Article(id=1156908302891312007, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1156908295593223005, articleNumber=null, orderNo=null, doi=10.12404/j.issn.1671-1815.2400502, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=research-article, receivedDate=1705420800000, receivedDateStr=2024-01-17, revisedDate=1727452800000, revisedDateStr=2024-09-28, acceptedDate=null, acceptedDateStr=null, onlineDate=1753758033725, onlineDateStr=2025-07-29, pubDate=1736265600000, pubDateStr=2025-01-08, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1753758033725, onlineIssueDateStr=2025-07-29, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1753758033725, creator=13701087609, updateTime=1753758033725, updator=13701087609, issue=Issue{id=1156908295593223005, tenantId=1146029695717560320, journalId=1146123166801305609, year='2025', volume='25', issue='1', pageStart='1', pageEnd='438', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=0, createTime=1753758031985, creator=13701087609, updateTime=1765425680602, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1205845960933049001, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1156908295593223005, language=EN, specialIssueTitle=, coverIllustrator=, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1205845960933049002, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1156908295593223005, language=CN, specialIssueTitle=, coverIllustrator=, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=339, endPage=345, ext={EN=ArticleExt(id=1156908303688229771, articleId=1156908302891312007, tenantId=1146029695717560320, journalId=1146123166801305609, language=EN, title=Calibration Method for Mesoscopic Parameters of Hollow Cylindrical Sandstone Discrete Element Based on Machine Learning Algorithm, columnId=1156262735643005297, journalTitle=Science Technology and Engineering, columnName=Papers·Hydraulic Engineering, runingTitle=null, highlight=null, articleAbstract=

Primary cracks and new cracks develop within the engineering rock mass, leading to the formation of macroscopic cracks. The hollow cylindrical discrete element simulation test enables the emulation of complex stress paths. In order to solve the problems existing in the simulation test of hollow cylindrical discrete element, such as numerous influencing factors and lengthy meso-parameter calibration, a method of mesoscale parameter calibration of hollow cylindrical sandstone discrete element based on machine learning algorithm was proposed. Through variations in input variables within the discrete element model, 210 sets of simulation data were obtained. A mesoscopic parameter calibration model based on random forest algorithm and extreme gradient boosting(XGBoost) algorithm was established, the prediction accuracy of the model was compared, the parameter sensitivity was analyzed, and the contribution of input parameters to the overall mechanical properties of the rock was quantified. Combined with the indoor triaxial test of hollow cylinder, the calibration results show that the XGBoost algorithm has the advantages of computing speed, and can quickly locate the range of discrete element mesoscopic parameters, which provides a new idea for the calibration of discrete element mesoscopic parameters of hollow cylinder, and has the value of engineering application.

, correspAuthors=Jing-hong WU, 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=Hai-chao PAN, Jing-hong WU, Yue JIANG, Wen-dong ZOU), CN=ArticleExt(id=1156908400723452555, articleId=1156908302891312007, tenantId=1146029695717560320, journalId=1146123166801305609, language=CN, title=基于机器学习算法的空心圆柱砂岩离散元细观参数标定方法, columnId=1156262735810777459, journalTitle=科学技术与工程, columnName=论文·水利工程, runingTitle=null, highlight=null, articleAbstract=

工程岩体存在原生裂纹和新生裂纹最终形成宏观裂缝,空心圆柱离散元模拟试验可以实现复杂应力路径的模拟。对于空心圆柱离散元模拟试验中存在的问题,如细观参数标定的影响因素众多和耗时过长等,提出了一种基于机器学习算法的空心圆柱砂岩离散元细观参数标定方法。通过改变离散元模型中不同输入变量得到210组模拟数据,建立基于随机森林算法和极端梯度提升(extreme gradient boosting,XGBoost)算法的细观参数标定模型,对比了模型预测精度,分析了参数敏感性,量化了输入参数对岩石整体力学特性的贡献,据此给出了微观参数修正的建议取值。结合空心圆柱室内三轴试验,标定结果表明:XGBoost算法具有计算速度优势,可快速定位离散元细观参数范围,为空心圆柱的离散元细观参数标定提供了新思路,具有工程应用价值。

, correspAuthors=吴静红, authorNote=null, correspAuthorsNote=
* 吴静红(1989—),女,汉族,博士,副教授。研究方向:地质工程监测与评价。E-mail:
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=qVO5wzsaSSF3GIAf6PTYhA==, magXml=ofgBocVYVwADW2Z9V3TABw==, pdfUrl=null, pdf=yWjUC6OZ3/j3LrUxK7k/Qw==, pdfFileSize=7816435, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=zM8sn37rkHKr+4AJzk/Qlg==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=sd3aNiHiAA7bdEyevzmG9A==, mapNumber=null, authorCompany=null, fund=null, authors=

潘海潮(1997—),男,汉族,江苏徐州人,硕士研究生。研究方向:岩土测试与监测新技术及应用。E-mail:

, authorsList=潘海潮, 吴静红, 姜玥, 邹文栋)}, authors=[Author(id=1205908712414310948, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=2932875221@qq.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1205908712485614118, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, authorId=1205908712414310948, language=EN, stringName=Hai-chao PAN, firstName=Hai-chao, middleName=null, lastName=PAN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1. School of Civil Engineering, Suzhou University of Science and Technology, Suzhou 215011, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1205908712556917287, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, authorId=1205908712414310948, language=CN, stringName=潘海潮, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.苏州科技大学土木工程学院, 苏州 215011, bio={"content":"

潘海潮(1997—),男,汉族,江苏徐州人,硕士研究生。研究方向:岩土测试与监测新技术及应用。E-mail:

"}, bioImg=null, bioContent=

潘海潮(1997—),男,汉族,江苏徐州人,硕士研究生。研究方向:岩土测试与监测新技术及应用。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1205908712217178651, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, xref=null, ext=[AuthorCompanyExt(id=1205908712225567260, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, companyId=1205908712217178651, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1. School of Civil Engineering, Suzhou University of Science and Technology, Suzhou 215011, China), AuthorCompanyExt(id=1205908712229761565, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, companyId=1205908712217178651, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.苏州科技大学土木工程学院, 苏州 215011)])]), Author(id=1205908712632414761, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=wjh@mail.usts.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1205908712775021098, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, authorId=1205908712632414761, language=EN, stringName=Jing-hong WU, firstName=Jing-hong, middleName=null, lastName=WU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, *, address=1. School of Civil Engineering, Suzhou University of Science and Technology, Suzhou 215011, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1205908712837935660, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, authorId=1205908712632414761, language=CN, stringName=吴静红, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, *, address=1.苏州科技大学土木工程学院, 苏州 215011, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1205908712217178651, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, xref=null, ext=[AuthorCompanyExt(id=1205908712225567260, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, companyId=1205908712217178651, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1. School of Civil Engineering, Suzhou University of Science and Technology, Suzhou 215011, China), AuthorCompanyExt(id=1205908712229761565, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, companyId=1205908712217178651, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.苏州科技大学土木工程学院, 苏州 215011)])]), Author(id=1205908712930210349, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, 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=1205908713114759728, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, authorId=1205908712930210349, language=EN, stringName=Yue JIANG, firstName=Yue, middleName=null, lastName=JIANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1. School of Civil Engineering, Suzhou University of Science and Technology, Suzhou 215011, China
2. State Key Laboratory of Geomechanics and Geotechnical Engineering, Institute of Rock and Soil Mechanics,Chinese Academy of Sciences, Wuhan 430071, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1205908713228005937, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, authorId=1205908712930210349, language=CN, stringName=姜玥, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1.苏州科技大学土木工程学院, 苏州 215011
2.中国科学院武汉岩土力学研究所岩土力学与工程国家重点实验室, 武汉 430071, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1205908712217178651, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, xref=null, ext=[AuthorCompanyExt(id=1205908712225567260, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, companyId=1205908712217178651, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1. School of Civil Engineering, Suzhou University of Science and Technology, Suzhou 215011, China), AuthorCompanyExt(id=1205908712229761565, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, companyId=1205908712217178651, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.苏州科技大学土木工程学院, 苏州 215011)]), AuthorCompany(id=1205908712313647647, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, xref=null, ext=[AuthorCompanyExt(id=1205908712317841952, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, companyId=1205908712313647647, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2. State Key Laboratory of Geomechanics and Geotechnical Engineering, Institute of Rock and Soil Mechanics,Chinese Academy of Sciences, Wuhan 430071, China), AuthorCompanyExt(id=1205908712326230561, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, companyId=1205908712313647647, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.中国科学院武汉岩土力学研究所岩土力学与工程国家重点实验室, 武汉 430071)])]), Author(id=1205908713307697716, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, 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=1205908713416749624, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, authorId=1205908713307697716, language=EN, stringName=Wen-dong ZOU, firstName=Wen-dong, middleName=null, lastName=ZOU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1. School of Civil Engineering, Suzhou University of Science and Technology, Suzhou 215011, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1205908713525801530, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, authorId=1205908713307697716, language=CN, stringName=邹文栋, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.苏州科技大学土木工程学院, 苏州 215011, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1205908712217178651, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, xref=null, ext=[AuthorCompanyExt(id=1205908712225567260, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, companyId=1205908712217178651, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1. School of Civil Engineering, Suzhou University of Science and Technology, Suzhou 215011, China), AuthorCompanyExt(id=1205908712229761565, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, companyId=1205908712217178651, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.苏州科技大学土木工程学院, 苏州 215011)])])], keywords=[Keyword(id=1205908713672602174, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, language=EN, orderNo=1, keyword=machine learning), Keyword(id=1205908713739711041, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, language=EN, orderNo=2, keyword=discrete elements), Keyword(id=1205908713823597123, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, language=EN, orderNo=3, keyword=XGBoost), Keyword(id=1205908713928454725, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, language=EN, orderNo=4, keyword=mesotropic parameters), Keyword(id=1205908714133975624, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, language=EN, orderNo=5, keyword=hollow cylindrical sandstone), Keyword(id=1205908714213667402, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, language=CN, orderNo=1, keyword=机器学习), Keyword(id=1205908714297553484, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, language=CN, orderNo=2, keyword=离散元), Keyword(id=1205908714381439565, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, language=CN, orderNo=3, keyword=XGBoost), Keyword(id=1205908714444354126, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, language=CN, orderNo=4, keyword=细观参数), Keyword(id=1205908714515657295, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, language=CN, orderNo=5, keyword=空心圆柱砂岩)], refs=[Reference(id=1205908718143730328, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, doi=null, pmid=null, pmcid=null, year=2017, volume=14, issue=2, pageStart=1, pageEnd=14, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=Zheng Y F, Lo C M, Lin Q F, journalName=Landslides, refType=null, unstructuredReference=Zheng Y F, Lo C M, Lin Q F. The characteristics of the seismic signals induced by landslides using a coupling of discrete element and finite difference methods[J]. Landslides, 2017, 14(2): 1-14., articleTitle=The characteristics of the seismic signals induced by landslides using a coupling of discrete element and finite difference methods, refAbstract=null), Reference(id=1205908718210839194, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, doi=null, pmid=null, pmcid=null, year=2007, volume=44, issue=6, pageStart=871, pageEnd=889, url=null, language=null, rfNumber=[2], rfOrder=1, authorNames=Yoon J, journalName=International Journal of Rock Mechanics & Mining Sciences, refType=null, unstructuredReference=Yoon J. Application of experimental design and optimization to PFC model calibration in uniaxial compression simulation[J]. International Journal of Rock Mechanics & Mining Sciences, 2007, 44(6): 871-889., articleTitle=Application of experimental design and optimization to PFC model calibration in uniaxial compression simulation, refAbstract=null), Reference(id=1205908718282142366, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, doi=null, pmid=null, pmcid=null, year=2018, volume=20, issue=1, pageStart=11, pageEnd=null, url=null, language=null, rfNumber=[3], rfOrder=2, authorNames=Cheng H, Shuku T, Thoeni K, journalName=Granular Matter, refType=null, unstructuredReference=Cheng H, Shuku T, Thoeni K, et al. Probabilistic calibration of discrete element simulations using the sequential quasi-Monte Carlo filter[J]. Granular Matter, 2018, 20(1): 11., articleTitle=Probabilistic calibration of discrete element simulations using the sequential quasi-Monte Carlo filter, refAbstract=null), Reference(id=1205908718340862624, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, doi=null, pmid=null, pmcid=null, year=2019, volume=114, issue=null, pageStart=101, pageEnd=121, url=null, language=null, rfNumber=[4], rfOrder=3, authorNames=Yang S Q, Fei P, journalName=International Journal of Rock Mechanics and Mining Sciences, refType=null, unstructuredReference=Yang S Q, Fei P. Failure behavior and crack evolution mechanism of a non-persistent jointed rock mass containing a circular hole[J]. International Journal of Rock Mechanics and Mining Sciences, 2019, 114: 101-121., articleTitle=Failure behavior and crack evolution mechanism of a non-persistent jointed rock mass containing a circular hole, refAbstract=null), Reference(id=1205908718403777186, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, doi=null, pmid=null, pmcid=null, year=2019, volume=12, issue=22, pageStart=668, pageEnd=679, url=null, language=null, rfNumber=[5], rfOrder=4, authorNames=Liu W R, Liu J K, Zhu C, journalName=Arabian Journal of Geosciences, refType=null, unstructuredReference=Liu W R, Liu J K, Zhu C. Multi-scale effect of acoustic emission characteristics of 3D rock damage[J]. Arabian Journal of Geosciences, 2019, 12(22): 668-679., articleTitle=Multi-scale effect of acoustic emission characteristics of 3D rock damage, refAbstract=null), Reference(id=1205908718542189220, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, doi=null, pmid=null, pmcid=null, year=2023, volume=41, issue=8, pageStart=156, pageEnd=160, url=null, language=null, rfNumber=[6], rfOrder=5, authorNames=覃茜, 徐千军, journalName=水电能源, refType=null, unstructuredReference=覃茜, 徐千军. 基于离散元模拟的混凝土直剪试验细观参数研究[J]. 水电能源, 2023, 41(8): 156-160., articleTitle=基于离散元模拟的混凝土直剪试验细观参数研究, refAbstract=null), Reference(id=1205908718680601255, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, doi=null, pmid=null, pmcid=null, year=2023, volume=41, issue=8, pageStart=156, pageEnd=160, url=null, language=null, rfNumber=[6], rfOrder=6, authorNames=Qin Qian, Xu Qianjun, journalName=Hydropower Energy, refType=null, unstructuredReference=Qin Qian, Xu Qianjun. Mesoscopic parameters of concrete direct shear test based on discrete element simulation[J]. Hydropower Energy, 2023, 41(8): 156-160., articleTitle=Mesoscopic parameters of concrete direct shear test based on discrete element simulation, refAbstract=null), Reference(id=1205908718743515816, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, doi=null, pmid=null, pmcid=null, year=2024, volume=24, issue=10, pageStart=3984, pageEnd=3996, url=null, language=null, rfNumber=[7], rfOrder=7, authorNames=于小鸽, 王世超, 李岩, journalName=科学技术与工程, refType=null, unstructuredReference=于小鸽, 王世超, 李岩, 等. 泰安市蒸发量变化趋势分析与基于神经网络的预测[J]. 科学技术与工程, 2024, 24(10): 3984-3996., articleTitle=泰安市蒸发量变化趋势分析与基于神经网络的预测, refAbstract=null), Reference(id=1205908718793847465, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, doi=null, pmid=null, pmcid=null, year=2024, volume=24, issue=10, pageStart=3984, pageEnd=3996, url=null, language=null, rfNumber=[7], rfOrder=8, authorNames=Yu Xiaoge, Wang Shichao, Li Yan, journalName=Science Technology and Engineering, refType=null, unstructuredReference=Yu Xiaoge, Wang Shichao, Li Yan, et al. Analysis of evaporation trend and prediction based on neural network in Tai’an City[J]. Science Technology and Engineering, 2024, 24(10): 3984-3996., articleTitle=Analysis of evaporation trend and prediction based on neural network in Tai’an City, refAbstract=null), Reference(id=1205908718873539242, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, doi=null, pmid=null, pmcid=null, year=1998, volume=20, issue=8, pageStart=832, pageEnd=844, url=null, language=null, rfNumber=[8], rfOrder=9, authorNames=Ho T K, journalName=Trans on Pattern Analysis and Machine Intelligence, refType=null, unstructuredReference=Ho T K. The random subspace method for constructing decision forests[J]. Trans on Pattern Analysis and Machine Intelligence, 1998, 20(8): 832-844., articleTitle=The random subspace method for constructing decision forests, refAbstract=null), Reference(id=1205908718940648108, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, doi=null, pmid=null, pmcid=null, year=2001, volume=45, issue=1, pageStart=5, pageEnd=32, url=null, language=null, rfNumber=[9], rfOrder=10, authorNames=Breiman L, journalName=Machine Learning, refType=null, unstructuredReference=Breiman L. Random forests[J]. Machine Learning, 2001, 45(1): 5-32., articleTitle=Random forests, refAbstract=null), Reference(id=1205908718999368366, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, doi=null, pmid=null, pmcid=null, year=2016, volume=null, issue=null, pageStart=785, pageEnd=794, url=null, language=null, rfNumber=[10], rfOrder=11, authorNames=Chen T, Guestrin C, journalName=ACM SIGKDD International Conference on Knowledge Discovery and Data Mining ACM, refType=null, unstructuredReference=Chen T, Guestrin C. XGBoost: a scalable tree boosting system[C]// ACM SIGKDD International Conference on Knowledge Discovery and Data Mining ACM. SanFrancisico: ACM, 2016: 785-794., articleTitle=XGBoost: a scalable tree boosting system, refAbstract=null), Reference(id=1205908719074865840, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, doi=null, pmid=null, pmcid=null, year=2021, volume=43, issue=4, pageStart=7, pageEnd=12, url=null, language=null, rfNumber=[11], rfOrder=12, authorNames=黄宜胜, 夏晓丹, journalName=三峡大学学报 (自然科学版), refType=null, unstructuredReference=黄宜胜, 夏晓丹. 砂岩颗粒流平行黏结模型细观参数标定方法研究[J]. 三峡大学学报 (自然科学版), 2021, 43(4): 7-12., articleTitle=砂岩颗粒流平行黏结模型细观参数标定方法研究, refAbstract=null), Reference(id=1205908719188112050, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, doi=null, pmid=null, pmcid=null, year=2021, volume=43, issue=4, pageStart=7, pageEnd=12, url=null, language=null, rfNumber=[11], rfOrder=13, authorNames=Huang Yisheng, Xia Xiaodan, journalName=Journal of China Three Gorges University (Natural Science Edition), refType=null, unstructuredReference=Huang Yisheng, Xia Xiaodan. Research on the meso scale parameter calibration method of sandstone particle flow parallel bonding model[J]. Journal of China Three Gorges University (Natural Science Edition), 2021, 43(4): 7-12., articleTitle=Research on the meso scale parameter calibration method of sandstone particle flow parallel bonding model, refAbstract=null), Reference(id=1205908719351689908, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, doi=null, pmid=null, pmcid=null, year=2004, volume=41, issue=8, pageStart=1329, pageEnd=1364, url=null, language=null, rfNumber=[12], rfOrder=14, authorNames=Dop A, Pac B, journalName=International Journal of Rock Mechanics and Mining Sciences, refType=null, unstructuredReference=Dop A, Pac B. A bonded-particle model for rock[J]. International Journal of Rock Mechanics and Mining Sciences, 2004, 41(8): 1329-1364., articleTitle=A bonded-particle model for rock, refAbstract=null), Reference(id=1205908719439770294, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, doi=null, pmid=null, pmcid=null, year=2018, volume=26, issue=4, pageStart=918, pageEnd=928, url=null, language=null, rfNumber=[13], rfOrder=15, authorNames=刘相如, 杨圣奇, journalName=应用基础与工程科学学报, refType=null, unstructuredReference=刘相如, 杨圣奇. 基于正交试验的岩石细观力学参数数值研究[J]. 应用基础与工程科学学报, 2018, 26(4): 918-928., articleTitle=基于正交试验的岩石细观力学参数数值研究, refAbstract=null), Reference(id=1205908719511073463, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, doi=null, pmid=null, pmcid=null, year=2018, volume=26, issue=4, pageStart=918, pageEnd=928, url=null, language=null, rfNumber=[13], rfOrder=16, authorNames=Liu Xiangru, Yang Shengqi, journalName=Journal of Applied Basic and Journal of Engineering Science, refType=null, unstructuredReference=Liu Xiangru, Yang Shengqi. Based on orthogonal experiment rock mesoscopic mechanics parameters of the numerical study[J]. Journal of Applied Basic and Journal of Engineering Science, 2018, 26(4): 918-928., articleTitle=Based on orthogonal experiment rock mesoscopic mechanics parameters of the numerical study, refAbstract=null), Reference(id=1205908719582376632, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, doi=null, pmid=null, pmcid=null, year=2018, volume=null, issue=S2, pageStart=36, pageEnd=null, url=null, language=null, rfNumber=[14], rfOrder=17, authorNames=石崇, 张强, 王盛年, journalName=岩土力学, refType=null, unstructuredReference=石崇, 张强, 王盛年. 颗粒流(PFC5.0)数值模拟技术及应用[J]. 岩土力学, 2018(S2): 36., articleTitle=颗粒流(PFC5.0)数值模拟技术及应用, refAbstract=null), Reference(id=1205908719653679802, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, doi=null, pmid=null, pmcid=null, year=2018, volume=null, issue=S2, pageStart=36, pageEnd=null, url=null, language=null, rfNumber=[14], rfOrder=18, authorNames=Shi Chong, Zhang Qiang, Wang Shengnian, journalName=Rock and Soil Mechanics, refType=null, unstructuredReference=Shi Chong, Zhang Qiang, Wang Shengnian. Numerical simulation of particle flow (PFC5.0) and its application[J]. Rock and Soil Mechanics, 2018(S2): 36., articleTitle=Numerical simulation of particle flow (PFC5.0) and its application, refAbstract=null), Reference(id=1205908719733371580, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, doi=null, pmid=null, pmcid=null, year=2019, volume=null, issue=null, pageStart=55, pageEnd=60, url=null, language=null, rfNumber=[15], rfOrder=19, authorNames=王晨, 赵晨曦, 杨杰, journalName=2019年中国智慧炼化高峰论坛, refType=null, unstructuredReference=王晨, 赵晨曦, 杨杰. Pearson相关系数-BP神经网络法用于加氢装置高压换热器结盐分析[C]// 2019年中国智慧炼化高峰论坛. 北京: 中国化工学会, 中国石油化工集团, 2019: 55-60., articleTitle=Pearson相关系数-BP神经网络法用于加氢装置高压换热器结盐分析, refAbstract=null), Reference(id=1205908719787897534, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, doi=null, pmid=null, pmcid=null, year=2019, volume=null, issue=null, pageStart=55, pageEnd=60, url=null, language=null, rfNumber=[15], rfOrder=20, authorNames=Wang Chen, Zhao Chenxi, Yang Jie, journalName=2019 China Smart Refining Summit Forum, refType=null, unstructuredReference=Wang Chen, Zhao Chenxi, Yang Jie. Pearson correlation core-BP neural network method for salt formation analysis of high-pressure heat exchangers in hydrogenation units[C]// 2019 China Smart Refining Summit Forum. Beijing: Chemical Industry Society of China, China Petroleum & Chemical Corporation, 2019: 55-60., articleTitle=Pearson correlation core-BP neural network method for salt formation analysis of high-pressure heat exchangers in hydrogenation units, refAbstract=null), Reference(id=1205908719850812096, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, doi=null, pmid=null, pmcid=null, year=2017, volume=28, issue=11, pageStart=2879, pageEnd=2890, url=null, language=null, rfNumber=[16], rfOrder=21, authorNames=卢泓宇, 张敏, 刘奕群, journalName=软件学报, refType=null, unstructuredReference=卢泓宇, 张敏, 刘奕群, 等. 卷积神经网络特征重要性分析及增强特征选择模型[J]. 软件学报, 2017, 28(11): 2879-2890., articleTitle=卷积神经网络特征重要性分析及增强特征选择模型, refAbstract=null), Reference(id=1205908721000051394, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, doi=null, pmid=null, pmcid=null, year=2017, volume=28, issue=11, pageStart=2879, pageEnd=2890, url=null, language=null, rfNumber=[16], rfOrder=22, authorNames=Lu Hongyu, Zhang Min, Liu Yiqun, journalName=Journal of Software, refType=null, unstructuredReference=Lu Hongyu, Zhang Min, Liu Yiqun, et al. Convolution neural network feature importance analysis and enhanced feature selection model[J]. Journal of Software, 2017, 28(11): 2879-2890., articleTitle=Convolution neural network feature importance analysis and enhanced feature selection model, refAbstract=null), Reference(id=1205908721151046339, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, doi=null, pmid=null, pmcid=null, year=2022, volume=43, issue=4, pageStart=932, pageEnd=944, url=null, language=null, rfNumber=[17], rfOrder=23, authorNames=姜玥, 周辉, 卢景景, journalName=岩土力学, refType=null, unstructuredReference=姜玥, 周辉, 卢景景, 等. 空心圆柱砂岩真三轴试验研究[J]. 岩土力学, 2022, 43(4): 932-944., articleTitle=空心圆柱砂岩真三轴试验研究, refAbstract=null), Reference(id=1205908721213960901, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, doi=null, pmid=null, pmcid=null, year=2022, volume=43, issue=4, pageStart=932, pageEnd=944, url=null, language=null, rfNumber=[17], rfOrder=24, authorNames=Jiang Yue, Zhou Hui, Lu Jingjing, journalName=Geotechnical Mechanics, refType=null, unstructuredReference=Jiang Yue, Zhou Hui, Lu Jingjing, et al. Study on true triaxial testing of hollow cylindrical sandstone[J]. Geotechnical Mechanics, 2022, 43(4): 932-944., articleTitle=Study on true triaxial testing of hollow cylindrical sandstone, refAbstract=null)], funds=[Fund(id=1205908717996929683, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, awardId=41907232, language=CN, fundingSource=国家自然科学基金(41907232), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1205908712217178651, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, xref=null, ext=[AuthorCompanyExt(id=1205908712225567260, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, companyId=1205908712217178651, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1. School of Civil Engineering, Suzhou University of Science and Technology, Suzhou 215011, China), AuthorCompanyExt(id=1205908712229761565, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, companyId=1205908712217178651, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.苏州科技大学土木工程学院, 苏州 215011)]), AuthorCompany(id=1205908712313647647, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, xref=null, ext=[AuthorCompanyExt(id=1205908712317841952, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, companyId=1205908712313647647, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2. State Key Laboratory of Geomechanics and Geotechnical Engineering, Institute of Rock and Soil Mechanics,Chinese Academy of Sciences, Wuhan 430071, China), AuthorCompanyExt(id=1205908712326230561, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, companyId=1205908712313647647, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.中国科学院武汉岩土力学研究所岩土力学与工程国家重点实验室, 武汉 430071)])], figs=[ArticleFig(id=1205908714704400976, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, language=EN, label=Fig.1, caption=Random forest flowchart, figureFileSmall=YyHv98ogIZwEinXwXQCqYg==, figureFileBig=MlHCK/6kdsU4CfebUnpE0A==, tableContent=null), ArticleFig(id=1205908714758926930, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, language=CN, label=图1, caption=随机森林流程图, figureFileSmall=YyHv98ogIZwEinXwXQCqYg==, figureFileBig=MlHCK/6kdsU4CfebUnpE0A==, tableContent=null), ArticleFig(id=1205908714872173141, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, language=EN, label=Fig.2, caption=Discrete element model, figureFileSmall=i4+rsS9QRovhoIi+/Q4NYA==, figureFileBig=IzY4q9vH/UD8lyclI7rxbA==, tableContent=null), ArticleFig(id=1205908714930893399, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, language=CN, label=图2, caption=离散元模型, figureFileSmall=i4+rsS9QRovhoIi+/Q4NYA==, figureFileBig=IzY4q9vH/UD8lyclI7rxbA==, tableContent=null), ArticleFig(id=1205908715031556697, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, language=EN, label=Fig.3, caption=Correlation graph between input and output variables, figureFileSmall=SMMNqPEqArNEtWuPP6vLMA==, figureFileBig=L72TkSLO6MBJFo9irB3obA==, tableContent=null), ArticleFig(id=1205908715119637084, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, language=CN, label=图3, caption=输入变量与输出变量相关图, figureFileSmall=SMMNqPEqArNEtWuPP6vLMA==, figureFileBig=L72TkSLO6MBJFo9irB3obA==, tableContent=null), ArticleFig(id=1205908715195134558, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, language=EN, label=Fig.4, caption=Comparison of true and predicted peak intensity values, figureFileSmall=EKqjvK3A4cCYOyOO5FXh8Q==, figureFileBig=ffE6cUXFx5UToFczHKtvBQ==, tableContent=null), ArticleFig(id=1205908715283214945, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, language=CN, label=图4, caption=峰值强度真实值与预测值对比, figureFileSmall=EKqjvK3A4cCYOyOO5FXh8Q==, figureFileBig=ffE6cUXFx5UToFczHKtvBQ==, tableContent=null), ArticleFig(id=1205908715350323810, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, language=EN, label=Fig.5, caption=Comparison of actual and predicted elastic modulus values, figureFileSmall=NVugx0buIAfcH1DcWHo2Sw==, figureFileBig=ZkWz/GeyR0mGWq+0f7MeLA==, tableContent=null), ArticleFig(id=1205908715404849764, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, language=CN, label=图5, caption=弹性模量真实值与预测值对比, figureFileSmall=NVugx0buIAfcH1DcWHo2Sw==, figureFileBig=ZkWz/GeyR0mGWq+0f7MeLA==, tableContent=null), ArticleFig(id=1205908716554089062, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, language=EN, label=Fig.6, caption=Comparison of Poisson’s ratio between real value and predicted value, figureFileSmall=0ag7nEEhLFOeVCGudlmWnA==, figureFileBig=Vo2PEDHxAsF1B6U2PhdaWg==, tableContent=null), ArticleFig(id=1205908716663140968, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, language=CN, label=图6, caption=泊松比真实值与预测值对比, figureFileSmall=0ag7nEEhLFOeVCGudlmWnA==, figureFileBig=Vo2PEDHxAsF1B6U2PhdaWg==, tableContent=null), ArticleFig(id=1205908716721861226, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, language=EN, label=Fig.7, caption=The importance of features generated by XGBoost model, figureFileSmall=Xx7ZAAkslU/7SRagnVGppA==, figureFileBig=b9F986x4L5CyAL3EqOWIcw==, tableContent=null), ArticleFig(id=1205908716772192875, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, language=CN, label=图7, caption=XGBoost模型生成的特征重要性, figureFileSmall=Xx7ZAAkslU/7SRagnVGppA==, figureFileBig=b9F986x4L5CyAL3EqOWIcw==, tableContent=null), ArticleFig(id=1205908716830913132, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, language=EN, label=Fig.8, caption=The stress-strain relationship curves were obtained by numerical simulation and triaxial test under different confining pressures, figureFileSmall=7fSzwrQvXTxRayh2q2EWjA==, figureFileBig=qhY/GnCiyAlEAuhhjcYF4g==, tableContent=null), ArticleFig(id=1205908716898021997, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, language=CN, label=图8, caption=不同围压下通过数值模拟与三轴试验得到应力-应变关系曲线, figureFileSmall=7fSzwrQvXTxRayh2q2EWjA==, figureFileBig=qhY/GnCiyAlEAuhhjcYF4g==, tableContent=null), ArticleFig(id=1205908716960936558, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, language=EN, label=Table 1, caption=

Microscopic parameter classification table

, figureFileSmall=null, figureFileBig=null, tableContent=
颗粒部分 Ec Rmin μ kn/ks ρ Rmax/Rmin
黏结部分 E C ¯ k n ¯/ k s ¯ σ c ¯ C - μ - φ - λ -
), ArticleFig(id=1205908717032239727, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, language=CN, label=表1, caption=

细观参数分类表

, figureFileSmall=null, figureFileBig=null, tableContent=
颗粒部分 Ec Rmin μ kn/ks ρ Rmax/Rmin
黏结部分 E C ¯ k n ¯/ k s ¯ σ c ¯ C - μ - φ - λ -
), ArticleFig(id=1205908717124514416, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, language=EN, label=Table 2, caption=

Assumed values for parameters

, figureFileSmall=null, figureFileBig=null, tableContent=
参数 假定取值
平行黏结半径因子 1
颗粒半径比 1.66
颗粒密度/(kg· m - 3) 2 600
摩擦因数 0.5
颗粒最小半径/mm 0.6
孔隙比 0.34
), ArticleFig(id=1205908717179040372, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, language=CN, label=表2, caption=

参数假定取值

, figureFileSmall=null, figureFileBig=null, tableContent=
参数 假定取值
平行黏结半径因子 1
颗粒半径比 1.66
颗粒密度/(kg· m - 3) 2 600
摩擦因数 0.5
颗粒最小半径/mm 0.6
孔隙比 0.34
), ArticleFig(id=1205908717254537848, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, language=EN, label=Table 3, caption=

Value ranges of mesoscopic parameters

, figureFileSmall=null, figureFileBig=null, tableContent=
参数 E C ¯ k n ¯/ k s ¯ σ c ¯ k φ - 围压/MPa
取值
范围
1×1010~
8×1010
10~
60
1×107~
3.5×1010
1~15 12.8~20 5、10、20
), ArticleFig(id=1205908717330035322, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, language=CN, label=表3, caption=

细观参数取值范围

, figureFileSmall=null, figureFileBig=null, tableContent=
参数 E C ¯ k n ¯/ k s ¯ σ c ¯ k φ - 围压/MPa
取值
范围
1×1010~
8×1010
10~
60
1×107~
3.5×1010
1~15 12.8~20 5、10、20
), ArticleFig(id=1205908717397144188, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, language=EN, label=Table 4, caption=

Random forest algorithm model

, figureFileSmall=null, figureFileBig=null, tableContent=
参数 取值
数据切分 0.8
内部节点分裂的最小样本数 2
叶子节点的最小样本数 1
叶子节点中样本的最小权重 0
树的最大深度 10
叶子节点的最大数量 50
节点划分不纯度的阈值 0
决策树数量 100
), ArticleFig(id=1205908717472641664, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, language=CN, label=表4, caption=

随机森林算法模型参数

, figureFileSmall=null, figureFileBig=null, tableContent=
参数 取值
数据切分 0.8
内部节点分裂的最小样本数 2
叶子节点的最小样本数 1
叶子节点中样本的最小权重 0
树的最大深度 10
叶子节点的最大数量 50
节点划分不纯度的阈值 0
决策树数量 100
), ArticleFig(id=1205908717543944834, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, language=EN, label=Table 5, caption=

XGBoost algorithm model parameters

, figureFileSmall=null, figureFileBig=null, tableContent=
参数 取值
数据切分 0.8
基学习器 gbtree
基学习器数量 50
学习率 0.1
L1正则项 0.000 1
L2正则项 1
样本特征采样率 1
树特征采样率 1
节点特征采样率 1
叶子节点中样本的最小权重 0
树的最大深度 5
), ArticleFig(id=1205908717611053700, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, language=CN, label=表5, caption=

XGBoost算法模型参数

, figureFileSmall=null, figureFileBig=null, tableContent=
参数 取值
数据切分 0.8
基学习器 gbtree
基学习器数量 50
学习率 0.1
L1正则项 0.000 1
L2正则项 1
样本特征采样率 1
树特征采样率 1
节点特征采样率 1
叶子节点中样本的最小权重 0
树的最大深度 5
), ArticleFig(id=1205908717699134088, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, language=EN, label=Table 6, caption=

Comparison of machine learning prediction results

, figureFileSmall=null, figureFileBig=null, tableContent=
预测模型 R2
峰值强度 弹性模量 泊松比
随机森林 0.81 0.79 0.85
XGBoost 0.92 0.85 0.95
), ArticleFig(id=1205908717770437258, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, language=CN, label=表6, caption=

机器学习预测结果对比

, figureFileSmall=null, figureFileBig=null, tableContent=
预测模型 R2
峰值强度 弹性模量 泊松比
随机森林 0.81 0.79 0.85
XGBoost 0.92 0.85 0.95
), ArticleFig(id=1205908717820768908, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, language=EN, label=Table 7, caption=

Range of mesoscopic parameter values and calibration results

, figureFileSmall=null, figureFileBig=null, tableContent=
细观
参数
有效
模量/GPa
刚度比 抗拉强
度/MPa
黏结刚
度比
摩擦角/
(°)
标定结果(围压
5、10、20 MPa)
11.933 2.923 29.726 4.181 11.781
), ArticleFig(id=1205908717883683472, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908302891312007, language=CN, label=表7, caption=

细观参数标定结果

, figureFileSmall=null, figureFileBig=null, tableContent=
细观
参数
有效
模量/GPa
刚度比 抗拉强
度/MPa
黏结刚
度比
摩擦角/
(°)
标定结果(围压
5、10、20 MPa)
11.933 2.923 29.726 4.181 11.781
)], 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.1671-1815.2400502, detailUrlEn=https://castjournals.cast.org.cn/joweb/kxjsygc/EN/10.12404/j.issn.1671-1815.2400502, pdfUrlCn=https://castjournals.cast.org.cn/joweb/kxjsygc/CN/PDF/10.12404/j.issn.1671-1815.2400502, pdfUrlEn=https://castjournals.cast.org.cn/joweb/kxjsygc/EN/PDF/10.12404/j.issn.1671-1815.2400502, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于机器学习算法的空心圆柱砂岩离散元细观参数标定方法
收藏切换
PDF下载
潘海潮 1 , 吴静红 1, * , 姜玥 1, 2 , 邹文栋 1
科学技术与工程 | 论文·水利工程 2025,25(1): 339-345
收起
收藏切换
科学技术与工程 | 论文·水利工程 2025, 25(1): 339-345
基于机器学习算法的空心圆柱砂岩离散元细观参数标定方法
全屏
潘海潮1 , 吴静红1, * , 姜玥1, 2, 邹文栋1
作者信息
  • 1.苏州科技大学土木工程学院, 苏州 215011
  • 2.中国科学院武汉岩土力学研究所岩土力学与工程国家重点实验室, 武汉 430071
  • 潘海潮(1997—),男,汉族,江苏徐州人,硕士研究生。研究方向:岩土测试与监测新技术及应用。E-mail:

通讯作者:

* 吴静红(1989—),女,汉族,博士,副教授。研究方向:地质工程监测与评价。E-mail:
Calibration Method for Mesoscopic Parameters of Hollow Cylindrical Sandstone Discrete Element Based on Machine Learning Algorithm
Hai-chao PAN1 , Jing-hong WU1, * , Yue JIANG1, 2, Wen-dong ZOU1
Affiliations
  • 1. School of Civil Engineering, Suzhou University of Science and Technology, Suzhou 215011, China
  • 2. State Key Laboratory of Geomechanics and Geotechnical Engineering, Institute of Rock and Soil Mechanics,Chinese Academy of Sciences, Wuhan 430071, China
出版时间: 2025-01-08 doi: 10.12404/j.issn.1671-1815.2400502
文章导航
收藏切换

工程岩体存在原生裂纹和新生裂纹最终形成宏观裂缝,空心圆柱离散元模拟试验可以实现复杂应力路径的模拟。对于空心圆柱离散元模拟试验中存在的问题,如细观参数标定的影响因素众多和耗时过长等,提出了一种基于机器学习算法的空心圆柱砂岩离散元细观参数标定方法。通过改变离散元模型中不同输入变量得到210组模拟数据,建立基于随机森林算法和极端梯度提升(extreme gradient boosting,XGBoost)算法的细观参数标定模型,对比了模型预测精度,分析了参数敏感性,量化了输入参数对岩石整体力学特性的贡献,据此给出了微观参数修正的建议取值。结合空心圆柱室内三轴试验,标定结果表明:XGBoost算法具有计算速度优势,可快速定位离散元细观参数范围,为空心圆柱的离散元细观参数标定提供了新思路,具有工程应用价值。

机器学习  /  离散元  /  XGBoost  /  细观参数  /  空心圆柱砂岩

Primary cracks and new cracks develop within the engineering rock mass, leading to the formation of macroscopic cracks. The hollow cylindrical discrete element simulation test enables the emulation of complex stress paths. In order to solve the problems existing in the simulation test of hollow cylindrical discrete element, such as numerous influencing factors and lengthy meso-parameter calibration, a method of mesoscale parameter calibration of hollow cylindrical sandstone discrete element based on machine learning algorithm was proposed. Through variations in input variables within the discrete element model, 210 sets of simulation data were obtained. A mesoscopic parameter calibration model based on random forest algorithm and extreme gradient boosting(XGBoost) algorithm was established, the prediction accuracy of the model was compared, the parameter sensitivity was analyzed, and the contribution of input parameters to the overall mechanical properties of the rock was quantified. Combined with the indoor triaxial test of hollow cylinder, the calibration results show that the XGBoost algorithm has the advantages of computing speed, and can quickly locate the range of discrete element mesoscopic parameters, which provides a new idea for the calibration of discrete element mesoscopic parameters of hollow cylinder, and has the value of engineering application.

machine learning  /  discrete elements  /  XGBoost  /  mesotropic parameters  /  hollow cylindrical sandstone
潘海潮, 吴静红, 姜玥, 邹文栋. 基于机器学习算法的空心圆柱砂岩离散元细观参数标定方法. 科学技术与工程, 2025 , 25 (1) : 339 -345 . DOI: 10.12404/j.issn.1671-1815.2400502
Hai-chao PAN, Jing-hong WU, Yue JIANG, Wen-dong ZOU. Calibration Method for Mesoscopic Parameters of Hollow Cylindrical Sandstone Discrete Element Based on Machine Learning Algorithm[J]. Science Technology and Engineering, 2025 , 25 (1) : 339 -345 . DOI: 10.12404/j.issn.1671-1815.2400502
由于岩石中存在大量微孔隙和微裂纹,受到应力作用后,微裂纹会逐渐扩展,进而导致岩石内部的损伤和弱化。在岩石受到压剪应力的作用下,微裂纹会发生扩展和汇合,最终形成宏观裂缝。对岩石进行室内三轴试验,能够测量岩石力学性质,模拟岩石实际应力状态,精确测量岩石变形,为研究岩石裂纹扩展提供条件。在室内三轴试验对于试验材料的选择中,相对于标准岩石试样,空心圆柱试样可以实现复杂应力路径的模拟,这对于在复杂应力环境中深入理解岩石力学性质,岩石的强度、变形能力和破坏显得尤为关键。然而,室内三轴试验无法观察岩石内部及宏观现象下的微观机理。
离散元方法是一种用于模拟颗粒物质运动的数值方法,该方法的优点在于可以模拟颗粒间的接触、碰撞与运动等问题,从而更加准确预测物体的运动和变形。在土工试验数值模拟方面,离散元方法可以模拟土体的变形和破坏过程,得到广泛应用。 因此,将空心圆柱试样室内三轴试验和离散元方法相结合进行岩石裂纹扩展的研究,将能够更准确地理解和预测岩体的力学行为。
在离散元模拟中,细观参数的选择对模拟结果具有决定性影响。然而,岩石材料的宏观参数与细观参数并不一一对应,这使得细观参数的选择变得复杂且具有挑战性。因此,寻找一种有效的方法来确定这些细观参数,以便更准确地模拟岩石材料的力学行为,是当前离散元模拟研究的重要课题。
Zheng等[1]使用“试凑法”标定细观参数,将PFC2D和FLAC耦合起来模拟滑坡过程。Yoon[2]采用中心合成设计对接触黏结模型的细观参数进行标定,并研究了各细观参数与宏观力学特性的相关性。Cheng等[3]使用连续准蒙特卡罗滤波器对颗粒土提出了一种新的概率标定方法。Yang等[4]在PFC2D中利用“试凑法”建立节理岩样的离散单元法模型与单轴压缩试验进行结果对比。Liu等[5]针对不同的岩石尺寸,首先使用“试凑法”建立PFC软件建立3D数值岩石模型,研究了岩石的力学性能和声发射特性。覃茜等[6]通过控制变量法研究细观参数对混凝土直剪试验结果的影响。
目前,大多数针对PFC程序的细观参数识别方法选择使用“试凑法”及控制变量法。这些方法基于室内力学试验获取的宏观参数,在程序内调整相关的细观参数,确保模拟结果与实验数据的一致性。然而,这种方法的缺点在于其盲目性较大,且工作量较大,无法快速定量。近年来,机器学习算法迅速发展,其在处理小样本、非线性、多输出方面具有明显优势,可实现快速、准确预测,如于小鸽等[7]基于神经网络科学准确地分析及预测泰安市蒸发量的特点和走势。
针对岩石细观参数标定方法的不足,现基于空心圆柱砂岩常规三轴压缩试验结果,通过改变离散元模型细观参数得到宏观参数数据,建立机器学习细观参数标定模型,并进行参数敏感性分析,量化细观参数对岩石整体力学特性的贡献,据此给出细观参数修正的建议取值。
决策树是一种无参数的监督学习技术,能从带有特征和标签的数据集中提炼出决策规则,并以树形图的方式展示这些规则。在处理回归问题时,分类与回归树(classification and regression tree,CART)决策树算法常被采用。而在构建决策树时,选择非叶节点上的特征是关键步骤[8]
Bagging集成学习算法是集成学习中的经典算法之一,其基本思想即为抽样与投票。所谓抽样,即在建立模型时利用抽样法从整体数据集中随机、均匀地选取一部分数据进行弱学习器的模型训练,以此得到多个基于该数据集所建立的模型与预测结果。而所谓投票是对所有模型的预测结果取平均的方法以得到平均预测值,即为最终输出结果。
随机森林算法结合了决策树的构造原则与Bagging的集成策略[9],其流程如图1所示。利用Bagging 算法将决策树算法相结合,所输出的结果为多个决策树所输出结果取平均值,该模型克服了单一决策树预测结果精确度不足的缺点,并提高了模型的泛化性能。
极端梯度提升(extreme gradient boosting,XGBoost)是一种集成了很多个基学习器的算法,其基学习器是CART回归树。XGBoost使用的是模型树,模型树的叶节点的输出值,是由一个函数生成的值[10]
XGBoost建模流程如下:初始阶段,利用训练数据集建立基础树模型以训练并计算预测与实际观测值的差异。随后,在迭代过程中逐步引入新树以逼近先前迭代的残差,此过程持续至模型训练停止。由此产生的模型为多棵树构成的集成,其中每棵树指向特定的叶节点,而各叶节点赋予一定的得分。最终,样本的预测输出为所有叶节点得分的累积。
这个过程可以看作是一种梯度提升算法,通过不断迭代来逐步改进模型的预测能力。每次迭代都会根据上次预测的残差来构建一棵新的树,以进一步减少模型的预测误差。最后,通过对所有树的预测结果进行加权累加,以获得最终的预测值。
图2所示,利用PFC3D开展空心圆柱砂岩常规三轴压缩数值模拟,确定空心圆柱砂岩模型尺寸为:50 mm×30 mm×120 mm(外径×内径×高),内外围压分别选取5、10、20 MPa。颗粒接触模型选取平行黏结模型,采用wall构建边界条件,编写command命令流赋予其一定速度达到施加轴向压力以及内、外围压的效果,采用伺服控制算法保证围压的稳定。
控制平行黏结模型的细观参数可以分为颗粒和黏结两部分,其中颗粒细观参数有颗粒有效接触模量Ec、颗粒最小粒径Rmin、摩擦因数μ、颗粒刚度比kn/ks、颗粒密度ρ、颗粒粒径比Rmax/Rmin共6个;平行黏结模型细观参数有平行黏结有效模量 E C ¯、平行黏结刚度比 k n ¯/ k s ¯、抗拉强度 σ c ¯、内聚力 C -、平行黏结内摩擦因数 μ -、平行黏结摩擦角 φ -、平行黏结半径因子 λ -,如表1所示。
平行黏结模型包含大量的细观参数,需要对这些参数做出一些假设,以便减少细观参数的数量。
基于黄宜胜等[11]、Dop等[12]、刘相如等[13]、石崇等[14]的研究,颗粒的有效接触模量、刚度比、摩擦因数均与平行黏结模型相匹配,其余参数假定如表2所示。
抗拉强度与内聚力的比值定义为黏结强度比k(σc/C=k),k取1~2.5。综上,平行黏结模型需要考虑的参数由13个减小到了5个,分别为 E C ¯ k n ¯/ k s ¯ σ c ¯k φ -
通过上述分析,选取5个细观参数和围压作为输入变量,3个宏观参数(峰值强度、弹性模量及泊松比)作为输出量。
在对空心圆柱试样的常规三轴压缩模拟试验(内外等压)中,围压的设定值为5、10、20 MPa。将内外围压和轴向应力加载至预定值,保持伺服围压量值不变,增加轴向应力直至试样破裂且应力降至峰值强度75%时停止加载。对内外墙体实施应力控制,并通过自定义的Fish函数使内外墙体实现伺服机制。每200时步对围压进行监测和调整,以确保计算效率和围压稳定性。
通过改变上述离散元模型细观参数,细观参数取值范围如表3所示,得到210组宏观参数数据,将这210组细观、宏观参数数据用于构建预测模型,作为训练样本和测试样本。其中,随机抽取80%的数据作为训练集,剩余的20%数据用作测试集,分别采用随机森林算法和XGBoost算法进行参数标定。
通过Pearson相关系数图来展示输入变量与输出变量之间的关系,以及这种关系的强度。Pearson相关系数的取值范围为[-1,1]。当相关系数接近1或-1时,表示变量间存在显著的正或负相关,其中1代表正相关,-1代表负相关。相反,如果相关系数接近零,就意味着变量之间的关联性不强。可以通过Pearson相关系数图清晰地看到输入变量与输出变量之间的关系强弱[15]。如图3所示,输入变量与输出变量之间具有一定程度的关联性,可以更好地理解和优化模型,后续研究各输入参数对输出结果的相对权重提供。
机器学习模型的评价指标非常重要,评价指标可以量化地评估模型的性能,帮助理解模型在预测过程中可能出现的问题,并对模型进行优化。
采用拟合优度R2作为评价两种算法模型精度指标,有解释性强、易于比较、消除量纲影响等特点,R2是一个介于-1~1的值,用于衡量模型的拟合程度,当R2越接近1时,说明模型的拟合越好。
机器学习模型参数的重要性在于决定了模型的性能和预测能力。随机森林算法模型参数如表4所示,XGBoost算法模型参数如表5所示。
图4~图6所示为随机森林与XGBoost模型对峰值强度、弹性模量及泊松比模拟值与预测值对比。两种模型对峰值强度、弹性模量和泊松比的预测均取得了不错的预测效果,特别是XGBoost模型,预测值曲线与真实值的曲线吻合程度颇高,在曲线波动剧烈的区间内还能保持着较小的误差。
各模型在测试集上的性能表现如表6所示。可以看出:XGBoost算法具有较高的预测精度,其拟合优度都在0.85以上,而随机森林的预测效果相对较差。
在机器学习算法中,特征重要性[16]是指评估每个特征对模型预测结果的贡献程度。可以帮助理解哪些特征对于模型的预测最为关键,从而进行特征选择、特征工程或解释模型的预测结果。基于XGBoost模型分析有效模量、刚度比、抗拉强度、摩擦角、黏结强度比和围压对峰值强度、弹性模量及泊松比的敏感性,对输入参数对岩石全局力学特性的影响进行量化分析,结果如图7所示,其中所有重要性系数总和为1。
图7(a)所示,峰值强度受到多个因素的影响,根据重要性排名,这些因素的影响程度从低到高依次为:摩擦角、有效模量、黏结强度比、刚度比、抗拉强度和围压。其中,围压在所有参数影响因素中占比最高且占比量最大,说明围压的变化对峰值强度的影响最为显著。因此,调整围压可以对峰值强度产生较大的变化。如图7(b)所示,弹性模量受到多个因素的影响,根据重要性排名,这些因素的影响程度从低到高依次为:摩擦角、抗拉强度、围压、黏结强度比、刚度比和有效模量。特别是有效模量和刚度比对弹性模量的影响较为显著,因此在标定细观参数时,应重点考虑这两个因素。如图7(c)所示,泊松比受到多个因素的影响,根据重要性排名,这些因素的影响程度从低到高依次为:摩擦角、抗拉强度、有效模量、黏结强度比、刚度比和围压。围压对泊松比有巨大的影响,占比达到0.977。然而,如果围压保持不变,泊松比与刚度比之间的关系相对于其他细观参数来说更为显著。因此,在标定细观参数时,需要重点考虑围压和刚度比的影响。
根据上述权重分析,黏结强度比和平行黏结摩擦角对3个输出变量影响较小。因此,可将黏结强度比和平行黏结摩擦角设为较小值。基于已经训练好的XGBoost模型,利用其高效性,通过遍历法将细观参数按不同的排列组合代入所建立的XGBoost模型得到输出变量进行预测。
相较于离散元软件,已经构建好的模型可以快速预测输出变量,而不需要进行耗时的模拟运算。
以空心圆柱砂岩常规三轴压缩试验结果(围压为5、10及20 MPa)为例,试验在中国科学院武汉岩土力学研究所自行研制的岩石空心圆柱扭剪试验系统上完成[17],得到空心圆柱砂岩峰值强度、弹性模量和泊松比,标定结果如表7所示,将标定结果代入PFC3D中,如图8所示,展示了XGBoost计算值与室内三轴试验对比情况。
图8可知,在3种围压下,在轴向应变为0.008之前,基于XGBoost的空心圆柱离散元细观参数标定模型与实际应力-应变曲线吻合度较高。然而,在轴向应变大于0.008后曲线存在一定的误差,这表明需要加强XGBoost在应变大于0.008后的训练。综上所述,基于XGBoost的空心圆柱离散元细观参数标定模型是可行的,但需要进一步优化。
为了解决以往离散元细观参数标定效率低、精度差的问题,提出了一种基于机器学习算法的离散元细观参数标定方法,通过与室内试验数据的对比分析,得出以下结论。
(1) XGBoost模型在空心圆柱离散元细观参数标定方面优于随机森林模型,能更准确地预测和标定参数,提高模型精度和效率,为选择模型和优化参数标定方法提供指导。
(2) XGBoost模型的敏感性分析揭示了微观参数对宏观参数的不同影响程度,如抗拉强度对峰值强度,有效接触模量对弹性模量,刚度比对泊松比的显著影响,有助于优化离散元模型的参数设置。
(3) 利用XGBoost算法的高效性排列细观参数,最小化计算应力-应变曲线与实测值的差异,得到接近试验结果的数值用于离散元模拟,证明XGBoost在细观参数选取上的可行性。
综上所述,研究结果为空心圆柱离散元模拟提供了一种新的细观参数标定方法。基于XGBoost算法的优化过程能够显著提高参数的准确性和模拟结果的精度。未来的研究方向包括探索更多的机器学习算法和验证方法,以进一步提升细观参数标定的可靠性和适用性。
  • 国家自然科学基金(41907232)
参考文献 引证文献
排序方式:
[1]
Zheng Y F, Lo C M, Lin Q F. The characteristics of the seismic signals induced by landslides using a coupling of discrete element and finite difference methods[J]. Landslides, 2017, 14(2): 1-14.
[2]
Yoon J. Application of experimental design and optimization to PFC model calibration in uniaxial compression simulation[J]. International Journal of Rock Mechanics & Mining Sciences, 2007, 44(6): 871-889.
[3]
Cheng H, Shuku T, Thoeni K, et al. Probabilistic calibration of discrete element simulations using the sequential quasi-Monte Carlo filter[J]. Granular Matter, 2018, 20(1): 11.
[4]
Yang S Q, Fei P. Failure behavior and crack evolution mechanism of a non-persistent jointed rock mass containing a circular hole[J]. International Journal of Rock Mechanics and Mining Sciences, 2019, 114: 101-121.
[5]
Liu W R, Liu J K, Zhu C. Multi-scale effect of acoustic emission characteristics of 3D rock damage[J]. Arabian Journal of Geosciences, 2019, 12(22): 668-679.
[6]
覃茜, 徐千军. 基于离散元模拟的混凝土直剪试验细观参数研究[J]. 水电能源, 2023, 41(8): 156-160.
Qin Qian, Xu Qianjun. Mesoscopic parameters of concrete direct shear test based on discrete element simulation[J]. Hydropower Energy, 2023, 41(8): 156-160.
[7]
于小鸽, 王世超, 李岩, 等. 泰安市蒸发量变化趋势分析与基于神经网络的预测[J]. 科学技术与工程, 2024, 24(10): 3984-3996.
Yu Xiaoge, Wang Shichao, Li Yan, et al. Analysis of evaporation trend and prediction based on neural network in Tai’an City[J]. Science Technology and Engineering, 2024, 24(10): 3984-3996.
[8]
Ho T K. The random subspace method for constructing decision forests[J]. Trans on Pattern Analysis and Machine Intelligence, 1998, 20(8): 832-844.
[9]
Breiman L. Random forests[J]. Machine Learning, 2001, 45(1): 5-32.
[10]
Chen T, Guestrin C. XGBoost: a scalable tree boosting system[C]// ACM SIGKDD International Conference on Knowledge Discovery and Data Mining ACM. SanFrancisico: ACM, 2016: 785-794.
[11]
黄宜胜, 夏晓丹. 砂岩颗粒流平行黏结模型细观参数标定方法研究[J]. 三峡大学学报 (自然科学版), 2021, 43(4): 7-12.
Huang Yisheng, Xia Xiaodan. Research on the meso scale parameter calibration method of sandstone particle flow parallel bonding model[J]. Journal of China Three Gorges University (Natural Science Edition), 2021, 43(4): 7-12.
[12]
Dop A, Pac B. A bonded-particle model for rock[J]. International Journal of Rock Mechanics and Mining Sciences, 2004, 41(8): 1329-1364.
[13]
刘相如, 杨圣奇. 基于正交试验的岩石细观力学参数数值研究[J]. 应用基础与工程科学学报, 2018, 26(4): 918-928.
Liu Xiangru, Yang Shengqi. Based on orthogonal experiment rock mesoscopic mechanics parameters of the numerical study[J]. Journal of Applied Basic and Journal of Engineering Science, 2018, 26(4): 918-928.
[14]
石崇, 张强, 王盛年. 颗粒流(PFC5.0)数值模拟技术及应用[J]. 岩土力学, 2018(S2): 36.
Shi Chong, Zhang Qiang, Wang Shengnian. Numerical simulation of particle flow (PFC5.0) and its application[J]. Rock and Soil Mechanics, 2018(S2): 36.
[15]
王晨, 赵晨曦, 杨杰. Pearson相关系数-BP神经网络法用于加氢装置高压换热器结盐分析[C]// 2019年中国智慧炼化高峰论坛. 北京: 中国化工学会, 中国石油化工集团, 2019: 55-60.
Wang Chen, Zhao Chenxi, Yang Jie. Pearson correlation core-BP neural network method for salt formation analysis of high-pressure heat exchangers in hydrogenation units[C]// 2019 China Smart Refining Summit Forum. Beijing: Chemical Industry Society of China, China Petroleum & Chemical Corporation, 2019: 55-60.
[16]
卢泓宇, 张敏, 刘奕群, 等. 卷积神经网络特征重要性分析及增强特征选择模型[J]. 软件学报, 2017, 28(11): 2879-2890.
Lu Hongyu, Zhang Min, Liu Yiqun, et al. Convolution neural network feature importance analysis and enhanced feature selection model[J]. Journal of Software, 2017, 28(11): 2879-2890.
[17]
姜玥, 周辉, 卢景景, 等. 空心圆柱砂岩真三轴试验研究[J]. 岩土力学, 2022, 43(4): 932-944.
Jiang Yue, Zhou Hui, Lu Jingjing, et al. Study on true triaxial testing of hollow cylindrical sandstone[J]. Geotechnical Mechanics, 2022, 43(4): 932-944.
2025年第25卷第1期
PDF下载
291
101
引用本文
BibTeX
文章信息
doi: 10.12404/j.issn.1671-1815.2400502
  • 接收时间:2024-01-17
  • 首发时间:2025-07-29
  • 出版时间:2025-01-08
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2024-01-17
  • 修回日期:2024-09-28
基金
国家自然科学基金(41907232)
作者信息
    1.苏州科技大学土木工程学院, 苏州 215011
    2.中国科学院武汉岩土力学研究所岩土力学与工程国家重点实验室, 武汉 430071

通讯作者:

* 吴静红(1989—),女,汉族,博士,副教授。研究方向:地质工程监测与评价。E-mail:
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/kxjsygc/CN/10.12404/j.issn.1671-1815.2400502
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