Article(id=1156908037400252755, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1156907871645556837, articleNumber=null, orderNo=null, doi=10.12404/j.issn.1671-1815.2309410, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=research-article, receivedDate=1701187200000, receivedDateStr=2023-11-29, revisedDate=1719158400000, revisedDateStr=2024-06-24, acceptedDate=null, acceptedDateStr=null, onlineDate=1753757970427, onlineDateStr=2025-07-29, pubDate=1737993600000, pubDateStr=2025-01-28, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1753757970427, onlineIssueDateStr=2025-07-29, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1753757970427, creator=13701087609, updateTime=1753757970427, 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=1214, endPage=1224, ext={EN=ArticleExt(id=1156908038784373078, articleId=1156908037400252755, tenantId=1146029695717560320, journalId=1146123166801305609, language=EN, title=Asphalt Mixture Performance Prediction Method Based on BP Neural Network Optimized by Genetic Algorithm, columnId=1156262728772735295, journalTitle=Science Technology and Engineering, columnName=Papers·Traffics and Transportations, runingTitle=null, highlight=null, articleAbstract=

To achieve rapid and reliable prediction of asphalt mixture performance, a method for predicting asphalt mixture performance by optimizing the back propagation (BP) neural network with a genetic algorithm (GA) from the perspective of material composition design was proposed. Initially, a grey relational analysis method was employed to reduce the dimensionality of multidimensional input variables, identifying the core influencing factors of asphalt mixture performance. Subsequently, integrating the GA, a GA-BP neural network prediction model was constructed with the core influencing factors as the input layer and asphalt mixture performance as the output layer. The model underwent training, validation analysis, and prediction generalization application. A comparison with the training effectiveness and prediction accuracy of the BP neural network was conducted to verify the accuracy of the GA-BP neural network model. The research results indicate that the grey relational degrees of eight performance characteristics, including air void, asphalt-aggregate ratio, nominal maximum aggregate size, 4.75 mm passing rate, asphalt type, softening point, penetration, and ductility, are all greater than 0.6, signifying their significant impact on asphalt mixture performance. Compared to the BP neural network model, the GA-BP neural network model reduces the root mean square error (RMSE) by 16% to 31%, decreases the mean absolute error (MAE) by 15% to 24%, and improves the R2 value by 0.01 to 0.27, indicating that it has better learning and fitting capabilities. The prediction accuracy for dynamic modulus, dynamic stability, residual stability, splitting tensile strength ratio, and ultimate bending strain of the asphalt mixture is respectively enhanced by 35.26%, 47.78%, 23.13%, 31.92%, and 35.75%, revealing the superior generalization application capability of the GA-BP neural network model. The research findings provide essential references for the rapid prediction of asphalt mixture performance and guidance in the design of asphalt mixture material composition.

, correspAuthors=Li LIU, authorNote=null, correspAuthorsNote=null, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=null, magXml=null, pdfUrl=null, pdf=null, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=null, mapNumber=null, authorCompany=null, fund=null, authors=null, authorsList=Jia-hao SHENG, Li LIU, Zhao-hui LIU, Bo-yang PAN), CN=ArticleExt(id=1156908082514186767, articleId=1156908037400252755, tenantId=1146029695717560320, journalId=1146123166801305609, language=CN, title=基于遗传算法优化BP神经网络的沥青混合料性能预测方法, columnId=1156262730664366426, journalTitle=科学技术与工程, columnName=论文·交通运输, runingTitle=null, highlight=null, articleAbstract=

为实现沥青混合料性能的快速可靠预测,从材料组成设计角度出发,提出了一种基于遗传算法(genetic algorithm, GA)优化反向传播(back propagation, BP)神经网络的沥青混合料性能预测方法。首先运用灰关联分析方法对多维输入变量进行降维处理,确定了沥青混合料性能的核心影响因素,然后结合遗传算法(GA),构建了以核心影响因素为输入层、沥青混合料性能为输出层的GA-BP神经网络预测模型,再对模型进行训练验证分析与预测泛化应用,同时与BP神经网络的训练效果和预测精度进行对比,验证GA-BP神经网络模型的准确性。研究结果表明:空隙率、油石比、公称最大粒径、4.75 mm通过率、沥青种类、软化点、针入度、延度等8项性能特征的灰关联度r>0.6,对沥青混合料性能影响显著;相比于BP神经网络模型,经过GA优化后的BP神经网络模型的均方根误差(root mean square error, RMSE)降低了16%~31%,平均绝对误差(mean absolute error, MAE)降低了15%~24%,R2 值提升了0.01~0.27,说明其具有更好的学习拟合能力;在对沥青混合料动态模量、动稳定度、残留稳定度、劈裂抗拉强度比和极限弯拉应变的预测精度上分别提高了35.26%、47.78%、23.13%、31.92%、35.75%,说明GA-BP神经网络模型具有更强的泛化应用能力。研究成果为实现沥青混合料性能的快速预测、指导沥青混合料材料组成设计提供重要参考。

, correspAuthors=柳力, authorNote=null, correspAuthorsNote=
* 柳力(1988—),男,汉族,湖南长沙人,博士,副教授。研究方向:道路工程。E-mail:
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=Y/Ixr4XAuusUBtw80gEMJw==, magXml=70bTTd/juLTGhkkpNW79qw==, pdfUrl=null, pdf=Xwf4B87wYOzNLbf+WIvrIg==, pdfFileSize=7661180, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=QIWH/WSYFmypBo2NmyhrTQ==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=VY4i750A4Tz9HVRuXQQDhw==, mapNumber=null, authorCompany=null, fund=null, authors=

盛佳豪(2000—),男,汉族,湖南益阳人,博士研究生。研究方向:道路工程。E-mail:

, authorsList=盛佳豪, 柳力, 刘朝晖, 潘博洋)}, authors=[Author(id=1204780264137400614, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=JiaH_Sheng@163.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1204780264254841134, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, authorId=1204780264137400614, language=EN, stringName=Jia-hao SHENG, firstName=Jia-hao, middleName=null, lastName=SHENG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=School of Traffic and Transportation Engineering, Changsha University of Science and Technology, Changsha 410114, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1204780264372281652, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, authorId=1204780264137400614, language=CN, stringName=盛佳豪, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=长沙理工大学交通运输工程学院, 长沙 410114, bio={"content":"

盛佳豪(2000—),男,汉族,湖南益阳人,博士研究生。研究方向:道路工程。E-mail:

"}, bioImg=null, bioContent=

盛佳豪(2000—),男,汉族,湖南益阳人,博士研究生。研究方向:道路工程。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1204780263994794265, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, xref=null, ext=[AuthorCompanyExt(id=1204780264007377178, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, companyId=1204780263994794265, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Traffic and Transportation Engineering, Changsha University of Science and Technology, Changsha 410114, China), AuthorCompanyExt(id=1204780264015765788, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, companyId=1204780263994794265, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=长沙理工大学交通运输工程学院, 长沙 410114)])]), Author(id=1204780264472944962, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=805296712@qq.com, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1204780264561025356, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, authorId=1204780264472944962, language=EN, stringName=Li LIU, firstName=Li, middleName=null, lastName=LIU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=*, address=School of Traffic and Transportation Engineering, Changsha University of Science and Technology, Changsha 410114, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1204780264670077266, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, authorId=1204780264472944962, language=CN, stringName=柳力, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=*, address=长沙理工大学交通运输工程学院, 长沙 410114, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1204780263994794265, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, xref=null, ext=[AuthorCompanyExt(id=1204780264007377178, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, companyId=1204780263994794265, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Traffic and Transportation Engineering, Changsha University of Science and Technology, Changsha 410114, China), AuthorCompanyExt(id=1204780264015765788, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, companyId=1204780263994794265, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=长沙理工大学交通运输工程学院, 长沙 410114)])]), Author(id=1204780264787517788, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, 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=1204780264930124130, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, authorId=1204780264787517788, language=EN, stringName=Zhao-hui LIU, firstName=Zhao-hui, middleName=null, lastName=LIU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=School of Traffic and Transportation Engineering, Changsha University of Science and Technology, Changsha 410114, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1204780265043370344, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, authorId=1204780264787517788, language=CN, stringName=刘朝晖, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=长沙理工大学交通运输工程学院, 长沙 410114, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1204780263994794265, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, xref=null, ext=[AuthorCompanyExt(id=1204780264007377178, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, companyId=1204780263994794265, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Traffic and Transportation Engineering, Changsha University of Science and Technology, Changsha 410114, China), AuthorCompanyExt(id=1204780264015765788, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, companyId=1204780263994794265, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=长沙理工大学交通运输工程学院, 长沙 410114)])]), Author(id=1204780265173393777, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, 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=1204780265303417211, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, authorId=1204780265173393777, language=EN, stringName=Bo-yang PAN, firstName=Bo-yang, middleName=null, lastName=PAN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=School of Traffic and Transportation Engineering, Changsha University of Science and Technology, Changsha 410114, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1204780265408274813, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, authorId=1204780265173393777, language=CN, stringName=潘博洋, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=长沙理工大学交通运输工程学院, 长沙 410114, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1204780263994794265, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, xref=null, ext=[AuthorCompanyExt(id=1204780264007377178, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, companyId=1204780263994794265, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Traffic and Transportation Engineering, Changsha University of Science and Technology, Changsha 410114, China), AuthorCompanyExt(id=1204780264015765788, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, companyId=1204780263994794265, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=长沙理工大学交通运输工程学院, 长沙 410114)])])], keywords=[Keyword(id=1204780265655738767, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, language=EN, orderNo=1, keyword=road engineering), Keyword(id=1204780265748013459, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, language=EN, orderNo=2, keyword=performance prediction), Keyword(id=1204780265852871061, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, language=EN, orderNo=3, keyword=GA-BP neural network), Keyword(id=1204780265961922974, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, language=EN, orderNo=4, keyword=asphalt mixture), Keyword(id=1204780266096140705, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, language=EN, orderNo=5, keyword=gray correlation analysis), Keyword(id=1204780266200998310, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, language=CN, orderNo=1, keyword=道路工程), Keyword(id=1204780266310050219, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, language=CN, orderNo=2, keyword=性能预测), Keyword(id=1204780267505426863, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, language=CN, orderNo=3, keyword=GA-BP神经网络), Keyword(id=1204780267669004726, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, language=CN, orderNo=4, keyword=沥青混合料), Keyword(id=1204780267773862329, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, language=CN, orderNo=5, keyword=灰关联分析)], refs=[Reference(id=1204780277378818668, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, doi=null, pmid=null, pmcid=null, year=2000, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=沈金安, journalName=沥青及沥青混合料路用性能, refType=null, unstructuredReference=沈金安. 沥青及沥青混合料路用性能[M]. 北京: 人民交通出版社, 2000., articleTitle=null, refAbstract=null), Reference(id=1204780277462704751, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, doi=null, pmid=null, pmcid=null, year=2000, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[1], rfOrder=1, authorNames=Shen Jin’an, journalName=Asphalt and asphalt mixture road performance, refType=null, unstructuredReference=Shen Jin’an. Asphalt and asphalt mixture road performance[M]. Beijing: China Communication Press, 2000., articleTitle=null, refAbstract=null), Reference(id=1204780277580145266, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, doi=null, pmid=null, pmcid=null, year=2019, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[2], rfOrder=2, authorNames=黄晓明, journalName=路基路面工程, refType=null, unstructuredReference=黄晓明. 路基路面工程[M]. 6版. 北京: 人民交通出版社, 2019., articleTitle=null, refAbstract=null), Reference(id=1204780277743723126, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, doi=null, pmid=null, pmcid=null, year=1999, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[2], rfOrder=3, authorNames=Huang Xiaoming, journalName=Road subgrade and pavement engineering, refType=null, unstructuredReference=Huang Xiaoming. Road subgrade and pavement engineering[M]. 6th ed. Beijing: China Communication Press, 1999., articleTitle=null, refAbstract=null), Reference(id=1204780277831803513, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, doi=null, pmid=null, pmcid=null, year=2024, volume=24, issue=8, pageStart=3389, pageEnd=3398, url=null, language=null, rfNumber=[3], rfOrder=4, authorNames=陆学元, 陈远播, 魏星, journalName=科学技术与工程, refType=null, unstructuredReference=陆学元, 陈远播, 魏星, 等. 沥青混合料低温劈裂虚拟试验影响因素研究[J]. 科学技术与工程, 2024, 24(8): 3389-3398., articleTitle=沥青混合料低温劈裂虚拟试验影响因素研究, refAbstract=null), Reference(id=1204780277949244028, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, doi=null, pmid=null, pmcid=null, year=2024, volume=24, issue=8, pageStart=3389, pageEnd=3398, url=null, language=null, rfNumber=[3], rfOrder=5, authorNames=Lu Xueyuan, Chen Yuanbo, Wei Xing, journalName=Science Technology and Engineering, refType=null, unstructuredReference=Lu Xueyuan, Chen Yuanbo, Wei Xing, et al. Influence factors of low-temperature virtual indirect tensile test for asphalt mixtures[J]. Science Technology and Engineering, 2024, 24(8): 3389-3398., articleTitle=Influence factors of low-temperature virtual indirect tensile test for asphalt mixtures, refAbstract=null), Reference(id=1204780278075073152, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, doi=null, pmid=null, pmcid=null, year=2023, volume=41, issue=3, pageStart=306, pageEnd=310, url=null, language=null, rfNumber=[4], rfOrder=6, authorNames=刘莉萍, 杜婷, 郭建博, journalName=石河子大学学报(自然科学版), refType=null, unstructuredReference=刘莉萍, 杜婷, 郭建博. 基于响应曲面法硅藻土改性沥青混合料性能研究[J]. 石河子大学学报(自然科学版), 2023, 41(3): 306-310., articleTitle=基于响应曲面法硅藻土改性沥青混合料性能研究, refAbstract=null), Reference(id=1204780278184125060, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, doi=null, pmid=null, pmcid=null, year=2023, volume=41, issue=3, pageStart=306, pageEnd=310, url=null, language=null, rfNumber=[4], rfOrder=7, authorNames=Liu Liping, Du Ting, Guo Jianbo, journalName=Journal of Shihezi University(Natural Science), refType=null, unstructuredReference=Liu Liping, Du Ting, Guo Jianbo. Response surface method for performance of diatomite modified asphalt mixture[J]. Journal of Shihezi University(Natural Science), 2023, 41(3): 306-310., articleTitle=Response surface method for performance of diatomite modified asphalt mixture, refAbstract=null), Reference(id=1204780278276399752, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=11, pageStart=40, pageEnd=44, url=null, language=null, rfNumber=[5], rfOrder=8, authorNames=郭忠宝, journalName=北方交通, refType=null, unstructuredReference=郭忠宝. 溶剂型冷补沥青混合料材料组成设计研究[J]. 北方交通, 2022(11): 40-44., articleTitle=溶剂型冷补沥青混合料材料组成设计研究, refAbstract=null), Reference(id=1204780278356091530, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=11, pageStart=40, pageEnd=44, url=null, language=null, rfNumber=[5], rfOrder=9, authorNames=Guo Zhongbao, journalName=Northern Communications, refType=null, unstructuredReference=Guo Zhongbao. Research on the material composition design of solvent cold patching asphalt mixture[J]. Northern Communications, 2022(11): 40-44., articleTitle=Research on the material composition design of solvent cold patching asphalt mixture, refAbstract=null), Reference(id=1204780278473532044, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, doi=null, pmid=null, pmcid=null, year=2016, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[6], rfOrder=10, authorNames=刘树俊, journalName=新型冷拌沥青混合料制备及其性能研究, refType=null, unstructuredReference=刘树俊. 新型冷拌沥青混合料制备及其性能研究[D]. 青岛: 中国石油大学(华东), 2016., articleTitle=null, refAbstract=null), Reference(id=1204780278603555472, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, doi=null, pmid=null, pmcid=null, year=2016, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[6], rfOrder=11, authorNames=Liu Shujun, journalName=Fabrication and performance of novel cold-mix asphalt mixture, refType=null, unstructuredReference=Liu Shujun. Fabrication and performance of novel cold-mix asphalt mixture[D]. Qingdao: China University of Petroleum(East China), 2016., articleTitle=null, refAbstract=null), Reference(id=1204780278670664337, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, doi=null, pmid=null, pmcid=null, year=2020, volume=6, issue=5, pageStart=2, pageEnd=12, url=null, language=null, rfNumber=[7], rfOrder=12, authorNames=谭忆秋, 吕慧杰, 徐慧宁, journalName=交通运输研究, refType=null, unstructuredReference=谭忆秋, 吕慧杰, 徐慧宁. 材料基因思想在沥青路面材料领域的应用展望[J]. 交通运输研究, 2020, 6(5): 2-12., articleTitle=材料基因思想在沥青路面材料领域的应用展望, refAbstract=null), Reference(id=1204780278750356115, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, doi=null, pmid=null, pmcid=null, year=2020, volume=6, issue=5, pageStart=2, pageEnd=12, url=null, language=null, rfNumber=[7], rfOrder=13, authorNames=Tan Yiqiu, Lü Huijie, Xu Huining, journalName=Transport Research, refType=null, unstructuredReference=Tan Yiqiu, Huijie, Xu Huining. Application prospect of material genetics idea in asphalt pavement materials[J]. Transport Research, 2020, 6(5): 2-12., articleTitle=Application prospect of material genetics idea in asphalt pavement materials, refAbstract=null), Reference(id=1204780278855213718, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, doi=null, pmid=null, pmcid=null, year=2020, volume=33, issue=10, pageStart=76, pageEnd=90, url=null, language=null, rfNumber=[8], rfOrder=14, authorNames=邢超, 谭忆秋, 张凯, journalName=中国公路学报, refType=null, unstructuredReference=邢超, 谭忆秋, 张凯, 等. 基于材料基因组方法的沥青混合料基因特性综述及展望[J]. 中国公路学报, 2020, 33(10): 76-90., articleTitle=基于材料基因组方法的沥青混合料基因特性综述及展望, refAbstract=null), Reference(id=1204780278934905497, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, doi=null, pmid=null, pmcid=null, year=2020, volume=33, issue=10, pageStart=76, pageEnd=90, url=null, language=null, rfNumber=[8], rfOrder=15, authorNames=Xing Chao, Tan Yiqiu, Zhang Kai, journalName=China Journal of Highway and Transport, refType=null, unstructuredReference=Xing Chao, Tan Yiqiu, Zhang Kai, et al. Review and prospect of genetic characteristics of asphalt mixture based on material genome method[J]. China Journal of Highway and Transport, 2020, 33(10): 76-90., articleTitle=Review and prospect of genetic characteristics of asphalt mixture based on material genome method, refAbstract=null), Reference(id=1204780279014597276, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, doi=null, pmid=null, pmcid=null, year=2014, volume=18, issue=2, pageStart=99, pageEnd=117, url=null, language=null, rfNumber=[9], rfOrder=16, authorNames=Pablo J, Jones B, Lind C, journalName=Current Opinion in Solid State & Materials Science, refType=null, unstructuredReference=Pablo J, Jones B, Lind C, et al. The materials genome initiative, the interplay of experiment, theory and computation[J]. Current Opinion in Solid State & Materials Science, 2014, 18(2): 99-117., articleTitle=The materials genome initiative, the interplay of experiment, theory and computation, refAbstract=null), Reference(id=1204780279102677659, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, doi=null, pmid=null, pmcid=null, year=2020, volume=242, issue=null, pageStart=118043, pageEnd=null, url=null, language=null, rfNumber=[10], rfOrder=17, authorNames=Fan Z P, journalName=Construction and Building Materials, refType=null, unstructuredReference=Fan Z P. Effects of freeze-thaw cycles on fatigue performance of asphalt mixture and development of fatigue-freeze-thaw(FFT) uniform equation[J]. Construction and Building Materials, 2020, 242: 118043., articleTitle=Effects of freeze-thaw cycles on fatigue performance of asphalt mixture and development of fatigue-freeze-thaw(FFT) uniform equation, refAbstract=null), Reference(id=1204780279186563740, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, doi=null, pmid=null, pmcid=null, year=2023, volume=126, issue=null, pageStart=103954, pageEnd=null, url=null, language=null, rfNumber=[11], rfOrder=18, authorNames=Li C Y, journalName=Theoretical and Applied Fracture Mechanics, refType=null, unstructuredReference=Li C Y. Study on the factors affecting the self-healing performance of asphalt mixture and pavement based on fracture mechanics and calculation formula[J]. Theoretical and Applied Fracture Mechanics, 2023, 126: 103954., articleTitle=Study on the factors affecting the self-healing performance of asphalt mixture and pavement based on fracture mechanics and calculation formula, refAbstract=null), Reference(id=1204780279291421343, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, doi=null, pmid=null, pmcid=null, year=2020, volume=46, issue=11, pageStart=2350, pageEnd=2358, url=null, language=null, rfNumber=[12], rfOrder=19, authorNames=赵文迪, 陈德旺, 卓永强, journalName=自动化学报, refType=null, unstructuredReference=赵文迪, 陈德旺, 卓永强, 等. 深度神经模糊系统算法及其回归应用[J]. 自动化学报, 2020, 46(11): 2350-2358., articleTitle=深度神经模糊系统算法及其回归应用, refAbstract=null), Reference(id=1204780279387890338, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, doi=null, pmid=null, pmcid=null, year=2020, volume=46, issue=11, pageStart=2350, pageEnd=2358, url=null, language=null, rfNumber=[12], rfOrder=20, authorNames=Zhao Wendi, Chen Dewang, Zhuo Yongqiang, journalName=Acta Automatica Sinica, refType=null, unstructuredReference=Zhao Wendi, Chen Dewang, Zhuo Yongqiang, et al. Deep neural fuzzy system algorithm and its regression application[J]. Acta Automatica Sinica, 2020, 46(11): 2350-2358., articleTitle=Deep neural fuzzy system algorithm and its regression application, refAbstract=null), Reference(id=1204780279547273892, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, doi=null, pmid=null, pmcid=null, year=2024, volume=41, issue=3, pageStart=484, pageEnd=495, url=null, language=null, rfNumber=[13], rfOrder=21, authorNames=孙剑, 蒙西, 乔俊飞, journalName=控制理论与应用, refType=null, unstructuredReference=孙剑, 蒙西, 乔俊飞. 数据驱动的城市固废焚烧过程烟气含氧量预测控制[J]. 控制理论与应用, 2024, 41(3): 484-495., articleTitle=数据驱动的城市固废焚烧过程烟气含氧量预测控制, refAbstract=null), Reference(id=1204780279681491622, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, doi=null, pmid=null, pmcid=null, year=2024, volume=41, issue=3, pageStart=484, pageEnd=495, url=null, language=null, rfNumber=[13], rfOrder=22, authorNames=Sun Jian, Meng Xi, Qiao Junfei, journalName=Control Theory & Applications, refType=null, unstructuredReference=Sun Jian, Meng Xi, Qiao Junfei. Data-driven predictive control of oxygen content in flue gas for municipal solid waste incineration process[J]. Control Theory & Applications, 2024, 41(3): 484-495., articleTitle=Data-driven predictive control of oxygen content in flue gas for municipal solid waste incineration process, refAbstract=null), Reference(id=1204780279777960617, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, doi=null, pmid=null, pmcid=null, year=2023, volume=45, issue=2, pageStart=83, pageEnd=86, url=null, language=null, rfNumber=[14], rfOrder=23, authorNames=王琪, 张洪, journalName=物流工程与管理, refType=null, unstructuredReference=王琪, 张洪. 基于组合预测模型的南京禄口国际机场货运吞吐量预测[J]. 物流工程与管理, 2023, 45(2): 83-86., articleTitle=基于组合预测模型的南京禄口国际机场货运吞吐量预测, refAbstract=null), Reference(id=1204780280956560040, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, doi=null, pmid=null, pmcid=null, year=2023, volume=45, issue=2, pageStart=83, pageEnd=86, url=null, language=null, rfNumber=[14], rfOrder=24, authorNames=Wang Qi, Zhang Hong, journalName=Logistics Engineering and Management, refType=null, unstructuredReference=Wang Qi, Zhang Hong. Cargo throughput prediction of nanjing lukou international airport based on combined prediction model[J]. Logistics Engineering and Management, 2023, 45(2): 83-86., articleTitle=Cargo throughput prediction of nanjing lukou international airport based on combined prediction model, refAbstract=null), Reference(id=1204780281099166378, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, doi=null, pmid=null, pmcid=null, year=2022, volume=351, issue=null, pageStart=128969, pageEnd=null, url=null, language=null, rfNumber=[15], rfOrder=25, authorNames=Nian T, journalName=Construction and Building Materials, refType=null, unstructuredReference=Nian T. Method to predict the interlayer shear strength of asphalt pavement based on improved back propagation neural network[J]. Construction and Building Materials, 2022, 351: 128969., articleTitle=Method to predict the interlayer shear strength of asphalt pavement based on improved back propagation neural network, refAbstract=null), Reference(id=1204780281204023981, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, doi=null, pmid=null, pmcid=null, year=2012, volume=29, issue=2, pageStart=40, pageEnd=45, url=null, language=null, rfNumber=[16], rfOrder=26, authorNames=孙益民, 钟明, 徐玲, journalName=公路交通科技, refType=null, unstructuredReference=孙益民, 钟明, 徐玲, 等. 基于神经网络的沥青混合料配合比设计[J]. 公路交通科技, 2012, 29(2): 40-45., articleTitle=基于神经网络的沥青混合料配合比设计, refAbstract=null), Reference(id=1204780281279521456, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, doi=null, pmid=null, pmcid=null, year=2012, volume=29, issue=2, pageStart=40, pageEnd=45, url=null, language=null, rfNumber=[16], rfOrder=27, authorNames=Sun Yimin, Zhong Ming, Xu Ling, journalName=Journal of Highway and Transportation Research and Development, refType=null, unstructuredReference=Sun Yimin, Zhong Ming, Xu Ling, et al. Design on asphalt mixture ratio based on neural networks[J]. Journal of Highway and Transportation Research and Development, 2012, 29(2): 40-45., articleTitle=Design on asphalt mixture ratio based on neural networks, refAbstract=null), Reference(id=1204780281380184751, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, doi=null, pmid=null, pmcid=null, year=2008, volume=28, issue=6, pageStart=213, pageEnd=216, url=null, language=null, rfNumber=[17], rfOrder=28, authorNames=谭忆秋, 公维强, 周纯秀, journalName=中外公路, refType=null, unstructuredReference=谭忆秋, 公维强, 周纯秀, 等. 基于BP神经网络的沥青混合料低温性能预测模型[J]. 中外公路, 2008, 28(6): 213-216., articleTitle=基于BP神经网络的沥青混合料低温性能预测模型, refAbstract=null), Reference(id=1204780281443099313, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, doi=null, pmid=null, pmcid=null, year=2008, volume=28, issue=6, pageStart=213, pageEnd=216, url=null, language=null, rfNumber=[17], rfOrder=29, authorNames=Tan Yiqiu, Gong Weiqiang, Zhou Chunxiu, journalName=Journal of China & Foreign Highway, refType=null, unstructuredReference=Tan Yiqiu, Gong Weiqiang, Zhou Chunxiu, et al. Research on the application of neural network in the model for asphalt mixture performance at low temperature[J]. Journal of China & Foreign Highway, 2008, 28(6): 213-216., articleTitle=Research on the application of neural network in the model for asphalt mixture performance at low temperature, refAbstract=null), Reference(id=1204780281506013875, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, doi=null, pmid=null, pmcid=null, year=2017, volume=120, issue=null, pageStart=568, pageEnd=580, url=null, language=null, rfNumber=[18], rfOrder=30, authorNames=Xu B, Dan H C, Li L, journalName=Applied Thermal Engineering, refType=null, unstructuredReference=Xu B, Dan H C, Li L. Temperature prediction model of asphalt pavement in cold regions based on an improved BP neural network[J]. Applied Thermal Engineering, 2017, 120: 568-580., articleTitle=Temperature prediction model of asphalt pavement in cold regions based on an improved BP neural network, refAbstract=null), Reference(id=1204780281577317045, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, doi=null, pmid=null, pmcid=null, year=2015, volume=35, issue=S1, pageStart=41, pageEnd=44, url=null, language=null, rfNumber=[19], rfOrder=31, authorNames=刘阳, 赵晖, journalName=长安大学学报(自然科学版), refType=null, unstructuredReference=刘阳, 赵晖. 基于小波神经网络的城市交通出行方式交互预测[J]. 长安大学学报(自然科学版), 2015, 35(S1): 41-44, 48., articleTitle=基于小波神经网络的城市交通出行方式交互预测, refAbstract=null), Reference(id=1204780281648620214, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, doi=null, pmid=null, pmcid=null, year=2015, volume=35, issue=S1, pageStart=41, pageEnd=44, url=null, language=null, rfNumber=[19], rfOrder=32, authorNames=Liu Yang, Zhao Hui, journalName=Journal of Chang’an University(Natural Science Edition), refType=null, unstructuredReference=Liu Yang, Zhao Hui. Interactive prediction for traffic model split based on wavelet neural networks[J]. Journal of Chang’an University(Natural Science Edition), 2015, 35(S1): 41-44, 48., articleTitle=Interactive prediction for traffic model split based on wavelet neural networks, refAbstract=null), Reference(id=1204780281749283512, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, doi=null, pmid=null, pmcid=null, year=2018, volume=37, issue=2, pageStart=35, pageEnd=40, url=null, language=null, rfNumber=[20], rfOrder=33, authorNames=谢春磊, 张勇, 耿红斌, journalName=重庆交通大学学报(自然科学版), refType=null, unstructuredReference=谢春磊, 张勇, 耿红斌, 等. 基于BP神经网络的沥青混合料疲劳性能预测模型[J]. 重庆交通大学学报(自然科学版), 2018, 37(2): 35-40., articleTitle=基于BP神经网络的沥青混合料疲劳性能预测模型, refAbstract=null), Reference(id=1204780281833169594, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, doi=null, pmid=null, pmcid=null, year=2018, volume=37, issue=2, pageStart=35, pageEnd=40, url=null, language=null, rfNumber=[20], rfOrder=34, authorNames=Xie Chunlei, Zhang Yong, Geng Hongbin, journalName=Journal of Chongqing Jiaotong University(Natural Science), refType=null, unstructuredReference=Xie Chunlei, Zhang Yong, Geng Hongbin, et al. Asphalt mixture fatigue life prediction model based on neural network[J]. Journal of Chongqing Jiaotong University(Natural Science), 2018, 37(2): 35-40., articleTitle=Asphalt mixture fatigue life prediction model based on neural network, refAbstract=null), Reference(id=1204780281908667068, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, doi=null, pmid=null, pmcid=null, year=2023, volume=23, issue=24, pageStart=10264, pageEnd=10272, url=null, language=null, rfNumber=[21], rfOrder=35, authorNames=刘伟吉, 冯嘉豪, 祝效华, journalName=科学技术与工程, refType=null, unstructuredReference=刘伟吉, 冯嘉豪, 祝效华, 等. 基于动量自适应学习率PSO-BP神经网络的钻速预测模型研究[J]. 科学技术与工程, 2023, 23(24): 10264-10272., articleTitle=基于动量自适应学习率PSO-BP神经网络的钻速预测模型研究, refAbstract=null), Reference(id=1204780281988358846, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, doi=null, pmid=null, pmcid=null, year=2023, volume=23, issue=24, pageStart=10264, pageEnd=10272, url=null, language=null, rfNumber=[21], rfOrder=36, authorNames=Liu Weiji, Feng Jiahao, Zhu Xiaohua, journalName=Science Technology and Engineering, refType=null, unstructuredReference=Liu Weiji, Feng Jiahao, Zhu Xiaohua, et al. Prediction model of penetration rate based on PSO-BP neural network with momentum adaptive learning rate[J]. Science Technology and Engineering, 2023, 23(24): 10264-10272., articleTitle=Prediction model of penetration rate based on PSO-BP neural network with momentum adaptive learning rate, refAbstract=null), Reference(id=1204780282076439231, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, doi=null, pmid=null, pmcid=null, year=2019, volume=33, issue=16, pageStart=2704, pageEnd=2709, url=null, language=null, rfNumber=[22], rfOrder=37, authorNames=吕政桦, 申爱琴, 李悦, journalName=材料导报, refType=null, unstructuredReference=吕政桦, 申爱琴, 李悦, 等. 基于遗传优化的乳化沥青冷再生混合料的疲劳性能及机理研究[J]. 材料导报, 2019, 33(16): 2704-2709., articleTitle=基于遗传优化的乳化沥青冷再生混合料的疲劳性能及机理研究, refAbstract=null), Reference(id=1204780282151936704, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, doi=null, pmid=null, pmcid=null, year=2019, volume=33, issue=16, pageStart=2704, pageEnd=2709, url=null, language=null, rfNumber=[22], rfOrder=38, authorNames=Lyu Zhenghua, Shen Aiqin, Li Yue, journalName=Materials Reports, refType=null, unstructuredReference=Lyu Zhenghua, Shen Aiqin, Li Yue, et al. Study on fatigue performance and mechanism of emulsified asphalt cold recycled micture based on genetic optimization[J]. Materials Reports, 2019, 33(16): 2704-2709., articleTitle=Study on fatigue performance and mechanism of emulsified asphalt cold recycled micture based on genetic optimization, refAbstract=null), Reference(id=1204780282219045570, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, doi=null, pmid=null, pmcid=null, year=2005, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[23], rfOrder=39, authorNames=邓聚龙, journalName=灰色系统基本方法, refType=null, unstructuredReference=邓聚龙. 灰色系统基本方法[M]. 2版. 武汉: 华中科技大学出版社, 2005., articleTitle=null, refAbstract=null), Reference(id=1204780282277765828, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, doi=null, pmid=null, pmcid=null, year=2005, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[23], rfOrder=40, authorNames=Deng Julong, journalName=The primary method of grey system theory, refType=null, unstructuredReference=Deng Julong. The primary method of grey system theory[M]. 2nd ed. Wuhan: Huazhong University of Science and Technology Press, 2005., articleTitle=null, refAbstract=null), Reference(id=1204780282349068998, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, doi=null, pmid=null, pmcid=null, year=2017, volume=17, issue=6, pageStart=1, pageEnd=9, url=null, language=null, rfNumber=[24], rfOrder=41, authorNames=周兴林, 刘万康, 肖旺新, journalName=交通运输工程学报, refType=null, unstructuredReference=周兴林, 刘万康, 肖旺新, 等. 沥青混合料体积指标对沥青路面抗滑性能的影响[J]. 交通运输工程学报, 2017, 17(6): 1-9., articleTitle=沥青混合料体积指标对沥青路面抗滑性能的影响, refAbstract=null), Reference(id=1204780282437149384, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, doi=null, pmid=null, pmcid=null, year=2017, volume=17, issue=6, pageStart=1, pageEnd=9, url=null, language=null, rfNumber=[24], rfOrder=42, authorNames=Zhou Xinglin, Liu Wankang, Xiao Wangxin, journalName=Journal of Traffic and Transportation Engineering, refType=null, unstructuredReference=Zhou Xinglin, Liu Wankang, Xiao Wangxin, et al. Influence of asphalt mixture volume indexes on asphalt pavement skid resistance performance[J]. Journal of Traffic and Transportation Engineering, 2017, 17(6): 1-9., articleTitle=Influence of asphalt mixture volume indexes on asphalt pavement skid resistance performance, refAbstract=null), Reference(id=1204780282504258250, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, doi=null, pmid=null, pmcid=null, year=2023, volume=23, issue=5, pageStart=2147, pageEnd=2155, url=null, language=null, rfNumber=[25], rfOrder=43, authorNames=刘朝晖, 朱国虎, 柳力, journalName=科学技术与工程, refType=null, unstructuredReference=刘朝晖, 朱国虎, 柳力, 等. 玄武岩纤维与高模量外掺剂复合增强沥青混合料性能[J]. 科学技术与工程, 2023, 23(5): 2147-2155., articleTitle=玄武岩纤维与高模量外掺剂复合增强沥青混合料性能, refAbstract=null), Reference(id=1204780282575561419, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, doi=null, pmid=null, pmcid=null, year=2023, volume=23, issue=5, pageStart=2147, pageEnd=2155, url=null, language=null, rfNumber=[25], rfOrder=44, authorNames=Liu Zhaohui, Zhu Guohu, Liu Li, journalName=Science Technology and Engineering, refType=null, unstructuredReference=Liu Zhaohui, Zhu Guohu, Liu Li, et al. Performance of asphalt mixture reinforced by basalt fiber and high modulus admixture[J]. Science Technology and Engineering, 2023, 23(5): 2147-2155., articleTitle=Performance of asphalt mixture reinforced by basalt fiber and high modulus admixture, refAbstract=null), Reference(id=1204780282688807630, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, doi=null, pmid=null, pmcid=null, year=2013, volume=33, issue=8, pageStart=2041, pageEnd=2046, url=null, language=null, rfNumber=[26], rfOrder=45, authorNames=刘思峰, 蔡华, 杨英杰, journalName=系统工程理论与实践, refType=null, unstructuredReference=刘思峰, 蔡华, 杨英杰, 等. 灰色关联分析模型研究进展[J]. 系统工程理论与实践, 2013, 33(8): 2041-2046., articleTitle=灰色关联分析模型研究进展, refAbstract=null), Reference(id=1204780282768499406, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, doi=null, pmid=null, pmcid=null, year=2013, volume=33, issue=8, pageStart=2041, pageEnd=2046, url=null, language=null, rfNumber=[26], rfOrder=46, authorNames=Liu Sifeng, Cai Hua, Yang Yingjie, journalName=Systems Engineering-Theory & Practice, refType=null, unstructuredReference=Liu Sifeng, Cai Hua, Yang Yingjie, et al. Advance in grey incidence analysis modelling[J]. Systems Engineering-Theory & Practice, 2013, 33(8): 2041-2046., articleTitle=Advance in grey incidence analysis modelling, refAbstract=null), Reference(id=1204780282848191183, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, doi=null, pmid=null, pmcid=null, year=2010, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[27], rfOrder=47, authorNames=Azzeh M, Neagu D, journalName=Fuzzy grey relational analysis for software effort estimation, refType=null, unstructuredReference=Azzeh M, Neagu D. Fuzzy grey relational analysis for software effort estimation[M]. Netherlands: Kluwer Academic Publishers, 2010., articleTitle=null, refAbstract=null), Reference(id=1204780282919494352, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, doi=null, pmid=null, pmcid=null, year=2019, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[28], rfOrder=48, authorNames=文常保, journalName=人工神经网络理论及应用, refType=null, unstructuredReference=文常保. 人工神经网络理论及应用[M]. 西安: 西安电子科技大学出版社, 2019., articleTitle=null, refAbstract=null), Reference(id=1204780282982408913, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, doi=null, pmid=null, pmcid=null, year=2019, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[28], rfOrder=49, authorNames=Wen Changbao, journalName=Artificial neural network theory and its applications, refType=null, unstructuredReference=Wen Changbao. Artificial neural network theory and its applications[M]. Xi’an: Xidian University Press, 2019., articleTitle=null, refAbstract=null), Reference(id=1204780283070489298, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, doi=null, pmid=null, pmcid=null, year=2024, volume=24, issue=1, pageStart=281, pageEnd=288, url=null, language=null, rfNumber=[29], rfOrder=50, authorNames=李晓娟, 张芳媛, 喻玲, journalName=科学技术与工程, refType=null, unstructuredReference=李晓娟, 张芳媛, 喻玲. 基于主成分分析-BP神经网络的风电备件需求预测[J]. 科学技术与工程, 2024, 24(1): 281-288., articleTitle=基于主成分分析-BP神经网络的风电备件需求预测, refAbstract=null), Reference(id=1204780283125015251, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, doi=null, pmid=null, pmcid=null, year=2024, volume=24, issue=1, pageStart=281, pageEnd=288, url=null, language=null, rfNumber=[29], rfOrder=51, authorNames=Li Xiaojuan, Zhang Fangyuan, Yu Ling, journalName=Science Technology and Engineering, refType=null, unstructuredReference=Li Xiaojuan, Zhang Fangyuan, Yu Ling. Wind power spare parts demand forecasting based on PCA-BP neural networks[J]. Science Technology and Engineering, 2024, 24(1): 281-288., articleTitle=Wind power spare parts demand forecasting based on PCA-BP neural networks, refAbstract=null), Reference(id=1204780283196318420, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, doi=null, pmid=null, pmcid=null, year=2015, volume=29, issue=14, pageStart=148, pageEnd=151, url=null, language=null, rfNumber=[30], rfOrder=52, authorNames=张浩, 袁军座, 曹现雷, journalName=材料导报, refType=null, unstructuredReference=张浩, 袁军座, 曹现雷, 等. 基于BP神经网络的Cu-Ce掺杂TiO2光催化剂性能预测组合模型研究[J]. 材料导报, 2015, 29(14): 148-151, 155., articleTitle=基于BP神经网络的Cu-Ce掺杂TiO2光催化剂性能预测组合模型研究, refAbstract=null), Reference(id=1204780283255038677, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, doi=null, pmid=null, pmcid=null, year=2015, volume=29, issue=14, pageStart=148, pageEnd=151, url=null, language=null, rfNumber=[30], rfOrder=53, authorNames=Zhang Hao, Yuan Junzuo, Cao Xianlei, journalName=Materials Reports, refType=null, unstructuredReference=Zhang Hao, Yuan Junzuo, Cao Xianlei, et al. Research on hybrid prediction methods for Cu-Ce-doped TiO2 photocatalytic performance based on BP network[J]. Materials Reports, 2015, 29(14): 148-151, 155., articleTitle=Research on hybrid prediction methods for Cu-Ce-doped TiO2 photocatalytic performance based on BP network, refAbstract=null), Reference(id=1204780283322147542, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, doi=null, pmid=null, pmcid=null, year=2021, volume=35, issue=15, pageStart=15026, pageEnd=15030, url=null, language=null, rfNumber=[31], rfOrder=54, authorNames=黄炜, 周烺, 葛培, journalName=材料导报, refType=null, unstructuredReference=黄炜, 周烺, 葛培, 等. 基于PSO-BP和GA-BP神经网络再生砖骨料混凝土强度模型的对比研究[J]. 材料导报, 2021, 35(15): 15026-15030., articleTitle=基于PSO-BP和GA-BP神经网络再生砖骨料混凝土强度模型的对比研究, refAbstract=null), Reference(id=1204780283406033623, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, doi=null, pmid=null, pmcid=null, year=2021, volume=35, issue=15, pageStart=15026, pageEnd=15030, url=null, language=null, rfNumber=[31], rfOrder=55, authorNames=Huang Wei, Zhou Lang, Ge Pei, journalName=Materials Reports, refType=null, unstructuredReference=Huang Wei, Zhou Lang, Ge Pei, et al. A comparative study on compressive model of recycled Brick aggregate concrete based on PSO-BP and neural networks[J]. Materials Reports, 2021, 35(15): 15026-15030., articleTitle=A comparative study on compressive model of recycled Brick aggregate concrete based on PSO-BP and neural networks, refAbstract=null), Reference(id=1204780283468948184, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, doi=null, pmid=null, pmcid=null, year=2008, volume=null, issue=34, pageStart=118, pageEnd=123, url=null, language=null, rfNumber=[32], rfOrder=56, authorNames=范高锋, 王伟胜, 刘纯, journalName=中国电机工程学报, refType=null, unstructuredReference=范高锋, 王伟胜, 刘纯, 等. 基于人工神经网络的风电功率预测[J]. 中国电机工程学报, 2008,(34): 118-123., articleTitle=基于人工神经网络的风电功率预测, refAbstract=null), Reference(id=1204780283544445657, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, doi=null, pmid=null, pmcid=null, year=2008, volume=null, issue=34, pageStart=118, pageEnd=123, url=null, language=null, rfNumber=[32], rfOrder=57, authorNames=Fan Gaofeng, Wang Weisheng, Liu Chun, journalName=Proceedings of the CSEE, refType=null, unstructuredReference=Fan Gaofeng, Wang Weisheng, Liu Chun, et al. Wind power prediction based on artificial neural network[J]. Proceedings of the CSEE, 2008(34): 118-123., articleTitle=Wind power prediction based on artificial neural network, refAbstract=null), Reference(id=1204780283611554522, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, doi=null, pmid=null, pmcid=null, year=2020, volume=53, issue=S1, pageStart=75, pageEnd=80, url=null, language=null, rfNumber=[33], rfOrder=58, authorNames=黄靓钰, 阳军生, 张聪, journalName=土木工程学报, refType=null, unstructuredReference=黄靓钰, 阳军生, 张聪, 等. 基于BP神经网络的水下岩溶地层盾构掘进参数预测与分析[J]. 土木工程学报, 2020, 53(S1): 75-80, 98., articleTitle=基于BP神经网络的水下岩溶地层盾构掘进参数预测与分析, refAbstract=null), Reference(id=1204780283687051995, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, doi=null, pmid=null, pmcid=null, year=2020, volume=53, issue=S1, pageStart=75, pageEnd=80, url=null, language=null, rfNumber=[33], rfOrder=59, authorNames=Huang Liangyu, Yang Junsheng, Zhang Cong, journalName=China Civil Engineering Journal, refType=null, unstructuredReference=Huang Liangyu, Yang Junsheng, Zhang Cong, et al. Prediction and analysis of sheild tunneling parameters in underwater karst stratum based on BP neural network[J]. China Civil Engineering Journal, 2020, 53(S1): 75-80, 98., articleTitle=Prediction and analysis of sheild tunneling parameters in underwater karst stratum based on BP neural network, refAbstract=null), Reference(id=1204780283758355164, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, doi=null, pmid=null, pmcid=null, year=2007, volume=null, issue=7, pageStart=93, pageEnd=98, url=null, language=null, rfNumber=[34], rfOrder=60, authorNames=王雪青, 喻刚, 孟海涛, journalName=土木工程学报, refType=null, unstructuredReference=王雪青, 喻刚, 孟海涛. 基于GA改进BP神经网络的建设工程投标报价研究[J]. 土木工程学报, 2007(7): 93-98., articleTitle=基于GA改进BP神经网络的建设工程投标报价研究, refAbstract=null), Reference(id=1204780283846435549, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, doi=null, pmid=null, pmcid=null, year=2007, volume=null, issue=7, pageStart=93, pageEnd=98, url=null, language=null, rfNumber=[34], rfOrder=61, authorNames=Wang Xueqing, Yu Gang, Meng Haitao, journalName=China Civil Engineering Journal, refType=null, unstructuredReference=Wang Xueqing, Yu Gang, Meng Haitao. Study of construction project bidding based on neural network improved by GA[J]. China Civil Engineering Journal, 2007(7): 93-98., articleTitle=Study of construction project bidding based on neural network improved by GA, refAbstract=null), Reference(id=1204780283905155806, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, doi=null, pmid=null, pmcid=null, year=2023, volume=44, issue=2, pageStart=52, pageEnd=58, url=null, language=null, rfNumber=[35], rfOrder=62, authorNames=王晓东, 栗杉杉, 刘颖明, journalName=太阳能学报, refType=null, unstructuredReference=王晓东, 栗杉杉, 刘颖明, 等. 基于特征变权的超短期风电功率预测[J]. 太阳能学报, 2023, 44(2): 52-58., articleTitle=基于特征变权的超短期风电功率预测, refAbstract=null), Reference(id=1204780283963876063, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, doi=null, pmid=null, pmcid=null, year=2023, volume=44, issue=2, pageStart=52, pageEnd=58, url=null, language=null, rfNumber=[35], rfOrder=63, authorNames=Wang Xiaodong, Li Shanshan, Liu yingming, journalName=Acta Energiae Solaris Sinica, refType=null, unstructuredReference=Wang Xiaodong, Li Shanshan, Liu yingming, et al. Ultra-short-term wind power prediction based on variable feature weight[J]. Acta Energiae Solaris Sinica, 2023, 44(2): 52-58., articleTitle=Ultra-short-term wind power prediction based on variable feature weight, refAbstract=null), Reference(id=1204780284043567840, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, doi=null, pmid=null, pmcid=null, year=2023, volume=40, issue=7, pageStart=185, pageEnd=195, url=null, language=null, rfNumber=[36], rfOrder=64, authorNames=庄亮东, 杨悦, 吴桢灏, journalName=工程力学, refType=null, unstructuredReference=庄亮东, 杨悦, 吴桢灏. 遗传算法在Y型偏心支撑组合框架抗震性能优化中的应用研究[J]. 工程力学, 2023, 40(7): 185-195., articleTitle=遗传算法在Y型偏心支撑组合框架抗震性能优化中的应用研究, refAbstract=null), Reference(id=1204780284127453921, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, doi=null, pmid=null, pmcid=null, year=2023, volume=40, issue=7, pageStart=185, pageEnd=195, url=null, language=null, rfNumber=[36], rfOrder=65, authorNames=Zhuang Liangdong, Yang Yue, Wu Zhenhao, journalName=Engineering Mechanics, refType=null, unstructuredReference=Zhuang Liangdong, Yang Yue, Wu Zhenhao. The application of genetic algorithm in seismic performance optimization of Y-shape eccentrically braced composite frame[J]. Engineering Mechanics, 2023, 40(7): 185-195., articleTitle=The application of genetic algorithm in seismic performance optimization of Y-shape eccentrically braced composite frame, refAbstract=null), Reference(id=1204780284194562786, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, doi=null, pmid=null, pmcid=null, year=2023, volume=35, issue=8, pageStart=32, pageEnd=37, url=null, language=null, rfNumber=[37], rfOrder=66, authorNames=刘艳冬, 卢兰萍, 刘林林, journalName=中国煤炭地质, refType=null, unstructuredReference=刘艳冬, 卢兰萍, 刘林林, 等. 基于GA-BP神经网络的煤层底板突水量等级预测[J]. 中国煤炭地质, 2023, 35(8): 32-37., articleTitle=基于GA-BP神经网络的煤层底板突水量等级预测, refAbstract=null), Reference(id=1204780284261671651, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, doi=null, pmid=null, pmcid=null, year=2023, volume=35, issue=8, pageStart=32, pageEnd=37, url=null, language=null, rfNumber=[37], rfOrder=67, authorNames=Liu Yandong, Lu Lanping, Liu Linlin, journalName=Coal Geology of China, refType=null, unstructuredReference=Liu Yandong, Lu Lanping, Liu Linlin, et al. Prediction of water inrush grade of coal seam floor based on GA-BP neural network[J]. Coal Geology of China, 2023, 35(8): 32-37., articleTitle=Prediction of water inrush grade of coal seam floor based on GA-BP neural network, refAbstract=null), Reference(id=1204780284332974820, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, doi=null, pmid=null, pmcid=null, year=2024, volume=24, issue=11, pageStart=4472, pageEnd=4478, url=null, language=null, rfNumber=[38], rfOrder=68, authorNames=鲁宇涛, 张引弟, 徐刘伟, journalName=科学技术与工程, refType=null, unstructuredReference=鲁宇涛, 张引弟, 徐刘伟, 等. 基于遗传算法的盐穴储气库注气能力方案优化[J]. 科学技术与工程, 2024, 24(11): 4472-4478., articleTitle=基于遗传算法的盐穴储气库注气能力方案优化, refAbstract=null), Reference(id=1204780285465436901, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, doi=null, pmid=null, pmcid=null, year=2024, volume=24, issue=11, pageStart=4472, pageEnd=4478, url=null, language=null, rfNumber=[38], rfOrder=69, authorNames=Lu Yutao, Zhang Yindi, Xu Liuwei, journalName=Science Technology and Engineering, refType=null, unstructuredReference=Lu Yutao, Zhang Yindi, Xu Liuwei, et al. Optimization of gas injection capacity strategy for salt cavern gas storage based on genetic algorithm[J]. Science Technology and Engineering, 2024, 24(11): 4472-4478., articleTitle=Optimization of gas injection capacity strategy for salt cavern gas storage based on genetic algorithm, refAbstract=null), Reference(id=1204780285532545766, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, doi=null, pmid=null, pmcid=null, year=2009, volume=40, issue=1, pageStart=180, pageEnd=184, url=null, language=null, rfNumber=[39], rfOrder=70, authorNames=吴景龙, 杨淑霞, 刘承水, journalName=中南大学学报(自然科学版), refType=null, unstructuredReference=吴景龙, 杨淑霞, 刘承水. 基于遗传算法优化参数的支持向量机短期负荷预测方法[J]. 中南大学学报(自然科学版), 2009, 40(1): 180-184., articleTitle=基于遗传算法优化参数的支持向量机短期负荷预测方法, refAbstract=null), Reference(id=1204780285616431847, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, doi=null, pmid=null, pmcid=null, year=2009, volume=40, issue=1, pageStart=180, pageEnd=184, url=null, language=null, rfNumber=[39], rfOrder=71, authorNames=Wu Jinglong, Yang Shuxia, Liu Chengshui, journalName=Journal of Central South University(Science and Technology), refType=null, unstructuredReference=Wu Jinglong, Yang Shuxia, Liu Chengshui. Parameter selection for support vector machines based on genetic algorithms to short-term power load forecasting[J]. Journal of Central South University(Science and Technology), 2009, 40(1): 180-184., articleTitle=Parameter selection for support vector machines based on genetic algorithms to short-term power load forecasting, refAbstract=null), Reference(id=1204780285683540712, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, doi=null, pmid=null, pmcid=null, year=2011, volume=17, issue=12, pageStart=2629, pageEnd=2637, url=null, language=null, rfNumber=[40], rfOrder=72, authorNames=刘爱军, 杨育, 邢青松, journalName=计算机集成制造系统, refType=null, unstructuredReference=刘爱军, 杨育, 邢青松, 等. 柔性作业车间多目标动态调度[J]. 计算机集成制造系统, 2011, 17(12): 2629-2637., articleTitle=柔性作业车间多目标动态调度, refAbstract=null), Reference(id=1204780285750649577, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, doi=null, pmid=null, pmcid=null, year=2011, volume=17, issue=12, pageStart=2629, pageEnd=2637, url=null, language=null, rfNumber=[40], rfOrder=73, authorNames=Liu Aijun, Yang Yu, Xing Qingsong, journalName=Computer Integrated Manufacturing Systems, refType=null, unstructuredReference=Liu Aijun, Yang Yu, Xing Qingsong, et al. Dynamic scheduling on multi-objective flexible job shop[J]. Computer Integrated Manufacturing Systems, 2011, 17(12): 2629-2637., articleTitle=Dynamic scheduling on multi-objective flexible job shop, refAbstract=null)], funds=[Fund(id=1204780276917445211, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, awardId=2021YFB2601000, language=CN, fundingSource=国家重点研发计划(2021YFB2601000), fundOrder=null, country=null), Fund(id=1204780277018108509, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, awardId=52278437, language=CN, fundingSource=国家自然科学基金(52278437), fundOrder=null, country=null), Fund(id=1204780277097800288, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, awardId=52208423, language=CN, fundingSource=国家自然科学基金(52208423), fundOrder=null, country=null), Fund(id=1204780277177492068, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, awardId=kq2306009, language=CN, fundingSource=长沙市杰出创新青年培养计划(kq2306009), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1204780263994794265, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, xref=null, ext=[AuthorCompanyExt(id=1204780264007377178, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, companyId=1204780263994794265, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Traffic and Transportation Engineering, Changsha University of Science and Technology, Changsha 410114, China), AuthorCompanyExt(id=1204780264015765788, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, companyId=1204780263994794265, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=长沙理工大学交通运输工程学院, 长沙 410114)])], figs=[ArticleFig(id=1204780268084240842, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, language=EN, label=Fig.1, caption=Gray correlation analysis process, figureFileSmall=zu1Bqy/FBfEtTPaGresfCA==, figureFileBig=58wtBFqyQ8r94OeH5JReSA==, tableContent=null), ArticleFig(id=1204780268210069969, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, language=CN, label=图1, caption=灰关联分析流程, figureFileSmall=zu1Bqy/FBfEtTPaGresfCA==, figureFileBig=58wtBFqyQ8r94OeH5JReSA==, tableContent=null), ArticleFig(id=1204780268327510490, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, language=EN, label=Fig.2, caption=Sketch of BP neural network structure, figureFileSmall=gwNkaxFUI2aWbZh/b0NVqw==, figureFileBig=1mOLJQk1MYbYRW5bsA/KiQ==, tableContent=null), ArticleFig(id=1204780268465922527, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, language=CN, label=图2, caption=BP神经网络结构简图, figureFileSmall=gwNkaxFUI2aWbZh/b0NVqw==, figureFileBig=1mOLJQk1MYbYRW5bsA/KiQ==, tableContent=null), ArticleFig(id=1204780270357553636, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, language=EN, label=Fig.3, caption=BP neural network design process, figureFileSmall=yQUgGo8NvNj4xf4CnqORgw==, figureFileBig=RmuW7JLHje8DCb6WFyT9iw==, tableContent=null), ArticleFig(id=1204780270470799850, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, language=CN, label=图3, caption=BP神经网络设计流程, figureFileSmall=yQUgGo8NvNj4xf4CnqORgw==, figureFileBig=RmuW7JLHje8DCb6WFyT9iw==, tableContent=null), ArticleFig(id=1204780270579851760, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, language=EN, label=Fig.4, caption=Structure of BP neural network model, figureFileSmall=y6M0v7INZW654cPtC20sbQ==, figureFileBig=Lk1E06GO43L2boxSu1ZDiQ==, tableContent=null), ArticleFig(id=1204780270739235325, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, language=CN, label=图4, caption=BP神经网络模型结构图

Wi表示输入层与隐含层之间的连接权重;Wk表示隐含层与输出层之间的连接权重;xuy分别代表输入层、隐含层和输出层神经元

, figureFileSmall=y6M0v7INZW654cPtC20sbQ==, figureFileBig=Lk1E06GO43L2boxSu1ZDiQ==, tableContent=null), ArticleFig(id=1204780270869258756, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, language=EN, label=Fig.5, caption=Flow of GA-BP neural network algorithm, figureFileSmall=SbSF7Wi1dZZriv7Kehi1BQ==, figureFileBig=Iihn/+8yz4ZnNA5wRsh7hA==, tableContent=null), ArticleFig(id=1204780272073024007, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, language=CN, label=图5, caption=GA-BP神经网络算法流程, figureFileSmall=SbSF7Wi1dZZriv7Kehi1BQ==, figureFileBig=Iihn/+8yz4ZnNA5wRsh7hA==, tableContent=null), ArticleFig(id=1204780272182075912, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, language=EN, label=Fig.6, caption=Comparison of predicted and measured values performance, figureFileSmall=kalUUmXH4v/F0CJ2tn3mBw==, figureFileBig=ob/wTJAmMz+fxPFWnT311A==, tableContent=null), ArticleFig(id=1204780272303710733, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, language=CN, label=图6, caption=

预测值与实测值对比

, figureFileSmall=kalUUmXH4v/F0CJ2tn3mBw==, figureFileBig=ob/wTJAmMz+fxPFWnT311A==, tableContent=null), ArticleFig(id=1204780272379208209, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, language=EN, label=Table 1, caption=

Asphalt mixture composition and its performance

, figureFileSmall=null, figureFileBig=null, tableContent=
性能 指标类型 总计
原材料性能 软化点、延度、公称最大粒径、针入度、沥青相对密度、吸水率、沥青种类、矿粉表观密度、细集料棱角性 9项
沥青混合料细观性能 4.75 mm通过率、油石比、空隙率 3项
沥青混合料宏观性能 动态模量、动稳定度、残留稳定度、劈裂抗拉强度比、极限弯拉应变 5项
), ArticleFig(id=1204780272442122773, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, language=CN, label=表1, caption=

沥青混合料材料组成及其性能

, figureFileSmall=null, figureFileBig=null, tableContent=
性能 指标类型 总计
原材料性能 软化点、延度、公称最大粒径、针入度、沥青相对密度、吸水率、沥青种类、矿粉表观密度、细集料棱角性 9项
沥青混合料细观性能 4.75 mm通过率、油石比、空隙率 3项
沥青混合料宏观性能 动态模量、动稳定度、残留稳定度、劈裂抗拉强度比、极限弯拉应变 5项
), ArticleFig(id=1204780272521814554, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, language=EN, label=Table 2, caption=

Asphalt mixture properties gray correlation calculation results

, figureFileSmall=null, figureFileBig=null, tableContent=
子序列特征项 性能
动态模量 动稳定度 残留稳定度 劈裂抗拉强度比 极限弯拉应变
ri 排序 ri 排序 ri 排序 ri 排序 ri 排序
空隙率 0.872 1 0.807 4 0.861 1 0.861 1 0.858 1
公称最大粒径 0.845 2 0.805 5 0.795 4 0.840 4 0.807 4
油石比 0.809 3 0.809 3 0.803 3 0.813 5 0.835 2
4.75 mm通过率 0.807 4 0.778 6 0.769 6 0.850 3 0.798 5
针入度 0.805 5 0.687 8 0.781 5 0.853 2 0.812 3
延度 0.778 6 0.754 7 0.767 7 0.805 6 0.780 7
沥青种类 0.754 7 0.872 1 0.818 2 0.738 7 0.784 6
软化点 0.687 8 0.845 2 0.715 8 0.679 8 0.691 8
细集料棱角性 0.542 9 0.587 9 0.573 10 0.558 10 0.562 10
吸水率 0.538 10 0.581 10 0.582 9 0.563 9 0.552 12
沥青相对密度 0.525 11 0.565 12 0.568 11 0.552 11 0.559 11
矿粉表观相对密度 0.521 12 0.574 11 0.545 12 0.549 12 0.578 9
), ArticleFig(id=1204780272618283551, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, language=CN, label=表2, caption=

沥青混合料性能灰关联度计算结果

, figureFileSmall=null, figureFileBig=null, tableContent=
子序列特征项 性能
动态模量 动稳定度 残留稳定度 劈裂抗拉强度比 极限弯拉应变
ri 排序 ri 排序 ri 排序 ri 排序 ri 排序
空隙率 0.872 1 0.807 4 0.861 1 0.861 1 0.858 1
公称最大粒径 0.845 2 0.805 5 0.795 4 0.840 4 0.807 4
油石比 0.809 3 0.809 3 0.803 3 0.813 5 0.835 2
4.75 mm通过率 0.807 4 0.778 6 0.769 6 0.850 3 0.798 5
针入度 0.805 5 0.687 8 0.781 5 0.853 2 0.812 3
延度 0.778 6 0.754 7 0.767 7 0.805 6 0.780 7
沥青种类 0.754 7 0.872 1 0.818 2 0.738 7 0.784 6
软化点 0.687 8 0.845 2 0.715 8 0.679 8 0.691 8
细集料棱角性 0.542 9 0.587 9 0.573 10 0.558 10 0.562 10
吸水率 0.538 10 0.581 10 0.582 9 0.563 9 0.552 12
沥青相对密度 0.525 11 0.565 12 0.568 11 0.552 11 0.559 11
矿粉表观相对密度 0.521 12 0.574 11 0.545 12 0.549 12 0.578 9
), ArticleFig(id=1204780272693781027, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, language=EN, label=Table 3, caption=

Results of training metrics with different number of hidden layer neurons

, figureFileSmall=null, figureFileBig=null, tableContent=
训练指标 隐含层神经元个数
k=5 k=6 k=7 k=8 k=9 k=10 k=11 k=12 k=13 k=14
相关系数 r - 0.868 0.868 0.866 0.867 0.873 0.878 0.883 0.881 0.873 0.865
均方误差 M S E ¯ 0.016 0.016 0.015 0.015 0.012 0.016 0.011 0.016 0.014 0.017
), ArticleFig(id=1204780272786055720, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, language=CN, label=表3, caption=

不同隐含层神经元个数训练指标结果

, figureFileSmall=null, figureFileBig=null, tableContent=
训练指标 隐含层神经元个数
k=5 k=6 k=7 k=8 k=9 k=10 k=11 k=12 k=13 k=14
相关系数 r - 0.868 0.868 0.866 0.867 0.873 0.878 0.883 0.881 0.873 0.865
均方误差 M S E ¯ 0.016 0.016 0.015 0.015 0.012 0.016 0.011 0.016 0.014 0.017
), ArticleFig(id=1204780272886719021, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, language=EN, label=Table 4, caption=

Training metrics for the three algorithms

, figureFileSmall=null, figureFileBig=null, tableContent=
沥青混合料
性能
算法模型 评价指标
RMSE MAE R2
动态模量/
MPa
GA-BP 训练集 212 158 0.91
测试集 339 226 0.83
BP 训练集 309 208 0.87
测试集 361 257 0.78
动稳定度/
(次·mm-1)
GA-BP 训练集 1 275 893 0.82
测试集 1 710 1 233 0.70
BP 训练集 1 595 1 112 0.73
测试集 1 803 1 388 0.63
残留稳定度/
%
GA-BP 训练集 2.3 1.7 0.51
测试集 2.9 2.2 0.32
BP 训练集 2.9 2.2 0.24
测试集 3.1 2.5 0.19
劈裂抗拉
强度比/%
GA-BP 训练集 3.0 2.3 0.49
测试集 3.7 2.7 0.25
BP 训练集 3.7 2.8 0.22
测试集 3.8 2.9 0.16
极限弯拉
应变/με
GA-BP 训练集 117 78 0.72
测试集 150 90 0.58
BP 训练集 140 92 0.59
测试集 155 96 0.57
), ArticleFig(id=1204780273033519668, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, language=CN, label=表4, caption=

3种算法训练指标

, figureFileSmall=null, figureFileBig=null, tableContent=
沥青混合料
性能
算法模型 评价指标
RMSE MAE R2
动态模量/
MPa
GA-BP 训练集 212 158 0.91
测试集 339 226 0.83
BP 训练集 309 208 0.87
测试集 361 257 0.78
动稳定度/
(次·mm-1)
GA-BP 训练集 1 275 893 0.82
测试集 1 710 1 233 0.70
BP 训练集 1 595 1 112 0.73
测试集 1 803 1 388 0.63
残留稳定度/
%
GA-BP 训练集 2.3 1.7 0.51
测试集 2.9 2.2 0.32
BP 训练集 2.9 2.2 0.24
测试集 3.1 2.5 0.19
劈裂抗拉
强度比/%
GA-BP 训练集 3.0 2.3 0.49
测试集 3.7 2.7 0.25
BP 训练集 3.7 2.8 0.22
测试集 3.8 2.9 0.16
极限弯拉
应变/με
GA-BP 训练集 117 78 0.72
测试集 150 90 0.58
BP 训练集 140 92 0.59
测试集 155 96 0.57
), ArticleFig(id=1204780273125794361, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, language=EN, label=Table 5, caption=

Untrained 10 sets of asphalt mixture composition data

, figureFileSmall=null, figureFileBig=null, tableContent=
沥青
种类
公称最大
粒径/mm
延度/
cm
针入度/
0.1 mm
空隙率/
%
软化点/
油石比/
%
4.75 mm
通过率/
%
实测性能指标
动态模量/
MPa
动稳定度/
(次·mm-1)
残留稳定
度/%
抗拉强度
比/%
极限弯拉
应变/με
1 19.0 127.0 63.0 3.9 49.0 4.1 35.3 10 459 2 033 87.7 79.5 2 366
1 19.0 135.0 73.0 4.0 47.5 4.2 39.4 10 651 1 695 87.9 79.0 2 402
1 13.2 124.0 73.0 4.2 47.5 5.0 44.2 10 289 1 296 86.2 78.7 2 350
2 13.2 19.2 87.0 4.0 48.2 5.2 47.2 9 780 2 067 89.2 86.1 2 265
2 19.0 19.2 87.0 4.3 48.2 4.5 39.0 9 525 2 207 86.3 80.3 2 460
2 13.2 19.2 87.0 4.0 48.2 5.2 46.4 9 843 2 228 89.5 87.1 2 463
3 16.0 132.0 108.0 4.3 45.0 4.8 44.0 9 000 2 126 84.7 82.2 2 604
3 13.2 132.0 108.0 4.2 45.0 5.2 47.1 9 100 1 820 87.2 83.6 2 674
4 19.0 39.0 49.0 4.0 79.2 4.5 36.8 11 572 9 357 89.5 87.6 2 577
4 13.2 54.0 63.0 4.1 78.0 5.1 45.1 10 490 6 456 87.3 85.5 2 615
), ArticleFig(id=1204780273239040576, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, language=CN, label=表5, caption=

未训练的10组沥青混合料组成数据

, figureFileSmall=null, figureFileBig=null, tableContent=
沥青
种类
公称最大
粒径/mm
延度/
cm
针入度/
0.1 mm
空隙率/
%
软化点/
油石比/
%
4.75 mm
通过率/
%
实测性能指标
动态模量/
MPa
动稳定度/
(次·mm-1)
残留稳定
度/%
抗拉强度
比/%
极限弯拉
应变/με
1 19.0 127.0 63.0 3.9 49.0 4.1 35.3 10 459 2 033 87.7 79.5 2 366
1 19.0 135.0 73.0 4.0 47.5 4.2 39.4 10 651 1 695 87.9 79.0 2 402
1 13.2 124.0 73.0 4.2 47.5 5.0 44.2 10 289 1 296 86.2 78.7 2 350
2 13.2 19.2 87.0 4.0 48.2 5.2 47.2 9 780 2 067 89.2 86.1 2 265
2 19.0 19.2 87.0 4.3 48.2 4.5 39.0 9 525 2 207 86.3 80.3 2 460
2 13.2 19.2 87.0 4.0 48.2 5.2 46.4 9 843 2 228 89.5 87.1 2 463
3 16.0 132.0 108.0 4.3 45.0 4.8 44.0 9 000 2 126 84.7 82.2 2 604
3 13.2 132.0 108.0 4.2 45.0 5.2 47.1 9 100 1 820 87.2 83.6 2 674
4 19.0 39.0 49.0 4.0 79.2 4.5 36.8 11 572 9 357 89.5 87.6 2 577
4 13.2 54.0 63.0 4.1 78.0 5.1 45.1 10 490 6 456 87.3 85.5 2 615
), ArticleFig(id=1204780273348092483, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, language=EN, label=Table 6, caption=

GA-BP neural network model prediction results and relative error

, figureFileSmall=null, figureFileBig=null, tableContent=
沥青混合料性能预测值 相对误差/%
动态模量/
MPa
动稳定度/
(次·mm-1)
残留稳定
度/%
劈裂抗拉
比/%
极限弯拉
应变/με
动态模量 动稳定度 残留稳定度 劈裂抗拉比 极限弯拉应变
10 648 2 191 86.6 81.1 2 326 1.81 7.77 1.25 2.01 1.69
10 525 1 936 88.2 80.8 2 398 1.18 14.22 0.34 2.28 0.17
10 293 1 473 87.3 82.3 2 290 0.04 13.66 1.28 4.57 2.55
9 698 2 512 88.2 85.2 2 278 0.84 21.53 1.12 1.05 0.57
9 684 2 511 87.8 83.9 2 382 1.67 13.77 1.74 4.48 3.17
9 632 2 092 88.2 85.3 2 401 2.14 6.10 1.45 2.07 2.52
8 832 2 362 85.9 82.0 2 537 1.87 11.10 1.42 0.24 2.57
8 902 2 036 87.8 84.5 2 575 2.18 11.87 0.69 1.08 3.70
11 682 8 006 89.4 86.6 2 692 0.95 14.44 0.11 1.14 4.46
10 563 6 603 88.1 85.9 2 681 0.70 2.28 0.92 0.47 2.52
最大误差/% 2.18 21.53 1.74 4.57 4.46
最小误差/% 0.04 2.28 0.11 0.24 0.17
平均误差/% 1.34 11.67 1.03 1.94 2.39
), ArticleFig(id=1204780273431978568, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, language=CN, label=表6, caption=

GA-BP神经网络模型预测结果与相对误差

, figureFileSmall=null, figureFileBig=null, tableContent=
沥青混合料性能预测值 相对误差/%
动态模量/
MPa
动稳定度/
(次·mm-1)
残留稳定
度/%
劈裂抗拉
比/%
极限弯拉
应变/με
动态模量 动稳定度 残留稳定度 劈裂抗拉比 极限弯拉应变
10 648 2 191 86.6 81.1 2 326 1.81 7.77 1.25 2.01 1.69
10 525 1 936 88.2 80.8 2 398 1.18 14.22 0.34 2.28 0.17
10 293 1 473 87.3 82.3 2 290 0.04 13.66 1.28 4.57 2.55
9 698 2 512 88.2 85.2 2 278 0.84 21.53 1.12 1.05 0.57
9 684 2 511 87.8 83.9 2 382 1.67 13.77 1.74 4.48 3.17
9 632 2 092 88.2 85.3 2 401 2.14 6.10 1.45 2.07 2.52
8 832 2 362 85.9 82.0 2 537 1.87 11.10 1.42 0.24 2.57
8 902 2 036 87.8 84.5 2 575 2.18 11.87 0.69 1.08 3.70
11 682 8 006 89.4 86.6 2 692 0.95 14.44 0.11 1.14 4.46
10 563 6 603 88.1 85.9 2 681 0.70 2.28 0.92 0.47 2.52
最大误差/% 2.18 21.53 1.74 4.57 4.46
最小误差/% 0.04 2.28 0.11 0.24 0.17
平均误差/% 1.34 11.67 1.03 1.94 2.39
), ArticleFig(id=1204780273578779212, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, language=EN, label=Table 7, caption=

BP neural network model prediction results and relative error

, figureFileSmall=null, figureFileBig=null, tableContent=
沥青混合料性能预测值 相对误差/%
动态模量/
MPa
动稳定度/
(次·mm-1)
残留稳定度/
%
劈裂抗拉比/
%
极限弯拉应变/
με
动态模量 动稳定度 残留稳定度 劈裂抗拉比 极限弯拉应变
10 774 2 226 87.1 81.2 2 426 3.01 9.49 0.65 2.19 2.54
10 423 2 235 87.4 81.4 2 405 2.14 31.91 0.57 3.07 0.13
10 284 1 874 88.0 82.9 2 337 0.05 29.62 2.09 5.27 0.54
9 521 2 714 87.7 84.2 2 395 2.64 31.33 1.67 2.25 5.75
9 841 2 830 88.7 85.7 2 333 3.32 28.23 2.82 6.77 5.13
9 521 2 714 87.7 84.2 2 395 3.26 21.84 2.00 3.37 2.75
9 096 2 512 86.3 82.4 2 522 1.07 18.18 1.85 0.26 3.10
8 860 2 254 86.8 82.7 2 505 2.62 23.84 0.42 1.12 6.28
11 334 6 885 89.3 85.3 2 723 2.05 26.41 0.25 2.57 5.69
10 550 6 629 88.2 84.1 2 754 0.57 2.68 1.03 1.60 5.31
最大误差/% 3.32 31.91 2.82 6.77 6.28
最小误差/% 0.05 2.68 0.25 0.26 0.13
平均误差/% 2.07 22.35 1.34 2.85 3.72
), ArticleFig(id=1204780273738162769, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156908037400252755, language=CN, label=表7, caption=

BP神经网络模型预测结果与相对误差

, figureFileSmall=null, figureFileBig=null, tableContent=
沥青混合料性能预测值 相对误差/%
动态模量/
MPa
动稳定度/
(次·mm-1)
残留稳定度/
%
劈裂抗拉比/
%
极限弯拉应变/
με
动态模量 动稳定度 残留稳定度 劈裂抗拉比 极限弯拉应变
10 774 2 226 87.1 81.2 2 426 3.01 9.49 0.65 2.19 2.54
10 423 2 235 87.4 81.4 2 405 2.14 31.91 0.57 3.07 0.13
10 284 1 874 88.0 82.9 2 337 0.05 29.62 2.09 5.27 0.54
9 521 2 714 87.7 84.2 2 395 2.64 31.33 1.67 2.25 5.75
9 841 2 830 88.7 85.7 2 333 3.32 28.23 2.82 6.77 5.13
9 521 2 714 87.7 84.2 2 395 3.26 21.84 2.00 3.37 2.75
9 096 2 512 86.3 82.4 2 522 1.07 18.18 1.85 0.26 3.10
8 860 2 254 86.8 82.7 2 505 2.62 23.84 0.42 1.12 6.28
11 334 6 885 89.3 85.3 2 723 2.05 26.41 0.25 2.57 5.69
10 550 6 629 88.2 84.1 2 754 0.57 2.68 1.03 1.60 5.31
最大误差/% 3.32 31.91 2.82 6.77 6.28
最小误差/% 0.05 2.68 0.25 0.26 0.13
平均误差/% 2.07 22.35 1.34 2.85 3.72
)], 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.1671-1815.2309410, detailUrlEn=https://castjournals.cast.org.cn/joweb/kxjsygc/EN/10.12404/j.issn.1671-1815.2309410, pdfUrlCn=https://castjournals.cast.org.cn/joweb/kxjsygc/CN/PDF/10.12404/j.issn.1671-1815.2309410, pdfUrlEn=https://castjournals.cast.org.cn/joweb/kxjsygc/EN/PDF/10.12404/j.issn.1671-1815.2309410, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于遗传算法优化BP神经网络的沥青混合料性能预测方法
收藏切换
PDF下载
盛佳豪 , 柳力 * , 刘朝晖 , 潘博洋
科学技术与工程 | 论文·交通运输 2025,25(3): 1214-1224
收起
收藏切换
科学技术与工程 | 论文·交通运输 2025, 25(3): 1214-1224
基于遗传算法优化BP神经网络的沥青混合料性能预测方法
全屏
盛佳豪 , 柳力* , 刘朝晖, 潘博洋
作者信息
  • 长沙理工大学交通运输工程学院, 长沙 410114
  • 盛佳豪(2000—),男,汉族,湖南益阳人,博士研究生。研究方向:道路工程。E-mail:

通讯作者:

* 柳力(1988—),男,汉族,湖南长沙人,博士,副教授。研究方向:道路工程。E-mail:
Asphalt Mixture Performance Prediction Method Based on BP Neural Network Optimized by Genetic Algorithm
Jia-hao SHENG , Li LIU* , Zhao-hui LIU, Bo-yang PAN
Affiliations
  • School of Traffic and Transportation Engineering, Changsha University of Science and Technology, Changsha 410114, China
出版时间: 2025-01-28 doi: 10.12404/j.issn.1671-1815.2309410
文章导航
收藏切换

为实现沥青混合料性能的快速可靠预测,从材料组成设计角度出发,提出了一种基于遗传算法(genetic algorithm, GA)优化反向传播(back propagation, BP)神经网络的沥青混合料性能预测方法。首先运用灰关联分析方法对多维输入变量进行降维处理,确定了沥青混合料性能的核心影响因素,然后结合遗传算法(GA),构建了以核心影响因素为输入层、沥青混合料性能为输出层的GA-BP神经网络预测模型,再对模型进行训练验证分析与预测泛化应用,同时与BP神经网络的训练效果和预测精度进行对比,验证GA-BP神经网络模型的准确性。研究结果表明:空隙率、油石比、公称最大粒径、4.75 mm通过率、沥青种类、软化点、针入度、延度等8项性能特征的灰关联度r>0.6,对沥青混合料性能影响显著;相比于BP神经网络模型,经过GA优化后的BP神经网络模型的均方根误差(root mean square error, RMSE)降低了16%~31%,平均绝对误差(mean absolute error, MAE)降低了15%~24%,R2 值提升了0.01~0.27,说明其具有更好的学习拟合能力;在对沥青混合料动态模量、动稳定度、残留稳定度、劈裂抗拉强度比和极限弯拉应变的预测精度上分别提高了35.26%、47.78%、23.13%、31.92%、35.75%,说明GA-BP神经网络模型具有更强的泛化应用能力。研究成果为实现沥青混合料性能的快速预测、指导沥青混合料材料组成设计提供重要参考。

道路工程  /  性能预测  /  GA-BP神经网络  /  沥青混合料  /  灰关联分析

To achieve rapid and reliable prediction of asphalt mixture performance, a method for predicting asphalt mixture performance by optimizing the back propagation (BP) neural network with a genetic algorithm (GA) from the perspective of material composition design was proposed. Initially, a grey relational analysis method was employed to reduce the dimensionality of multidimensional input variables, identifying the core influencing factors of asphalt mixture performance. Subsequently, integrating the GA, a GA-BP neural network prediction model was constructed with the core influencing factors as the input layer and asphalt mixture performance as the output layer. The model underwent training, validation analysis, and prediction generalization application. A comparison with the training effectiveness and prediction accuracy of the BP neural network was conducted to verify the accuracy of the GA-BP neural network model. The research results indicate that the grey relational degrees of eight performance characteristics, including air void, asphalt-aggregate ratio, nominal maximum aggregate size, 4.75 mm passing rate, asphalt type, softening point, penetration, and ductility, are all greater than 0.6, signifying their significant impact on asphalt mixture performance. Compared to the BP neural network model, the GA-BP neural network model reduces the root mean square error (RMSE) by 16% to 31%, decreases the mean absolute error (MAE) by 15% to 24%, and improves the R2 value by 0.01 to 0.27, indicating that it has better learning and fitting capabilities. The prediction accuracy for dynamic modulus, dynamic stability, residual stability, splitting tensile strength ratio, and ultimate bending strain of the asphalt mixture is respectively enhanced by 35.26%, 47.78%, 23.13%, 31.92%, and 35.75%, revealing the superior generalization application capability of the GA-BP neural network model. The research findings provide essential references for the rapid prediction of asphalt mixture performance and guidance in the design of asphalt mixture material composition.

road engineering  /  performance prediction  /  GA-BP neural network  /  asphalt mixture  /  gray correlation analysis
盛佳豪, 柳力, 刘朝晖, 潘博洋. 基于遗传算法优化BP神经网络的沥青混合料性能预测方法. 科学技术与工程, 2025 , 25 (3) : 1214 -1224 . DOI: 10.12404/j.issn.1671-1815.2309410
Jia-hao SHENG, Li LIU, Zhao-hui LIU, Bo-yang PAN. Asphalt Mixture Performance Prediction Method Based on BP Neural Network Optimized by Genetic Algorithm[J]. Science Technology and Engineering, 2025 , 25 (3) : 1214 -1224 . DOI: 10.12404/j.issn.1671-1815.2309410
沥青混合料是公路建设中常用的路面材料之一,其性能的优劣与道路的服役寿命和使用状况息息相关[1-3]。在沥青混合料的设计和施工中,油石比、沥青种类、空隙率等材料组成指标将直接影响沥青混合料的宏观性能[4-6],目前沥青混合料的性能研究仍然以经验试错法为主,若设计的沥青混合料性能指标不符合规范,则需重新进行材料组成设计,这将消耗大量人工、材料和成本[7-8],拖延了研究进度。
为避免昂贵且耗时的实验室传统测试方法,诸多学者开始尝试将研究重点从常规试验转向数学方法。2011年美国提出材料基因组计划[9],通过将材料进行基因表征,运用数学方法和核心算法构建性能预测模型,从而研究满足某种功能的材料组成。Fan等[10]通过建立疲劳-冻融均一方程,探明了冻融循环对沥青混合料疲劳性能的影响,并验证了方程的普适性。Li等[11]结合考虑沥青路面的温度修正系数、统计交通量和荷载系数等指标,推导并验证了沥青混合料自愈性能的计算公式。该公式有助于研究沥青路面自愈性能的特点和发展规律,为计算设计沥青混合料自愈合性能提供参考。然而,沥青混合料性能与其影响因素之间存在许多难以量化的非线性关联,上述方法无法保证其具有较强泛化性,导致存在一定的局限性。
随着计算机技术和人工智能的发展,神经网络成为人工智能领域研究的热点[12-14]。反向传播(back propagation, BP)神经网络是一种严格按照误差反向传播及训练的多层前馈神经网络,是目前应用最广泛的神经网络,受到了越来越多的国内外学者的关注。为克服季节性冻土地区沥青路面层间抗剪切难度影响因素复杂的问题,Nian等[15]以剪切角、黏结层材料类型等指标为输入,剪切强度为输出构建了BP神经网络模型,结果显示所建模型的预测精度较高,且模型分析不受试件形状影响。孙益民等[16]以4种不同粒径的矿石用量比例等指标作为输入,构建了用于预测沥青混合料马歇尔稳定度和流值的BP神经网络模型,并通过此模型确定了其适宜配合比。谭忆秋等[17]通过构建BP神经网络,选取沥青性质和矿料级配的性能指标作为输入层,搭建了其与沥青混合料低温性能指标之间的关联,实现了性能预测。当然,许多学者也将BP神经网络运用于温度预测或行为选择分析等多种领域[18-19],验证了BP神经网络的适用性,并发现其预测性能明显优于传统方程模型[20]
然而,BP神经网络的权值阈值及学习率等参数随机性较大,容易导致神经网络在实际应用中出现迭代时间过长、陷入局部最优解等问题[21]。遗传算法(genetic algorithm, GA) 是一种引入自然选择和进化思想的优化算法[22],模拟了自然选择和遗传中发生的复制、交叉和变异等现象,具有优良的全局寻优性能。通过遗传算法的随机全局搜索优化功能对BP神经网络进行改进,可克服BP神经网络本身的缺陷,进一步提高网络性能。
因此,为更高精度地实现沥青混合料性能预测,以灰关联分析降维处理后的沥青混合料性能的核心影响因素作为模型输入层,以沥青混合料动态模量、动稳定度、残留稳定度、劈裂抗拉强度比和极限弯拉应变作为模型输出层,建立各性能特征之间的映射关系,构建了基于遗传算法优化BP神经网络(GA-BP神经网络)的沥青混合料性能预测模型,并将其与BP神经网络模型进行对比分析,验证了GA-BP神经网络模型的预测精度和泛化能力。研究成果对实现沥青混合料性能预测、指导沥青混合料组成设计具有重要的研究意义。
灰关联分析是指一个系统发展变化态势的定量描述和比较的方法,其基本思想是通过确定母序列和若干个子序列的几何形状相似程度来判断其联系是否紧密,它反映了曲线间的关联程度[23-24]
考虑到影响沥青混合料性能的材料组成特征繁多且复杂[25],为了对原始多维输入特征进行降维处理,采用灰关联分析方法,筛选提取出影响沥青混合料性能的核心影响因素。现共收集实测数据558组,包含17项性能特征,其中包括空隙率、油石比、公称最大粒径、软化点、延度、针入度、沥青相对密度、吸水率、沥青种类、矿粉表观相对密度、细集料棱角性、4.75 mm通过率等原材料性能、沥青混合料细观性能共12项,动态模量、动稳定度、残留稳定度、劈裂抗拉强度比和极限弯拉应变等沥青混合料宏观性能共5项。沥青混合料材料组成及其性能指标如表1所示。
针对沥青混合料性能的核心影响因素灰关联分析步骤如下[26-27]:①数据处理与选择;②求解子序列与母序列间的灰关联系数值;③求解灰关联度值;④对灰关联度值进行排序,得出结论。灰关联分析流程如图1所示。
(1) 数据处理与选择:分别选取动态模量、动稳定度、残留稳定度、劈裂抗拉强度比、极限弯拉应变5项宏观性能特征作为母序列,空隙率、公称最大粒径、油石比等12项材料组成特征作为子序列,为方便数据表征,其中沥青种类的70#沥青、90#沥青、110#沥青和SBS改性沥青分别用数字1、2、3、4来表示,其他数据均以原始数据形式表达。同时,为避免因数据量纲不同而影响评价模型的情况,选择均值化的无量纲处理方式,即每类数据以平均值作为单位,全部数据均除以该数据类的平均值。
(2) 求解灰关联系数:每项沥青混合料性能定义为母序列N0x各项材料组成特征定义为子序列Ni,则灰关联系数为
ξi(k)= m i n i m i n k | N 0 x k - N i k | + ρ m a x i m a x k | N 0 x k - N i k | | N 0 x k - N i k | + ρ m a x i m a x k | N 0 x k - N i k |,i=1,2,…,12;x=1,2,3,4,5
式(1)中:N0xk-Nik表示第x个母序列与第i个子序列在第k个点的差值;ρ为关联分辨系数,一般为0~1,ρ越小,分辨力越大,计算时取0.5。
(3) 求解灰关联度值:灰关联度值ri可直接用于评判该材料组成特征对沥青混合料性能的影响程度,关联度值越高,即影响程度越大。计算公式为
ri= 1 m k = 1 m ξi(k)
式(2)中:m为样本的总数量。
(4) 灰关联度排序,结果分析:分别对5项沥青混合料性能的灰关联度值进行排序,比较各材料组成特征对其的影响程度大小。
根据上述灰关联分析步骤,计算得到各材料组成对动态模量、动稳定度等5项沥青混合料性能的灰关联度ri,并对其进行排序,计算结果如表2所示。
表2中可以看出,空隙率、油石比、公称最大粒径等8项材料组成特征对各母序列的灰关联关联度值均大于0.6,对沥青混合料性能的影响显著,可选取作为核心影响因素用于进一步研究;沥青相对密度、矿粉表观相对密度、细集料棱角性以及吸水率这4项特征的关联度均小于0.6,对沥青混合料性能的影响较小,说明其并不适宜用来评价沥青混合料的路用性能及力学性能,故在性能研究中不考虑此4项特征对模型及结果的影响。
BP神经网络是一种按照误差反向传播算法训练的多层前馈网络[28-29],分为输入层、隐含层和输出层,并由信息的正向传播和误差的反向传播两个过程组成,具有良好的非线性映射能力和适应性[30-31]。BP神经网络结构简图如图2所示。
1) 正向传播
神经网络神经元的净输入为
n i m= j = 1 S m - 1 W i , j m y j m - 1+ b i m,m=1,2,…,M(M≥2)
式中: n i m表示神经网络第m层第i个神经元的权值与偏置值的净输入和; S m - 1表示第m-1层的神经元个数; W i , j m表示第m层第i个神经元与第m-1层第j个神经元之间的权值; y j m - 1表示第m-1层第j个神经元的输出; b i m表示第m层第i个神经元的偏置;M为神经网络的层数。
m层的输出为
ym=fm(nm)
式(4)中:fm表示神经网络第m层的传递函数。
2) 反向传播
(1)误差函数。所建BP神经网络算法使用的误差函数为均方误差函数,则以算法的输入和对应的理想或期望输出作为样本的集合为
{x1,t1},{x2,t2},…,{xR,tR}
式(5)中:R为输入层神经元的个数;xR为神经网络的输入;tR为期望输出。
每一个输入样本,都会将神经网络真实输出与期望输出作比较,算法将会计算新的神经网络参数以使均方误差最小化,可表示为
F(z)=E(e2)=E[(t-y)2]
式中:E ( )为期望值;e为误差;t为期望输出;y为神经网络实际输出;z为神经网络权值和偏置值的向量,可表示为
z= W b
当BP神经网络有多个输出则式(6)的一般形式可表示为
F(z)=E[eTe]=E[(t-y)T(t-y)]
当用 F (z)来近似计算均方误差,则可表示为
F (z)=[t(k)-y(k)]T[t(k)-y(k)]=eT(k)e(k)
式(9)中:k为迭代次数。
(2)权值修正方法。为不断更新迭代神经网络的权值,采用的近似均方误差的梯度下降法为
ω i , j m(k+1)= ω i , j m(k)-η F ω i , j m
b i m(k+1)= b i m(k)-η F b i m
式中:η为学习速率。
BP神经网络的结构设计主要包括输入层、输出层与隐含层的设计,具体设计流程如图3所示。
1) 输入层与输出层的设计
在BP神经网络的训练中,将由灰关联分析所得的8项材料组成特征,包括空隙率、油石比、公称最大粒径、沥青种类、4.75 mm通过率、延度、针入度和软化点,作为网络模型的输入层;将5项沥青混合料性能特征,包括动态模量、动稳定度、残留稳定度、劈裂抗拉强度比和极限弯拉应变,作为网络模型的输出层。因此,所建BP神经网络模型的输入层神经元个数为8,输出层神经元个数为5。
为取消各维变量数据间的数量级差别,避免因输入或输出数据量纲差别过大而造成网络模型误差较大,对数据进行归一化处理,使所有数据均处于[0,1]的范围内,再用于网络模型训练。归一化公式为
x*= x - x m i n x m a x - x m i n, x*∈[0,1]
式(12)中:x*为归一化后样本数据值;x为原始学习样本数据;xmax为原始样本数据的最大值;xmin为原始学习样本数据的最小值。
2) 隐含层的设计
BP神经网络的隐含层层数会对模型训练时间及精度产生影响,目前一个三层网络结构就可以完成任意的n维到m维的非线性映射[32-33]。因此,采用隐含层数为1的BP神经网络作为模型计算。
隐含层神经元个数的选择会影响迭代速度以及模型误差,根据经验公式计算隐含层的神经元数量,即
k=log2m
k= m + n+c
0.02m<k<4m
式中:k为隐含层神经元个数; m为输入层神经元个数;n为输出层神经元个数;c为1~10的任意整数。
根据式(13)~式(15)可得隐含层神经元个数区间为[5,14],保持模型参数不变,仅改变网络隐含层神经元个数进行重复训练。为综合评价不同隐含层神经元下的网络模型性能,分别计算5项沥青混合料性能的相关系数r与均方误差(mean square error, MSE),再分别取其均值作为模型综合评价指标值,从而确定最佳隐含层神经元个数。第j项沥青混合料性能的相关系数rj与均方误差MSEj的计算公式为
rj= i = 1 N ( x i - x ) ( y i - y ) i = 1 N ( x i - x ) 2 i = 1 N ( y i - y ) 2
r = j = 1 5 r j 5
MSEj= i = 1 N ( o i - y o i ) 2 N
M S E ¯= j = 1 5 M S E j 5
式中: r 为5项沥青混合料性能相关系数的均值;xi为第i组数据的模型预测值;yi为第i组数据的模型真实值; M S E ¯为5项沥青混合料性能均方误差的均值;o为期望输出值;yo为实际输出值;N为样本总数。不同隐含层神经元下模型训练指标结果如表3所示。
表3可知,随着k值的增大,相关系数r整体呈先增大后减小的趋势,均方误差MSE整体呈先减小后增大的趋势,且均在k=11时达到峰值,此时相关系数r=0.883,均方误差MSE=0.011。因此BP神经网络模型的隐含层神经元个数取11。
3) 网络参数设置与模型构建
在BP神经网络模型中,传递函数是将每个神经元的输出按照指定的函数关系得到一个新的映射输出,进而完成神经网络的训练。根据经验[34],模型选取Tan-Sigmoid函数作为从输入层到隐含层的激活函数,选取Purelin 函数作为从隐含层到输出层的激活函数,公式分别为
y= e n - e - n e n + e - n
y=n
式中:n为净输入。
设置模型训练参数[35],取迭代次数k=1 000,学习率l=0.001,模型误差阈值e=10-6,构建用于预测沥青混合料性能的BP神经网络模型,其模型结构图如图4所示。
遗传算法(genetic algorithm, GA)基于达尔文自然界遗传与进化的基本原理,综合适者生存与遗传信息随机交换的生物进化特点,以一种概率性搜索的形式,逐步寻找到研究问题的最优解或近似最优解[36-38]。遗传算法的基本步骤如下:
(1) 初始化种群。遗传算法根据模型规模随机生成一组初始解作为种群的个体,将数据表达为基因型序列,再执行搜索。常见的有二进制编码、实数编码等多种编码方式,其中二进制编码容易受到多维度问题的影响,实数编码具有精度高、搜索能力强的优点,因此选用实数编码的方式对染色体进行编码。染色体长度S的计算公式为
S=mk+kn+k+n
式(22)中:mkn分别为输入层、隐含层和输出层的神经元个数,具体分别取8、11、5。
(2) 计算适应度。通过计算找出种群中的每一代进化中的最优染色体并记录保留,适应度函数为
Hi= 1 i = 1 n ( y i - y i ) 2
式(23)中:n为样本数; y iyi分别为样本i的预测值与实测值。
(3) 选择。从当前种群中选择一部分个体作为下一代的父代,依据个体适应度值在总适应度值中的占比来判断被选择的概率,占比越大,被选择的概率越大。
(4) 交叉。模拟生物遗传中的杂交过程,对选中的父代进行交叉操作,产生新个体。
(5) 变异。模拟生物遗传中的基因突变过程,对新产生的个体进行变异操作,设定变异概率,引入一定的随机性。
(6) 重复步骤(2)~(5),达到设定迭代次数停止,获得最优初始权值和阈值。
根据经验[39-40],遗传算法各参数选择为:种群规模取30,种群大小取200,交叉概率取0.5,变异概率取0.05,遗传代数取50,最大迭代次数取1 000。
BP神经网络具有较强的学习泛化能力,但由于其初始权值和阈值通常是随机初始化的,往往会导致出现迭代时间过长、易陷入局部最优解等问题。而遗传算法具有良好的全局搜索能力,可以快速搜索出全体解,且容易与其他算法相结合,具有可拓展性。GA-BP神经网络的本质是将GA算法与BP神经网络相结合,通过迭代优化BP神经网络的初始权值和阈值,避免陷入局部最优解,提高神经网络性能。GA-BP神经网络算法流程如图5所示。
为综合评价GA-BP神经网络模型的预测精度,以BP神经网络模型为对比模型,选取均方根误差(root mean error, RMSE)、平均绝对误差(mean absolute error, MAE)和决定系数(R2)3种评价指标对神经网络模型性能进行衡量,计算公式分别为
RMSE= 1 n j = 1 n ( y j - y j ) 2
MAE= 1 n j = 1 n y j-yj|
R2=1- j = 0 n - 1 ( y j - y j ) 2 j = 0 n - 1 ( y j - y - j ) 2
式中:n为样本数量; y jyj y - j分别为输出数据的预测值、实测值和平均值。
考虑到机器学习模型均可能出现训练过拟合现象,所以在558组闭合实测数据中,取548组数据用于GA-BP神经网络模型和BP神经网络模型的训练验证分析,10组数据用于预测泛化应用,进一步验证GA-BP神经网络模型的准确性。
在548组训练数据中,将训练集与测试集比例设置为7.5∶2.5,即随机取其中410组数据作为训练集,另外138组数据作为测试集,并采用RMSE、MAE、R2等指标对模型训练效果进行评价。
表4展示了GA-BP与BP神经网络模型在训练集和测试集上的训练表现,从表4可以看出,两种模型在训练集上的RMSE与MAE均低于测试集,且R2均高于测试集,这说明两者均具有较好的学习拟合能力。另外,从表中可以得知,在对沥青混合料5项性能的训练中,相比于常规的BP神经网络模型,经遗传算法改进后的GA-BP神经网络模型在训练集和测试集上均具有更低的均方根误差RMSE、平均绝对误差MAE,同时具有数值更接近1的决定系数R2,其RMSE值降低了16%~31%, MAE值降低了15%~24%, R2 提升了0.01~0.27,很大程度上优化了BP神经网络模型的预测精度,说明GA-BP神经网络模型在沥青混合料性能的预测上优于BP神经网络模型,具有更好的学习拟合能力,能更好地解释沥青混合料材料组成与性能之间的非线性映射关系。
为进一步验证GA-BP神经网络对沥青混合料性能预测的泛化应用能力,对10组沥青混合料组成数据(表5)进行预测,并将预测值与实测值进行对比分析,误差对比图如图6所示。
图6可知,尽管各项性能预测值与实测值之间存在一定的偏差,但相比于BP神经网络,GA-BP神经网络的预测曲线的波动规律和变化趋势更接近实测曲线。表6表7分别展示了GA-BP神经网络和BP神经网络的预测结果与相对误差情况,从表中可以得知,BP神经网络模型对沥青混合料动态模量、动稳定度、残留稳定度、劈裂抗拉强度比和极限弯拉应变的平均误差分别为2.07%、22.35%、1.34%、2.85%、3.72%,而GA-BP神经网络模型对其的平均误差为1.34%、11.67%、1.03%、1.94%、2.39%,预测精度分别提高了35.26%、47.78%、23.13%、31.92%、35.75%,说明GA-BP神经网络模型对于未知数据的预测效果比BP神经网络模型更好,具有更强的泛化应用能力。
总体而言,该沥青混合料性能GA-BP神经网络预测模型表现出了较强的预测能力和泛化能力,可用于沥青混合料性能的预测,也为沥青混合料的材料组成设计提供了思路。
利用大数据分析,提出了一种基于遗传算法优化BP神经网络的沥青混合料性能预测方法,实现了沥青混合料性能的快速可靠预测,得到如下主要结论。
(1) 通过灰关联分析方法对沥青混合料材料组成特征进行降维处理,确定了沥青混合料性能核心影响因素,即空隙率、油石比、公称最大粒径、沥青种类、4.75 mm通过率、延度、针入度以及软化点。
(2) 以空隙率、油石比、公称最大粒径等8项材料组成特征作为输入层,以动态模量、动稳定度等5项沥青混合料性能作为输出层,结合遗传优化算法,构建了沥青混合料性能GA-BP神经网络预测模型。
(3) 通过将GA-BP神经网络和BP神经网络的训练验证结果进行对比,结果表明,经过遗传算法优化后的BP神经网络模型的RMSE值降低了16%~31%, MAE降低了15%~24%, R2 提升了0.01~0.27,说明GA-BP神经网络模型在沥青混合料性能的预测上优于BP神经网络模型,具有更好的学习拟合能力。
(4) 利用GA-BP神经网络模型和BP神经网络模型对10组实测数据进行预测,结果显示,GA-BP神经网络模型相比于BP神经网络模型,在对沥青混合料动态模量、动稳定度、残留稳定度、劈裂抗拉强度比和极限弯拉应变的预测精度上分别提高了35.26%、47.78%、23.13%、31.92%、35.75%,说明GA-BP神经网络模型对于未知数据的预测效果比BP神经网络模型更好,具有更强的泛化应用能力。
(5) 研究成果可通过沥青混合料的材料组成特征预测得到沥青混合料性能,但并未对路面结构类型进行细分。在后续的研究中,可进一步考虑路面结构类型,提出更适合不同路面结构类型的沥青混合料性能预测方法。
  • 国家重点研发计划(2021YFB2601000)
  • 国家自然科学基金(52278437)
  • 国家自然科学基金(52208423)
  • 长沙市杰出创新青年培养计划(kq2306009)
参考文献 引证文献
排序方式:
[1]
沈金安. 沥青及沥青混合料路用性能[M]. 北京: 人民交通出版社, 2000.
Shen Jin’an. Asphalt and asphalt mixture road performance[M]. Beijing: China Communication Press, 2000.
[2]
黄晓明. 路基路面工程[M]. 6版. 北京: 人民交通出版社, 2019.
Huang Xiaoming. Road subgrade and pavement engineering[M]. 6th ed. Beijing: China Communication Press, 1999.
[3]
陆学元, 陈远播, 魏星, 等. 沥青混合料低温劈裂虚拟试验影响因素研究[J]. 科学技术与工程, 2024, 24(8): 3389-3398.
Lu Xueyuan, Chen Yuanbo, Wei Xing, et al. Influence factors of low-temperature virtual indirect tensile test for asphalt mixtures[J]. Science Technology and Engineering, 2024, 24(8): 3389-3398.
[4]
刘莉萍, 杜婷, 郭建博. 基于响应曲面法硅藻土改性沥青混合料性能研究[J]. 石河子大学学报(自然科学版), 2023, 41(3): 306-310.
Liu Liping, Du Ting, Guo Jianbo. Response surface method for performance of diatomite modified asphalt mixture[J]. Journal of Shihezi University(Natural Science), 2023, 41(3): 306-310.
[5]
郭忠宝. 溶剂型冷补沥青混合料材料组成设计研究[J]. 北方交通, 2022(11): 40-44.
Guo Zhongbao. Research on the material composition design of solvent cold patching asphalt mixture[J]. Northern Communications, 2022(11): 40-44.
[6]
刘树俊. 新型冷拌沥青混合料制备及其性能研究[D]. 青岛: 中国石油大学(华东), 2016.
Liu Shujun. Fabrication and performance of novel cold-mix asphalt mixture[D]. Qingdao: China University of Petroleum(East China), 2016.
[7]
谭忆秋, 吕慧杰, 徐慧宁. 材料基因思想在沥青路面材料领域的应用展望[J]. 交通运输研究, 2020, 6(5): 2-12.
Tan Yiqiu, Huijie, Xu Huining. Application prospect of material genetics idea in asphalt pavement materials[J]. Transport Research, 2020, 6(5): 2-12.
[8]
邢超, 谭忆秋, 张凯, 等. 基于材料基因组方法的沥青混合料基因特性综述及展望[J]. 中国公路学报, 2020, 33(10): 76-90.
Xing Chao, Tan Yiqiu, Zhang Kai, et al. Review and prospect of genetic characteristics of asphalt mixture based on material genome method[J]. China Journal of Highway and Transport, 2020, 33(10): 76-90.
[9]
Pablo J, Jones B, Lind C, et al. The materials genome initiative, the interplay of experiment, theory and computation[J]. Current Opinion in Solid State & Materials Science, 2014, 18(2): 99-117.
[10]
Fan Z P. Effects of freeze-thaw cycles on fatigue performance of asphalt mixture and development of fatigue-freeze-thaw(FFT) uniform equation[J]. Construction and Building Materials, 2020, 242: 118043.
[11]
Li C Y. Study on the factors affecting the self-healing performance of asphalt mixture and pavement based on fracture mechanics and calculation formula[J]. Theoretical and Applied Fracture Mechanics, 2023, 126: 103954.
[12]
赵文迪, 陈德旺, 卓永强, 等. 深度神经模糊系统算法及其回归应用[J]. 自动化学报, 2020, 46(11): 2350-2358.
Zhao Wendi, Chen Dewang, Zhuo Yongqiang, et al. Deep neural fuzzy system algorithm and its regression application[J]. Acta Automatica Sinica, 2020, 46(11): 2350-2358.
[13]
孙剑, 蒙西, 乔俊飞. 数据驱动的城市固废焚烧过程烟气含氧量预测控制[J]. 控制理论与应用, 2024, 41(3): 484-495.
Sun Jian, Meng Xi, Qiao Junfei. Data-driven predictive control of oxygen content in flue gas for municipal solid waste incineration process[J]. Control Theory & Applications, 2024, 41(3): 484-495.
[14]
王琪, 张洪. 基于组合预测模型的南京禄口国际机场货运吞吐量预测[J]. 物流工程与管理, 2023, 45(2): 83-86.
Wang Qi, Zhang Hong. Cargo throughput prediction of nanjing lukou international airport based on combined prediction model[J]. Logistics Engineering and Management, 2023, 45(2): 83-86.
[15]
Nian T. Method to predict the interlayer shear strength of asphalt pavement based on improved back propagation neural network[J]. Construction and Building Materials, 2022, 351: 128969.
[16]
孙益民, 钟明, 徐玲, 等. 基于神经网络的沥青混合料配合比设计[J]. 公路交通科技, 2012, 29(2): 40-45.
Sun Yimin, Zhong Ming, Xu Ling, et al. Design on asphalt mixture ratio based on neural networks[J]. Journal of Highway and Transportation Research and Development, 2012, 29(2): 40-45.
[17]
谭忆秋, 公维强, 周纯秀, 等. 基于BP神经网络的沥青混合料低温性能预测模型[J]. 中外公路, 2008, 28(6): 213-216.
Tan Yiqiu, Gong Weiqiang, Zhou Chunxiu, et al. Research on the application of neural network in the model for asphalt mixture performance at low temperature[J]. Journal of China & Foreign Highway, 2008, 28(6): 213-216.
[18]
Xu B, Dan H C, Li L. Temperature prediction model of asphalt pavement in cold regions based on an improved BP neural network[J]. Applied Thermal Engineering, 2017, 120: 568-580.
[19]
刘阳, 赵晖. 基于小波神经网络的城市交通出行方式交互预测[J]. 长安大学学报(自然科学版), 2015, 35(S1): 41-44, 48.
Liu Yang, Zhao Hui. Interactive prediction for traffic model split based on wavelet neural networks[J]. Journal of Chang’an University(Natural Science Edition), 2015, 35(S1): 41-44, 48.
[20]
谢春磊, 张勇, 耿红斌, 等. 基于BP神经网络的沥青混合料疲劳性能预测模型[J]. 重庆交通大学学报(自然科学版), 2018, 37(2): 35-40.
Xie Chunlei, Zhang Yong, Geng Hongbin, et al. Asphalt mixture fatigue life prediction model based on neural network[J]. Journal of Chongqing Jiaotong University(Natural Science), 2018, 37(2): 35-40.
[21]
刘伟吉, 冯嘉豪, 祝效华, 等. 基于动量自适应学习率PSO-BP神经网络的钻速预测模型研究[J]. 科学技术与工程, 2023, 23(24): 10264-10272.
Liu Weiji, Feng Jiahao, Zhu Xiaohua, et al. Prediction model of penetration rate based on PSO-BP neural network with momentum adaptive learning rate[J]. Science Technology and Engineering, 2023, 23(24): 10264-10272.
[22]
吕政桦, 申爱琴, 李悦, 等. 基于遗传优化的乳化沥青冷再生混合料的疲劳性能及机理研究[J]. 材料导报, 2019, 33(16): 2704-2709.
Lyu Zhenghua, Shen Aiqin, Li Yue, et al. Study on fatigue performance and mechanism of emulsified asphalt cold recycled micture based on genetic optimization[J]. Materials Reports, 2019, 33(16): 2704-2709.
[23]
邓聚龙. 灰色系统基本方法[M]. 2版. 武汉: 华中科技大学出版社, 2005.
Deng Julong. The primary method of grey system theory[M]. 2nd ed. Wuhan: Huazhong University of Science and Technology Press, 2005.
[24]
周兴林, 刘万康, 肖旺新, 等. 沥青混合料体积指标对沥青路面抗滑性能的影响[J]. 交通运输工程学报, 2017, 17(6): 1-9.
Zhou Xinglin, Liu Wankang, Xiao Wangxin, et al. Influence of asphalt mixture volume indexes on asphalt pavement skid resistance performance[J]. Journal of Traffic and Transportation Engineering, 2017, 17(6): 1-9.
[25]
刘朝晖, 朱国虎, 柳力, 等. 玄武岩纤维与高模量外掺剂复合增强沥青混合料性能[J]. 科学技术与工程, 2023, 23(5): 2147-2155.
Liu Zhaohui, Zhu Guohu, Liu Li, et al. Performance of asphalt mixture reinforced by basalt fiber and high modulus admixture[J]. Science Technology and Engineering, 2023, 23(5): 2147-2155.
[26]
刘思峰, 蔡华, 杨英杰, 等. 灰色关联分析模型研究进展[J]. 系统工程理论与实践, 2013, 33(8): 2041-2046.
Liu Sifeng, Cai Hua, Yang Yingjie, et al. Advance in grey incidence analysis modelling[J]. Systems Engineering-Theory & Practice, 2013, 33(8): 2041-2046.
[27]
Azzeh M, Neagu D. Fuzzy grey relational analysis for software effort estimation[M]. Netherlands: Kluwer Academic Publishers, 2010.
[28]
文常保. 人工神经网络理论及应用[M]. 西安: 西安电子科技大学出版社, 2019.
Wen Changbao. Artificial neural network theory and its applications[M]. Xi’an: Xidian University Press, 2019.
[29]
李晓娟, 张芳媛, 喻玲. 基于主成分分析-BP神经网络的风电备件需求预测[J]. 科学技术与工程, 2024, 24(1): 281-288.
Li Xiaojuan, Zhang Fangyuan, Yu Ling. Wind power spare parts demand forecasting based on PCA-BP neural networks[J]. Science Technology and Engineering, 2024, 24(1): 281-288.
[30]
张浩, 袁军座, 曹现雷, 等. 基于BP神经网络的Cu-Ce掺杂TiO2光催化剂性能预测组合模型研究[J]. 材料导报, 2015, 29(14): 148-151, 155.
Zhang Hao, Yuan Junzuo, Cao Xianlei, et al. Research on hybrid prediction methods for Cu-Ce-doped TiO2 photocatalytic performance based on BP network[J]. Materials Reports, 2015, 29(14): 148-151, 155.
[31]
黄炜, 周烺, 葛培, 等. 基于PSO-BP和GA-BP神经网络再生砖骨料混凝土强度模型的对比研究[J]. 材料导报, 2021, 35(15): 15026-15030.
Huang Wei, Zhou Lang, Ge Pei, et al. A comparative study on compressive model of recycled Brick aggregate concrete based on PSO-BP and neural networks[J]. Materials Reports, 2021, 35(15): 15026-15030.
[32]
范高锋, 王伟胜, 刘纯, 等. 基于人工神经网络的风电功率预测[J]. 中国电机工程学报, 2008,(34): 118-123.
Fan Gaofeng, Wang Weisheng, Liu Chun, et al. Wind power prediction based on artificial neural network[J]. Proceedings of the CSEE, 2008(34): 118-123.
[33]
黄靓钰, 阳军生, 张聪, 等. 基于BP神经网络的水下岩溶地层盾构掘进参数预测与分析[J]. 土木工程学报, 2020, 53(S1): 75-80, 98.
Huang Liangyu, Yang Junsheng, Zhang Cong, et al. Prediction and analysis of sheild tunneling parameters in underwater karst stratum based on BP neural network[J]. China Civil Engineering Journal, 2020, 53(S1): 75-80, 98.
[34]
王雪青, 喻刚, 孟海涛. 基于GA改进BP神经网络的建设工程投标报价研究[J]. 土木工程学报, 2007(7): 93-98.
Wang Xueqing, Yu Gang, Meng Haitao. Study of construction project bidding based on neural network improved by GA[J]. China Civil Engineering Journal, 2007(7): 93-98.
[35]
王晓东, 栗杉杉, 刘颖明, 等. 基于特征变权的超短期风电功率预测[J]. 太阳能学报, 2023, 44(2): 52-58.
Wang Xiaodong, Li Shanshan, Liu yingming, et al. Ultra-short-term wind power prediction based on variable feature weight[J]. Acta Energiae Solaris Sinica, 2023, 44(2): 52-58.
[36]
庄亮东, 杨悦, 吴桢灏. 遗传算法在Y型偏心支撑组合框架抗震性能优化中的应用研究[J]. 工程力学, 2023, 40(7): 185-195.
Zhuang Liangdong, Yang Yue, Wu Zhenhao. The application of genetic algorithm in seismic performance optimization of Y-shape eccentrically braced composite frame[J]. Engineering Mechanics, 2023, 40(7): 185-195.
[37]
刘艳冬, 卢兰萍, 刘林林, 等. 基于GA-BP神经网络的煤层底板突水量等级预测[J]. 中国煤炭地质, 2023, 35(8): 32-37.
Liu Yandong, Lu Lanping, Liu Linlin, et al. Prediction of water inrush grade of coal seam floor based on GA-BP neural network[J]. Coal Geology of China, 2023, 35(8): 32-37.
[38]
鲁宇涛, 张引弟, 徐刘伟, 等. 基于遗传算法的盐穴储气库注气能力方案优化[J]. 科学技术与工程, 2024, 24(11): 4472-4478.
Lu Yutao, Zhang Yindi, Xu Liuwei, et al. Optimization of gas injection capacity strategy for salt cavern gas storage based on genetic algorithm[J]. Science Technology and Engineering, 2024, 24(11): 4472-4478.
[39]
吴景龙, 杨淑霞, 刘承水. 基于遗传算法优化参数的支持向量机短期负荷预测方法[J]. 中南大学学报(自然科学版), 2009, 40(1): 180-184.
Wu Jinglong, Yang Shuxia, Liu Chengshui. Parameter selection for support vector machines based on genetic algorithms to short-term power load forecasting[J]. Journal of Central South University(Science and Technology), 2009, 40(1): 180-184.
[40]
刘爱军, 杨育, 邢青松, 等. 柔性作业车间多目标动态调度[J]. 计算机集成制造系统, 2011, 17(12): 2629-2637.
Liu Aijun, Yang Yu, Xing Qingsong, et al. Dynamic scheduling on multi-objective flexible job shop[J]. Computer Integrated Manufacturing Systems, 2011, 17(12): 2629-2637.
2025年第25卷第3期
PDF下载
402
171
引用本文
BibTeX
文章信息
doi: 10.12404/j.issn.1671-1815.2309410
  • 接收时间:2023-11-29
  • 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:2023-11-29
  • 修回日期:2024-06-24
基金
国家重点研发计划(2021YFB2601000)
国家自然科学基金(52278437)
国家自然科学基金(52208423)
长沙市杰出创新青年培养计划(kq2306009)
作者信息
    长沙理工大学交通运输工程学院, 长沙 410114

通讯作者:

* 柳力(1988—),男,汉族,湖南长沙人,博士,副教授。研究方向:道路工程。E-mail:
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/kxjsygc/CN/10.12404/j.issn.1671-1815.2309410
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