当然像cos、sin、sqrt、square、exp和布尔逻辑函数如and、not、or等一些其他的数学函数也可以用于树形构建块,在程序中方程则使用相应的N×M输入x矩阵来预测出y的(N×1)向量,其中N是响应变量的观察数,M是输入(预测)变量的数量。
在遗传编程中,其主要目标是通过进化来生成和改进计算机程序,开始随机生成一组初始解即一组参数组合形成初始种群,是由二进制字符串表示的一组个体(解决方案),对每个个体使用均方根误差(root mean squared error, RMSE)、平均绝对误差(mean absolute error, MAE)和误差平方和等常用的适应度函数评估其适应度结果,再由适应度值进行选择操作,在这个过程中更倾向于选择适应度高的个体作为父代用以产生下一代个体,但也会保留一些适应度差的个体以保持种群的多样性,由选定的父代通过交叉和变异等操作引入新的种群以替代之前的旧种群,交叉操作模拟生物遗传中的基因重组,这有助于算法在更广泛的搜索空间中产生新的个体,变异操作即随机改变某些基因,这有助于防止陷入局部最优解,交叉与变异的结构过程表示如图2所示,完整程序即重复图3所示循环,直到达到终止条件,如达到最大迭代次数或找到最佳程序。
为了使最后得到的预测模型同时具有准确性和鲁棒性,所采用的数据集需具有广泛性和代表性。本次研究基于Wang等[22]收集并整理的共226组土击实试验数据,根据粒径分布,涵盖了黏土到碎石土。每组数据中包括了土中的碎石含量 C G、砂含量 C S、细粒含量 C F,土的液限 ω L、塑限 ω P,试验过程中的击实能E,土的最优含水量 ω o p t和最大干密度 ρ d m a x。其中,细粒土、砂和碎石分别由以下三个粒径组划分:<0.075 mm,0.075~4.75 mm,>4.75 mm,上述变量的基本统计信息见表1
数据预处理是开发机器学习模型的必要阶段,这有助于建立特征值与预测值之间的关系。由于本研究的输入变量分别为x1(CG)、x2(CS)、x3(CF)、x4 ( ω L )x5 ( ω P )x6 (E),为了评估数据之间的相互关联性,一个常用且有效的方法是计算Pearson系数,可以帮助理解两个变量间的线性关系强度和方向,其取值范围在[-1,1],相关系数为1意味着完全正相关,相关系数为-1则表示完全负相关。图4绘制了所有变量的Pearson相关性矩阵热图,深蓝色对应于强负相关,深橘色对应于强正相关,由图4可以看出CF ω P ω L ω o p t ρ d m a x分别呈正相关和负相关,其中CF ω P表现为强正相关和强负相关,而CGCSE ω o p t ρ d m a x分别呈负相关和正相关。
除此之外,在进行多元回归分析时,还需要特别注意输入变量的多重共线性,这可以通过方差膨胀系数(variance inflation factor, VIF)来评估,能够帮助确定每个变量是否受其他变量的高度相关影响,其公式为
V I F i = 1 T i
T i = 1 - R i 2
式中: T i为容忍度;Ri为相关系数。根据式(1)、式(2)分别计算每两个输入变量的VIF,如表2所示,由结果可以看出方差膨胀因子均小于5,所以输入参数之间不存在多重共线性问题。通常VIF的评估标准为,当0<VIF<5时,没有复共线性[23]
在建模之前,还需要对数据进行标准化处理以消除量纲的影响,若数据未进行标准化处理直接用于模型,则可能会导致模型对数值大的变量学习过多而对数值小的变量训练不够充分,往往导致模型效果不佳。因此本研究采用最大最小值归一化方法,顾名思义,就是利用数据列中的最大值和最小值进行标准化,将输入变量从原始范围按式(3)映射到[-1,0]或[0,1]的范围内,再将得到的缩放结果用于预测模型中。
x '   i = x i - m i n ( x ) m a x ( x ) - m i n ( x )
式(3)中:xi为第i个原始数据; x '   i为第i个归一化数据;min(x)与max(x)分别为原始数据的最小值和最大值。
数据集由8个参数组成,即CGCSCF ω L ω PE ρ d m a x ω o p t,其中CGCSCF ω L ω PE作为模型预测的输入参数, ρ d m a x ω o p t在模型预测中单独考虑作为输出参数。为建立预测土体压实参数的准确模型并评估其有效性,选择数据库中奇数行共133个样本为训练数据,偶数行共133个样本为测试数据用以检验模型,其中数据涵盖了各种土体类型和广泛的可塑性范围。为了找到最佳代码参数的模型,首先对种群数大小、要运行的最大代数、基因数量和函数集等根据先前研究者的建议值[23-29]中选择,并采用试错法确定其代码参数,最后结合决定系数 R 2、均方根误差RMSE、平均百分比绝对误差(mean absolute percentage error, MAPE)三个指标来评估预测模型性能,其计算公式为
$R^{2}=1-\frac{\sum_{i=1}^{n}\left(A_{i}-B_{i}\right)^{2}}{\sum_{i=1}^{n}\left(A_{i}-\overline{A_{i}}\right)^{2}}$
$\text { RMSE }=\sqrt{\frac{\sum_{i=1}^{n}\left(A_{i}-B_{i}\right)^{2}}{n}}$
$\text { MAPE }=\frac{1}{n} \sum_{i=1}^{n}\left|\frac{A_{i}-B_{i}}{A_{i}}\right|$
式中:Ai为第i个数据点的输出实测值;Bi为第i个数据点的输出预测值;n为数据点的个数; A ¯ i数据点的输出预测平均值。其中R2越接近于1则表明具有更高精度和良好的相关性,相反,RMSE和MAE越接近于0则对应于高精度。通过不断调试代码和参数变化对结果的影响,最终得到一个最优组合模型,代码参数设置如表3所示,这个优化过程自然会得到一个显式表达式用以描述特征值和预测值之间的函数关系,然而在实际应用中,除了模型的准确性之外,预测模型所提供的显示表达式的简洁性和可解释性也是至关重要的,因为这可以使得决策者和施工人员更好地理解数据的内在关系从而增强对预测结果的信任。
使用上述代码参数设置,基于所有运行结果中最大R2、最小RMSE和更简单的模型结构原则,最终得到用于预测土压实参数即最优含水量和最大干密度的最优表达式分别为
ω o p t = 4.399 x 3 x 5 [ x 3 2 x 4 - x 6 ) + 5.417 ] - 4.399 ( x 1 2 - x 6 ) + 13.060
ρ d m a x = 0.216 ( x 6 - x 4 - x 3 - x 3 x 6 ) - 0.433 x 5 - 0.216 x 4 ( x 3 - x 6 ) + 2.061
为验证基于最优代码参数的模型预测结果的准确性,绘制了由决定系数、平均百分比绝对误差MAPE与均方根误差RMSE量化使用GP模型对预测土压实参数的准确度和误差大小,如图5图6可以看出,不论是最优含水量还是最大干密度,所提出的最优模型预测结果均具有较高的预测精度,数据点均匀地分布在45°线的两侧。其中预测 ω o p t时,该模型训练数据和实测数据的决定系数(R2)、平均绝对百分比误差(MAPE)、均方根误差(RMSE)分别为0.871和0.882、0.282和0.300、1.385和1.656,预测 ρ d m a x时,该模型训练数据和实测数据的三个评估性能值分别为0.876和0.874、0.082和0.076、0.067和0.076,这表明预测的土压实参数与文献中实验测得的实际值之间很好的拟合且由MAPE和RMSE计算结果也说明预测结果在可接受的误差范围内。
为了进一步说明本方法所得模型的适用性及优越性,还比较了先前集中土壤压实参数的预测模型,同样以113组测试集数据基准,采用表4表5所列出文献中的经验计算公式得出的最优含水量和最大干密度,并与本方法所得结果相比较,在表4表5所列的预测模型中,主要考虑了土的液限、塑限以及击实能。将所得预测结果对应的决定系数R2、均方根误差RMSE及平均百分比绝对误差MAPE绘制成柱状图,如图7图8所示,从中可以明显看出,采用文献中的预测模型所得最优含水量和最大干密度的准确度较差R2 < 0.55,对应的RMSE和MAE较大。相比之下,采用GP模型预测得到的土压实参数与试验测得的真实值更为接近,精确度更高且误差小。这是因为所选择的模型中考虑了细粒土含量,该变量也是影响土压实参数的重要因素。通过模型结果和对比分析都可以表明本研究模型能够很好地预测土压实参数。
在岩土工程领域,不确定性始终是一个不可避免的挑战和现实,在利用不同机器学习方法时,由训练数据得到的预测模型,不免导致预测值与实际值之间有误差,那么为了更好地说明模型的可靠性,就需要对所开发模型进行不确定度评估。在本研究中,使用分位数回归方法(quantile regression, QR)量化模型预测土最优含水量和最大干密度的不确定性,是Koenker等[30]初次在经济学中引入,采用加权的最小绝对离差和进行估计的,不受离群点的影响,可以拟合响应特定的百分位,所以结果更为稳健,Rodriguez等[31]总结并对比了标准回归和分位数回归的区别。
标准回归模型为
s i = β 0 + β 1 u i 1 + β 2 u i 2 + + β l u i j ,   i = 1,2 , , n
式(9)中:si为第i个数据点的响应值; u i j为第i个数据点的第j个特征值;l为特征数量。si的分位数水平τ的回归模型为
Q τ ( s i ) = β 0 ( τ ) + β 1 ( τ ) u i 1 + β 2 ( τ ) u i 2 + + β l ( τ ) u i p ,   i = 1,2 , , n
并通过求解最小化问题估计 β j ( τ ),计算公式为
m i n [ β 0 ( τ ) , β 1 ( τ ) , , β l ( τ ) ] ×     i = 1 n ρ τ [ s i - β 0 ( τ ) - j = 1 p u i j β j ( τ ) ]
式(11)中 : ρ τ ( x )为检验损失函数,其形式为
ρ τ ( x ) = τ m a x ( x , 0 ) + ( 1 - τ ) m a x ( - x , 0 )
式(12)中:x为每个数据点的误差;max函数即为返回0和x中的最大值。
对于此方法中每个分位数τ,实测值y与由GP模型获得的预测值 y 之间存在线性关系,即
y = β 1 ( τ ) y + β 0 ( τ )
为了评估QR方法的性能,本文中采用Solomatine等[32]提出的平均预测区间(mean prediction interval, MPI)作为不确定度统计量,是对预测值的不确定性范围的估计,表示所有预测区间的平均值。MPI值越小,意味着对于每个预测值其预测区间相对较窄,则预测结果的确定性较高,其计算公式[33]
M P I = 1 n r = 1 n ( P L r u p p e r - P L r l o w e r )
式(14)中: P L r u p p e r P L r l o w e r分别为预测上限和下限。
通过上述方法,图9绘制了土压实参数的QR模型,其中分位数 τ分别为0.05和0.95,以预测90%的预测区间,当 τ = 0.95,得到的QR模型表明数据点在回归直线之下的可能性为95%,而在该直线之上的可能性为5%,相当于提供了90%的置信度。由图9也可以看出几乎所有预测值都在预测区间内,同时表6列出了通过式(14)计算得出不确定度MPI值,由表6数据可知,MPI值均较小,说明不确定性较低。图10绘制了土压实参数测试数据的不确定带,是由QR法确定的GP模型不确定度区间,很明显绝大多数实测值都在预测模型的不确定上下限范围内,进一步证明了本研究提出的模型具有较高的预测精度。
不确定度分析是研究算法结果中的不确定性,而敏感性分析是试图确定输入参数的可变性对输出参数的贡献,哪些参数对结果的影响最大即被表述为关键参数,帮助了解机器学习模型中的输入和输出变量之间的关系,计算敏感度[28]的公式为
S = i = 1 n ( A i B i ) i = 1 n A i 2 i = 1 n B i 2
式(15)中:Ai为计算灵敏度的输入变量;Bi为预测模型的输出变量;n为本研究中的226个数据点。根据模型获得的最优含水量和最大干密度函数式(7)和式(8)可以得出二者对应的预测值即Bi,由式(7)计算并绘制敏感度分析图,如图11所示,6个输入变量对最优含水量模型的重要性排序是 ω P > CF > CS > E > ω L > CG,同样对最大干密度模型的影响程度是ωP > CF > CS > E > CG > ω L,对土压实参数来说,CF ω P敏感度最高,说明这两个输入特征对预测结果有显著影响,而的影响较小的分别是CG ω L
这是因为细粒土颗粒(尤其是黏土)具有较大的比表面积和较强的水合作用能力,这也决定了土的保水能力和塑性变形性质,使得在压实过程中,其能够通过物理吸附和化学吸附与水形成水合作用结构进而实现良好的密实效果[22]。当在最优含水量下,土体的颗粒间孔隙得到有效填充,内聚力达到最大,从而使得土体的最大干密度显著提高。然而,如果水分过多,细粒土的水合作用达到饱和,颗粒间的黏结力减弱,土体结构松散,干密度减小。塑限作为土体由塑性状态向液态转变的关键水分点,直接影响了土的压实行为和力学特性,当土体的塑限较低时,水分能更容易渗透并改善土体的塑性,使得土在特定水分条件下更容易达到最大干密度。相对而言,碎石作为粗颗粒材料,虽然增加了土体的骨架稳定性和力学强度,但其本身较低的吸水性、较高的孔隙率和水合作用能力使其在水分分布和颗粒间相互作用上有限,增强了排水性能,减小了土体内部的孔隙水压力,降低了有效应力,导致其对土压实特性的影响不如细粒土明显。液性极限则更多反映了土的流动性特征,并不直接影响土的压实性能。因此细粒土含量和塑限对土压实参数的敏感度最高,而碎石含量和液限的敏感度较低。
所以,在道路建设、土工填筑及隧道工程中,高含量细粒土和低塑限易导致施工运行中的塌陷和变形,因而在施工过程中需要更多的注意和调整,以确保达到理想的工程要求,同时本研究得到的敏感性分析结果与Wang等[22]和Khan等[34]一致,也说明了本研究所采用的遗传编码算法具有较高的可靠度和准确性。
采用遗传编码算法GP,建立了土最优含水量和最大干密度的预测模型,由文献收集的土体特性指标作为模型的输入参数,即CGCSCF ω L ω PE,通过三个准确度指标并将其与已有研究结果作对比,进一步对预测模型的有效性进行了深入研究来全面评估其预测能力,此外,使用QR方法量化预测模型的不确定性。从这项研究中可以得出以下结论。
(1)通过遗传编程基于符号表示进而构造出具有良好解释性的函数方程,可以借助理解数据及数据之间的数学关系,适合多因素导向下土压实参数(最优含水量和最大干密度)的预测,同时在复杂的非线性问题方面依旧可以寻找到最优的特征构造程序。
(2)利用最优代码组合得到土压实参数的两个显示表达式,由其得到的最优含水量测值与实测值之间的R2=0.882、RMSE=0.300、MAPE=1.656,得到的最大干密度测试值与实测值之间的R2=0.859、RMSE=0.076、MAPE=0.076,表明土压实参数的实测值与预测值具有较好的一致性。
(3)采用GP方法得到的预测最优含水量和最大干密度的最优模型中,均包含细粒土含量和塑限,说明二者是影响土压实参数的关键。从敏感性分析来看,细粒土含量和塑限对土压实参数的影响最大,而碎石量和液限对其影响较小,这与Wang等[22]的敏感性分析结果一致。相较于现有的最优含水量预测模型,利用GP方法所得的预测结果精度更高,误差更小。
(4)基于QR方法,得到了最优含水量和最大干密度数据的90%预测区间,通过MPI作为不确定度统计量量化预测区间覆盖率,对于预测土最优含水量中训练数据和测试数据的MPI值分别为0.206 8和0.265 3,对于预测土最大干密度中训练数据和测试数据对的MPI值分别为0.009 4和0.009 5,其值均较小表明不确定性较低,另外由不确定区间带图可知,数据都落在模型不确定范围内,也再次说明预测模型具有较好的可靠性和准确性。
  • 国家自然科学基金地区科学基金(52068066)
  • 国家自然科学基金地区科学基金(52368052)
  • 新疆维吾尔自治区自然科学基金杰出青年科学基金(2022D01E32)
参考文献 引证文献
排序方式:
[1]
李宇佳. 湿陷性黄土地基冲击压实处治分析[J]. 西部交通科技, 2023(12): 81-83.
Li Yujia. Analysis of impact compaction treatment of collapsible loess foundation[J]. Western Communicational Science, 2023(12): 81-83.
[2]
王伟伟. 高填方路基沉降特性及填土参数影响分析[J]. 交通世界, 2023(11): 38-40.
Wang Weiwei. Analysis of settlement characteristics of high fill subgrade and influence of filling parameters[J]. Transpo World, 2023(11): 38-40.
[3]
王术剑, 李小勇, 韩沛, 等. 路基振动压实响应特征分析与指标适用性[J]. 科学技术与工程, 2024, 24(23): 10072-10083.
Wang Shujian, Li Xiaoyong, Han Pei, et al. Analysis of subgrade vibration compaction response characteristics and applicability of indicators[J]. Science Technology and Engineering, 2024, 24(23) : 10072-10083.
[4]
于际都, 刘斯宏, 王涛, 等. 间断级配粗粒土压实特性试验研究[J]. 岩土工程学报, 2019, 41(11): 2142-2148.
Yu Jidu, Liu Sihong, Wang Tao, et al. Experimental study on compaction characteristics of discontinuous graded coarse-grained soil[J]. Chinese Journal of Geotechnical Engineering, 2019, 41(11): 2142-2148.
[5]
黄崇伟, 郭丹丹, 王德荣, 等. 粗粒土压实特性与高填体沉降规律研究[J]. 上海理工大学学报, 2020, 42(5): 512-518.
Huang Chongwei, Guo Dandan, Wang Derong, et al. Study on compaction characteristics of coarse-grained soil and settlement law of high fill[J]. Journal of University of Shanghai for Science and Technology, 2020, 42(5): 512-518.
[6]
耿宏斌. 细粒土压实特性与颗粒组成相关性分析[J]. 长江科学院院报, 2020, 37(8): 161-165.
Geng Hongbin. Correlation analysis between compaction characteristics and particle composition of fine-grained soil[J]. Journal of Changjiang River Scientific Research Institute, 2020, 37(8): 161-165.
[7]
陈渊召, 李振霞, 付新元. 基于四参数方程的细粒土全压实特性研究[J]. 中国公路学报, 2010, 23(3): 15-21.
Chen Yuanzhao, Li Zhenxia, Fu Xinyuan. Study on full compaction characteristics of fine-grained soil based on four-parameter equation[J]. China Journal of Highway and Transport, 2010, 23(3): 15-21.
[8]
赵乐, 倪万魁, 张镇飞, 等. 不同干密度压实黄土垂直积水入渗特性[J]. 科学技术与工程, 2021, 21(33): 14310-14317.
Zhao Le, Ni Wankui, Zhang Zhenfei, et al. Vertical water infiltration characteristics of compacted loess with different dry densities[J]. Science Technology and Engineering, 2021, 21(33) : 14310-14317.
[9]
吴跃东, 罗如平, 王维春. 南京地区砂砾卵石土压实特性的离散元模拟[J]. 中国公路学报, 2015, 28(4): 13-18, 26.
Wu Yuedong, Luo Ruping, Wang Weichun. Discrete element simulation of compaction characteristics of sandy pebble soil in Nanjing area[J]. China Journal of Highway and Transport, 2015, 28(4): 13-18, 26.
[10]
白祥瑞, 戎晓力, 文祝, 等. 基于DE-SVR的土压平衡盾构隧道施工阶段地表沉降预测研究[J]. 隧道建设, 2021, 41(S2): 336-345.
Bai Xiangrui, Rong Xiaoli, Wen Zhu, et al. Prediction of ground settlement during construction of EPB shield tunnel based on DE-SVR[J]. Tunnel Construction, 2021, 41(S2): 336-345.
[11]
Chen R P, Zhang P, Kang X, et al. Prediction of maximum surface settlement caused by earth pressure balance (EPB) shield tunneling with ANN methods[J]. Soils and Foundations, 2019, 59(2): 284-295.
[12]
何昌春, 赵鹏, 荣耀, 等. 基于地表沉陷实测数据的覆岩内部移动变形预计方法[J]. 科学技术与工程, 2024, 24(22): 9309-9315.
He Changchun, Zhao Peng, Rong Yao, et al. Method for predicting the internal movement and deformation of overlying strata based on the measured data of surface subsidence[J]. Science Technology and Engineering, 2024, 24(22) : 9309-9315.
[13]
Cheng Z L, Zhou W H, Garg A. Genetic programming model for estimating soil suction in shallow soil layers in the vicinity of a tree[J]. Engineering Geology, 2020, 268: 105506.
[14]
Garg A, Garg A, Tai K. A multi-gene genetic programming model for estimating stress-dependent soil water retention curves[J]. Computational Geosciences, 2014, 18: 45-56.
[15]
苏国韶, 宋咏春, 燕柳斌. 高斯过程机器学习在边坡稳定性评价中的应用[J]. 岩土力学, 2009, 30(3): 675-679, 687.
Su Guoshao, Song Yongchun, Yan Liubin. Application of Gaussian process machine learning in slope stability evaluation[J]. Rock and Soil Mechanics, 2009, 30(3): 675-679, 687.
[16]
冯希尧, 苟俊程, 刘瑞, 等. 基于遗传算法优化机器学习模型的地下水潜在性预测[J]. 科学技术与工程, 2024, 24(19): 7988-7998.
Feng Xiyao, Gou Juncheng, Liu Rui, et al. Prediction of groundwater potential based on machine learning model optimized by genetic algorithm[J]. Science Technology and Engineering, 2024, 24(19) : 7988-7998.
[17]
Makke N, Chawla S. Interpretable scientific discovery with symbolic regression: a review[J]. Artificial Intelligence Review, 2024, 57(1): 10462.
[18]
Cramer N L. A representation for the adaptive generation of simple sequential programs[C]// Proceedings of the First International Conference on Genetic Algorithms and Their Applications. Lundon: Psychology Press, 2014: 183-187.
[19]
Koza J R. Genetic programming as a means for programming computers by natural selection[J]. Statistics and Computing, 1994, 4: 87-112.
[20]
Mei Y, Chen Q, Lensen A, et al. Explainable artificial intelligence by genetic programming: a survey[J]. IEEE Transactions on Evolutionary Computation, 2022, 27(3): 621-641.
[21]
Qin S, Xu T, Cheng Z L, et al. Analysis of spatiotemporal variations of excess pore water pressure during mechanized tunneling using genetic programming[J]. Acta Geotechnica, 2023, 18(4): 1721-1738.
[22]
Wang H L, Yin Z Y. High performance prediction of soil compaction parameters using multi expression programming[J]. Engineering Geology, 2020, 276: 105758.
[23]
Kalnins A. Multicollinearity: how common factors cause type 1 errors in multivariate regression[J]. Strategic Management Journal, 2018, 39(8): 2362-2385.
[24]
Gurtug Y, Sridharan A. Compaction behaviour and prediction of its characteristics of fine grained soils with particular reference to compaction energy[J]. Soils and Foundations, 2004, 44(5): 27-36.
[25]
Günaydın O. Estimation of soil compaction parameters by using statistical analyses and artificial neural networks[J]. Environmental Geology, 2009, 57: 203-215.
[26]
Nagaraj H B, Reesha B, Sravan M V, et al. Correlation of compaction characteristics of natural soils with modified plastic limit[J]. Transportation Geotechnics, 2015, 2: 65-77.
[27]
Farooq K, Khalid U, Mujtaba H. Prediction of compaction characteristics of fine-grained soils using consistency limits[J]. Arabian Journal for Science and Engineering, 2016, 41: 1319-1328.
[28]
Ardakani A, Kordnaeij A. Soil compaction parameters prediction using GMDH-type neural network and genetic algorithm[J]. European Journal of Environmental and Civil Engineering, 2019, 23(4): 449-462.
[29]
Kurnaz T F, Kaya Y. The performance comparison of the soft computing methods on the prediction of soil compaction parameters[J]. Arabian Journal of Geosciences, 2020, 13: 1-13.
[30]
Koenker R, Basset G. Asymptotic theory of least absolute error regression[J]. Journal of the American Statistical Association, 1978, 73(363): 618-622.
[31]
Rodriguez R N, Yao Y. Five things you should know about quantile regression[J]. Cary: SAS Institute Inc, 2017.
[32]
Solomatine D P, Shrestha D L. A novel method to estimate model uncertainty using machine learning techniques[J]. Water Resources Research, 2009, 45(12): W00B11.
[33]
Rahmati O, Choubin B, Fathabadi A, et al. Predicting uncertainty of machine learning models for modelling nitrate pollution of groundwater using quantile regression and UNEEC methods[J]. Science of the Total Environment, 2019, 688: 855-866.
[34]
Khan M H A, Jafri T H, Ud-Din S, et al. Prediction of soil compaction parameters through the development and experimental validation of Gaussian process regression models[J]. Environmental Earth Sciences, 2024, 83(4): 129.
2025年第25卷第19期
PDF下载
641
306
引用本文
BibTeX
文章信息
doi: 10.12404/j.issn.1671-1815.2405717
  • 接收时间:2024-07-30
  • 首发时间:2025-12-22
  • 出版时间:2025-07-08
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2024-07-30
  • 修回日期:2024-12-23
基金
国家自然科学基金地区科学基金(52068066)
国家自然科学基金地区科学基金(52368052)
新疆维吾尔自治区自然科学基金杰出青年科学基金(2022D01E32)
作者信息
    1 中铁十五局集团城市轨道交通工程有限公司, 广州 510400
    2 新疆大学建筑工程学院, 乌鲁木齐 830017

通讯作者:

*刘烨(2001—),女,汉族,山东高密人,硕士研究生。研究方向:岩土工程。E-mail:
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/kxjsygc/CN/10.12404/j.issn.1671-1815.2405717
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