Article(id=1174390603526848678, tenantId=1146029695717560320, journalId=1146123222451335185, issueId=1174385906053165285, articleNumber=1671-1807(2025)14-0055-09, orderNo=null, doi=null, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1736092800000, receivedDateStr=2025-01-06, revisedDate=null, revisedDateStr=null, acceptedDate=null, acceptedDateStr=null, onlineDate=1757926139002, onlineDateStr=2025-09-15, pubDate=1753372800000, pubDateStr=2025-07-25, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1757926139002, onlineIssueDateStr=2025-09-15, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1757926139002, creator=13701087609, updateTime=1757926139002, updator=13701087609, issue=Issue{id=1174385906053165285, tenantId=1146029695717560320, journalId=1146123222451335185, year='2025', volume='25', issue='14', pageStart='1', pageEnd='286', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1757925019038, creator=13701087609, updateTime=1758072769121, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1175005614947316471, tenantId=1146029695717560320, journalId=1146123222451335185, issueId=1174385906053165285, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1175005614947316472, tenantId=1146029695717560320, journalId=1146123222451335185, issueId=1174385906053165285, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=55, endPage=63, ext={EN=ArticleExt(id=1174390603807867051, articleId=1174390603526848678, tenantId=1146029695717560320, journalId=1146123222451335185, language=EN, title=Neural Network Prediction and Sensitivity Analysis of Geotechnical Thermophysical Parameters, columnId=1151876674645226399, journalTitle=Science Technology and Industry, columnName=Technology Innovation, runingTitle=null, highlight=null, articleAbstract=

With the development of engineering in cold regions, it is important to accurately derive the thermoplastic parameters of soils under freeze-thaw conditions. In view of the large error of the commonly used BP neural network to predict the thermal property parameters, 120 sets of thermal property parameters of frozen and thawed soil were used as samples, and the prediction model was improved by Bayesian regularization method to establish a multi-input and multi-output BP neural network, and the prediction accuracy of the model was significantly improved. Sensitivity analyses of the Bayesian neural network and random forest model were carried out with the improved Monte Carlo method and SHAP interpretation, respectively. The results show that the freeze-thaw condition does not change the sensitivity ranking of the influencing factors. The sensitivity of volumetric heat capacity and thermal conductivity to water content, dry density, and soil quality decreases in the order of freezing and thawing state, and the sensitivity of thermal conductivity to soil quality, water content and dry density decreases in the order of soil quality, water content and dry density.

, correspAuthors=null, authorNote=null, correspAuthorsNote=null, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=null, magXml=null, pdfUrl=null, pdf=null, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=null, mapNumber=null, authorCompany=null, fund=null, authors=null, authorsList=Zhaoming YAO, Xiaolong WANG, Xun WANG, Hang WEI, Penghui LI, Qin FANG), CN=ArticleExt(id=1174390837690647222, articleId=1174390603526848678, tenantId=1146029695717560320, journalId=1146123222451335185, language=CN, title=岩土热物参数贝叶斯神经网络预测及敏感性分析, columnId=1151876674787832737, journalTitle=科技和产业, columnName=科技创新, runingTitle=null, highlight=null, articleAbstract=

随着寒区工程的开发,准确得出岩土在冻融状态下的热物参数具有重要意义。鉴于常用BP神经网络预测热物参数误差较大,以120组冻土、融土热物参数为样本,采用贝叶斯正则化方法对预测模型进行改进,建立多输入多输出的BP神经网络,模型的预测精度明显提高。用改进蒙特卡洛法和SHAP解释分别对贝叶斯神经网络和随机森林模型进行敏感性分析。结果表明,冻融状态不改变影响因素的敏感性排序。容积热容量和导热系数在冻融状态下,对含水率、干密度、土质的敏感程度依次降低,导温系数对土质、含水率、干密度的敏感程度依次降低。

, correspAuthors=null, authorNote=null, correspAuthorsNote=null, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=e928+L+YurRWUGxyk4gPPA==, magXml=1lSiGgkNoy2/P/8p8yv7Mw==, pdfUrl=null, pdf=AWF2XTIru2UJPuoMHDETBg==, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=PT46DK9MhWTBpsyQQSRCDQ==, mapNumber=null, authorCompany=null, fund=null, authors=

姚兆明(1975—),男,安徽黄山人,博士,教授,研究方向为土体本构理论和岩土数值分析;

王晓龙(2001—),男,安徽芜湖人,硕士研究生,研究方向为人工智能在岩土工程中的应用;

王洵(2000—),男,安徽黄山人,硕士研究生,研究方向为人工智能在岩土工程中的应用;

魏航(2001—),男,安徽淮南人,硕士研究生,研究方向为寒区岩土流变理论;

李鹏辉(1989—),男,宁夏隆德人,高级工程师,研究方向为地质调查与矿产勘查;

方庆(1987—),男,江西湖口人,硕士,高级工程师,研究方向为岩土工程设计与施工。

, authorsList=姚兆明, 王晓龙, 王洵, 魏航, 李鹏辉, 方庆)}, authors=[Author(id=1175040320350864094, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1175040320434750177, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, authorId=1175040320350864094, language=EN, stringName=Zhaoming YAO, firstName=Zhaoming, middleName=null, lastName=YAO, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1 College of Civil Engineering, Anhui University of Science and Technology, Huainan 232001, Anhui, China
2 Engineering Research Cener of Underground Mine Construction, Ministry of Education, Huainan 232001, Anhui, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1175040320489276130, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, authorId=1175040320350864094, language=CN, stringName=姚兆明, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1 安徽理工大学土木建筑学院, 安徽 淮南 232001
2 矿山地下工程教育部工程研究中心, 安徽 淮南 232001, bio={"content":"

姚兆明(1975—),男,安徽黄山人,博士,教授,研究方向为土体本构理论和岩土数值分析;

"}, bioImg=null, bioContent=

姚兆明(1975—),男,安徽黄山人,博士,教授,研究方向为土体本构理论和岩土数值分析;

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1175040319981765329, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, xref=1, ext=[AuthorCompanyExt(id=1175040319990153938, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, companyId=1175040319981765329, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 College of Civil Engineering, Anhui University of Science and Technology, Huainan 232001, Anhui, China), AuthorCompanyExt(id=1175040319998542547, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, companyId=1175040319981765329, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 安徽理工大学土木建筑学院, 安徽 淮南 232001)]), AuthorCompany(id=1175040320065651412, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, xref=2, ext=[AuthorCompanyExt(id=1175040320074040021, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, companyId=1175040320065651412, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 Engineering Research Cener of Underground Mine Construction, Ministry of Education, Huainan 232001, Anhui, China), AuthorCompanyExt(id=1175040320082428630, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, companyId=1175040320065651412, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 矿山地下工程教育部工程研究中心, 安徽 淮南 232001)])]), Author(id=1175040320552190692, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, 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=1175040320623493863, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, authorId=1175040320552190692, language=EN, stringName=Xiaolong WANG, firstName=Xiaolong, middleName=null, lastName=WANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1 College of Civil Engineering, Anhui University of Science and Technology, Huainan 232001, Anhui, China
2 Engineering Research Cener of Underground Mine Construction, Ministry of Education, Huainan 232001, Anhui, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1175040320678019816, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, authorId=1175040320552190692, language=CN, stringName=王晓龙, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1 安徽理工大学土木建筑学院, 安徽 淮南 232001
2 矿山地下工程教育部工程研究中心, 安徽 淮南 232001, bio={"content":"

王晓龙(2001—),男,安徽芜湖人,硕士研究生,研究方向为人工智能在岩土工程中的应用;

"}, bioImg=null, bioContent=

王晓龙(2001—),男,安徽芜湖人,硕士研究生,研究方向为人工智能在岩土工程中的应用;

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1175040319981765329, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, xref=1, ext=[AuthorCompanyExt(id=1175040319990153938, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, companyId=1175040319981765329, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 College of Civil Engineering, Anhui University of Science and Technology, Huainan 232001, Anhui, China), AuthorCompanyExt(id=1175040319998542547, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, companyId=1175040319981765329, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 安徽理工大学土木建筑学院, 安徽 淮南 232001)]), AuthorCompany(id=1175040320065651412, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, xref=2, ext=[AuthorCompanyExt(id=1175040320074040021, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, companyId=1175040320065651412, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 Engineering Research Cener of Underground Mine Construction, Ministry of Education, Huainan 232001, Anhui, China), AuthorCompanyExt(id=1175040320082428630, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, companyId=1175040320065651412, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 矿山地下工程教育部工程研究中心, 安徽 淮南 232001)])]), Author(id=1175040320740934378, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, 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=1175040320816431853, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, authorId=1175040320740934378, language=EN, stringName=Xun WANG, firstName=Xun, middleName=null, lastName=WANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1 College of Civil Engineering, Anhui University of Science and Technology, Huainan 232001, Anhui, China
2 Engineering Research Cener of Underground Mine Construction, Ministry of Education, Huainan 232001, Anhui, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1175040320883540718, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, authorId=1175040320740934378, language=CN, stringName=王洵, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1 安徽理工大学土木建筑学院, 安徽 淮南 232001
2 矿山地下工程教育部工程研究中心, 安徽 淮南 232001, bio={"content":"

王洵(2000—),男,安徽黄山人,硕士研究生,研究方向为人工智能在岩土工程中的应用;

"}, bioImg=null, bioContent=

王洵(2000—),男,安徽黄山人,硕士研究生,研究方向为人工智能在岩土工程中的应用;

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1175040319981765329, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, xref=1, ext=[AuthorCompanyExt(id=1175040319990153938, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, companyId=1175040319981765329, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 College of Civil Engineering, Anhui University of Science and Technology, Huainan 232001, Anhui, China), AuthorCompanyExt(id=1175040319998542547, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, companyId=1175040319981765329, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 安徽理工大学土木建筑学院, 安徽 淮南 232001)]), AuthorCompany(id=1175040320065651412, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, xref=2, ext=[AuthorCompanyExt(id=1175040320074040021, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, companyId=1175040320065651412, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 Engineering Research Cener of Underground Mine Construction, Ministry of Education, Huainan 232001, Anhui, China), AuthorCompanyExt(id=1175040320082428630, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, companyId=1175040320065651412, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 矿山地下工程教育部工程研究中心, 安徽 淮南 232001)])]), Author(id=1175040320946455280, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, 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=1175040321026147059, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, authorId=1175040320946455280, language=EN, stringName=Hang WEI, firstName=Hang, middleName=null, lastName=WEI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1 College of Civil Engineering, Anhui University of Science and Technology, Huainan 232001, Anhui, China
2 Engineering Research Cener of Underground Mine Construction, Ministry of Education, Huainan 232001, Anhui, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1175040321089061620, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, authorId=1175040320946455280, language=CN, stringName=魏航, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1 安徽理工大学土木建筑学院, 安徽 淮南 232001
2 矿山地下工程教育部工程研究中心, 安徽 淮南 232001, bio={"content":"

魏航(2001—),男,安徽淮南人,硕士研究生,研究方向为寒区岩土流变理论;

"}, bioImg=null, bioContent=

魏航(2001—),男,安徽淮南人,硕士研究生,研究方向为寒区岩土流变理论;

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1175040319981765329, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, xref=1, ext=[AuthorCompanyExt(id=1175040319990153938, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, companyId=1175040319981765329, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 College of Civil Engineering, Anhui University of Science and Technology, Huainan 232001, Anhui, China), AuthorCompanyExt(id=1175040319998542547, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, companyId=1175040319981765329, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 安徽理工大学土木建筑学院, 安徽 淮南 232001)]), AuthorCompany(id=1175040320065651412, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, xref=2, ext=[AuthorCompanyExt(id=1175040320074040021, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, companyId=1175040320065651412, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 Engineering Research Cener of Underground Mine Construction, Ministry of Education, Huainan 232001, Anhui, China), AuthorCompanyExt(id=1175040320082428630, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, companyId=1175040320065651412, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 矿山地下工程教育部工程研究中心, 安徽 淮南 232001)])]), Author(id=1175040321147781878, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, orderNo=4, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1175040321231667960, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, authorId=1175040321147781878, language=EN, stringName=Penghui LI, firstName=Penghui, middleName=null, lastName=LI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3 Geological team of Shandong Provincial Bureau of Geology and Mineral Resources, Jinan 250000, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1175040321307165433, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, authorId=1175040321147781878, language=CN, stringName=李鹏辉, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3 山东省第一地质矿产勘查院, 济南 250000, bio={"content":"

李鹏辉(1989—),男,宁夏隆德人,高级工程师,研究方向为地质调查与矿产勘查;

"}, bioImg=null, bioContent=

李鹏辉(1989—),男,宁夏隆德人,高级工程师,研究方向为地质调查与矿产勘查;

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1175040320153731799, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, xref=3, ext=[AuthorCompanyExt(id=1175040320166314712, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, companyId=1175040320153731799, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 Geological team of Shandong Provincial Bureau of Geology and Mineral Resources, Jinan 250000, China), AuthorCompanyExt(id=1175040320174703321, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, companyId=1175040320153731799, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 山东省第一地质矿产勘查院, 济南 250000)])]), Author(id=1175040321361691387, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, 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=1175040321432994557, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, authorId=1175040321361691387, language=EN, stringName=Qin FANG, firstName=Qin, middleName=null, lastName=FANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=4, address=4 The First Geological Brigade of Jiangsu Geological Bureau, Nanjing 210042, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1175040321504297726, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, authorId=1175040321361691387, language=CN, stringName=方庆, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=4, address=4 江苏省地质局第一地质大队, 南京 210042, bio={"content":"

方庆(1987—),男,江西湖口人,硕士,高级工程师,研究方向为岩土工程设计与施工。

"}, bioImg=null, bioContent=

方庆(1987—),男,江西湖口人,硕士,高级工程师,研究方向为岩土工程设计与施工。

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1175040320246006490, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, xref=4, ext=[AuthorCompanyExt(id=1175040320250200795, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, companyId=1175040320246006490, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=4 The First Geological Brigade of Jiangsu Geological Bureau, Nanjing 210042, China), AuthorCompanyExt(id=1175040320262783708, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, companyId=1175040320246006490, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=4 江苏省地质局第一地质大队, 南京 210042)])])], keywords=[Keyword(id=1175040321621738239, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, language=EN, orderNo=1, keyword=thermal parameter), Keyword(id=1175040321684652800, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, language=EN, orderNo=2, keyword=BP neural network), Keyword(id=1175040321755955969, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, language=EN, orderNo=3, keyword=Bayesian regularization), Keyword(id=1175040321814676226, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, language=EN, orderNo=4, keyword=Monte Carlo), Keyword(id=1175040321873396483, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, language=EN, orderNo=5, keyword=SHAP), Keyword(id=1175040321932116740, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, language=CN, orderNo=1, keyword=热物参数), Keyword(id=1175040321986642693, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, language=CN, orderNo=2, keyword=BP神经网络), Keyword(id=1175040322053751558, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, language=CN, orderNo=3, keyword=贝叶斯正则化), Keyword(id=1175040322125054727, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, language=CN, orderNo=4, keyword=蒙特卡洛), Keyword(id=1175040322196357896, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, language=CN, orderNo=5, keyword=SHAP)], refs=[Reference(id=1175040324494836516, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, doi=null, pmid=null, pmcid=null, year=2019, volume=19, issue=24, pageStart=352, pageEnd=358, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=姚兆明, 潘旋, 张秋瑾, journalName=科学技术与工程, refType=null, unstructuredReference=姚兆明, 潘旋, 张秋瑾. 人工冻土温度场模型试验及冻土导热系数反分析[J]. 科学技术与工程, 2019, 19(24): 352-358., articleTitle=人工冻土温度场模型试验及冻土导热系数反分析, refAbstract=null), Reference(id=1175040324561945381, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, doi=null, pmid=null, pmcid=null, year=2021, volume=16, issue=null, pageStart=3455, pageEnd=3466, url=null, language=null, rfNumber=[2], rfOrder=1, authorNames=LI K Q, LI D Q, CHEN D H, journalName=Acta Geotechnica, refType=null, unstructuredReference=LI K Q, LI D Q, CHEN D H, et al. A generalized model for effective thermal conductivity of soils considering porosity and mineral composition[J]. Acta Geotechnica, 2021, 16: 3455-3466., articleTitle=A generalized model for effective thermal conductivity of soils considering porosity and mineral composition, refAbstract=null), Reference(id=1175040324629054246, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, doi=null, pmid=null, pmcid=null, year=2022, volume=43, issue=5, pageStart=1335, pageEnd=1340, url=null, language=null, rfNumber=[3], rfOrder=2, authorNames=金宗川, 王雪晴, 乌效鸣, journalName=岩土力学, refType=null, unstructuredReference=金宗川, 王雪晴, 乌效鸣, 等. 土壤热参数及其影响因素测试分析[J]. 岩土力学, 2022, 43(5): 1335-1340., articleTitle=土壤热参数及其影响因素测试分析, refAbstract=null), Reference(id=1175040324712940327, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, doi=null, pmid=null, pmcid=null, year=2024, volume=24, issue=7, pageStart=2724, pageEnd=2733, url=null, language=null, rfNumber=[4], rfOrder=3, authorNames=李文岚婷, 苏顺玉, journalName=科学技术与工程, refType=null, unstructuredReference=李文岚婷, 苏顺玉. 三相土壤分形导热系数模型[J]. 科学技术与工程, 2024, 24(7): 2724-2733., articleTitle=三相土壤分形导热系数模型, refAbstract=null), Reference(id=1175040324788437800, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, doi=null, pmid=null, pmcid=null, year=2023, volume=23, issue=5, pageStart=2084, pageEnd=2092, url=null, language=null, rfNumber=[5], rfOrder=4, authorNames=王红旗, 李栋伟, 钟石明, journalName=科学技术与工程, refType=null, unstructuredReference=王红旗, 李栋伟, 钟石明, 等. 石灰改良红黏土导热系数影响因素及模型预测[J]. 科学技术与工程, 2023, 23(5): 2084-2092., articleTitle=石灰改良红黏土导热系数影响因素及模型预测, refAbstract=null), Reference(id=1175040324868129577, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, doi=null, pmid=null, pmcid=null, year=2024, volume=45, issue=5, pageStart=1440, pageEnd=1449, url=null, language=null, rfNumber=[6], rfOrder=5, authorNames=姚兆明, 王洵, 齐健, journalName=工程热物理学报, refType=null, unstructuredReference=姚兆明, 王洵, 齐健. 土体导热系数智能方法预测及影响因素敏感性分析[J]. 工程热物理学报, 2024, 45(5): 1440-1449., articleTitle=土体导热系数智能方法预测及影响因素敏感性分析, refAbstract=null), Reference(id=1175040324947821354, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, doi=null, pmid=null, pmcid=null, year=2024, volume=217, issue=null, pageStart=104027, pageEnd=null, url=null, language=null, rfNumber=[7], rfOrder=6, authorNames=REN X L, journalName=Cold Regions Science and Technology, refType=null, unstructuredReference=REN X L. Research progress of soil thermal conductivity and its predictive models[J]. Cold Regions Science and Technology, 2024, 217: 104027., articleTitle=Research progress of soil thermal conductivity and its predictive models, refAbstract=null), Reference(id=1175040325027513131, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, doi=null, pmid=null, pmcid=null, year=2022, volume=22, issue=16, pageStart=6369, pageEnd=6376, url=null, language=null, rfNumber=[8], rfOrder=7, authorNames=徐拴海, 沈浩, journalName=科学技术与工程, refType=null, unstructuredReference=徐拴海, 沈浩. 岩石导热系数影响因素及预测研究综述[J]. 科学技术与工程, 2022, 22(16): 6369-6376., articleTitle=岩石导热系数影响因素及预测研究综述, refAbstract=null), Reference(id=1175040325090427692, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, doi=null, pmid=null, pmcid=null, year=2014, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[9], rfOrder=8, authorNames=中华人民共和国住房和城乡建设部. GB, journalName=null, refType=null, unstructuredReference=中华人民共和国住房和城乡建设部. GB 50324-2014冻土工程地质勘查规范[S]. 北京: 中国计划出版社, 2014., articleTitle=null, refAbstract=null), Reference(id=1175040325153342253, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, doi=null, pmid=null, pmcid=null, year=2010, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[10], rfOrder=9, authorNames=徐学祖, 王家澄, 张立新, journalName=冻土物理学, refType=null, unstructuredReference=徐学祖, 王家澄, 张立新. 冻土物理学[M]. 北京: 科学出版社, 2010., articleTitle=null, refAbstract=null), Reference(id=1175040325233034030, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, doi=null, pmid=null, pmcid=null, year=2022, volume=40, issue=9, pageStart=120, pageEnd=124, url=null, language=null, rfNumber=[11], rfOrder=10, authorNames=隋旭鹏, 朱圣辉, 王少伟, journalName=水电能源科学, refType=null, unstructuredReference=隋旭鹏, 朱圣辉, 王少伟, 等. 贝叶斯正则化对混凝土坝位移机器学习模型性能的提升[J]. 水电能源科学, 2022, 40(9): 120-124., articleTitle=贝叶斯正则化对混凝土坝位移机器学习模型性能的提升, refAbstract=null), Reference(id=1175040325300142895, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, doi=null, pmid=null, pmcid=null, year=2023, volume=74, issue=null, pageStart=139, pageEnd=155, url=null, language=null, rfNumber=[12], rfOrder=11, authorNames=KARIMOVA D, LEENDERS R T A J, MEIJERINK-BOSMAN M, journalName=Social Networks, refType=null, unstructuredReference=KARIMOVA D, LEENDERS R T A J, MEIJERINK-BOSMAN M, et al. Separating the Wheat from the chaff: Bayesian regularization in dynamic social networks[J]. Social Networks, 2023, 74: 139-155., articleTitle=Separating the Wheat from the chaff: Bayesian regularization in dynamic social networks, refAbstract=null), Reference(id=1175040325367251760, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, doi=null, pmid=null, pmcid=null, year=2022, volume=35, issue=3, pageStart=035001, pageEnd=null, url=null, language=null, rfNumber=[13], rfOrder=12, authorNames=LIU Q Y, KIM S, journalName=Superconductor Science Technology, refType=null, unstructuredReference=LIU Q Y, KIM S. Temperature-field-angle dependent critical current estimation of commercial second generation high temperature superconducting conductor using double hidden layer Bayesian regularized neural network[J]. Superconductor Science Technology, 2022, 35(3): 035001., articleTitle=Temperature-field-angle dependent critical current estimation of commercial second generation high temperature superconducting conductor using double hidden layer Bayesian regularized neural network, refAbstract=null), Reference(id=1175040325430166321, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, doi=null, pmid=null, pmcid=null, year=2022, volume=44, issue=10, pageStart=1899, pageEnd=1907, url=null, language=null, rfNumber=[14], rfOrder=13, authorNames=王才进, 蔡国军, 武猛, journalName=岩土工程报, refType=null, unstructuredReference=王才进, 蔡国军, 武猛, 等. 基于人工智能算法预测土体导热系数[J]. 岩土工程报, 2022, 44(10): 1899-1907., articleTitle=基于人工智能算法预测土体导热系数, refAbstract=null), Reference(id=1175040325526635314, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, doi=null, pmid=null, pmcid=null, year=2012, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[15], rfOrder=14, authorNames=SOIZE C, journalName=Stochastic models of uncertainties in computational mechanics, refType=null, unstructuredReference=SOIZE C. Stochastic models of uncertainties in computational mechanics[M]. Reston VA: American Society of Civil Engineers, 2012., articleTitle=null, refAbstract=null), Reference(id=1175040325589549875, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, doi=null, pmid=null, pmcid=null, year=2024, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[16], rfOrder=15, authorNames=LÜ W, JIA J, CHEN X, journalName=Case Studies in Construction Materials, refType=null, unstructuredReference= W, JIA J, CHEN X, et al. Predicting shear strength in UHPC beams through an innovative neural network with SHAP interpretation[J]. Case Studies in Construction Materials, 2024, 20: e03211., articleTitle=Predicting shear strength in UHPC beams through an innovative neural network with SHAP interpretation, refAbstract=null), Reference(id=1175040325665047348, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, doi=null, pmid=null, pmcid=null, year=2024, volume=41, issue=S1, pageStart=300, pageEnd=309, url=null, language=null, rfNumber=[17], rfOrder=16, authorNames=刘廷滨, 黄滔, 欧嘉祥, journalName=工程力学, refType=null, unstructuredReference=刘廷滨, 黄滔, 欧嘉祥, 等. 基于ANN和XGB算法的锈蚀钢筋混凝土高温黏结强度预测方法[J]. 工程力学, 2024, 41(S1): 300-309., articleTitle=基于ANN和XGB算法的锈蚀钢筋混凝土高温黏结强度预测方法, refAbstract=null), Reference(id=1175040325723767605, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, doi=null, pmid=null, pmcid=null, year=2017, volume=29, issue=8, pageStart=3510, pageEnd=3523, url=null, language=null, rfNumber=[18], rfOrder=17, authorNames=WANG Y A, XIA S T, TANG Q T, journalName=IEEE Transactions on Neural Networks and Learning Systems, refType=null, unstructuredReference=WANG Y A, XIA S T, TANG Q T, et al. A novel consist ent ran-dom forest framework: bernoulli random forests[J]. IEEE Transactions on Neural Networks and Learning Systems, 2017, 29(8): 3510-3523., articleTitle=A novel consist ent ran-dom forest framework: bernoulli random forests, refAbstract=null), Reference(id=1175040325799265078, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, doi=null, pmid=null, pmcid=null, year=2001, volume=45, issue=null, pageStart=5, pageEnd=32, url=null, language=null, rfNumber=[19], rfOrder=18, authorNames=LEO B, journalName=Machine Learning, refType=null, unstructuredReference=LEO B. Random forest[J]. Machine Learning, 2001, 45: 5-32., articleTitle=Random forest, refAbstract=null)], funds=[Fund(id=1175040324335452963, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, awardId=JYBGCZX2021104, language=CN, fundingSource=矿山地下工程教育部工程研究中心开放研究项目(JYBGCZX2021104), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1175040319981765329, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, xref=1, ext=[AuthorCompanyExt(id=1175040319990153938, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, companyId=1175040319981765329, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 College of Civil Engineering, Anhui University of Science and Technology, Huainan 232001, Anhui, China), AuthorCompanyExt(id=1175040319998542547, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, companyId=1175040319981765329, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 安徽理工大学土木建筑学院, 安徽 淮南 232001)]), AuthorCompany(id=1175040320065651412, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, xref=2, ext=[AuthorCompanyExt(id=1175040320074040021, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, companyId=1175040320065651412, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 Engineering Research Cener of Underground Mine Construction, Ministry of Education, Huainan 232001, Anhui, China), AuthorCompanyExt(id=1175040320082428630, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, companyId=1175040320065651412, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 矿山地下工程教育部工程研究中心, 安徽 淮南 232001)]), AuthorCompany(id=1175040320153731799, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, xref=3, ext=[AuthorCompanyExt(id=1175040320166314712, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, companyId=1175040320153731799, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 Geological team of Shandong Provincial Bureau of Geology and Mineral Resources, Jinan 250000, China), AuthorCompanyExt(id=1175040320174703321, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, companyId=1175040320153731799, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 山东省第一地质矿产勘查院, 济南 250000)]), AuthorCompany(id=1175040320246006490, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, xref=4, ext=[AuthorCompanyExt(id=1175040320250200795, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, companyId=1175040320246006490, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=4 The First Geological Brigade of Jiangsu Geological Bureau, Nanjing 210042, China), AuthorCompanyExt(id=1175040320262783708, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, companyId=1175040320246006490, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=4 江苏省地质局第一地质大队, 南京 210042)])], figs=[ArticleFig(id=1175040322401878793, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, language=EN, label=null, caption=null, figureFileSmall=5IINjy1BqWZ72cgHX9z1Dw==, figureFileBig=eMl6kzeJ1vFyD3mYGU/paQ==, tableContent=null), ArticleFig(id=1175040322477376266, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, language=CN, label=图1, caption=含水率与导热系数散点图, figureFileSmall=5IINjy1BqWZ72cgHX9z1Dw==, figureFileBig=eMl6kzeJ1vFyD3mYGU/paQ==, tableContent=null), ArticleFig(id=1175040322557068043, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, language=EN, label=null, caption=null, figureFileSmall=sLJifPiPohtJB3AFNk0nOg==, figureFileBig=mKoJNzfWpzwzWotGA0DeOg==, tableContent=null), ArticleFig(id=1175040322636759820, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, language=CN, label=图2, caption=干密度与导热系数散点图, figureFileSmall=sLJifPiPohtJB3AFNk0nOg==, figureFileBig=mKoJNzfWpzwzWotGA0DeOg==, tableContent=null), ArticleFig(id=1175040322720645901, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, language=EN, label=null, caption=null, figureFileSmall=sD+0z7PV7dVgjSJ6HaEQ4g==, figureFileBig=yu69Z/AM+fm6h2/PY8pRsw==, tableContent=null), ArticleFig(id=1175040322796143374, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, language=CN, label=图3, caption=BP神经网络对融土热物参数预测效果, figureFileSmall=sD+0z7PV7dVgjSJ6HaEQ4g==, figureFileBig=yu69Z/AM+fm6h2/PY8pRsw==, tableContent=null), ArticleFig(id=1175040322859057935, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, language=EN, label=null, caption=null, figureFileSmall=C0Q8e5C96u5WDfPM6bRf1g==, figureFileBig=SURH33kdbUaeQf8AaAjvBQ==, tableContent=null), ArticleFig(id=1175040322917778192, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, language=CN, label=图4, caption=BP神经网络对冻土热物参数预测效果, figureFileSmall=C0Q8e5C96u5WDfPM6bRf1g==, figureFileBig=SURH33kdbUaeQf8AaAjvBQ==, tableContent=null), ArticleFig(id=1175040322989081361, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, language=EN, label=null, caption=null, figureFileSmall=Evt++gnsziWRBRcGdaa3ZA==, figureFileBig=QwI07sqNG6usOvLgGR9cqg==, tableContent=null), ArticleFig(id=1175040323043607314, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, language=CN, label=图5, caption=贝叶斯神经网络对融土热物参数预测, figureFileSmall=Evt++gnsziWRBRcGdaa3ZA==, figureFileBig=QwI07sqNG6usOvLgGR9cqg==, tableContent=null), ArticleFig(id=1175040323102327571, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, language=EN, label=null, caption=null, figureFileSmall=QJmJvsY46UWutCLcWY+97A==, figureFileBig=nb0GVgWYaeic8A3e+Wg4VQ==, tableContent=null), ArticleFig(id=1175040323165242132, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, language=CN, label=图6, caption=贝叶斯神经网络对冻土热物参数预测, figureFileSmall=QJmJvsY46UWutCLcWY+97A==, figureFileBig=nb0GVgWYaeic8A3e+Wg4VQ==, tableContent=null), ArticleFig(id=1175040323236545301, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, language=EN, label=null, caption=null, figureFileSmall=ueRHbKpdAeeTwap9aoMrtw==, figureFileBig=jpaNrimetaQVA4dPFGrf3w==, tableContent=null), ArticleFig(id=1175040323303654166, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, language=CN, label=图7, caption=融土敏感性分析柱状图, figureFileSmall=ueRHbKpdAeeTwap9aoMrtw==, figureFileBig=jpaNrimetaQVA4dPFGrf3w==, tableContent=null), ArticleFig(id=1175040323362374423, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, language=EN, label=null, caption=null, figureFileSmall=69XML0axDv4oZL/bv1zQ1w==, figureFileBig=12prnWzI4WhL3wsC1+2bHw==, tableContent=null), ArticleFig(id=1175040323429483288, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, language=CN, label=图8, caption=冻土敏感性分析柱状图, figureFileSmall=69XML0axDv4oZL/bv1zQ1w==, figureFileBig=12prnWzI4WhL3wsC1+2bHw==, tableContent=null), ArticleFig(id=1175040323484009241, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, language=EN, label=null, caption=null, figureFileSmall=uX2Nz40op2B1hOqj8SlcFg==, figureFileBig=YNd8bJOqc/XeRz3nespyOA==, tableContent=null), ArticleFig(id=1175040323538535194, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, language=CN, label=图9, caption=SHAP分析融土敏感性概要图, figureFileSmall=uX2Nz40op2B1hOqj8SlcFg==, figureFileBig=YNd8bJOqc/XeRz3nespyOA==, tableContent=null), ArticleFig(id=1175040323597255451, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, language=EN, label=null, caption=null, figureFileSmall=9Q3LMgLKcxS47P+94goGFQ==, figureFileBig=QVkz1Yo9fQCe7r/D5ztt/w==, tableContent=null), ArticleFig(id=1175040323660170012, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, language=CN, label=图10, caption=SHAP分析冻土敏感性概要图, figureFileSmall=9Q3LMgLKcxS47P+94goGFQ==, figureFileBig=QVkz1Yo9fQCe7r/D5ztt/w==, tableContent=null), ArticleFig(id=1175040323748250397, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, language=EN, label=null, caption=null, figureFileSmall=null, figureFileBig=null, tableContent=
土质 干密度/
(kg·m-3)
含水率/% 容积热容量/
(kJ· m-3·℃-1)
导热系数/
[W·(m·℃)-1]
导温系数/
(m2·h-1)
ρd ω Cu Cf λu λf αu×103 αf×103
草炭粉质黏土 400 30 903.3 710.9 0.13 0.13 0.50 0.62
草炭粉质黏土 400 50 1 237.9 878.2 0.19 0.22 0.52 0.92
草炭粉质黏土 400 70 1 572.4 1 045.5 0.23 0.37 0.54 1.26
草炭粉质黏土 400 90 1 907.0 1 212.8 0.29 0.53 0.56 1.59
草炭粉质黏土 400 110 2 241.6 1 380.1 0.35 0.72 0.57 1.87
砾砂 1 800 6 1 818.9 1 543.2 1.71 2.27 3.27 5.31
砾砂 1 800 10 2 183.0 1 693.7 1.91 2.61 3.17 5.56
砾砂 1 800 14 2 484.1 1 844.3 2.09 2.85 3.02 5.58
砾砂 1 800 18 2 785.2 1 994.8 1.18 3.05 2.85 5.51
), ArticleFig(id=1175040323869885214, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, language=CN, label=表1, caption=

土体热物参数

, figureFileSmall=null, figureFileBig=null, tableContent=
土质 干密度/
(kg·m-3)
含水率/% 容积热容量/
(kJ· m-3·℃-1)
导热系数/
[W·(m·℃)-1]
导温系数/
(m2·h-1)
ρd ω Cu Cf λu λf αu×103 αf×103
草炭粉质黏土 400 30 903.3 710.9 0.13 0.13 0.50 0.62
草炭粉质黏土 400 50 1 237.9 878.2 0.19 0.22 0.52 0.92
草炭粉质黏土 400 70 1 572.4 1 045.5 0.23 0.37 0.54 1.26
草炭粉质黏土 400 90 1 907.0 1 212.8 0.29 0.53 0.56 1.59
草炭粉质黏土 400 110 2 241.6 1 380.1 0.35 0.72 0.57 1.87
砾砂 1 800 6 1 818.9 1 543.2 1.71 2.27 3.27 5.31
砾砂 1 800 10 2 183.0 1 693.7 1.91 2.61 3.17 5.56
砾砂 1 800 14 2 484.1 1 844.3 2.09 2.85 3.02 5.58
砾砂 1 800 18 2 785.2 1 994.8 1.18 3.05 2.85 5.51
), ArticleFig(id=1175040323957965599, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, language=EN, label=null, caption=null, figureFileSmall=null, figureFileBig=null, tableContent=
变量 Cf Cu λf λu αf αu
RMSE 57.4 214.3 0.3 0.1 4.6×10-4 3.3×10-4
R2 0.99 0.96 0.85 0.97 0.85 0.84
), ArticleFig(id=1175040324016685856, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, language=CN, label=表2, caption=

BP神经网络预测误差指标

, figureFileSmall=null, figureFileBig=null, tableContent=
变量 Cf Cu λf λu αf αu
RMSE 57.4 214.3 0.3 0.1 4.6×10-4 3.3×10-4
R2 0.99 0.96 0.85 0.97 0.85 0.84
), ArticleFig(id=1175040324100571937, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, language=EN, label=null, caption=null, figureFileSmall=null, figureFileBig=null, tableContent=
变量 Cf Cu λf λu αf αu
RMSE 22.70 42.81 0.05 0.06 1.6×10-4 5.3×10-5
R2 0.99 0.99 0.99 0.98 0.98 0.99
), ArticleFig(id=1175040324167680802, tenantId=1146029695717560320, journalId=1146123222451335185, articleId=1174390603526848678, language=CN, label=表3, caption=

贝叶斯神经网络预测误差

, figureFileSmall=null, figureFileBig=null, tableContent=
变量 Cf Cu λf λu αf αu
RMSE 22.70 42.81 0.05 0.06 1.6×10-4 5.3×10-5
R2 0.99 0.99 0.99 0.98 0.98 0.99
)], attaches=null, journal=Journal(id=1146119232468656133, delFlag=0, nameCn=科技和产业, nameEn=Science Technology and Industry, nameHistory1=null, nameHistory2=null, issn=1671-1807, eissn=, cn=11-4671/T, coden=null, periodic=3, 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=65omA9nasEwsJtKyya4q2A==, journalPrice=null, startedYear=null, abbrevIsoEn=Sci Technol Ind, journalRemark=null, publicationField=null, createdTime=null, updatedTime=1755589264235, createdBy=null, updatedBy=15831073675, firstLetterCn=S, firstLetterEn=S, subjectCode=Engineering, subjectName=工程, subjectCodeEn=Engineering, subjectNameEn=null, picCn=65omA9nasEwsJtKyya4q2A==, picEn=/wwFtLNQXxKpecNSjAf1AQ==, jcr=null, cjcr=null, exts=[JournalExt(id=1164589040427811221, language=CN, name=科技和产业, 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.kjhcy.org/kjycy/home, createdTime=1755589264256, updatedTime=1755589264256, createdBy=15831073675, updatedBy=15831073675, submissionGuidelinesUrl=http://www.kjhcy.org/kjycy/site/menu/20110121105642001, submissionAuthorUrl=http://www.kjhcy.org/kjycy/author/login, submissionEditorUrl=http://www.kjhcy.org/kjycy/editor/login, submissionReviewUrl=http://www.kjhcy.org/kjycy/user/login, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1164589040473948566, language=EN, name=Science Technology and Industry, 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.kjhcy.org/kjycy/home, createdTime=1755589264267, updatedTime=1755589264267, createdBy=15831073675, updatedBy=15831073675, submissionGuidelinesUrl=, submissionAuthorUrl=http://www.kjhcy.org/kjycy/author/login, submissionEditorUrl=http://www.kjhcy.org/kjycy/editor/login, submissionReviewUrl=http://www.kjhcy.org/kjycy/user/login, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1146123222451335185, websiteList=[Website(id=1148243202395595182, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146123222451335185, 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/kjhcy/CN, language=CN, createTime=1751692112778, createBy=18614031015, updateTime=1753522130587, updateBy=18614031015, name=科技和产业-中文站点, tplId=1146099689490845704, title=科技和产业, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1155919343281103033, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202395595182, code=articleTextType, value=kx, createTime=1753522247381, updateTime=1753522247381, creator=18614031015, updator=18614031015), WebsiteProps(id=1155919343260131510, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202395595182, code=banner, value=null, createTime=1753522247376, updateTime=1753522247376, creator=18614031015, updator=18614031015), WebsiteProps(id=1155919343251742901, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202395595182, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=NeDGaoVSnAwTO5bjjrifjg==, createTime=1753522247374, updateTime=1753522247374, creator=18614031015, updator=18614031015), WebsiteProps(id=1155919343272714424, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202395595182, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1753522247379, updateTime=1753522247379, creator=18614031015, updator=18614031015), WebsiteProps(id=1155919343268520119, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202395595182, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1753522247378, updateTime=1753522247378, creator=18614031015, updator=18614031015)]), Website(id=1155919131955314719, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146123222451335185, 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/kjhcy/EN, language=EN, createTime=1753522197002, createBy=18614031015, updateTime=1753522207756, updateBy=18614031015, name=科技和产业-英文站点, tplId=1146101810881728533, title=Science Technology and Industry, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1155919498877194448, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155919131955314719, code=articleTextType, value=kx, createTime=1753522284478, updateTime=1753522284478, creator=18614031015, updator=18614031015), WebsiteProps(id=1155919498860417229, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155919131955314719, code=banner, value=null, createTime=1753522284474, updateTime=1753522284474, creator=18614031015, updator=18614031015), WebsiteProps(id=1155919498852028620, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155919131955314719, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=NeDGaoVSnAwTO5bjjrifjg==, createTime=1753522284472, updateTime=1753522284472, creator=18614031015, updator=18614031015), WebsiteProps(id=1155919498873000143, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155919131955314719, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1753522284477, updateTime=1753522284477, creator=18614031015, updator=18614031015), WebsiteProps(id=1155919498864611534, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155919131955314719, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1753522284476, updateTime=1753522284476, creator=18614031015, updator=18614031015)])], journalTitle=科技和产业, weixinUrl=null, journalUrl=null, iacademicId=null, status=0, seqNo=null, journalTitleEn=Science Technology and Industry, journalPhotoCn=65omA9nasEwsJtKyya4q2A==, journalPhotoEn=/wwFtLNQXxKpecNSjAf1AQ==, 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=, provinceCode=null, provinceName=null, collectFlag=false), detailUrlCn=https://castjournals.cast.org.cn/joweb/kjhcy/CN/Y2025/V25/I14/55, detailUrlEn=https://castjournals.cast.org.cn/joweb/kjhcy/EN/Y2025/V25/I14/55, pdfUrlCn=https://castjournals.cast.org.cn/joweb/kjhcy/CN/PDF/Y2025/V25/I14/55, pdfUrlEn=https://castjournals.cast.org.cn/joweb/kjhcy/EN/PDF/Y2025/V25/I14/55, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
岩土热物参数贝叶斯神经网络预测及敏感性分析
收藏切换
PDF下载
姚兆明 1, 2 , 王晓龙 1, 2 , 王洵 1, 2 , 魏航 1, 2 , 李鹏辉 3 , 方庆 4
科技和产业 | 科技创新 2025,25(14): 55-63
收起
收藏切换
科技和产业 | 科技创新 2025, 25(14): 55-63
岩土热物参数贝叶斯神经网络预测及敏感性分析
全屏
姚兆明1, 2, 王晓龙1, 2, 王洵1, 2, 魏航1, 2, 李鹏辉3, 方庆4
作者信息
  • 1 安徽理工大学土木建筑学院, 安徽 淮南 232001
  • 2 矿山地下工程教育部工程研究中心, 安徽 淮南 232001
  • 3 山东省第一地质矿产勘查院, 济南 250000
  • 4 江苏省地质局第一地质大队, 南京 210042
  • 姚兆明(1975—),男,安徽黄山人,博士,教授,研究方向为土体本构理论和岩土数值分析;

    王晓龙(2001—),男,安徽芜湖人,硕士研究生,研究方向为人工智能在岩土工程中的应用;

    王洵(2000—),男,安徽黄山人,硕士研究生,研究方向为人工智能在岩土工程中的应用;

    魏航(2001—),男,安徽淮南人,硕士研究生,研究方向为寒区岩土流变理论;

    李鹏辉(1989—),男,宁夏隆德人,高级工程师,研究方向为地质调查与矿产勘查;

    方庆(1987—),男,江西湖口人,硕士,高级工程师,研究方向为岩土工程设计与施工。

Neural Network Prediction and Sensitivity Analysis of Geotechnical Thermophysical Parameters
Zhaoming YAO1, 2, Xiaolong WANG1, 2, Xun WANG1, 2, Hang WEI1, 2, Penghui LI3, Qin FANG4
Affiliations
  • 1 College of Civil Engineering, Anhui University of Science and Technology, Huainan 232001, Anhui, China
  • 2 Engineering Research Cener of Underground Mine Construction, Ministry of Education, Huainan 232001, Anhui, China
  • 3 Geological team of Shandong Provincial Bureau of Geology and Mineral Resources, Jinan 250000, China
  • 4 The First Geological Brigade of Jiangsu Geological Bureau, Nanjing 210042, China
出版时间: 2025-07-25
文章导航
收藏切换

随着寒区工程的开发,准确得出岩土在冻融状态下的热物参数具有重要意义。鉴于常用BP神经网络预测热物参数误差较大,以120组冻土、融土热物参数为样本,采用贝叶斯正则化方法对预测模型进行改进,建立多输入多输出的BP神经网络,模型的预测精度明显提高。用改进蒙特卡洛法和SHAP解释分别对贝叶斯神经网络和随机森林模型进行敏感性分析。结果表明,冻融状态不改变影响因素的敏感性排序。容积热容量和导热系数在冻融状态下,对含水率、干密度、土质的敏感程度依次降低,导温系数对土质、含水率、干密度的敏感程度依次降低。

热物参数  /  BP神经网络  /  贝叶斯正则化  /  蒙特卡洛  /  SHAP

With the development of engineering in cold regions, it is important to accurately derive the thermoplastic parameters of soils under freeze-thaw conditions. In view of the large error of the commonly used BP neural network to predict the thermal property parameters, 120 sets of thermal property parameters of frozen and thawed soil were used as samples, and the prediction model was improved by Bayesian regularization method to establish a multi-input and multi-output BP neural network, and the prediction accuracy of the model was significantly improved. Sensitivity analyses of the Bayesian neural network and random forest model were carried out with the improved Monte Carlo method and SHAP interpretation, respectively. The results show that the freeze-thaw condition does not change the sensitivity ranking of the influencing factors. The sensitivity of volumetric heat capacity and thermal conductivity to water content, dry density, and soil quality decreases in the order of freezing and thawing state, and the sensitivity of thermal conductivity to soil quality, water content and dry density decreases in the order of soil quality, water content and dry density.

thermal parameter  /  BP neural network  /  Bayesian regularization  /  Monte Carlo  /  SHAP
姚兆明, 王晓龙, 王洵, 魏航, 李鹏辉, 方庆. 岩土热物参数贝叶斯神经网络预测及敏感性分析. 科技和产业, 2025 , 25 (14) : 55 -63 .
Zhaoming YAO, Xiaolong WANG, Xun WANG, Hang WEI, Penghui LI, Qin FANG. Neural Network Prediction and Sensitivity Analysis of Geotechnical Thermophysical Parameters[J]. Science Technology and Industry, 2025 , 25 (14) : 55 -63 .
在全球变暖等诸多背景下,地热能作为一种可再生的清洁能源,在我国有着巨大的发展潜力。近年来,我国寒区的地热资源也在不断开发利用。准确得出土体在冻融状态下的热物参数,对寒区地热资源的开发有着重要意义。在热传递计算中,容积热容量、导热系数以及导温系数,是岩土三种重要的热学指标。根据现有的相关研究表明,土质、含水率、干密度对土体的热物参数影响最大。目前土体热物参数的研究方法以理论计算和实验研究为主。姚兆明等[1]利用有限元数值模拟软件对冻土温度场进行数值模拟,进而反分析求解冻土的导热系数,得出的结果可用于实际工程。Li等[2]使用有限元软件模拟土体的微观结构,并基于孔隙率和土颗粒成分建立导热系数广义计算模型。得出的计算结果精度较高且优于几何平均模型和Johansen模型。金宗川等[3]采取广东湛江某工地的黏土进行试验,发现含水率增大到20%时,导热系数达到最大值,继续增大含水率导热系数会减小;含水率对黏土容积热容量影响程度较大;随着含水率升高,导温系数先增大后减小。李文岚婷和苏顺玉[4]考虑到土体弯曲的特点,将弯曲度引入导热系数计算公式,用分形理论建立新的计算模型。结果表明模型对土体孔隙率为0.2~1的导热系数计算效果最好,饱和度、孔隙率对导热系数的影响规律也与目前的研究结果相同。
随着人工智能技术的发展,越来越多的学者使用机器学习对土体导热系数进行预测。王红旗等[5]以含水率、干密度、龄期为输入,搭建反向神经传播网络(backpropagation neural network,BP)对石灰改良的红黏土导热系数进行预测,预测结果比传统经验模型的计算结果精度更高。姚兆明等[6]使用随机森林、径向基函数神经网络(radial basis function neural network,RBFNN)、鲸鱼优化算法优化的BP神经网络(whale optimization algorithm-backpro-pagation neural network,WOA-BP)三种不同的机器学习模型对土体导热系数进行预测,预测结果最好的是WOA-BP,随机森林其次,RBFNN预测效果较差。
岩土热物参数的相关研究成果较为丰富,但大部分的经验公式和机器学习模型仅在某一特定土质上有较好的表现,普适性较差。在高温或低温的特殊环境下,由于含水率、干密度、相变潜热等因素,岩土热物参数会发生较大程度的改变,对工程中热传递的计算造成影响。目前,现场由于设备受限等一系列问题,通过实验室测定得出寒区的岩土热物参数较为困难,且国内外缺乏岩土在冻结状态下热物参数数据集和计算模型[7-8]。本文通过构建神经网络预测模型,以主要影响因素作为输入变量,将四种不同土质在冻融状态下的容积热容量、导热系数以及导温系数作为输出变量,得到可以同时预测冻土和融土的热物参数模型。最后对热物参数进行敏感性分析,分析冻土和融土状态下,热物参数对主要影响因素的敏感程度。
本文所使用的数据集样本来源于现行规范[9],由中科院兰州冰川冻土研究所对西藏、内蒙古等地区的草碳粉质黏土、粉土、碎石亚黏土、砾砂四种土进行实验室测定,得出不同条件下的土体热物参数共计120组。中国寒区多为规范[9]所述的四种土质,因此得出实验结果在国内具有较强的普适性。
由于篇幅原因,表1列出了本文使用的部分数据样本。Cλα分别为容积热容、导热系数、导温系数,u为融土,f为冻土。
导热系数是反映土体传热能力大小的热学指标。现有研究均表明含水率和干密度是土体导热系数主要两种影响因素。姚兆明等[6]使用智能等方法对影响土体导热系数的敏感性因素进行分析,得出的结果均为含水率对导热系数的影响因素最大,干密度其次。根据本文所使用的数据集样本,绘制草炭粉质黏土在干密度为400 kg/m3时,含水率为30%~130%时,在冻融状态下的导热系数散点图(图1)。
图1可知,含水率对于土体导热系数影响较大,整体趋势为正相关。在保持干密度不变的前提下,随着含水率的不断增大,冻土的导热系数明显大于融土的导热系数。这是因为当土体中部分水分结冰,土体含冰量不断增大,而冰的导热系数约为水的4倍左右,导致土体导热系数迅速增大。
根据数据集样本,选择含水率为30%,干密度为400~900 kg/m3的草炭亚粉质黏土,绘制导热系数随干密度变化散点图(图2)。
图2可知,干密度对导热系数同样有着不可忽视的影响,两者变化在整体上呈现正相关,可以近似为线性关系。主要原因是由于干密度的增加,使土体的孔隙率减小,土体颗粒增多且相互之间的接触面积增大。土颗粒的导热系数远远大于气相充填物的导热系数,故干密度的增大导致导热系数增大。随着干密度的增加,冻土的导热系数和融土的导热系数变化速率总体相近,冻土的导热系数略大于融土的导热系数。
温度同样是影响土体导热系数的因素之一。但徐学祖等[10]表明,当土处于冻结状态时,若温度继续降低,导热系数增率很小;温度下降1 ℃,其导热系数变化小于5%。因此,在实际工程计算中,仅需考虑土的冻融状态即可,可忽视温度改变带来的导热系数变化。
导温系数,也叫热扩散系数,在研究非稳态传热、温度场的变化速率中,具有重要的意义。与导热系数相同,土体的含水率和干密度同样是对导温系数影响最大的两个因素,且变化规律也相同,此处不再进行赘述。
容积热容量表示了土体的蓄热能力,物理意义为单位体积的土体温度在上升或下降1 ℃时,所需要吸放的热量,单位为kJ/(m3·℃)。对于冻土和融土的容积热容量计算公式如下。
Cu=Cduρu
Cf=Cdfρf
式中:C为容积热容量,kJ/(m3·℃);Cd为比热,kJ/(kg·℃);ρ为天然容重,kg/m3;u为融土;f为冻土。比热的物理意义表示单位质量的土体,温度改变1 ℃时所需要吸放的热量。由于土是多相介质,在忽略掉土中的气相介质的比热后,将土骨架、水等介质的比热通过加权平均的方法,得到冻融土比热的计算公式[5]
Cdu= $\frac{{C}_{su}+W{C}_{w}}{1+W}$
Cdf= $\frac{{C}_{sf}+(W-{W}_{u}){C}_{i}+{W}_{u}{C}_{w}}{1+W}$
式中:Csu为融土骨架;Csf为冻土骨架;Cw为水的比热;Ci为冰的比热;W为含水率;Wu为冻土中的未冻水含量。
根据式(3)和式(4)可以看出,融土的容积热容量与干密度、含水率呈直线关系;冻土的容积热容量与干密度为直线关系。
目前人工智能发展迅速,在岩土工程领域中也得到了广泛的运用。人工神经网络(ANN)是一种在人脑的结构功能基础之上,进行抽象、简化和模拟,得到的高度复杂的网络系统。 利用神经网络强大的学习能力,可以得到许多复杂问题之间的非线性映射关系,从而找到问题的优化解。根据上文的分析,将土质、干密度、含水率这三种因素作为输入变量,将土体的热物参数作为输出变量。
采用常规的多输入单输出的BP神经网络,对冻土和融土的热物参数分别进行预测。对于网络参数的选取,依据经验确定输入节点数为3,隐藏层节点数为5,输出层节点为1,采用sigmod函数作为隐藏层的激活函数、purelin函数作为输出层的激活函数。最后用均方根误差RMSE作为预测结果好坏的评判标准,RMSE的计算公式为
RMSE= $\sqrt{\frac{1}{n}\sum _{i=1}^{n}({y}_{i}-y)}$
式中:yi为预测值;y为实际值;n为样本数量。
表1中的120个数据随机划分成100个训练样本,20个测试样本,并将训练好的结果绘制成散点图进行对比,得到预测结果。
图3图4为BP神经网络对土体热物参数的预测效果图,表2为BP神经网络预测结果的误差指标。将预测值和实测值进行线性拟合,若拟合出的直线方程越接近于等值线方程Y=X,说明预测值越接近于实测值,模型预测效果越好。同时计算预测值和实测值的相关系数R2、测试集数据的RMSE等指标,对模型预测能力进行综合评估。
可以看出,BP神经网络对冻融土的容积热容量有不错的拟合效果,两组数据的相关系数R2与1接近,但两组数据的评价指标RMSE相差较大。原因是融土的测试集RMSE与训练集的RMSE=68.84相差也较大,即训练过程中产生了过拟合现象。
BP神经网络对导热系数预测效果一般,冻土的导热系数的相关系数R2=0.85或1存在一定的偏差。虽然拟合曲线较接近于等值线Y=X,但是存在部分样本的预测值与实际值差距过大的现象。
BP网络对导温系数的预测效果较差,两组数据的拟合直线方程与等值线Y=X偏差大,相关系数R2也不接近1,并且存在较多的样本数据,它们的预测数据与实际值存在很大的误差。基于上述分析,BP神经网络对冻融土的热物参数总体预测效果差,对容积热容量的预测效果较好,导热系数其次,导温系数预测效果较差,这样的预测效果难以在工程上得以应用。根据对每组的样本训练集和测试集对比,发现BP网络在训练集上的训练效果较好,故造成预测效果不理想的主要原因是产生了过拟合现象。
过拟合现象是BP网络中容易出现的问题,这与BP网络的算法原理和网络结构有关。对于网络参数的选取,如学习率等,目前没有一种明确的方法进行确定,大部分是依靠经验进行选定。但这些参数的选取对结果的预测有很大影响,这会导致预测结果不稳定。BP网络的算法原理是梯度下降,这会使网络在找到某一最小值后就停止训练,导致陷入局部最优和过拟合现象。因此,要想获得预测精度更高的结果,还需要加入优化算法进行改进。
过拟合问题在神经网络种是一种常见的问题,解决过拟合问题的方法也有很多。根据上文的分析,预测模型产生了局部最优的现象。一般的BP网络采用的算法是LM算法,这种算法的原理是梯度下降法,这种算法在实际应用中通常找到的是局部最小值,而不是全局最小值,这是导致局部最优和过拟合现象的原因。所以选用正则化方法对模型进行改进。
正则化分为L1正则化和L2正则化,具体的计算公式为
L1正则化:Eω= $\sum _{i=1}^{n}\left|{\omega }_{i}\right|$
L2正则化:Eω= $\sum _{i=1}^{n}\left|{\omega }_{i}^{2}\right|$
式中:ω为网络权值。
这种方法的原理是通过修改了网络训练性能的函数来提高模型的泛化能力。在神经网络中,采用损失函数f(ω)来定义模型的训练性能。对于BP神经网络,使用最多的损失函数为MSE,其计算公式为
MSE= $\sum _{i=1}^{n}$(yi-y)2
式中:yi为预测值;y为实际值。
当采用正则化的BP神经网络后,损失函数f(ω)变为
f(ω)=αMSE+βEω
式中:α,β为超参数;Eω为正则化项。
然而,对于超参数αβ的选取却是十分困难的,如果α>β,则依然会造成过拟合的现象;但如果α<β,则会导致网络偏重于使模型的输出更加平滑,而忽视了模型的预测准确性。贝叶斯正则化将超参数αβ视为随机变量,根据权值的概率密度确定权值函数,主要目的是为αβ寻找最优的值,在有限的数据条件下获得最优的训练结果[11-13]。王才进等[14]建立了基于贝叶斯正则化的人工神经网络,对土体的导热系数进行预测,得出较好的预测结果。
对上文的BP网络进行改进。为了防止过拟合现象,提高预测精度,采用基于贝叶斯正则化算法的BP神经网络。同时,在实际工程中,土体的这三种热学指标在传热过程和温度场分析中,作为必需的计算参数具有重要意义。故将原先的单输出BP神经网络改为多输出的神经网络,以土质、含水率、干密度三种作为输入;容积热容量、导热系数、导温系数作为输出,建立基于贝叶斯正则化的多输出BP神经网络模型,可以同时输出土体冻融状态下的三种热物参数。经过机器学习后,将预测值和实测值进行线性拟合,并分析预测效果。
图5图6为贝叶斯网络对岩土在冻融状态下的热物参数预测效果图。六组预测数据的相关系数R2均在0.98~0.99,有着很强的相关性(表3)。每个样本的预测值与实际值较为接近,尤其是对于冻融土的导温系数预测,相较于一般的BP神经网络,预测精度明显提高。过拟合问题经过正则化后也得到了明显的改善,从图中可以看出,该模型的预测结果并没有陷入局部最优而导致部分预测值与实测值误差较大的现象。
由前文可知,含水率、干密度、土质等影响因素对于土体热物参数有着不同程度的影响,甚至同一土体在含水率和干密度相同的情况下,其冻融状态的热物参数都有着较大的差异。然而工程中,由于环境的随时变化等一些不可控的因素,土体的热物参数会在一定范围内发生变化,这可能会导致一定的误差。因此,若想更好地在实际中准确得到土体热物参数以及了解它们的变化规律,还需要对这些影响的因素做敏感性分析,得出影响较大的影响因素,在实际工程中可加以控制。
国内外学者对土体热物参数的研究重点在于如何更加精确地得到热物参数的具体数值,而忽视了热物参数对这些影响因素的敏感程度,得出的公式和模型并不具有普适性。所以,开展敏感性分析的工作是具有一定意义。
利用蒙特卡洛模拟对影响因素的敏感性进行分析,是一种常用的敏感性分析方法。其原理是利用概率论和统计学的基本理论,通过随机抽样来模拟不确定性的影响,并通过统计分析来评估不同影响因素对预测结果的影响[15]。蒙特卡洛模拟是一种统计技术,通过从概率分布中抽取大量样本,来模拟复杂系统的行为。
扰动分析法是一种输入—输出变量分析方法,在神经网络的敏感性分析中应用也较为广泛。方法原理是在网络的某一个输入加上一个微小的扰动,观察扰动后的输出结果。敏感性占比高的影响因素,经过微小扰动必定会对输出产生较大影响。但是这种方法的缺点在于无法观察到输入变量整体变化对输出的影响,只能对模型进行局部敏感性分析。因此,要对模型进行整体敏感性分析,还需要进行改进。
姚兆明等[6]利用改进的经验公式作为蒙特卡洛模拟的输入数学模型,对土体的导热系数进行敏感性进行分析。但是并未以其建立的神经网络预测模型为基础进行分析。没有模型支持的敏感性分析可能缺乏实时性和灵活性,难以应对快速变化的环境和条件。
以第三节建立的基于贝叶斯正则化的多输出BP神经网络为基础,采取将蒙特卡洛法和扰动法结合起来的方法对岩土冻融状态下的热物参数进行敏感性分析。首先使用蒙特卡洛模拟来生成大量的输入样本,然后对这些生成的输入样本进行微小扰动,以此评估输入参数的敏感性。这种改进的方法可以在大量的输入样本上进行敏感性分析,保证了模型全局敏感性分析的结果更加可靠。将蒙特卡洛法得出的敏感性占比绘制成柱状图进行分析,如图7图8所示。
图7图8清楚地展示了土质、含水率、干密度三种影响因素对土体热物参数的影响占比,证明了土体的冻融状态对热物参数的影响因素敏感性有一定的影响。以导热系数和容积热容量为例,在冻融状态下,热物参数对影响因素的敏感程度均为含水率、干密度、土质依次递减,但三种影响因素的敏感性占比发生了一定程度的变化。导温系数的敏感性占比基本保持不变,说明冻融状态、含水率、干密度等外部影响因素对导温系数的影响较小。土质是影响导温系数最大的影响因素,不同的土质类型之间导温系数有着较大的差别。
结合图7图8,对冻土和融土的热物参影响因素进行敏感性排序,得出的结论为土体的冻融状态影响敏感性占比,但并未影响敏感性排序;导温系数受到土体冻融状态的影响很小。容积热容量和导热系数的敏感性程度均为含水率>干密度>土质,而导温系数为土质>含水率>干密度。得出的结论也与目前一些关于热物参数的研究符合。
近年来,机器学习开始逐渐走向“可解释化”。SHAP(Shapely)值法是一个非常好的可解释方法,它可以解释任何机器学习的输出。SHAP值法来源于博弈论,用于衡量特征对因变量的影响程度。该方法的核心思想是计算模型中某一个特征对该模型的边际贡献,然后考虑到该特征在所有的特征序列的情况下不同的边际贡献,最后取平均值得到此特征在模型的SHAP值[16-17]。当每一个特征的SHAP值计算出来以后,将它们进行相加得出模型的最终预测值,数学表达式为
yi=ybase+ $\sum _{j=1}^{n}$f(xij)
式中:i为模型的第i个样本;n为第i个样本中共有n个特征;xij为第i个样本的第j个特征;f(xij)为第j个特征的SHAP值。
根据公式可以得出:某种特征的SHAP值越大,则该特征对输出的影响越大。除此之外,若得出的SHAP>0,即对模型的预测值进行了提升,起到了正向作用。反之,则起到了反向作用。这也是SHAP值法在计算特征重要性方面优越于其他算法的原因之一。利用SHAP值法得出每个影响因素对输出的贡献度,就能更加准确地对机器学习的过程进行解释。
为了验证改进蒙特卡洛法的敏感性分析结果,建立一个随机森林的预测模型,对冻融土体的三种热物参数分别进行预测,然后利用SHAP值法对随机森林模型的学习过程进行可视化,得出含水率、干密度、土质三种影响因素的贡献度后,并与上文得出的结论进行对比,观察两种模型使用不同的敏感性分析方法能否得出一致的结论,计算得到的SHAP值如图8图9所示。
随机森林是一种集成学习算法,这种算法是由决策树算法演变而成,在回归和分类问题上应用广泛[18]。决策树是一种强大的分类器,这种算法在遵循一定的规则下,将众多杂乱的数据转换成可以预测未知数据的树模型,从根节点到叶子节点的路径则代表了决策的路径。Leo[19]在决策树的基础上提出随机化决策树的方法,最后又提出了随机森林算法。随机森林由多颗决策树构成,但是每颗决策树是由随机子集的数据构成,通过投票和取平均的方法得出最后的预测结果。相较于决策树算法,随机森林的模型泛化能力和鲁棒性明显提高。
图9图10为利用SHAP值对随机森林模型的学习过程进行全局解释概要图。图中每个点都代表一个样本,横坐标为SHAP值,纵坐标为模型中的所有特征,并依据SHAP值从大到小的顺序依次从上往下进行了排序,故对输出影响最大的特征位于图中的顶部。图中的红蓝色表示了样本特征值的高低,红色样本代表着样本特征值较高,蓝色即代表着样本的特征值低。以融土的容积热容量为例,含水率是其最敏感的影响因素,红色样本点的SHAP值几乎均大于0,这表示随着含水率的提高,容积热容量越大,对模型的预测起到正向作用;蓝色样本点说明大部分低含水率的样本对预测起到负向作用,仅有少部分起到正向预测的效果。而土质是最低的影响因素,对模型的正向或负向预测并没有起到决定性的作用。
根据SHAP值概要图,得出结论为冻融状态没有改变影响因素的敏感性排序,容积热容量和导热系数对含水率、干密度、土质的敏感程度依次递减,导温系数对土质、含水率、干密度的敏感程度依次递减。
本文使用普通的BP神经网络和经过贝叶斯正则化的多输出BP网络,对冻融土的热物参数进行预测,随后用改进蒙特卡洛法和SHAP值法分别对多输出BP网络和随机森林两种预测模型进行敏感性分析,得出如下结论。
(1)普通的BP神经网络对热物参数整体预测效果差,预测过程中产生过拟合和局部最优现象。
(2)贝叶斯正则化解决BP神经网络的过拟合和陷入局部最优的现象,对热物参数预测效果明显提升,有着较高的预测精度。
(3)采用改进蒙特卡洛法对贝叶斯正则化神经网络模型进行冻融状态下的敏感性分析,容积热容量和导热系数的敏感程度均为含水率>干密度>土质,导温系数为土质>含水率>干密度。
(4)采用SHAP值法对随机森林模型做敏感性分析,得出的结论与改进蒙特卡洛法对贝叶斯神经网络敏感性分析一致。土体的冻融状态不改变影响因素的敏感性排序。
  • 矿山地下工程教育部工程研究中心开放研究项目(JYBGCZX2021104)
参考文献 引证文献
排序方式:
[1]
姚兆明, 潘旋, 张秋瑾. 人工冻土温度场模型试验及冻土导热系数反分析[J]. 科学技术与工程, 2019, 19(24): 352-358.
[2]
LI K Q, LI D Q, CHEN D H, et al. A generalized model for effective thermal conductivity of soils considering porosity and mineral composition[J]. Acta Geotechnica, 2021, 16: 3455-3466.
[3]
金宗川, 王雪晴, 乌效鸣, 等. 土壤热参数及其影响因素测试分析[J]. 岩土力学, 2022, 43(5): 1335-1340.
[4]
李文岚婷, 苏顺玉. 三相土壤分形导热系数模型[J]. 科学技术与工程, 2024, 24(7): 2724-2733.
[5]
王红旗, 李栋伟, 钟石明, 等. 石灰改良红黏土导热系数影响因素及模型预测[J]. 科学技术与工程, 2023, 23(5): 2084-2092.
[6]
姚兆明, 王洵, 齐健. 土体导热系数智能方法预测及影响因素敏感性分析[J]. 工程热物理学报, 2024, 45(5): 1440-1449.
[7]
REN X L. Research progress of soil thermal conductivity and its predictive models[J]. Cold Regions Science and Technology, 2024, 217: 104027.
[8]
徐拴海, 沈浩. 岩石导热系数影响因素及预测研究综述[J]. 科学技术与工程, 2022, 22(16): 6369-6376.
[9]
中华人民共和国住房和城乡建设部. GB 50324-2014冻土工程地质勘查规范[S]. 北京: 中国计划出版社, 2014.
[10]
徐学祖, 王家澄, 张立新. 冻土物理学[M]. 北京: 科学出版社, 2010.
[11]
隋旭鹏, 朱圣辉, 王少伟, 等. 贝叶斯正则化对混凝土坝位移机器学习模型性能的提升[J]. 水电能源科学, 2022, 40(9): 120-124.
[12]
KARIMOVA D, LEENDERS R T A J, MEIJERINK-BOSMAN M, et al. Separating the Wheat from the chaff: Bayesian regularization in dynamic social networks[J]. Social Networks, 2023, 74: 139-155.
[13]
LIU Q Y, KIM S. Temperature-field-angle dependent critical current estimation of commercial second generation high temperature superconducting conductor using double hidden layer Bayesian regularized neural network[J]. Superconductor Science Technology, 2022, 35(3): 035001.
[14]
王才进, 蔡国军, 武猛, 等. 基于人工智能算法预测土体导热系数[J]. 岩土工程报, 2022, 44(10): 1899-1907.
[15]
SOIZE C. Stochastic models of uncertainties in computational mechanics[M]. Reston VA: American Society of Civil Engineers, 2012.
[16]
W, JIA J, CHEN X, et al. Predicting shear strength in UHPC beams through an innovative neural network with SHAP interpretation[J]. Case Studies in Construction Materials, 2024, 20: e03211.
[17]
刘廷滨, 黄滔, 欧嘉祥, 等. 基于ANN和XGB算法的锈蚀钢筋混凝土高温黏结强度预测方法[J]. 工程力学, 2024, 41(S1): 300-309.
[18]
WANG Y A, XIA S T, TANG Q T, et al. A novel consist ent ran-dom forest framework: bernoulli random forests[J]. IEEE Transactions on Neural Networks and Learning Systems, 2017, 29(8): 3510-3523.
[19]
LEO B. Random forest[J]. Machine Learning, 2001, 45: 5-32.
2025年第25卷第14期
PDF下载
288
154
引用本文
BibTeX
文章信息
  • 接收时间:2025-01-06
  • 首发时间:2025-09-15
  • 出版时间:2025-07-25
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2025-01-06
基金
矿山地下工程教育部工程研究中心开放研究项目(JYBGCZX2021104)
作者信息
    1 安徽理工大学土木建筑学院, 安徽 淮南 232001
    2 矿山地下工程教育部工程研究中心, 安徽 淮南 232001
    3 山东省第一地质矿产勘查院, 济南 250000
    4 江苏省地质局第一地质大队, 南京 210042
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/kjhcy/CN/1174390603526848678
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