Article(id=1156908035860943181, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1156907871645556837, articleNumber=null, orderNo=null, doi=10.12404/j.issn.1671-1815.2402458, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=research-article, receivedDate=1712332800000, receivedDateStr=2024-04-06, revisedDate=1721232000000, revisedDateStr=2024-07-18, acceptedDate=null, acceptedDateStr=null, onlineDate=1753757970061, onlineDateStr=2025-07-29, pubDate=1737993600000, pubDateStr=2025-01-28, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1753757970061, onlineIssueDateStr=2025-07-29, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1753757970061, creator=13701087609, updateTime=1753757970061, updator=13701087609, issue=Issue{id=1156907871645556837, tenantId=1146029695717560320, journalId=1146123166801305609, year='2025', volume='25', issue='3', pageStart='879', pageEnd='1312', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=0, createTime=1753757930909, creator=13701087609, updateTime=1765095544280, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1204461268821320541, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1156907871645556837, language=EN, specialIssueTitle=, coverIllustrator=, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1204461268825514846, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1156907871645556837, language=CN, specialIssueTitle=, coverIllustrator=, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=1225, endPage=1234, ext={EN=ArticleExt(id=1156908036632695120, articleId=1156908035860943181, tenantId=1146029695717560320, journalId=1146123166801305609, language=EN, title=Enhanced XGBoost-based Prediction Method for Dynamic Modulus and Phase Angle of Asphalt Mixture, columnId=1156262728772735295, journalTitle=Science Technology and Engineering, columnName=Papers·Traffics and Transportations, runingTitle=null, highlight=null, articleAbstract=

The dynamic modulus of asphalt mixture is an important parameter in the design of asphalt pavement. Extracting material characteristics, dynamic modulus, and phase angle information from a large amount of asphalt concrete datasets using integrated methods is of great significance for optimizing the performance of asphalt pavement. The extreme gradient boost (XGBoost) model aggregated a series of decision tree models through weighted summation to construct a powerful prediction model, while optimizing the loss function to minimize prediction errors. In order to further improve the accuracy of dynamic modulus and phase angle prediction, heuristic algorithms were used to optimize the model. Initially, the basic model was initialized based on samples and the gradient of the loss function of the training data was calculated. Subsequently, XGBoost utilized gradient details to construct a decision tree model, optimized leaf node weights, and updated the model’s predictions through weighted summation. During this process, heuristic algorithms are used to optimize the optimal parameters of the entire XGBoost model. The experimental results show that the improved XGBoost model outperforms the original model in all performance evaluation indicators, improving the accuracy of predicting the dynamic modulus and phase angle of asphalt mixtures.

, correspAuthors=Zun-dong LIANG, 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=Shi-qi QU, Zun-dong LIANG, Xin ZHANG), CN=ArticleExt(id=1156908113812082762, articleId=1156908035860943181, tenantId=1146029695717560320, journalId=1146123166801305609, language=CN, title=基于增强极限梯度提升算法的沥青混合料动态模量和相位角预测方法, columnId=1156262730664366426, journalTitle=科学技术与工程, columnName=论文·交通运输, runingTitle=null, highlight=null, articleAbstract=

沥青混合料的动态模量是沥青路面设计的一个重要参数。利用集成方法从大量的沥青混凝土数据集中提取材料特性、动态模量和相位角信息,对优化沥青路面性能具有重要意义。极限梯度提升模型(extreme gradient boost, XGBoost)通过加权求和聚合一系列决策树模型,构建了一个强大的预测模型,同时通过优化损失函数将预测误差降至最低。为了进一步提高动态模量和相位角预测的准确性,使用启发式算法对模型进行了优化。最初,基于样本初始化基础模型,并计算训练数据的损失函数的梯度。随后,XGBoost利用梯度细节构建决策树模型,优化叶节点权重,并通过加权求和更新模型的预测。在此过程中,使用启发式算法对整个XGBoost模型的最佳参数进行优化。实验结果表明,改进的XGBoost模型在所有性能评价指标上都优于原模型,提高了预测沥青混合料动态模量和相位角的准确性。

, correspAuthors=梁尊东, authorNote=null, correspAuthorsNote=
* 梁尊东(1996—),男,汉族,海南澄迈人,博士研究生。研究方向:基于大数据材料性能预测及结构健康监测。E-mail:
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=2eOj1h2NEVdLLIfjhe4UsA==, magXml=2vIwgtvyZHIzxX9Bedwc5A==, pdfUrl=null, pdf=4lVl0rAb+WNkkEXPsCnw2g==, pdfFileSize=7959128, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=M6zZQ9ezzibUnHhUXkbxvQ==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=BLI22z5/W4kyjaggqdgC9A==, mapNumber=null, authorCompany=null, fund=null, authors=

曲世琦(1977—),男,汉族,黑龙江海伦人,硕士,高级工程师。研究方向:路桥工程。E-mail:

, authorsList=曲世琦, 梁尊东, 张鑫)}, authors=[Author(id=1204780264070296327, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=345080468@qq.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1204780264212902671, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, authorId=1204780264070296327, language=EN, stringName=Shi-qi QU, firstName=Shi-qi, middleName=null, lastName=QU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1. Heilongjiang Provincial Transportation Investment Group Co., Ltd, Harbin 150069, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1204780264321954581, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, authorId=1204780264070296327, language=CN, stringName=曲世琦, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.黑龙江省交通投资集团有限公司, 哈尔滨 150069, bio={"content":"

曲世琦(1977—),男,汉族,黑龙江海伦人,硕士,高级工程师。研究方向:路桥工程。E-mail:

"}, bioImg=null, bioContent=

曲世琦(1977—),男,汉族,黑龙江海伦人,硕士,高级工程师。研究方向:路桥工程。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1204780263810249457, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, xref=null, ext=[AuthorCompanyExt(id=1204780263818638064, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, companyId=1204780263810249457, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1. Heilongjiang Provincial Transportation Investment Group Co., Ltd, Harbin 150069, China), AuthorCompanyExt(id=1204780263827026673, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, companyId=1204780263810249457, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.黑龙江省交通投资集团有限公司, 哈尔滨 150069)])]), Author(id=1204780264422617886, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=zdong_liang@stu.hit.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1204780264535864105, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, authorId=1204780264422617886, language=EN, stringName=Zun-dong LIANG, firstName=Zun-dong, middleName=null, lastName=LIANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, *, address=2. School of Transportation Science and Engineering, Harbin Institute of Technology, Harbin 150090, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1204780264649110321, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, authorId=1204780264422617886, language=CN, stringName=梁尊东, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, *, address=2.哈尔滨工业大学交通学院, 哈尔滨 150090, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1204780263923495674, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, xref=null, ext=[AuthorCompanyExt(id=1204780263944467195, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, companyId=1204780263923495674, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2. School of Transportation Science and Engineering, Harbin Institute of Technology, Harbin 150090, China), AuthorCompanyExt(id=1204780263957050109, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, companyId=1204780263923495674, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.哈尔滨工业大学交通学院, 哈尔滨 150090)])]), Author(id=1204780264758162231, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, 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=1204780264900768574, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, authorId=1204780264758162231, language=EN, stringName=Xin ZHANG, firstName=Xin, middleName=null, lastName=ZHANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1. Heilongjiang Provincial Transportation Investment Group Co., Ltd, Harbin 150069, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1204780265026597703, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, authorId=1204780264758162231, language=CN, stringName=张鑫, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.黑龙江省交通投资集团有限公司, 哈尔滨 150069, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1204780263810249457, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, xref=null, ext=[AuthorCompanyExt(id=1204780263818638064, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, companyId=1204780263810249457, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1. Heilongjiang Provincial Transportation Investment Group Co., Ltd, Harbin 150069, China), AuthorCompanyExt(id=1204780263827026673, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, companyId=1204780263810249457, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.黑龙江省交通投资集团有限公司, 哈尔滨 150069)])])], keywords=[Keyword(id=1204780265274061653, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, language=EN, orderNo=1, keyword=asphalt mixture), Keyword(id=1204780265391502170, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, language=EN, orderNo=2, keyword=dynamic modulus), Keyword(id=1204780265508942689, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, language=EN, orderNo=3, keyword=phase angle), Keyword(id=1204780265630577515, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, language=EN, orderNo=4, keyword=enhanced algorithm), Keyword(id=1204780265722852212, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, language=CN, orderNo=1, keyword=沥青混合料), Keyword(id=1204780265831904123, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, language=CN, orderNo=2, keyword=动态模量), Keyword(id=1204780265940956037, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, language=CN, orderNo=3, keyword=相位角), Keyword(id=1204780266062590856, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, language=CN, orderNo=4, keyword=增强算法)], refs=[Reference(id=1204780276917448781, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, doi=null, pmid=null, pmcid=null, year=2023, volume=13, issue=8, pageStart=13081969, pageEnd=null, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=Ran W P, Qiu H Z, Ai X C, journalName=Buildings, refType=null, unstructuredReference=Ran W P, Qiu H Z, Ai X C, et al. Experimental study on the dynamic modulus of an asphalt roadbed grouting mixture under the influence of complex and multiple factors[J]. Buildings, 2023, 13(8): 13081969., articleTitle=Experimental study on the dynamic modulus of an asphalt roadbed grouting mixture under the influence of complex and multiple factors, refAbstract=null), Reference(id=1204780277039083603, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, doi=null, pmid=null, pmcid=null, year=2018, volume=190, issue=null, pageStart=740, pageEnd=751, url=null, language=null, rfNumber=[2], rfOrder=1, authorNames=Nobakht M, Sakhaeifar M S, journalName=Construction and Building Materials, refType=null, unstructuredReference=Nobakht M, Sakhaeifar M S. Dynamic modulus and phase angle prediction of laboratory aged asphalt mixtures[J]. Construction and Building Materials, 2018, 190: 740-751., articleTitle=Dynamic modulus and phase angle prediction of laboratory aged asphalt mixtures, refAbstract=null), Reference(id=1204780277156524121, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, doi=null, pmid=null, pmcid=null, year=2015, volume=2507, issue=null, pageStart=67, pageEnd=77, url=null, language=null, rfNumber=[3], rfOrder=2, authorNames=Cooper S B, Mohammad L N, Elseifi M A, journalName=Transportation Research Record, refType=null, unstructuredReference=Cooper S B, Mohammad L N, Elseifi M A, et al. Dynamic modules of asphalt mixtures evaluation of effects on pavement performance prediction[J]. Transportation Research Record, 2015, 2507: 67-77., articleTitle=Dynamic modules of asphalt mixtures evaluation of effects on pavement performance prediction, refAbstract=null), Reference(id=1204780277303324765, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, doi=null, pmid=null, pmcid=null, year=2015, volume=90, issue=null, pageStart=53, pageEnd=58, url=null, language=null, rfNumber=[4], rfOrder=3, authorNames=Zou X L, Sha A M, Jiang W, journalName=Construction and Building Materials, refType=null, unstructuredReference=Zou X L, Sha A M, Jiang W, et al. Modification mechanism of high modulus asphalt binders and mixtures performance evaluation[J]. Construction and Building Materials, 2015, 90: 53-58., articleTitle=Modification mechanism of high modulus asphalt binders and mixtures performance evaluation, refAbstract=null), Reference(id=1204780277424959586, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, doi=null, pmid=null, pmcid=null, year=2016, volume=44, issue=null, pageStart=868, pageEnd=877, url=null, language=null, rfNumber=[5], rfOrder=4, authorNames=Zhang J P, Hu D L, Yang F H, journalName=Journal of Testing and Evaluation, refType=null, unstructuredReference=Zhang J P, Hu D L, Yang F H, et al. Effect of property variations of raw materials on the variability of dynamic moduli of asphalt mixtures[J]. Journal of Testing and Evaluation, 2016, 44: 868-877., articleTitle=Effect of property variations of raw materials on the variability of dynamic moduli of asphalt mixtures, refAbstract=null), Reference(id=1204780277559177320, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, doi=null, pmid=null, pmcid=null, year=2024, volume=24, issue=1, pageStart=352, pageEnd=359, url=null, language=null, rfNumber=[6], rfOrder=5, authorNames=董子震, 张金喜, 孙国强, journalName=科学技术与工程, refType=null, unstructuredReference=董子震, 张金喜, 孙国强, 等. 骨料级配对相变沥青混合料性能的影响[J]. 科学技术与工程, 2024, 24(1): 352-359., articleTitle=骨料级配对相变沥青混合料性能的影响, refAbstract=null), Reference(id=1204780277726949484, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, doi=null, pmid=null, pmcid=null, year=2024, volume=24, issue=1, pageStart=352, pageEnd=359, url=null, language=null, rfNumber=[6], rfOrder=6, authorNames=Dong Zizhen, Zhang Jinxi, Sun Guoqiang, journalName=Science Technology and Engineering, refType=null, unstructuredReference=Dong Zizhen, Zhang Jinxi, Sun Guoqiang, et al. Effect of gradation on the performance of phase change asphalt mixture[J]. Science Technology and Engineering, 2024, 24(1): 352-359., articleTitle=Effect of gradation on the performance of phase change asphalt mixture, refAbstract=null), Reference(id=1204780277810835567, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, doi=null, pmid=null, pmcid=null, year=2023, volume=23, issue=6, pageStart=2595, pageEnd=2605, url=null, language=null, rfNumber=[7], rfOrder=7, authorNames=李昌辉, 倪广聪, 徐希忠, journalName=科学技术与工程, refType=null, unstructuredReference=李昌辉, 倪广聪, 徐希忠, 等. 不同胶粉掺量下橡胶沥青混合料路用性能分析[J]. 科学技术与工程, 2023, 23(6): 2595-2605., articleTitle=不同胶粉掺量下橡胶沥青混合料路用性能分析, refAbstract=null), Reference(id=1204780277924081777, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, doi=null, pmid=null, pmcid=null, year=2023, volume=23, issue=6, pageStart=2595, pageEnd=2605, url=null, language=null, rfNumber=[7], rfOrder=8, authorNames=Li Changhui, Ni Guangcong, Xu Xizhong, journalName=Science Technology and Engineering, refType=null, unstructuredReference=Li Changhui, Ni Guangcong, Xu Xizhong, et al. Road performance analysis of rubber asphalt mixture under different rubber powder dosage[J]. Science Technology and Engineering, 2023, 23(6): 2595-2605., articleTitle=Road performance analysis of rubber asphalt mixture under different rubber powder dosage, refAbstract=null), Reference(id=1204780278054105209, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, doi=null, pmid=null, pmcid=null, year=2020, volume=20, issue=34, pageStart=14243, pageEnd=14250, url=null, language=null, rfNumber=[8], rfOrder=9, authorNames=张琛, 潘峰, 李佳侬, journalName=科学技术与工程, refType=null, unstructuredReference=张琛, 潘峰, 李佳侬. 基于材料性能和数理统计的改性沥青适用性[J]. 科学技术与工程, 2020, 20(34): 14243-14250., articleTitle=基于材料性能和数理统计的改性沥青适用性, refAbstract=null), Reference(id=1204780278167351423, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, doi=null, pmid=null, pmcid=null, year=2020, volume=20, issue=34, pageStart=14243, pageEnd=14250, url=null, language=null, rfNumber=[8], rfOrder=10, authorNames=Zhang Chen, Pan Feng, Li Jianong, journalName=Science Technology and Engineering, refType=null, unstructuredReference=Zhang Chen, Pan Feng, Li Jianong. The applicability of modified asphalt based on material properties and mathematical statistics method[J]. Science Technology and Engineering, 2020, 20(34): 14243-14250., articleTitle=The applicability of modified asphalt based on material properties and mathematical statistics method, refAbstract=null), Reference(id=1204780278255431808, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, doi=null, pmid=null, pmcid=null, year=1996, volume=1540, issue=null, pageStart=15, pageEnd=23, url=null, language=null, rfNumber=[9], rfOrder=11, authorNames=Witczak M W, Fonseca O A, journalName=Transportation Research Record: Journal of the Transportation Research Board, refType=null, unstructuredReference=Witczak M W, Fonseca O A. Revised predictive model for dynamic(complex) modulus of asphalt mixtures[J]. Transportation Research Record: Journal of the Transportation Research Board, 1996, 1540: 15-23., articleTitle=Revised predictive model for dynamic(complex) modulus of asphalt mixtures, refAbstract=null), Reference(id=1204780278339317889, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, doi=null, pmid=null, pmcid=null, year=2021, volume=297, issue=null, pageStart=123655, pageEnd=null, url=null, language=null, rfNumber=[10], rfOrder=12, authorNames=Huang J D, Kumar G S, Ren J L, journalName=Construction and Building Materials, refType=null, unstructuredReference=Huang J D, Kumar G S, Ren J L, et al. Accurately predicting dynamic modulus of asphalt mixtures in low temperature regions using hybrid artificial intelligence mode[J]. Construction and Building Materials, 2021, 297: 123655., articleTitle=Accurately predicting dynamic modulus of asphalt mixtures in low temperature regions using hybrid artificial intelligence mode, refAbstract=null), Reference(id=1204780278456758407, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, doi=null, pmid=null, pmcid=null, year=2022, volume=23, issue=null, pageStart=1328, pageEnd=1338, url=null, language=null, rfNumber=[11], rfOrder=13, authorNames=Barugahare J, Amirkhanian A N, Xiao F P, journalName=International Journal of Pavement Engineering, refType=null, unstructuredReference=Barugahare J, Amirkhanian A N, Xiao F P, et al. ANN-based dynamic modulus models of asphalt mixtures with similar input variables as Hirsch and Witczak models[J]. International Journal of Pavement Engineering, 2022, 23: 1328-1338., articleTitle=ANN-based dynamic modulus models of asphalt mixtures with similar input variables as Hirsch and Witczak models, refAbstract=null), Reference(id=1204780278586781832, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, doi=null, pmid=null, pmcid=null, year=2022, volume=19, issue=null, pageStart=1312, pageEnd=1321, url=null, language=null, rfNumber=[12], rfOrder=14, authorNames=Zhang M, Zhao H, Fan L L, journalName=Journal of Materials Research and Technology, refType=null, unstructuredReference=Zhang M, Zhao H, Fan L L, et al. Dynamic modulus prediction model and analysis of factors influencing asphalt mixtures using gray relational analysis methods[J]. Journal of Materials Research and Technology, 2022, 19: 1312-1321., articleTitle=Dynamic modulus prediction model and analysis of factors influencing asphalt mixtures using gray relational analysis methods, refAbstract=null), Reference(id=1204780278679056524, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, doi=null, pmid=null, pmcid=null, year=2015, volume=76, issue=null, pageStart=221, pageEnd=231, url=null, language=null, rfNumber=[13], rfOrder=15, authorNames=Sakhaeifar M S, Kim Y R, Kabir P, journalName=Construction and Building Materials, refType=null, unstructuredReference=Sakhaeifar M S, Kim Y R, Kabir P. New predictive models for the dynamic modulus of hot mix asphalt[J]. Construction and Building Materials, 2015, 76: 221-231., articleTitle=New predictive models for the dynamic modulus of hot mix asphalt, refAbstract=null), Reference(id=1204780278796497040, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, doi=null, pmid=null, pmcid=null, year=2019, volume=145, issue=null, pageStart=04019025, pageEnd=null, url=null, language=null, rfNumber=[14], rfOrder=16, authorNames=Arefin M S, Quasem T, Nazzal M, journalName=Journal of Transportation Engineering Part B-Pavements, refType=null, unstructuredReference=Arefin M S, Quasem T, Nazzal M, et al. Accuracy of MEPDG dynamic modulus predictions for short-term and long-term aged asphalt mixtures[J]. Journal of Transportation Engineering Part B-Pavements, 2019, 145: 04019025., articleTitle=Accuracy of MEPDG dynamic modulus predictions for short-term and long-term aged asphalt mixtures, refAbstract=null), Reference(id=1204780278905548946, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, doi=null, pmid=null, pmcid=null, year=2020, volume=262, issue=null, pageStart=120544, pageEnd=null, url=null, language=null, rfNumber=[15], rfOrder=17, authorNames=Behnood A, Daneshvar D, journalName=Construction and Building Materials, refType=null, unstructuredReference=Behnood A, Daneshvar D. A machine learning study of the dynamic modulus of asphalt concretes an application of M5P model tree algorithm[J]. Construction and Building Materials, 2020, 262: 120544., articleTitle=A machine learning study of the dynamic modulus of asphalt concretes an application of M5P model tree algorithm, refAbstract=null), Reference(id=1204780278993629333, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, doi=null, pmid=null, pmcid=null, year=2020, volume=23, issue=null, pageStart=250, pageEnd=260, url=null, language=null, rfNumber=[16], rfOrder=18, authorNames=Daneshvar D, Behnood A, journalName=International Journal of Pavement Engineering, refType=null, unstructuredReference=Daneshvar D, Behnood A. Estimation of the dynamic modulus of asphalt concretes using random forests algorithm[J]. International Journal of Pavement Engineering, 2020, 23: 250-260., articleTitle=Estimation of the dynamic modulus of asphalt concretes using random forests algorithm, refAbstract=null), Reference(id=1204780279090098330, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, doi=null, pmid=null, pmcid=null, year=2020, volume=260, issue=null, pageStart=120468, pageEnd=null, url=null, language=null, rfNumber=[17], rfOrder=19, authorNames=Barugahare J, Amirkhanian A N, Xiao F P, journalName=Construction and Building Materials, refType=null, unstructuredReference=Barugahare J, Amirkhanian A N, Xiao F P, et al. Predicting the dynamic modulus of hot mix asphalt mixtures using bagged trees ensemble[J]. Construction and Building Materials, 2020, 260: 120468., articleTitle=Predicting the dynamic modulus of hot mix asphalt mixtures using bagged trees ensemble, refAbstract=null), Reference(id=1204780279228510360, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, doi=null, pmid=null, pmcid=null, year=2022, volume=23, issue=null, pageStart=2083, pageEnd=2098, url=null, language=null, rfNumber=[18], rfOrder=20, authorNames=Eleyedath A, Swamy A K, journalName=International Journal of Pavement Engineering, refType=null, unstructuredReference=Eleyedath A, Swamy A K. Prediction of dynamic modulus of asphalt concrete using hybrid machine learning technique[J]. International Journal of Pavement Engineering, 2022, 23: 2083-2098., articleTitle=Prediction of dynamic modulus of asphalt concrete using hybrid machine learning technique, refAbstract=null), Reference(id=1204780279350145180, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, doi=null, pmid=null, pmcid=null, year=2020, volume=263, issue=null, pageStart=119912, pageEnd=null, url=null, language=null, rfNumber=[19], rfOrder=21, authorNames=Gong H R, Sun Y R, Dong Y S, journalName=Construction and Building Materials, refType=null, unstructuredReference=Gong H R, Sun Y R, Dong Y S, et al. Improved estimation of dynamic modulus for hot mix asphalt using deep learning[J]. Construction and Building Materials, 2020, 263: 119912., articleTitle=Improved estimation of dynamic modulus for hot mix asphalt using deep learning, refAbstract=null), Reference(id=1204780279568248997, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, doi=null, pmid=null, pmcid=null, year=2021, volume=294, issue=null, pageStart=123589, pageEnd=null, url=null, language=null, rfNumber=[20], rfOrder=22, authorNames=Moussa G S, Owais M, journalName=Construction and Building Materials, refType=null, unstructuredReference=Moussa G S, Owais M. Modeling hot-mix asphalt dynamic modulus using deep residual neural networks parametric and sensitivity analysis study[J]. Construction and Building Materials, 2021, 294: 123589., articleTitle=Modeling hot-mix asphalt dynamic modulus using deep residual neural networks parametric and sensitivity analysis study, refAbstract=null), Reference(id=1204780279677300905, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, doi=null, pmid=null, pmcid=null, year=2022, volume=34, issue=null, pageStart=17289, pageEnd=17314, url=null, language=null, rfNumber=[21], rfOrder=23, authorNames=Eidgahee D R, Jahangir H, Solatifar N, journalName=Neural Computing & Applications, refType=null, unstructuredReference=Eidgahee D R, Jahangir H, Solatifar N, et al. Data-driven estimation models of asphalt mixtures dynamic modulus using ANN, GP and combinatorial GMDH approaches[J]. Neural Computing & Applications, 2022, 34: 17289-17314., articleTitle=Data-driven estimation models of asphalt mixtures dynamic modulus using ANN, GP and combinatorial GMDH approaches, refAbstract=null), Reference(id=1204780279765381293, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, doi=null, pmid=null, pmcid=null, year=2022, volume=47, issue=null, pageStart=13579, pageEnd=13591, url=null, language=null, rfNumber=[22], rfOrder=24, authorNames=Uwanuakwa I D, Busari A A, Shaban I A, journalName=Arabian Journal for Science and Engineering, refType=null, unstructuredReference=Uwanuakwa I D, Busari A A, Shaban I A, et al. Comparing machine learning models with witczak NCHRP 1-40D model for hot-mix asphalt dynamic modulus prediction[J]. Arabian Journal for Science and Engineering, 2022, 47: 13579-13591., articleTitle=Comparing machine learning models with witczak NCHRP 1-40D model for hot-mix asphalt dynamic modulus prediction, refAbstract=null), Reference(id=1204780280935592113, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, doi=null, pmid=null, pmcid=null, year=2019, volume=4, issue=null, pageStart=53, pageEnd=null, url=null, language=null, rfNumber=[23], rfOrder=25, authorNames=Ghasemi P, Aslani M, Rollins D K, journalName=Infrastructures, refType=null, unstructuredReference=Ghasemi P, Aslani M, Rollins D K, et al. Principal component neural networks for modeling, prediction, and optimization of hot mix asphalt dynamics modulus[J]. Infrastructures, 2019, 4: 53., articleTitle=Principal component neural networks for modeling, prediction, and optimization of hot mix asphalt dynamics modulus, refAbstract=null), Reference(id=1204780281074004149, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, doi=null, pmid=null, pmcid=null, year=2023, volume=365, issue=null, pageStart=130134, pageEnd=null, url=null, language=null, rfNumber=[24], rfOrder=26, authorNames=Chen H, Saba R G, Liu G, journalName=Construction and Building Materials, refType=null, unstructuredReference=Chen H, Saba R G, Liu G, et al. Influence of material factors on the determination of dynamic moduli and associated prediction models for different types of asphalt mixtures[J]. Construction and Building Materials, 2023, 365: 130134., articleTitle=Influence of material factors on the determination of dynamic moduli and associated prediction models for different types of asphalt mixtures, refAbstract=null), Reference(id=1204780281174667447, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, doi=null, pmid=null, pmcid=null, year=2024, volume=413, issue=null, pageStart=134775, pageEnd=null, url=null, language=null, rfNumber=[25], rfOrder=27, authorNames=Owais M, Moussa G S, journalName=Construction and Building Materials, refType=null, unstructuredReference=Owais M, Moussa G S. Global sensitivity analysis for studying hot-mix asphalt dynamic modulus parameters[J]. Construction and Building Materials, 2024, 413: 134775., articleTitle=Global sensitivity analysis for studying hot-mix asphalt dynamic modulus parameters, refAbstract=null), Reference(id=1204780281254359228, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, doi=null, pmid=null, pmcid=null, year=2016, volume=null, issue=null, pageStart=785, pageEnd=794, url=null, language=null, rfNumber=[26], rfOrder=28, authorNames=Chen T Q, Carlos G, journalName=KDD’16: Proceedings of the 22nd ACM Sigkdd International Conference on Knowledge Discovery and Data Mining, refType=null, unstructuredReference=Chen T Q, Carlos G. XGBoost:A scalable tree boosting system[C]// KDD’16: Proceedings of the 22nd ACM Sigkdd International Conference on Knowledge Discovery and Data Mining. New York: IEEE, 2016: 785-794., articleTitle=XGBoost:A scalable tree boosting, refAbstract=null), Reference(id=1204780281371799744, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, doi=null, pmid=null, pmcid=null, year=2021, volume=29, issue=null, pageStart=1189, pageEnd=1232, url=null, language=null, rfNumber=[27], rfOrder=29, authorNames=Friedman J H, journalName=Annals of Statistics, refType=null, unstructuredReference=Friedman J H. Greedy function approximation: a gradient boosting machine[J]. Annals of Statistics, 2021, 29: 1189-1232., articleTitle=Greedy function approximation: a gradient boosting machine, refAbstract=null), Reference(id=1204780281447297218, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, doi=null, pmid=null, pmcid=null, year=2023, volume=401, issue=null, pageStart=132731, pageEnd=null, url=null, language=null, rfNumber=[28], rfOrder=30, authorNames=Daneshvari M H, Nourmohammadi E, Ameri M, journalName=Construction and Building Materials, refType=null, unstructuredReference=Daneshvari M H, Nourmohammadi E, Ameri M, et al. Efficient LBP-GLCM texture analysis for asphalt pavement raveling detection using extreme gradient boost[J]. Construction and Building Materials, 2023, 401: 132731., articleTitle=Efficient LBP-GLCM texture analysis for asphalt pavement raveling detection using extreme gradient boost, refAbstract=null), Reference(id=1204780281514406086, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, doi=null, pmid=null, pmcid=null, year=2022, volume=188, issue=null, pageStart=110638, pageEnd=null, url=null, language=null, rfNumber=[29], rfOrder=31, authorNames=Zhan Y, Liu C, Deng Q S, journalName=Measurement, refType=null, unstructuredReference=Zhan Y, Liu C, Deng Q S, et al. Integrated FFT and XGBoost framework to predict pavement skid resistance using automatic 3D texture measurement[J]. Measurement, 2022, 188: 110638., articleTitle=Integrated FFT and XGBoost framework to predict pavement skid resistance using automatic 3D texture measurement, refAbstract=null), Reference(id=1204780281606680777, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, doi=null, pmid=null, pmcid=null, year=2021, volume=295, issue=null, pageStart=123642, pageEnd=null, url=null, language=null, rfNumber=[30], rfOrder=32, authorNames=Ali Y, Hussain F, Irfan M, journalName=Construction and Building Materials, refType=null, unstructuredReference=Ali Y, Hussain F, Irfan M, et al. An extreme gradient boosting model for predicting dynamic modulus of asphalt concrete mixtures[J]. Construction and Building Materials, 2021, 295: 123642., articleTitle=An extreme gradient boosting model for predicting dynamic modulus of asphalt concrete mixtures, refAbstract=null), Reference(id=1204780281673789644, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, doi=null, pmid=null, pmcid=null, year=2022, volume=65, issue=null, pageStart=1470, pageEnd=1481, url=null, language=null, rfNumber=[31], rfOrder=33, authorNames=Li Z X, Shi X L, Cao J D, journalName=Science China-Technological Sciences, refType=null, unstructuredReference=Li Z X, Shi X L, Cao J D, et al. CPSO-XGBoost segmented regression model for asphalt pavement deflection basin area prediction[J]. Science China-Technological Sciences, 2022, 65: 1470-1481., articleTitle=CPSO-XGBoost segmented regression model for asphalt pavement deflection basin area prediction, refAbstract=null), Reference(id=1204780281749287119, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, doi=null, pmid=null, pmcid=null, year=2023, volume=407, issue=null, pageStart=133610, pageEnd=null, url=null, language=null, rfNumber=[32], rfOrder=34, authorNames=Liu J, Liu F Y, Wang Z, journalName=Construction and Building Materials, refType=null, unstructuredReference=Liu J, Liu F Y, Wang Z, et al. Involving prediction of dynamic modulus in asphalt mix design with machine learning and mechanical-empirical analysis[J]. Construction and Building Materials, 2023, 407: 133610., articleTitle=Involving prediction of dynamic modulus in asphalt mix design with machine learning and mechanical-empirical analysis, refAbstract=null), Reference(id=1204780281837367506, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, doi=null, pmid=null, pmcid=null, year=2024, volume=37, issue=4, pageStart=98, pageEnd=120, url=null, language=null, rfNumber=[33], rfOrder=35, authorNames=刘志杨, 董泽蛟, 周涛, journalName=中国公路学报, refType=null, unstructuredReference=刘志杨, 董泽蛟, 周涛, 等. 基于材料信息学的沥青混合料性能提升综述及展望[J]. 中国公路学报, 2024, 37(4): 98-120., articleTitle=基于材料信息学的沥青混合料性能提升综述及展望, refAbstract=null), Reference(id=1204780281917059284, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, doi=null, pmid=null, pmcid=null, year=2024, volume=37, issue=4, pageStart=98, pageEnd=120, url=null, language=null, rfNumber=[33], rfOrder=36, authorNames=Liu Zhiyang, Dong Zejiao, Zhou Tao, journalName=China Journal of Highway and Transport, refType=null, unstructuredReference=Liu Zhiyang, Dong Zejiao, Zhou Tao, et al. Review and prospects of performance enhancement of asphalt mixtures based on material informatics[J]. China Journal of Highway and Transport, 2024, 37(4): 98-120., articleTitle=Review and prospects of performance enhancement of asphalt mixtures based on material informatics, refAbstract=null), Reference(id=1204780281975779544, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, doi=null, pmid=null, pmcid=null, year=2020, volume=45, issue=2, pageStart=61, pageEnd=67, url=null, language=null, rfNumber=[34], rfOrder=37, authorNames=沈楸, 肖鹏, 顾万, journalName=公路工程, refType=null, unstructuredReference=沈楸, 肖鹏, 顾万, 等. 基于遗传神经网络的再生沥青混合料性能预测研究[J]. 公路工程, 2020, 45(2): 61-67., articleTitle=基于遗传神经网络的再生沥青混合料性能预测研究, refAbstract=null), Reference(id=1204780282063859931, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, doi=null, pmid=null, pmcid=null, year=2020, volume=45, issue=2, pageStart=61, pageEnd=67, url=null, language=null, rfNumber=[34], rfOrder=38, authorNames=Shen Qiu, Xiao Peng, Gu Wan, journalName=Highway Engineering, refType=null, unstructuredReference=Shen Qiu, Xiao Peng, Gu Wan, et al. Prediction of performance of recycled asphalt mixture based on genetic neural network[J]. Highway Engineering, 2020, 45(2): 61-67., articleTitle=Prediction of performance of recycled asphalt mixture based on genetic neural network, refAbstract=null), Reference(id=1204780282147746014, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, doi=null, pmid=null, pmcid=null, year=2023, volume=55, issue=11, pageStart=7, pageEnd=15, url=null, language=null, rfNumber=[35], rfOrder=39, authorNames=郝晟, 纪伦, 邬金麒, journalName=哈尔滨工业大学学报, refType=null, unstructuredReference=郝晟, 纪伦, 邬金麒, 等. 基于筛余特征参数的沥青混合料路用性能预测方法[J]. 哈尔滨工业大学学报, 2023, 55(11): 7-15, 35., articleTitle=基于筛余特征参数的沥青混合料路用性能预测方法, refAbstract=null), Reference(id=1204780282252603616, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, doi=null, pmid=null, pmcid=null, year=2023, volume=55, issue=11, pageStart=7, pageEnd=15, url=null, language=null, rfNumber=[35], rfOrder=40, authorNames=Hao Sheng, Ji Lun, Wu Jinqi, journalName=Journal of Harbin Institute of Technology, refType=null, unstructuredReference=Hao Sheng, Ji Lun, Wu Jinqi, et al. Road performance prediction method of asphalt mixture based on screen residual characteristic parameters[J]. Journal of Harbin Institute of Technology, 2023, 55(11): 7-15, 35., articleTitle=Road performance prediction method of asphalt mixture based on screen residual characteristic parameters, refAbstract=null), Reference(id=1204780282328101090, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, doi=null, pmid=null, pmcid=null, year=2021, volume=9, issue=null, pageStart=162059, pageEnd=162080, url=null, language=null, rfNumber=[36], rfOrder=41, authorNames=Dehghani M, Hubalovsky S, Trojovsky P, journalName=IEEE Access, refType=null, unstructuredReference=Dehghani M, Hubalovsky S, Trojovsky P. Northern goshawk optimization: a new swarm-based algorithm for solving optimization problems[J]. IEEE Access, 2021, 9: 162059-162080., articleTitle=Northern goshawk optimization: a new swarm-based algorithm for solving optimization problems, refAbstract=null)], funds=[Fund(id=1204780273721389125, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, awardId=null, language=CN, fundingSource=黑龙江省交通投资集团有限公司研究项目, fundOrder=null, country=null)], companyList=[AuthorCompany(id=1204780263810249457, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, xref=null, ext=[AuthorCompanyExt(id=1204780263818638064, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, companyId=1204780263810249457, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1. Heilongjiang Provincial Transportation Investment Group Co., Ltd, Harbin 150069, China), AuthorCompanyExt(id=1204780263827026673, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, companyId=1204780263810249457, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.黑龙江省交通投资集团有限公司, 哈尔滨 150069)]), AuthorCompany(id=1204780263923495674, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, xref=null, ext=[AuthorCompanyExt(id=1204780263944467195, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, companyId=1204780263923495674, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2. School of Transportation Science and Engineering, Harbin Institute of Technology, Harbin 150090, China), AuthorCompanyExt(id=1204780263957050109, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, companyId=1204780263923495674, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.哈尔滨工业大学交通学院, 哈尔滨 150090)])], figs=[ArticleFig(id=1204780266284888980, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, language=EN, label=Fig.1, caption=The structure of NGO-XGBoost regression model, figureFileSmall=FOSOBvlAl2gBMs80EHCURA==, figureFileBig=cDRgZmTkFp1UJZS7zQBbHg==, tableContent=null), ArticleFig(id=1204780267480265625, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, language=CN, label=图1, caption=NGO-XGBoost回归模型结构, figureFileSmall=FOSOBvlAl2gBMs80EHCURA==, figureFileBig=cDRgZmTkFp1UJZS7zQBbHg==, tableContent=null), ArticleFig(id=1204780267664815011, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, language=EN, label=Fig.2, caption=Asphalt mixture grading curves, figureFileSmall=UnLFey86P4w0yE7u1QYZ3w==, figureFileBig=v1yTNY5oYoblH5hBd0d7NA==, tableContent=null), ArticleFig(id=1204780267786449834, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, language=CN, label=图2, caption=级配曲线

1 in=0.025 4 m

, figureFileSmall=UnLFey86P4w0yE7u1QYZ3w==, figureFileBig=v1yTNY5oYoblH5hBd0d7NA==, tableContent=null), ArticleFig(id=1204780267887113136, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, language=EN, label=Fig.3, caption=Processing of predicting dynamic modulus and phase angle, figureFileSmall=0opbNiJesQvZLky6xX823g==, figureFileBig=yE08z+0gfst+35MrMced1A==, tableContent=null), ArticleFig(id=1204780268008747959, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, language=CN, label=图3, caption=动态模量和相位角的预测过程, figureFileSmall=0opbNiJesQvZLky6xX823g==, figureFileBig=yE08z+0gfst+35MrMced1A==, tableContent=null), ArticleFig(id=1204780268109411265, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, language=EN, label=Fig.4, caption=Dynamic modulus prediction results, figureFileSmall=GIuugPU672XBE6PudvzxwA==, figureFileBig=Q0nR+TqThNtPd+NnpGfcPw==, tableContent=null), ArticleFig(id=1204780268201685960, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, language=CN, label=图4, caption=动态模量预测结果, figureFileSmall=GIuugPU672XBE6PudvzxwA==, figureFileBig=Q0nR+TqThNtPd+NnpGfcPw==, tableContent=null), ArticleFig(id=1204780268432372688, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, language=EN, label=Fig.5, caption=Phase angle prediction results, figureFileSmall=uq5Fq05OaWF+nx7RaV1i2g==, figureFileBig=STH/X/SxdhBoppDqYLeb1Q==, tableContent=null), ArticleFig(id=1204780270332392409, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, language=CN, label=图5, caption=相位角预测结果, figureFileSmall=uq5Fq05OaWF+nx7RaV1i2g==, figureFileBig=STH/X/SxdhBoppDqYLeb1Q==, tableContent=null), ArticleFig(id=1204780270441444318, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, language=EN, label=Fig.6, caption=Dynamic modulus residual value, figureFileSmall=VktMvTJYWyFNFBGNjSoflQ==, figureFileBig=IA+tgH45VLXBiURQB8TTqw==, tableContent=null), ArticleFig(id=1204780270504358883, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, language=CN, label=图6, caption=动态模量残差值, figureFileSmall=VktMvTJYWyFNFBGNjSoflQ==, figureFileBig=IA+tgH45VLXBiURQB8TTqw==, tableContent=null), ArticleFig(id=1204780270579856365, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, language=EN, label=Fig.7, caption=Phase angle residual value, figureFileSmall=FtVmhpEi8WePUX/UH29xBg==, figureFileBig=yfc2EnKtqEDW67DTxqv9ZQ==, tableContent=null), ArticleFig(id=1204780270663742448, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, language=CN, label=图7, caption=相位角残差值, figureFileSmall=FtVmhpEi8WePUX/UH29xBg==, figureFileBig=yfc2EnKtqEDW67DTxqv9ZQ==, tableContent=null), ArticleFig(id=1204780270806348791, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, language=EN, label=Fig.8, caption=Box plots of MAE and MSE values for dynamic modulus training sets of different algorithms, figureFileSmall=K5MKZ9hOKF6nOPBUiOobMQ==, figureFileBig=yZ14vRAMMO+ueq60U3If/A==, tableContent=null), ArticleFig(id=1204780271984948219, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, language=CN, label=图8, caption=不同算法动态模量训练集MAE、MSE箱型图, figureFileSmall=K5MKZ9hOKF6nOPBUiOobMQ==, figureFileBig=yZ14vRAMMO+ueq60U3If/A==, tableContent=null), ArticleFig(id=1204780272073027584, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, language=EN, label=Fig.9, caption=Box plots of MAE and MSE values for dynamic modulus test sets of different algorithms, figureFileSmall=/pSa7/44fR5aF7w0VeXC+w==, figureFileBig=khhvcHlVz+miTaQumKLgyw==, tableContent=null), ArticleFig(id=1204780272169496581, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, language=CN, label=图9, caption=不同算法动态模量测试集MAE、MSE箱型图, figureFileSmall=/pSa7/44fR5aF7w0VeXC+w==, figureFileBig=khhvcHlVz+miTaQumKLgyw==, tableContent=null), ArticleFig(id=1204780272291131404, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, language=EN, label=Fig.10, caption=Box plots of MAE and MSE values for phase angle training sets of different algorithms, figureFileSmall=m+LzrVPmk0QzEzoQRGPpTg==, figureFileBig=vN5fIj2exGAGwLozVfXreg==, tableContent=null), ArticleFig(id=1204780272387600399, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, language=CN, label=图10, caption=不同算法相位角训练集MAE、MSE值箱型图, figureFileSmall=m+LzrVPmk0QzEzoQRGPpTg==, figureFileBig=vN5fIj2exGAGwLozVfXreg==, tableContent=null), ArticleFig(id=1204780272492458005, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, language=EN, label=Fig.11, caption=Box plots of MAE and MSE values for phase angle test sets of different algorithms, figureFileSmall=0EZshK9fkCkMWvYXxVEJmQ==, figureFileBig=I8NJLNH1inWkyRz+xqht5g==, tableContent=null), ArticleFig(id=1204780272593121303, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, language=CN, label=图11, caption=不同算法相位角测试集MAE、MSE值箱型图, figureFileSmall=0EZshK9fkCkMWvYXxVEJmQ==, figureFileBig=I8NJLNH1inWkyRz+xqht5g==, tableContent=null), ArticleFig(id=1204780272681201695, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, language=EN, label=Table 1, caption=

Other testing conditions

, figureFileSmall=null, figureFileBig=null, tableContent=
测试条件 测试值
频率/Hz 0.1,1,10,25
温度/℃ 5,20,35,40,45
沥青含量/% 4.4,4.6,5.1,5.5,5.8,6
), ArticleFig(id=1204780272773476387, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, language=CN, label=表1, caption=

其他测试条件

, figureFileSmall=null, figureFileBig=null, tableContent=
测试条件 测试值
频率/Hz 0.1,1,10,25
温度/℃ 5,20,35,40,45
沥青含量/% 4.4,4.6,5.1,5.5,5.8,6
), ArticleFig(id=1204780272865751081, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, language=EN, label=Table 2, caption=

Model error indicators

, figureFileSmall=null, figureFileBig=null, tableContent=
指标 计算公式
MSE 1 m i = 1 m ( y i - y i ) 2
MAE 1 m i = 1 m y i-yi|
R2 1- i = 1 m ( y ( i ) - y ( i ) ) 2 i = 1 m ( y ( i ) - y ( i ) ) 2
), ArticleFig(id=1204780273012551722, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, language=CN, label=表2, caption=

模型误差指标

, figureFileSmall=null, figureFileBig=null, tableContent=
指标 计算公式
MSE 1 m i = 1 m ( y i - y i ) 2
MAE 1 m i = 1 m y i-yi|
R2 1- i = 1 m ( y ( i ) - y ( i ) ) 2 i = 1 m ( y ( i ) - y ( i ) ) 2
), ArticleFig(id=1204780273104826415, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, language=EN, label=Table 3, caption=

Statistical results of dynamic modulus prediction ability of different algorithms

, figureFileSmall=null, figureFileBig=null, tableContent=
算法 MAE平均值 MSE平均值
NGO-XGBoost 914.87 2 119 326.77
XGBoost 993.91 2 353 470.18
TBA 1 244.48 2 972 055.70
TCN 1 367.47 3 722 967.55
BiGRU 1 901.77 5 702 640.35
BiLSTM 1 654.12 4 984 951.91
SVM 1 983.33 6 555 789.38
), ArticleFig(id=1204780273213878321, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, language=CN, label=表3, caption=

不同算法的动态模量预测能力统计结果

, figureFileSmall=null, figureFileBig=null, tableContent=
算法 MAE平均值 MSE平均值
NGO-XGBoost 914.87 2 119 326.77
XGBoost 993.91 2 353 470.18
TBA 1 244.48 2 972 055.70
TCN 1 367.47 3 722 967.55
BiGRU 1 901.77 5 702 640.35
BiLSTM 1 654.12 4 984 951.91
SVM 1 983.33 6 555 789.38
), ArticleFig(id=1204780273339707446, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, language=EN, label=Table 4, caption=

Statistical results of phase angle prediction ability of different algorithms

, figureFileSmall=null, figureFileBig=null, tableContent=
算法 MAE平均值 MSE平均值
NGO-XGBoost 2.001 420 7.300 070
XGBoost 2.132 235 7.778 370
TBA 2.643 385 11.497 195
TCN 3.012 430 15.001 840
BiGRU 4.473 150 29.775 655
BiLSTM 3.870 970 23.408 675
SVM 4.618 935 31.797 550
), ArticleFig(id=1204780273444565050, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908035860943181, language=CN, label=表4, caption=

不同算法的相位角预测能力统计结果

, figureFileSmall=null, figureFileBig=null, tableContent=
算法 MAE平均值 MSE平均值
NGO-XGBoost 2.001 420 7.300 070
XGBoost 2.132 235 7.778 370
TBA 2.643 385 11.497 195
TCN 3.012 430 15.001 840
BiGRU 4.473 150 29.775 655
BiLSTM 3.870 970 23.408 675
SVM 4.618 935 31.797 550
)], 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.1671-1815.2402458, detailUrlEn=https://castjournals.cast.org.cn/joweb/kxjsygc/EN/10.12404/j.issn.1671-1815.2402458, pdfUrlCn=https://castjournals.cast.org.cn/joweb/kxjsygc/CN/PDF/10.12404/j.issn.1671-1815.2402458, pdfUrlEn=https://castjournals.cast.org.cn/joweb/kxjsygc/EN/PDF/10.12404/j.issn.1671-1815.2402458, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于增强极限梯度提升算法的沥青混合料动态模量和相位角预测方法
收藏切换
PDF下载
曲世琦 1 , 梁尊东 2, * , 张鑫 1
科学技术与工程 | 论文·交通运输 2025,25(3): 1225-1234
收起
收藏切换
科学技术与工程 | 论文·交通运输 2025, 25(3): 1225-1234
基于增强极限梯度提升算法的沥青混合料动态模量和相位角预测方法
全屏
曲世琦1 , 梁尊东2, * , 张鑫1
作者信息
  • 1.黑龙江省交通投资集团有限公司, 哈尔滨 150069
  • 2.哈尔滨工业大学交通学院, 哈尔滨 150090
  • 曲世琦(1977—),男,汉族,黑龙江海伦人,硕士,高级工程师。研究方向:路桥工程。E-mail:

通讯作者:

* 梁尊东(1996—),男,汉族,海南澄迈人,博士研究生。研究方向:基于大数据材料性能预测及结构健康监测。E-mail:
Enhanced XGBoost-based Prediction Method for Dynamic Modulus and Phase Angle of Asphalt Mixture
Shi-qi QU1 , Zun-dong LIANG2, * , Xin ZHANG1
Affiliations
  • 1. Heilongjiang Provincial Transportation Investment Group Co., Ltd, Harbin 150069, China
  • 2. School of Transportation Science and Engineering, Harbin Institute of Technology, Harbin 150090, China
出版时间: 2025-01-28 doi: 10.12404/j.issn.1671-1815.2402458
文章导航
收藏切换

沥青混合料的动态模量是沥青路面设计的一个重要参数。利用集成方法从大量的沥青混凝土数据集中提取材料特性、动态模量和相位角信息,对优化沥青路面性能具有重要意义。极限梯度提升模型(extreme gradient boost, XGBoost)通过加权求和聚合一系列决策树模型,构建了一个强大的预测模型,同时通过优化损失函数将预测误差降至最低。为了进一步提高动态模量和相位角预测的准确性,使用启发式算法对模型进行了优化。最初,基于样本初始化基础模型,并计算训练数据的损失函数的梯度。随后,XGBoost利用梯度细节构建决策树模型,优化叶节点权重,并通过加权求和更新模型的预测。在此过程中,使用启发式算法对整个XGBoost模型的最佳参数进行优化。实验结果表明,改进的XGBoost模型在所有性能评价指标上都优于原模型,提高了预测沥青混合料动态模量和相位角的准确性。

沥青混合料  /  动态模量  /  相位角  /  增强算法

The dynamic modulus of asphalt mixture is an important parameter in the design of asphalt pavement. Extracting material characteristics, dynamic modulus, and phase angle information from a large amount of asphalt concrete datasets using integrated methods is of great significance for optimizing the performance of asphalt pavement. The extreme gradient boost (XGBoost) model aggregated a series of decision tree models through weighted summation to construct a powerful prediction model, while optimizing the loss function to minimize prediction errors. In order to further improve the accuracy of dynamic modulus and phase angle prediction, heuristic algorithms were used to optimize the model. Initially, the basic model was initialized based on samples and the gradient of the loss function of the training data was calculated. Subsequently, XGBoost utilized gradient details to construct a decision tree model, optimized leaf node weights, and updated the model’s predictions through weighted summation. During this process, heuristic algorithms are used to optimize the optimal parameters of the entire XGBoost model. The experimental results show that the improved XGBoost model outperforms the original model in all performance evaluation indicators, improving the accuracy of predicting the dynamic modulus and phase angle of asphalt mixtures.

asphalt mixture  /  dynamic modulus  /  phase angle  /  enhanced algorithm
曲世琦, 梁尊东, 张鑫. 基于增强极限梯度提升算法的沥青混合料动态模量和相位角预测方法. 科学技术与工程, 2025 , 25 (3) : 1225 -1234 . DOI: 10.12404/j.issn.1671-1815.2402458
Shi-qi QU, Zun-dong LIANG, Xin ZHANG. Enhanced XGBoost-based Prediction Method for Dynamic Modulus and Phase Angle of Asphalt Mixture[J]. Science Technology and Engineering, 2025 , 25 (3) : 1225 -1234 . DOI: 10.12404/j.issn.1671-1815.2402458
沥青混合料的动态模量和相位角是评价其弹性性能的关键参数。这些参数用于确定材料的弹性模量,计算应力和变形响应,并评估路面疲劳性能[1-3]。随着沥青混合料性能测试数据的不断收集和存储,数据量迅速增加,呈现出海量、多尺度、多类型、动态的特点。沥青混合物是一种非均质多孔材料,包括各种材料,如骨料、沥青和矿物填料。骨料级配、沥青含量、沥青黏度、试验温度和频率都会影响沥青的动态模量和相位角[4-8]。充分挖掘数据背后的材料映射关系,可以实现沥青混合料的动态模量和相位角,为有效提高沥青混合料高低温性能和路面疲劳寿命提供数据支撑。
目前,基于广泛的室内荷载试验和路面试验数据,使用统计回归模型、复合材料力学理论和机器学习算法,建立了预测动态模量和相位角的不同方法。在统计回归模型的研究中,Witchzak等[9]根据不同沥青混合料的数据开发了Witchzak模型,在该模型中,沥青混合料的动态模量表示为沥青含量、沥青黏度、骨料级配、混合料空隙率和荷载频率的函数。Huang等[10]提出了一种改进的甲壳虫天线搜索算法(beetle antennae search,BAS),以提高随机森林模型的搜索效率,结果表明在所有温度和频率范围内,动态模量的预测精度都非常高,克服了传统Witczak模型的局限性。Barugahare等[11]将使用人工神经网络(artificial neural network, ANN)预测动态模量的准确性与基于回归的模型(如Hirsch、Bari-Witchzak和基于93种沥青混合料数据的改进Bari-Witzzak模型)进行了比较,研究表明在捕捉沥青流变特性和混合料体积特性对动态模量的影响方面,人工神经网络优于基于回归的模型。Zhang等[12]运用灰色数学理论,对影响沥青混合料动态模量的因素进行了详细分析。试验发现,沥青软化点和沥青混合料中集料空隙率对动态模量有显著影响。在此基础上,采用多元线性回归来预测动态模量。在采用复合材料力学构建动态模量模型时,Sakhaeifar等[13]利用混合物时间-温度等效原理和黏弹性理论,通过回归分析导出了全局模型及其简化版本,这些模型主要考虑了沥青黏弹性、矿物级配、混合料体积指数和环境温度等参数。在这两类预测模型的研究中,数据回归法主要关注各种影响因素与沥青混合料动态模量的相关性,而复合材料力学方法倾向于构建将沥青混合料的动态模量与各种影响因素联系起来的物理模型。
目前,许多研究人员已经利用机器学习或深度学习方法来预测沥青混合料的动态模量和相位角。Arefin等[14]基于国家公路合作研究计划(national cooperative highway research program,NCHRP),提出了NCHRP 1-37A和NCHRP 1-40D预测模型,并将其应用在预测短期和长期老化热拌沥青和泡沫温拌沥青混合料动态模量,研究发现NCHRP 1-40D显示出更高的预测准确性。Behnood等[15]提出了树状回归算法(model tree with piecewise linear leaf nodes algorithm,M5P),该算法将沥青特性、级配和混合料体积特性作为输入。Daneshvar等[16]采用随机森林算法建立了动态模量的预测模型。在这项研究中,研究人员发现,与传统的Witczak模型回归模型相比,该模型更准确,此外测试温度和频率被确定为影响动态模量的主要因素。Barugahare等[17]利用袋装树集成算法(bagged trees ensemble,BTE)成功预测了致密级配沥青混合料的动态模量,与Bari-Witczak和Hirsch回归模型相比,该模型显示出更高的预测精度。为了进一步提高预测精度,研究人员采用各种优化算法来改进机器学习算法。Eleyedath等[18]采用主成分分析(principal component analysis,PCA)来降低数据维度,并利用基因表达编程(gene expression programming,GEP)方法来预测沥青混合料的动态模量。Gong等[19]利用逻辑激活函数建立了用于预测动态模量的深度学习网络,研究表明沥青的黏度和模量对预测沥青混合料动态模量的准确性有重大影响。Moussa等[20]率先将深度残差神经网络技术应用于沥青混合料动态模量预测,显著提高了预测能力,并将蒙特卡罗算法用于基于方差的全局灵敏度分析,以研究每个输入变量对动态模量的影响。Eidgahee等[21]比较了人工神经网络(ANN)、遗传规划(genetic programming,GP)和数据处理组合群方法(group method of data handling,GMDH)的预测精度,其中人工神经网络具有更好的通用性和鲁棒性。Uwanuakwa等[22]对人工神经网络、支持向量机、极限学习机和随机森林模型等各种方法对沥青混合料模量的预测效果进行了比较分析。通过对参数的敏感性分析,发现沥青含量是影响混合料模量的最重要因素。Ghasemi等[23]在沥青混合料参数敏感性分析的基础上,利用均值方差优化算法实现了具有目标模量的混合料优化设计。Chen等[24]研究了各种因素对动态模量预测准确性的影响,按重要性降序排列:沥青黏度和黏结剂的复模量、空隙率、沥青渗透值和软化点,并基于混合逻辑回归算法(mixed logistic regression, MLR)建立了S形函数的参数,从而可靠地预测了动态模量。通过广泛的全球敏感性分析(global sensitivity analysis,GSA),Owais等[25]确定了决定沥青混合料动态模量的最重要因素,包括黏结剂含量、剪切模量、矿物骨料中的空隙和温度。
Chen[26-29]在2016年基于梯度提升决策树(gradient boosting decision tree,GBDT)算法提出的极限梯度提升算法(extreme gradient boost,XGBoost),通过梯度提升和正则化技术迭代训练决策树模型,提高预测精度。XGBoost算法被广泛应用在道路开裂和防滑预测等研究领域有应用。研究表明,与其他算法相比,XGBoost在预测道路开裂和防滑性方面表现出更高的准确性。在动态模量预测研究领域,Ali等[30]对16种沥青混合料进行了实验室试验,测量了不同试验温度和加载频率下的动态模量。实验数据分为3类:试验条件、混合物体积特性和级配,作为XGBoost模型的输入,与其他回归模型和机器学习方法相比,XGBoost模型在预测动态模量方面表现出卓越的准确性。Li等[31]提出了一种混沌粒子群优化(chaotic particle swarm optimization,CPSO)算法和分段回归策略来优化XGBoost模型,实验结果表明,与经典的机器学习算法相比,该方法预测路面车辙面积的均方误差(mean square error,MSE)和平均绝对误差(mean absolute error,MAE)分别为5.80和1.59,这突出了XGBoost算法在处理道路工程中的非线性问题方面优于经典的机器学习方法。与传统的Witczak方程相比,XGBoost在预测动态模量时也表现出优越的预测精度[32-33]。此外,在沥青混合料路用性能预测方面,研究学者将优化的遗传算法用于预测沥青混合料的动稳定度、残留稳定度等性能[34]。郝晟等[35]则根据级配通过回归分析建立变异级配筛余特征参数用于预测沥青混合料残留稳定度等路用性能参数。
先前概述的研究方法为各种机器学习技术在预测沥青混合料动态模量方面的应用提供了见解。针对机器学习技术在预测沥青混合料动态模量时泛化能力不足的问题,通过深入分析影响沥青混合料性能的关键因素,如级配、油石比和沥青黏度参数,提出一种结合北方苍鹰优化算法的XGBoost优化模型,旨在通过算法优化提高XGBoost在新数据集上的预测性能,从而获得更准确的动态模量及相位角预测结果。
Dehghani等[36]提出的北方苍鹰优化是一种处理优化问题的算法。为了找到最优解,北方苍鹰优化算法(northern goshawk optimization,NGO)由两个阶段组成:猎物识别和攻击(探索阶段)和追捕和逃跑(利用阶段)。在算法的初始阶段,北方苍鹰的种群可以用种群矩阵表示为
T= T 1 T 2 T N= t 1,1   t 1,2     t 1 , m t 2,1   t 2,2     t 2 , m         t N , 1   t N , 2     t N , m
式(1)中:T为北方苍鹰的种群矩阵;Ti为第i只北方苍鹰的位置;ti,j为第i只北方苍鹰的第j维度的位置;N为北方苍鹰的种群大小;m为解决问题的维度。
在该算法中,优化问题的目标函数可用于计算北方苍鹰的目标函数值,其中目标函数值可由以下目标函数值的向量表示。
F= F 1 F 2 F N= F ( T 1 ) F ( T 2 ) F ( T N )
式(2)中:F为北方苍鹰种群的目标函数向量;Fi为第i只北方苍鹰的目标函数值。
在探索阶段,该算法采用各种随机搜索策略来探索优化问题的潜在解决方案。这有助于增加发现全局最优的可能性,并降低陷入局部最优的风险。然后,该算法编译在此阶段发现的一系列解决方案,作为后续阶段的候选解决方案,该阶段的计算方法为
Pi=Tk, i=1,2,…,N
t i , j , P 1 n e w= t i , j + r ( p i , j - I t i , j ) , F P i F i t i , j + r ( t i , j - p i , j ) , F P i F i
Ti= T i , P 1 n e w , F i , P 1 n e w F i T i , F i , P 1 n e w F i
式中:Pi表示第i只北方苍鹰的猎物位置; F P i为第i只北方苍鹰的猎物位置的目标函数值;k为1~ N的随机整数;ti,j为第i只北方苍鹰的第j维度的位置;pi,j表示第i只北方苍鹰的第j维度的猎物位置; t i , j , P 1 n e w是第i只北方苍鹰的第j维度的新位置; T i , P 1 n e w指的是第i只北方苍鹰的新位置; F i , P 1 n e w表示基于第一阶段的更新的第i只北方苍鹰的目标函数的值;r为0~1的随机数;I为一个随机整数,可以是1或2。
下一阶段是开发阶段,该算法采用进化算法集中优化和细化发现的解,旨在更好地满足优化问题的要求。随后,迭代地进行个体更新,以逐步提高群体中个体的适应度,从而促进优秀解决方案的生成和保留。该阶段的计算方法为
t i , j , P 2 n e w=ti,j+R(2r-1)ti,j
R=0.02 1 - m M
Ti= T i , P 2 n e w , F i , P 2 n e w F i T i , F i , P 2 n e w F i
式中:m为当前执行的迭代次数;M为过程中允许的迭代次数的最大限制; T i , P 2 n e w为第i只北方苍鹰的新位置, t i , j , P 2 n e w为第i只北方苍鹰的第j维度中的新位置; F i , P 2 n e w为基于第二阶段更新的第i只北方苍鹰的目标函数值;R为计算范围。
在完成初始迭代后,该算法为总体建立新的值,以及目标函数和所提出的最佳解。然后,算法继续进行下一次迭代,继续这个过程,直到最后一次迭代结束。然后,在整个迭代过程中获得的最佳解被认为是给定优化问题的最优解。
对于回归问题,XGBoost模型的预测值是输入特征的加权组合,其中每个弱学习器负责预测输入空间的特定区域。首先,构建一个用于优化模型参数的目标函数是至关重要的,表达式为
Fobj= i = 1 n l[yi,F(xi)]+λ j = 1 J β j 2+α j = 1 J β j
式(9)中:F(xi)为模型对样本xi的预测;yi为真实目标值;l为损失函数(本研究中的平方误差);λα为正则化参数;βj为模型参数;j为参数个数。
为了确保模型的正常运行和最佳性能,需要进行初始化过程。模型的初始预测值可以表示为
F(0)(x)=argmin i = 1 n l[yi,F(xi)]
式(10)中:F(0)(x)为初始预测值。
对于每个迭代t=1,2,…,T,更新模型预测值表示为
F(t)(x)=F(t-1)(x)+λtht(x)
式(11)中:F(t-1)(x)为来自上一次迭代的模型预测;λt为第t次迭代的学习率;ht(x)为来自第t次弱学习器的预测。
在式(11)中每个弱学习器ht(x)可以是决策树,其预测值计算公式为
ht(x)= j = 1 J t βtjI, xRtj
式(12)中:Jt为第t决策树中的叶节点数;βtj为第t颗树中第j个叶节点的权重;I(·)为表示样本x是否属于叶节点区域Rtj的指示符函数。
对于每个样本i和每次迭代t,损失函数的梯度gi和二阶导数hi表达式为
$\begin{aligned} g_{i} & =\frac{\partial l\left[y_{i}, F^{(t-1)}\left(x_{i}\right)\right]}{\partial F^{(t-1)}\left(x_{i}\right)} \\ h_{i} & =\frac{\partial^{2} l\left[y_{i}, F^{(t-1)}\left(x_{i}\right)\right]}{\partial\left[F^{(t-1)}\left(x_{i}\right)\right]^{2}} \end{aligned}$
在构建决策树的过程中,使用等式的梯度和二阶导数来计算每个潜在分割点的增益G,并选择具有最高增益的分割点作为实际分割点。即
G=( i L + wigi)-( i L - wigi)+λ( i L + hi+ i L - hi)
式(14)中:L+为分割后进入左子节点的样本集;L-为进入右子节点的采样集;wi为样本i的权重。
该模型的最终预测值是来自所有弱学习器的预测的加权和,表达式为
y = t = 1 T λtht(x)
整个过程从定义目标函数开始,通过弱学习器的迭代构建和模型预测的更新进行,最终形成一个组合多个弱学习器预测的集成模型。在每一步,损失函数的梯度和二阶导数都指导决策树的构建和分裂,而正则化项有助于控制模型复杂性并防止过拟合。
XGBoost模型有5个主要参数,最大迭代次数为Miter,树的最大深度为dmax,XGBoost的学习率为l,每棵树的随机采样比例为subsample。参数在模型的构建和训练中至关重要,其功能和值对模型的性能和有效性产生重大影响。参数的优化取决于专业知识、经验判断和广泛的实验验证。因此,本文中采用北方苍鹰优化算法进行参数优化,利用均方误差作为适应度函数,并在每次迭代中保留整个种群的最佳解和最佳个体解。训练模块和预测模块的组成如图1所示。
在本研究中,对7种类型的沥青混合料在不同测试频率、温度和沥青黏度特性下的动态模量和相位角信息进行了统计分析。这些数据来源于美国和加拿大联邦公路管理局的长期路面性能(long term pavement performance,LTPP)计划中的服务测试路段,级配图如图2所示,其他测试条件如表1所示。
以7种不同沥青混合料的真实数据为基础进行分析,旨在预测这些混合料的动态模量和相位角。该数据集包括1 548个数据样本,其中1 048个指定用于模型训练,其余用于测试。在计算过程中采用均方误差(mean square error,MSE)和平均绝对误差(mean absolute error,MAE)来衡量该算法的有效性,这是回归分析中量化实际值和预测值之间偏差的标准度量(表2)。这些度量的值越低,表示预测准确度越高。预测动态模量和相位角的整个流程图如图3所示,测试中使用的算法硬件环境采用AMDRyzen 7 6800H(3.20 GHz 8核)微处理器,16 GB DDR4内存,操作系统采用64位Windows 11中文专业版。
根据NGO算法的特点,结合XGBoost的参数范围和沥青路面结构数据的特点,对参数进行适当的设置。初始参数配置如下:最大迭代次数Miter=100,种群数量Pop=30,树的最大深度dmax=50,每棵树随机采样的最大比例subsample=1,该实验进行了20次,最佳预测结果如图4图5所示。
图4图5可以看出,预测结果主要集中在对角线附近,表明在大多数情况下,模型的预测值与实际值非常接近。但仍有一些点偏离了对角线。这些点表明,在某些情况下,模型的预测值与实际值之间存在显著偏差,这是由数据中的噪声和异常值引起的。为了进一步评估模型的性能,计算了实际值和预测值之间的残差,如图6图7所示。
残差数据显示决定系数R2非常高,范围为0.91~0.95,这表明该模型具有很高的预测精度。该模型显示出相对稳定的预测结果,大多数样本点的预测误差较小。这表明,该模型不仅保持了预测的一致性,而且在应用于新数据时表现出强大的泛化能力。
为了验证NGO-XGBoost回归模型在预测动态模量和相位角的有效性,将其与常用模型进行了比较。使用XGBoost、具有双向门控递归单元和注意力机制的时间卷积网络(temporal convolutional network-bidirectional gated recurrent unit-attention,TBA)、时间卷积网络(temporal convolutional network,TCN)、双向门控循环单位(bidirectional gated recurrent unit, BiGRU)、双向长短期记忆网络(bidirectional long short-term memory, BiLSTM)、支持向量机(support vector machine, SVM)等模型进行比较。在不同的模型中,使用相同的训练数据集来训练模型,学习率为0.01, 采用Adam优化算法。训练时期的最大数量设置为150。学习率调整因子和正则化参数都固定在0.001。 比较了NGO XGBoost回归模型、XGBoost、TCN-BiGRU-Attention、TCN、BiGRU、BiLSTM和SVM在MAE和MSE上的性能,如图8~图11所示。
图8~图11可以看出,与XGBoost模型和其他传统模型相比,本文提出的模型在动态模量和相位角的预测方面表现出明显优越的性能,对新数据预测具有更好的泛化能力。在动态模量测试集中,与XGBoost模型相比,本文提出的模型在MSE中的预测精度提高了9.95%。同样,在相位角测试集中,精度在MSE中提高了6.15%。在MAE改进方面,与XGBoost模型相比,动态模量和相位角的预测分别提高了7.95%和6.14%,统计值如表3表4所示。
针对XGBoost模型在动态模量和相位角预测中泛化能力弱、难以选择最优参数的问题,提出了基于北方苍鹰优化算法的NGO-XGBoost算法。在本研究中,使用不同频率、温度、级配和黏度的沥青对模型的性能进行了评估。就均方误差(MSE)和平均绝对误差(MAE)而言,NGO-XGBoost模型在所有数据集上都优于其他比较算法。实验结果表明,NGO-XGBoost回归模型能够有效地预测沥青混合料的动态模量和相位角。具体而言,可以得到以下结论。
(1) NGO-XGBoost模型结合了XGBoost算法的高效预测能力和北方苍鹰优化算法的参数优化特性。
(2)通过与其他几种常用的机器学习模型进行比较,证明了NGO-XGBoost模型在预测精度上的优越性。
(3) NGO-XGBoost模型实验结果不仅在训练集上表现良好,同样在测试集上也展现了较高的预测准确性。这一点表明NGO-XGBoost模型不仅能够很好地拟合已知数据,也能够对新的、未见过的数据进行有效预测,这是模型泛化能力的重要体现。
尽管本文提出的算法在所有算法中表现出最佳的优化性能,但预测误差仍有较小的波动。首先,深度神经网络模型高度复杂,具有大量参数,这导致模型规模大,并使其在工程环境中实时应用具有挑战性。其次,模型训练需要大量的数据,很难获得沥青混合料的相关参数。最后,如何更好地适应进化算法并优化XGBoost模型是下一个需要研究和解决的问题。
  • 黑龙江省交通投资集团有限公司研究项目
参考文献 引证文献
排序方式:
[1]
Ran W P, Qiu H Z, Ai X C, et al. Experimental study on the dynamic modulus of an asphalt roadbed grouting mixture under the influence of complex and multiple factors[J]. Buildings, 2023, 13(8): 13081969.
[2]
Nobakht M, Sakhaeifar M S. Dynamic modulus and phase angle prediction of laboratory aged asphalt mixtures[J]. Construction and Building Materials, 2018, 190: 740-751.
[3]
Cooper S B, Mohammad L N, Elseifi M A, et al. Dynamic modules of asphalt mixtures evaluation of effects on pavement performance prediction[J]. Transportation Research Record, 2015, 2507: 67-77.
[4]
Zou X L, Sha A M, Jiang W, et al. Modification mechanism of high modulus asphalt binders and mixtures performance evaluation[J]. Construction and Building Materials, 2015, 90: 53-58.
[5]
Zhang J P, Hu D L, Yang F H, et al. Effect of property variations of raw materials on the variability of dynamic moduli of asphalt mixtures[J]. Journal of Testing and Evaluation, 2016, 44: 868-877.
[6]
董子震, 张金喜, 孙国强, 等. 骨料级配对相变沥青混合料性能的影响[J]. 科学技术与工程, 2024, 24(1): 352-359.
Dong Zizhen, Zhang Jinxi, Sun Guoqiang, et al. Effect of gradation on the performance of phase change asphalt mixture[J]. Science Technology and Engineering, 2024, 24(1): 352-359.
[7]
李昌辉, 倪广聪, 徐希忠, 等. 不同胶粉掺量下橡胶沥青混合料路用性能分析[J]. 科学技术与工程, 2023, 23(6): 2595-2605.
Li Changhui, Ni Guangcong, Xu Xizhong, et al. Road performance analysis of rubber asphalt mixture under different rubber powder dosage[J]. Science Technology and Engineering, 2023, 23(6): 2595-2605.
[8]
张琛, 潘峰, 李佳侬. 基于材料性能和数理统计的改性沥青适用性[J]. 科学技术与工程, 2020, 20(34): 14243-14250.
Zhang Chen, Pan Feng, Li Jianong. The applicability of modified asphalt based on material properties and mathematical statistics method[J]. Science Technology and Engineering, 2020, 20(34): 14243-14250.
[9]
Witczak M W, Fonseca O A. Revised predictive model for dynamic(complex) modulus of asphalt mixtures[J]. Transportation Research Record: Journal of the Transportation Research Board, 1996, 1540: 15-23.
[10]
Huang J D, Kumar G S, Ren J L, et al. Accurately predicting dynamic modulus of asphalt mixtures in low temperature regions using hybrid artificial intelligence mode[J]. Construction and Building Materials, 2021, 297: 123655.
[11]
Barugahare J, Amirkhanian A N, Xiao F P, et al. ANN-based dynamic modulus models of asphalt mixtures with similar input variables as Hirsch and Witczak models[J]. International Journal of Pavement Engineering, 2022, 23: 1328-1338.
[12]
Zhang M, Zhao H, Fan L L, et al. Dynamic modulus prediction model and analysis of factors influencing asphalt mixtures using gray relational analysis methods[J]. Journal of Materials Research and Technology, 2022, 19: 1312-1321.
[13]
Sakhaeifar M S, Kim Y R, Kabir P. New predictive models for the dynamic modulus of hot mix asphalt[J]. Construction and Building Materials, 2015, 76: 221-231.
[14]
Arefin M S, Quasem T, Nazzal M, et al. Accuracy of MEPDG dynamic modulus predictions for short-term and long-term aged asphalt mixtures[J]. Journal of Transportation Engineering Part B-Pavements, 2019, 145: 04019025.
[15]
Behnood A, Daneshvar D. A machine learning study of the dynamic modulus of asphalt concretes an application of M5P model tree algorithm[J]. Construction and Building Materials, 2020, 262: 120544.
[16]
Daneshvar D, Behnood A. Estimation of the dynamic modulus of asphalt concretes using random forests algorithm[J]. International Journal of Pavement Engineering, 2020, 23: 250-260.
[17]
Barugahare J, Amirkhanian A N, Xiao F P, et al. Predicting the dynamic modulus of hot mix asphalt mixtures using bagged trees ensemble[J]. Construction and Building Materials, 2020, 260: 120468.
[18]
Eleyedath A, Swamy A K. Prediction of dynamic modulus of asphalt concrete using hybrid machine learning technique[J]. International Journal of Pavement Engineering, 2022, 23: 2083-2098.
[19]
Gong H R, Sun Y R, Dong Y S, et al. Improved estimation of dynamic modulus for hot mix asphalt using deep learning[J]. Construction and Building Materials, 2020, 263: 119912.
[20]
Moussa G S, Owais M. Modeling hot-mix asphalt dynamic modulus using deep residual neural networks parametric and sensitivity analysis study[J]. Construction and Building Materials, 2021, 294: 123589.
[21]
Eidgahee D R, Jahangir H, Solatifar N, et al. Data-driven estimation models of asphalt mixtures dynamic modulus using ANN, GP and combinatorial GMDH approaches[J]. Neural Computing & Applications, 2022, 34: 17289-17314.
[22]
Uwanuakwa I D, Busari A A, Shaban I A, et al. Comparing machine learning models with witczak NCHRP 1-40D model for hot-mix asphalt dynamic modulus prediction[J]. Arabian Journal for Science and Engineering, 2022, 47: 13579-13591.
[23]
Ghasemi P, Aslani M, Rollins D K, et al. Principal component neural networks for modeling, prediction, and optimization of hot mix asphalt dynamics modulus[J]. Infrastructures, 2019, 4: 53.
[24]
Chen H, Saba R G, Liu G, et al. Influence of material factors on the determination of dynamic moduli and associated prediction models for different types of asphalt mixtures[J]. Construction and Building Materials, 2023, 365: 130134.
[25]
Owais M, Moussa G S. Global sensitivity analysis for studying hot-mix asphalt dynamic modulus parameters[J]. Construction and Building Materials, 2024, 413: 134775.
[26]
Chen T Q, Carlos G. XGBoost:A scalable tree boosting system[C]// KDD’16: Proceedings of the 22nd ACM Sigkdd International Conference on Knowledge Discovery and Data Mining. New York: IEEE, 2016: 785-794.
[27]
Friedman J H. Greedy function approximation: a gradient boosting machine[J]. Annals of Statistics, 2021, 29: 1189-1232.
[28]
Daneshvari M H, Nourmohammadi E, Ameri M, et al. Efficient LBP-GLCM texture analysis for asphalt pavement raveling detection using extreme gradient boost[J]. Construction and Building Materials, 2023, 401: 132731.
[29]
Zhan Y, Liu C, Deng Q S, et al. Integrated FFT and XGBoost framework to predict pavement skid resistance using automatic 3D texture measurement[J]. Measurement, 2022, 188: 110638.
[30]
Ali Y, Hussain F, Irfan M, et al. An extreme gradient boosting model for predicting dynamic modulus of asphalt concrete mixtures[J]. Construction and Building Materials, 2021, 295: 123642.
[31]
Li Z X, Shi X L, Cao J D, et al. CPSO-XGBoost segmented regression model for asphalt pavement deflection basin area prediction[J]. Science China-Technological Sciences, 2022, 65: 1470-1481.
[32]
Liu J, Liu F Y, Wang Z, et al. Involving prediction of dynamic modulus in asphalt mix design with machine learning and mechanical-empirical analysis[J]. Construction and Building Materials, 2023, 407: 133610.
[33]
刘志杨, 董泽蛟, 周涛, 等. 基于材料信息学的沥青混合料性能提升综述及展望[J]. 中国公路学报, 2024, 37(4): 98-120.
Liu Zhiyang, Dong Zejiao, Zhou Tao, et al. Review and prospects of performance enhancement of asphalt mixtures based on material informatics[J]. China Journal of Highway and Transport, 2024, 37(4): 98-120.
[34]
沈楸, 肖鹏, 顾万, 等. 基于遗传神经网络的再生沥青混合料性能预测研究[J]. 公路工程, 2020, 45(2): 61-67.
Shen Qiu, Xiao Peng, Gu Wan, et al. Prediction of performance of recycled asphalt mixture based on genetic neural network[J]. Highway Engineering, 2020, 45(2): 61-67.
[35]
郝晟, 纪伦, 邬金麒, 等. 基于筛余特征参数的沥青混合料路用性能预测方法[J]. 哈尔滨工业大学学报, 2023, 55(11): 7-15, 35.
Hao Sheng, Ji Lun, Wu Jinqi, et al. Road performance prediction method of asphalt mixture based on screen residual characteristic parameters[J]. Journal of Harbin Institute of Technology, 2023, 55(11): 7-15, 35.
[36]
Dehghani M, Hubalovsky S, Trojovsky P. Northern goshawk optimization: a new swarm-based algorithm for solving optimization problems[J]. IEEE Access, 2021, 9: 162059-162080.
2025年第25卷第3期
PDF下载
296
118
引用本文
BibTeX
文章信息
doi: 10.12404/j.issn.1671-1815.2402458
  • 接收时间:2024-04-06
  • 首发时间:2025-07-29
  • 出版时间:2025-01-28
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2024-04-06
  • 修回日期:2024-07-18
基金
黑龙江省交通投资集团有限公司研究项目
作者信息
    1.黑龙江省交通投资集团有限公司, 哈尔滨 150069
    2.哈尔滨工业大学交通学院, 哈尔滨 150090

通讯作者:

* 梁尊东(1996—),男,汉族,海南澄迈人,博士研究生。研究方向:基于大数据材料性能预测及结构健康监测。E-mail:
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/kxjsygc/CN/10.12404/j.issn.1671-1815.2402458
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