Article(id=1276896925886575114, tenantId=1146029695717560320, journalId=1276577754012160025, issueId=1276896661737701828, articleNumber=null, orderNo=null, doi=10.3724/j.gyjzG25111704, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1763308800000, receivedDateStr=2025-11-17, revisedDate=null, revisedDateStr=null, acceptedDate=null, acceptedDateStr=null, onlineDate=1782365550728, onlineDateStr=2026-06-25, pubDate=1779206400000, pubDateStr=2026-05-20, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1782365550728, onlineIssueDateStr=2026-06-25, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1782365550728, creator=13701087609, updateTime=1782365550728, updator=13701087609, issue=Issue{id=1276896661737701828, tenantId=1146029695717560320, journalId=1276577754012160025, year='2026', volume='56', issue='5', pageStart='1', pageEnd='264', issueExtLink='null', onlineDate='null', pubDate='1779206400000', pubDateStr='2026-05-20', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1782365487751, creator='13701087609', updateTime=1782367237543, updator='13701087609', preIssue=null, nextIssue=null, articleTotal=null, ext={EN=IssueExt(id=1276904000968589318, tenantId=1146029695717560320, journalId=1276577754012160025, issueId=1276896661737701828, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1276904000968589319, tenantId=1146029695717560320, journalId=1276577754012160025, issueId=1276896661737701828, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null, downloadFileDto=null}, startPage=167, endPage=175, ext={EN=ArticleExt(id=1276896926100484620, articleId=1276896925886575114, tenantId=1146029695717560320, journalId=1276577754012160025, language=EN, title=Research on Machine Learning-Based Prediction and Optimization Methods for the Performance of Traditional Building Wall Materials: a Case Study of Bamboo-Woven Mud Walls, columnId=null, journalTitle=Industrial Construction, columnName=null, runingTitle=null, highlight=null, articleAbstract=

This study applied machine learning to predict and optimize the hygrothermal performance of bamboo-woven mud walls, highlighting their potential in addressing environmental challenges. Generative adversarial networks (GANs) were first used to augment limited experimental data, addressing small-sample constraints. A back propagation (BP) neural network was employed to analyze and predict the performance of the wall materials. After optimization via a genetic algorithm (GA), the model’s R² improved to 0.77, indicating significantly enhanced predictive performance. These findings confirm the feasibility of using machine learning in the reuse of traditional building materials and provide a digital theoretical basis and technical support for the preservation and renewal of bamboo-woven mud walls.

, authors=null, authorsList=Yixi WANG, Jiaxiang ZHENG, Keyang HU, Jiayan FU, Xianglei HU, authorCompany=null, correspAuthors=null, authorNote=null, correspAuthorsNote=null, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=null, magXml=null, pdfUrl=null, pdf=null, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=null, mapNumber=null, fund=null), CN=ArticleExt(id=1276896930483532327, articleId=1276896925886575114, tenantId=1146029695717560320, journalId=1276577754012160025, language=CN, title=面向传统建筑墙体材料性能的机器学习预测优化方法研究——以竹编泥墙为例, columnId=1276896697703858872, journalTitle=工业建筑, columnName=工程诊断与性能提升技术, runingTitle=null, highlight=null, articleAbstract=

聚焦机器学习方法,对竹编泥墙的热湿性能进行预测与优化,挖掘竹编泥墙应对环境挑战的潜力。首先借助生成对抗网络(GANs)扩充试验数据,有效克服小样本数据集的局限;再利用反向传播(BP)神经网络对墙体性能开展预测分析。为提升预测性能,通过遗传算法(GA)对BP神经网络进行优化后,大幅提高预测精度,模型预测系数R²为0.77121,充分显示GA优化BP神经网络模型的预测性能优于原始模型。研究结果验证了机器学习在传统建筑材料再利用领域的可行性,为竹编泥墙的保护更新提供了数字化理论依据与技术支撑。

, authors=

王乙茜,博士研究生,主要从事智能建造方向研究,

, authorsList=王乙茜, 郑家祥, 胡柯杨, 傅嘉言, 胡向磊, authorCompany=null, correspAuthors=null, authorNote=null, correspAuthorsNote=
胡向磊,副教授,主要从事建筑工业化方向研究,
傅嘉言,博士后,主要从事智能建造方向研究,
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=T67gfWJtZpy/PRQATD1xfA==, magXml=v10z8O78O1uF6rbm1UHdxw==, pdfUrl=null, pdf=5ne5VZrGdIa8RzS+XTH9Ew==, pdfFileSize=9676449, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=hWJ7zZ/Ar9bmp9q38AfLng==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=FueYSL37AzYKpMHmfElyNA==, mapNumber=null, fund=null)}, authors=[Author(id=1276896931066540593, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=wyxsscici@tongji.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1276896931519525428, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, authorId=1276896931066540593, language=EN, stringName=Yixi WANG, firstName=Yixi, middleName=null, lastName=WANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1College of Architecture and Urban Planning, Tongji University, Shanghai200092, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1276896931817321013, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, authorId=1276896931066540593, language=CN, stringName=王乙茜, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1同济大学建筑与城市规划学院,上海200092, bio={"content":"

王乙茜,博士研究生,主要从事智能建造方向研究,

"}, bioImg=null, bioContent=

王乙茜,博士研究生,主要从事智能建造方向研究,

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1276896930735190569, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, xref=1, ext=[AuthorCompanyExt(id=1276896930743579178, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, companyId=1276896930735190569, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1College of Architecture and Urban Planning, Tongji University, Shanghai200092, China), AuthorCompanyExt(id=1276896930751967787, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, companyId=1276896930735190569, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1同济大学建筑与城市规划学院,上海200092)])]), Author(id=1276896932219974199, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1276896932329026105, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, authorId=1276896932219974199, language=EN, stringName=Jiaxiang ZHENG, firstName=Jiaxiang, middleName=null, lastName=ZHENG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1College of Architecture and Urban Planning, Tongji University, Shanghai200092, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1276896932643598906, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, authorId=1276896932219974199, language=CN, stringName=郑家祥, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1同济大学建筑与城市规划学院,上海200092, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1276896930735190569, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, xref=1, ext=[AuthorCompanyExt(id=1276896930743579178, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, companyId=1276896930735190569, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1College of Architecture and Urban Planning, Tongji University, Shanghai200092, China), AuthorCompanyExt(id=1276896930751967787, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, companyId=1276896930735190569, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1同济大学建筑与城市规划学院,上海200092)])]), Author(id=1276896932740067900, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, 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=1276896933079806526, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, authorId=1276896932740067900, language=EN, stringName=Keyang HU, firstName=Keyang, middleName=null, lastName=HU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2International School of Engineering, Tianjin Chengjian University, Tianjin300384, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1276896934610727487, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, authorId=1276896932740067900, language=CN, stringName=胡柯杨, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2天津城建大学国际工程学院,天津300384, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1276896930961682988, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, xref=2, ext=[AuthorCompanyExt(id=1276896930974265901, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, companyId=1276896930961682988, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2International School of Engineering, Tianjin Chengjian University, Tianjin300384, China), AuthorCompanyExt(id=1276896930982654510, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, companyId=1276896930961682988, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2天津城建大学国际工程学院,天津300384)])]), Author(id=1276896934690419265, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=tongjimail@126.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1276896934782693955, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, authorId=1276896934690419265, language=EN, stringName=Jiayan FU, firstName=Jiayan, middleName=null, lastName=FU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1College of Architecture and Urban Planning, Tongji University, Shanghai200092, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1276896934879162948, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, authorId=1276896934690419265, language=CN, stringName=傅嘉言, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1同济大学建筑与城市规划学院,上海200092, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1276896930735190569, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, xref=1, ext=[AuthorCompanyExt(id=1276896930743579178, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, companyId=1276896930735190569, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1College of Architecture and Urban Planning, Tongji University, Shanghai200092, China), AuthorCompanyExt(id=1276896930751967787, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, companyId=1276896930735190569, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1同济大学建筑与城市规划学院,上海200092)])]), Author(id=1276896935256650310, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, orderNo=4, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=fujiayan@tongji.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1276896935625749064, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, authorId=1276896935256650310, language=EN, stringName=Xianglei HU, firstName=Xianglei, middleName=null, lastName=HU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1College of Architecture and Urban Planning, Tongji University, Shanghai200092, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1276896935722218057, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, authorId=1276896935256650310, language=CN, stringName=胡向磊, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1同济大学建筑与城市规划学院,上海200092, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1276896930735190569, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, xref=1, ext=[AuthorCompanyExt(id=1276896930743579178, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, companyId=1276896930735190569, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1College of Architecture and Urban Planning, Tongji University, Shanghai200092, China), AuthorCompanyExt(id=1276896930751967787, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, companyId=1276896930735190569, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1同济大学建筑与城市规划学院,上海200092)])])], keywords=[Keyword(id=1276896936422666826, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, language=EN, orderNo=1, keyword=bamboo-woven mud wall), Keyword(id=1276896936519135819, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, language=EN, orderNo=2, keyword=machine learning), Keyword(id=1276896936875651660, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, language=EN, orderNo=3, keyword=hygrothermal properties), Keyword(id=1276896936976314957, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, language=EN, orderNo=4, keyword=generative adversarial networks), Keyword(id=1276896937248944718, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, language=EN, orderNo=5, keyword=genetic algorithm), Keyword(id=1276896937701929551, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, language=CN, orderNo=1, keyword=竹编泥墙), Keyword(id=1276896938633065040, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, language=CN, orderNo=2, keyword=机器学习), Keyword(id=1276896938721145425, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, language=CN, orderNo=3, keyword=热湿性能), Keyword(id=1276896938956026450, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, language=CN, orderNo=4, keyword=生成对抗网络), Keyword(id=1276896939044106835, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, language=CN, orderNo=5, keyword=遗传算法)], refs=[Reference(id=1276896942806397553, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, doi=null, pmid=null, pmcid=null, year=2016, volume=4, issue=5, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=AGRAWAL A, CHOUDHARY A, journalName=APL Materials, refType=null, unstructuredReference=AGRAWAL ACHOUDHARY A. Perspective: materials informatics and big data: realization of the “fourth paradigm” of science in materials science[J]. APL Materials20164(5): 053208., articleTitle=Perspective: materials informatics and big data: realization of the “fourth paradigm” of science in materials science, refAbstract=null), Reference(id=1276896942873506418, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, doi=null, pmid=null, pmcid=null, year=2019, volume=179, issue=null, pageStart=201, pageEnd=214, url=null, language=null, rfNumber=[2], rfOrder=1, authorNames=SHEN C, WANG C, WEI X, journalName=Acta Materialia, refType=null, unstructuredReference=SHEN CWANG CWEI Xet al. Physical metallurgy-guided machine learning and artificial intelligent design of ultrahigh-strength stainless steel[J]. Acta Materialia2019179: 201-214., articleTitle=Physical metallurgy-guided machine learning and artificial intelligent design of ultrahigh-strength stainless steel, refAbstract=null), Reference(id=1276896942944809587, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, doi=null, pmid=null, pmcid=null, year=2020, volume=2, issue=null, pageStart=3115, pageEnd=3130, url=null, language=null, rfNumber=[3], rfOrder=2, authorNames=CAI J Z, CHU X, XU K, journalName=Nanoscale Advances, refType=null, unstructuredReference=CAI J ZCHU XXU Ket al. Machine learning-driven new material discovery[J]. Nanoscale Advances20202:3115-3130., articleTitle=Machine learning-driven new material discovery, refAbstract=null), Reference(id=1276896943028695668, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, doi=null, pmid=null, pmcid=null, year=2022, volume=4, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[4], rfOrder=3, authorNames=CHAN C H, SUN M, HUANG B, journalName=EcoMat, refType=null, unstructuredReference=CHAN C HSUN MHUANG B. Application of machine learning for advanced material prediction and design[J]. EcoMat20224:e12194., articleTitle=Application of machine learning for advanced material prediction and design, refAbstract=null), Reference(id=1276896943104193141, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, doi=null, pmid=null, pmcid=null, year=2022, volume=222, issue=null, pageStart=117431, pageEnd=null, url=null, language=null, rfNumber=[5], rfOrder=4, authorNames=YANG C, REN C, JIA Y F, journalName=Acta Materialia, refType=null, unstructuredReference=YANG CREN CJIA Y Fet al. A machine learning-based alloy design system to facilitate the rational design of high entropy alloys with enhanced hardness[J]. Acta Materialia. 2022222:117431., articleTitle=A machine learning-based alloy design system to facilitate the rational design of high entropy alloys with enhanced hardness, refAbstract=null), Reference(id=1276896943154524790, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, doi=null, pmid=null, pmcid=null, year=2021, volume=7, issue=null, pageStart=23, pageEnd=null, url=null, language=null, rfNumber=[6], rfOrder=5, authorNames=TAO Q L, XU P C, LI M J, journalName=NPJ Computational Materials, refType=null, unstructuredReference=TAO Q LXU P CLI M Jet al. Machine learning for perovskite materials design and discovery[J]. NPJ Computational Materials20217:23., articleTitle=Machine learning for perovskite materials design and discovery, refAbstract=null), Reference(id=1276896943225827959, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, doi=null, pmid=null, pmcid=null, year=2022, volume=921, issue=null, pageStart=165984, pageEnd=null, url=null, language=null, rfNumber=[7], rfOrder=6, authorNames=LIU X J, XU P C, ZHAO J J, journalName=Journal of Alloys and Compounds, refType=null, unstructuredReference=LIU X JXU P CZHAO J Jet al. Material machine learning for alloys: applications, challenges and perspectives[J]. Journal of Alloys and Compounds2022921:165984., articleTitle=Material machine learning for alloys: applications, challenges and perspectives, refAbstract=null), Reference(id=1276896943326491256, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, doi=null, pmid=null, pmcid=null, year=2022, volume=5, issue=null, pageStart=2100565, pageEnd=null, url=null, language=null, rfNumber=[8], rfOrder=7, authorNames=XU P C, CHEN H M, LI M J, journalName=Advanced Theory and Simulations, refType=null, unstructuredReference=XU P CCHEN H MLI M Jet al. New opportunity: machine learning for polymer materials design and discovery[J]. Advanced Theory and Simulations20225:2100565., articleTitle=New opportunity: machine learning for polymer materials design and discovery, refAbstract=null), Reference(id=1276896943397794425, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, doi=null, pmid=null, pmcid=null, year=2022, volume=41, issue=12, pageStart=2281, pageEnd=2289, url=null, language=null, rfNumber=[9], rfOrder=8, authorNames=康孟羽, 朱月琴, 陈晨, journalName=地质通报, refType=null, unstructuredReference=康孟羽, 朱月琴, 陈晨,. 基于多元非线性回归和BP神经网络的滑坡滑动距离预测模型研究 [J]. 地质通报202241(12): 2281-2289., articleTitle=基于多元非线性回归和BP神经网络的滑坡滑动距离预测模型研究, refAbstract=null), Reference(id=1276896943469097594, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, doi=null, pmid=null, pmcid=null, year=2025, volume=49, issue=1, pageStart=366, pageEnd=372, url=null, language=null, rfNumber=[10], rfOrder=9, authorNames=魏乐, 李承霖, 房方, journalName=电网技术, refType=null, unstructuredReference=魏乐,李承霖,房方,.小样本下基于改进麻雀算法优化卷积神经网络的飞轮储能系统损耗[J].电网技术202549(1):366-372., articleTitle=小样本下基于改进麻雀算法优化卷积神经网络的飞轮储能系统损耗, refAbstract=null), Reference(id=1276896943561372283, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, doi=null, pmid=null, pmcid=null, year=2024, volume=40, issue=2, pageStart=111, pageEnd=119, url=null, language=null, rfNumber=[11], rfOrder=10, authorNames=凌薇, 杨遵挥, 张芷薇, journalName=建筑科学, refType=null, unstructuredReference=凌薇, 杨遵挥, 张芷薇,. 基于BP神经网络和遗传算法的封闭式厨房污染物模拟与优化[J]. 建筑科学202440(2): 111-119., articleTitle=基于BP神经网络和遗传算法的封闭式厨房污染物模拟与优化, refAbstract=null), Reference(id=1276896943624286844, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, doi=null, pmid=null, pmcid=null, year=2003, volume=null, issue=7, pageStart=67, pageEnd=71, url=null, language=null, rfNumber=[12], rfOrder=11, authorNames=蔡安辉 刘永刚, 孙国雄, journalName=中国工程科学, refType=null, unstructuredReference=蔡安辉 刘永刚, 孙国雄. 基于正交试验的BP神经网络预测研究 [J]. 中国工程科学2003(7): 67-71., articleTitle=基于正交试验的BP神经网络预测研究, refAbstract=null), Reference(id=1276896943708172925, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, doi=null, pmid=null, pmcid=null, year=2024, volume=127, issue=null, pageStart=571, pageEnd=587, url=null, language=null, rfNumber=[13], rfOrder=12, authorNames=ZHOU Y, DING F, journalName=Applied Mathematical Modelling, refType=null, unstructuredReference=ZHOU YDING F. A novel recursive multivariate nonlinear time-series modeling method by using the coupling identification concept[J]. Applied Mathematical Modelling2024127: 571-587., articleTitle=A novel recursive multivariate nonlinear time-series modeling method by using the coupling identification concept, refAbstract=null), Reference(id=1276896943771087486, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, doi=null, pmid=null, pmcid=null, year=2016, volume=131, issue=null, pageStart=233, pageEnd=247, url=null, language=null, rfNumber=[14], rfOrder=13, authorNames=MELO A P, VERSAGE R S, SAWAYA G, journalName=Energy and Buildings, refType=null, unstructuredReference=MELO A PVERSAGE R SSAWAYA Get al. A novel surrogate model to support building energy labelling system: a new approach to assess cooling energy demand in commercial buildings[J]. Energy and Buildings2016131: 233-247., articleTitle=A novel surrogate model to support building energy labelling system: a new approach to assess cooling energy demand in commercial buildings, refAbstract=null), Reference(id=1276896943842390655, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, doi=null, pmid=null, pmcid=null, year=2013, volume=67, issue=2, pageStart=404, pageEnd=413, url=null, language=null, rfNumber=[15], rfOrder=14, authorNames=KELCHNER S A, GROUP B P, journalName=Molecular Phylogenetics and Evolution, refType=null, unstructuredReference=KELCHNER S AGROUP B P. Higher level phylogenetic relationships within the bamboos (Poaceae: Bambusoideae) based on five plastid markers[J]. Molecular Phylogenetics and Evolution201367(2): 404-413., articleTitle=Higher level phylogenetic relationships within the bamboos (Poaceae: Bambusoideae) based on five plastid markers, refAbstract=null), Reference(id=1276896943917888128, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, doi=null, pmid=null, pmcid=null, year=2021, volume=31, issue=null, pageStart=685, pageEnd=695, url=null, language=null, rfNumber=[16], rfOrder=15, authorNames=JANIESCH C, ZSCHECH P, HEINRICH K, journalName=Electronic Markets, refType=null, unstructuredReference=JANIESCH CZSCHECH PHEINRICH K. Machine learning and deep learning[J]. Electronic Markets202131:685-695 ., articleTitle=Machine learning and deep learning, refAbstract=null), Reference(id=1276896943993385601, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, doi=null, pmid=null, pmcid=null, year=2019, volume=188, issue=null, pageStart=2222, pageEnd=2239, url=null, language=null, rfNumber=[17], rfOrder=16, authorNames=BI Q F, GOODMAN K E, KAMINSKY J, journalName=American Journal of Epidemiology, refType=null, unstructuredReference=BI Q FGOODMAN K EKAMINSKY Jet al. What is machine learning? a primer for the epidemiologist[J]. American Journal of Epidemiology2019188:2222-2239., articleTitle=What is machine learning? a primer for the epidemiologist, refAbstract=null), Reference(id=1276896944060494466, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, doi=null, pmid=null, pmcid=null, year=2021, volume=14, issue=7, pageStart=302, pageEnd=null, url=null, language=null, rfNumber=[18], rfOrder=17, authorNames=WARIN T, STOJKOV A, journalName=Journal of Risk and Financial Management, refType=null, unstructuredReference=WARIN TSTOJKOV A. Machine learning in finance: a metadata-based systematic review of the literature[J]. Journal of Risk and Financial Management202114(7):302., articleTitle=Machine learning in finance: a metadata-based systematic review of the literature, refAbstract=null), Reference(id=1276896944131797635, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, doi=null, pmid=null, pmcid=null, year=2022, volume=61, issue=null, pageStart=101646, pageEnd=null, url=null, language=null, rfNumber=[19], rfOrder=18, authorNames=AHMED S, ALSHATER M M, AMMARI A E, journalName=Research in International Business and Finance, refType=null, unstructuredReference=AHMED SALSHATER M MAMMARI A Eet al. Artificial intelligence and machine learning in finance: a bibliometric review[J]. Research in International Business and Finance202261:101646., articleTitle=Artificial intelligence and machine learning in finance: a bibliometric review, refAbstract=null), Reference(id=1276896944190517892, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, doi=null, pmid=null, pmcid=null, year=2022, volume=9, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[20], rfOrder=19, authorNames=MUELLER B, KINOSHITA T, PEEBLES A, journalName=Acute Medicine & Surgery, refType=null, unstructuredReference=MUELLER BKINOSHITA TPEEBLES Aet al. Artificial intelligence and machine learning in emergency medicine: a narrative review[J]. Acute Medicine & Surgery20229:e740., articleTitle=Artificial intelligence and machine learning in emergency medicine: a narrative review, refAbstract=null), Reference(id=1276896944266015365, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, doi=null, pmid=null, pmcid=null, year=2022, volume=2022, issue=1, pageStart=4653923, pageEnd=null, url=null, language=null, rfNumber=[21], rfOrder=20, authorNames=SABRY F, ELTARAS T, LABDA W, journalName=Joural of Healthcare Engineering, refType=null, unstructuredReference=SABRY FELTARAS TLABDA Wet al. Machine learning for healthcare wearable devices: the big picture[J]. Joural of Healthcare Engineering20222022(1):4653923., articleTitle=Machine learning for healthcare wearable devices: the big picture, refAbstract=null), Reference(id=1276896944345707142, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, doi=null, pmid=null, pmcid=null, year=2022, volume=102, issue=null, pageStart=102401, pageEnd=null, url=null, language=null, rfNumber=[22], rfOrder=21, authorNames=OKOROAFOR E R, SMITH C M, OCHIEET K I, journalName=Geothermics, refType=null, unstructuredReference=OKOROAFOR E RSMITH C MOCHIEET K Iet al. Machine learning in subsurface geothermal energy: two decades in review[J]. Geothermics2022102:102401., articleTitle=Machine learning in subsurface geothermal energy: two decades in review, refAbstract=null), Reference(id=1276896944417010311, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, doi=null, pmid=null, pmcid=null, year=2020, volume=12, issue=null, pageStart=492, pageEnd=null, url=null, language=null, rfNumber=[23], rfOrder=22, authorNames=CIOFFI R, TRAVAGLIONI M, PISCITELLI G, journalName=Sustainability, refType=null, unstructuredReference=CIOFFI RTRAVAGLIONI MPISCITELLI Get al. Artificial Intelli gence and machine learning applications in smart production: progress, trends, and directions[J]. Sustainability202012:492., articleTitle=Artificial Intelli gence and machine learning applications in smart production: progress, trends, and directions, refAbstract=null), Reference(id=1276896944475730568, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, doi=null, pmid=null, pmcid=null, year=2022, volume=27, issue=null, pageStart=151, pageEnd=164, url=null, language=null, rfNumber=[24], rfOrder=23, authorNames=CRAMPON K, GIORKALLOS A, DELDOSSI M, journalName=Drug Discovery Today, refType=null, unstructuredReference=CRAMPON KGIORKALLOS ADELDOSSI Met al. Machine learning methods for ligand-protein molecular docking[J]. Drug Discovery Today202227:151-164., articleTitle=Machine learning methods for ligand-protein molecular docking, refAbstract=null), Reference(id=1276896944618336905, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, doi=null, pmid=null, pmcid=null, year=2022, volume=13, issue=null, pageStart=925454, pageEnd=null, url=null, language=null, rfNumber=[25], rfOrder=24, authorNames=JIANG Y R, LUO J, HUANG D, journalName=Frontiers in Microbiology, refType=null, unstructuredReference=JIANG Y RLUO JHUANG Det al. Machine learning advances in microbiology: a review of methods and applications[J]. Frontiers in Microbiology202213:925454., articleTitle=Machine learning advances in microbiology: a review of methods and applications, refAbstract=null), Reference(id=1276896944689640074, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, doi=null, pmid=null, pmcid=null, year=2022, volume=28, issue=3, pageStart=1548, pageEnd=1576, url=null, language=null, rfNumber=[26], rfOrder=25, authorNames=SHAO Q M, ZHANG Z S, journalName=Bernoulli, refType=null, unstructuredReference=SHAO Q MZHANG Z S. Berry-Esseen bounds for multivariate nonlinear statistics with applications to M-estimators and stochastic gradient descent algorithms[J]. Bernoulli202228(3): 1548-1576., articleTitle=Berry-Esseen bounds for multivariate nonlinear statistics with applications to M-estimators and stochastic gradient descent algorithms, refAbstract=null), Reference(id=1276896944769331851, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, doi=null, pmid=null, pmcid=null, year=2018, volume=48, issue=5, pageStart=1, pageEnd=8, url=null, language=null, rfNumber=[27], rfOrder=26, authorNames=李紫微, 林波荣, 陈洪钟, journalName=暖通空调, refType=null, unstructuredReference=李紫微,林波荣,陈洪钟.建筑方案能耗快速预测方法研究综述[J].暖通空调201848(5):1-8., articleTitle=建筑方案能耗快速预测方法研究综述, refAbstract=null), Reference(id=1276896944836440716, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, doi=null, pmid=null, pmcid=null, year=2018, volume=177, issue=null, pageStart=26, pageEnd=34, url=null, language=null, rfNumber=[28], rfOrder=27, authorNames=ZHANG Q, CHANG D, ZHAI X, journalName=Chemometrics and Intelligent Laboratory Systems, refType=null, unstructuredReference=ZHANG QCHANG DZHAI Xet al. OCPMDM: online computation platform for materials data mining[J]. Chemometrics and Intelligent Laboratory Systems2018177:26-34., articleTitle=OCPMDM: online computation platform for materials data mining, refAbstract=null), Reference(id=1276896944903549581, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, doi=null, pmid=null, pmcid=null, year=2021, volume=199, issue=null, pageStart=110712, pageEnd=null, url=null, language=null, rfNumber=[29], rfOrder=28, authorNames=LI L, TAO Q L, XU P C, journalName=Computational Materials Science, refType=null, unstructuredReference=LI LTAO Q LXU P Cet al.Studies on the regularity of perovskite formation via machine learning[J]. Computational Materials Science2021199:110712., articleTitle=Studies on the regularity of perovskite formation via machine learning, refAbstract=null), Reference(id=1276896944983241358, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, doi=null, pmid=null, pmcid=null, year=2021, volume=196, issue=null, pageStart=110528, pageEnd=null, url=null, language=null, rfNumber=[30], rfOrder=29, authorNames=YANG X, LI L, TAO Q L, journalName=Computational Materials Science, refType=null, unstructuredReference=YANG XLI LTAO Q Let al. Rapid discovery of narrow bandgap oxide double perovskites using machine learning[J]. Computational Materials Science2021196:110528., articleTitle=Rapid discovery of narrow bandgap oxide double perovskites using machine learning, refAbstract=null), Reference(id=1276896945054544527, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, doi=null, pmid=null, pmcid=null, year=2021, volume=125, issue=null, pageStart=21141, pageEnd=21150, url=null, language=null, rfNumber=[31], rfOrder=30, authorNames=TAO Q L, CHANG D P, LU T, journalName=The Journal of Physical Chemistry C, refType=null, unstructuredReference=TAO Q LCHANG D PLU Tet al. Multiobjective stepwise design strategy-assisted design of high-performance perovskite oxide photocatalysts[J]. The Journal of Physical Chemistry C2021125:21141-21150., articleTitle=Multiobjective stepwise design strategy-assisted design of high-performance perovskite oxide photocatalysts, refAbstract=null), Reference(id=1276896945121653392, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, doi=null, pmid=null, pmcid=null, year=2023, volume=9, issue=1, pageStart=42, pageEnd=null, url=null, language=null, rfNumber=[32], rfOrder=31, authorNames=XU P C, JI X B, LI M J, journalName=NPJ Computational Materials, refType=null, unstructuredReference=XU P CJI X BLI M Jet al. Small data machine learning in materials science[J]. NPJ Computational Materials20239(1):42., articleTitle=Small data machine learning in materials science, refAbstract=null), Reference(id=1276896945192956561, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, doi=null, pmid=null, pmcid=null, year=2023, volume=17, issue=null, pageStart=1630, pageEnd=1647, url=null, language=null, rfNumber=[33], rfOrder=32, authorNames=WANG Y X, SHI Y, ZHOU B, journalName=International Journal of Architectural Heritage, refType=null, unstructuredReference=WANG Y XSHI YZHOU B, Improvement of the Hygrothermal performance of mud-coated material used in traditional bamboo-woven mud walls[J]. International Journal of Architectural Heritage202317:1630-1647., articleTitle=Improvement of the Hygrothermal performance of mud-coated material used in traditional bamboo-woven mud walls, refAbstract=null), Reference(id=1276896945268454034, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[34], rfOrder=33, authorNames=FENG H, journalName=Madison:The University of Wisconsin-Madison Press, refType=null, unstructuredReference=FENG H. Machine learning for composite material analysis and optimization[J]. Madison:The University of Wisconsin-Madison Press2023., articleTitle=Machine learning for composite material analysis and optimization, refAbstract=null), Reference(id=1276896945348145811, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, doi=null, pmid=null, pmcid=null, year=2021, volume=57, issue=11, pageStart=1343, pageEnd=1361, url=null, language=null, rfNumber=[35], rfOrder=34, authorNames=谢建新, 宿彦京, 薛德祯, journalName=金属学报, refType=null, unstructuredReference=谢建新, 宿彦京, 薛德祯, . 机器学习在材料研发中的应用[J]. 金属学报202157(11): 1343-1361., articleTitle=机器学习在材料研发中的应用, refAbstract=null), Reference(id=1276896945415254676, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, doi=null, pmid=null, pmcid=null, year=2020, volume=53, issue=3, pageStart=1, pageEnd=34, url=null, language=null, rfNumber=[36], rfOrder=35, authorNames=WANG Y Q, YAO Q M, KWOK J T, journalName=ACM computing Surveys, refType=null, unstructuredReference=WANG Y QYAO Q MKWOK J Tet al. Generalizing from a few examples: a survey on few-shot learning[J]. ACM computing Surveys202053(3): 1-34., articleTitle=Generalizing from a few examples: a survey on few-shot learning, refAbstract=null), Reference(id=1276896945490752149, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, doi=null, pmid=null, pmcid=null, year=2023, volume=139, issue=null, pageStart=109480, pageEnd=null, url=null, language=null, rfNumber=[37], rfOrder=36, authorNames=LU J, GONG P, YE J, journalName=Pattern Recognition, refType=null, unstructuredReference=LU JGONG PYE Jet al. A survey on machine learning from few samples[J]. Pattern Recognition2023139:109480., articleTitle=A survey on machine learning from few samples, refAbstract=null), Reference(id=1276896945557861014, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, doi=null, pmid=null, pmcid=null, year=2021, volume=11, issue=22, pageStart=10823, pageEnd=null, url=null, language=null, rfNumber=[38], rfOrder=37, authorNames=LI D C, CHEN S C, LIN Y S, journalName=Applied Sciences, refType=null, unstructuredReference=LI D CCHEN S CLIN Y Set al. A generative adversarial network structure for learning with small numerical data sets[J]. Applied Sciences202111(22): 10823., articleTitle=A generative adversarial network structure for learning with small numerical data sets, refAbstract=null), Reference(id=1276896945629164183, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, doi=null, pmid=null, pmcid=null, year=2018, volume=361, issue=null, pageStart=360, pageEnd=365, url=null, language=null, rfNumber=[39], rfOrder=38, authorNames=SANCHEZ-LENGELING B, ASPURU-GUZIK A, journalName=Science, refType=null, unstructuredReference=SANCHEZ-LENGELING BASPURU-GUZIK A. Inverse molecular design using machine learn-ing: generative models for matter engineering[J]. Science2018361:360-365., articleTitle=Inverse molecular design using machine learn-ing: generative models for matter engineering, refAbstract=null), Reference(id=1276896945704661656, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, doi=null, pmid=null, pmcid=null, year=2021, volume=31, issue=36, pageStart=2102606, pageEnd=null, url=null, language=null, rfNumber=[40], rfOrder=39, authorNames=BASH D, CAI Y, CHELLAPPAN V, journalName=Advanced Functional Materials, refType=null, unstructuredReference=BASH DCAI YCHELLAPPAN Vet al.Multi‐fidelity high‐throughput optimization of electrical conductivity in P3HT‐CNT composites[J]. Advanced Functional Materials202131(36): 2102606., articleTitle=Multi‐fidelity high‐throughput optimization of electrical conductivity in P3HT‐CNT composites, refAbstract=null), Reference(id=1276896945784353433, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, doi=null, pmid=null, pmcid=null, year=1993, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[41], rfOrder=40, authorNames=中华人民共和国建设部, journalName=null, refType=null, unstructuredReference=中华人民共和国建设部.民用建筑热工设计规范:GB/T 50176—1993[S].北京:中国计划出版社,1993., articleTitle=null, refAbstract=null), Reference(id=1276896945868239514, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, doi=null, pmid=null, pmcid=null, year=2015, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[42], rfOrder=41, authorNames=中华人民共和国住房和城乡建设部, journalName=null, refType=null, unstructuredReference=中华人民共和国住房和城乡建设部.公共建筑节能设计标准:GB 50189—2015[S].北京:中国建筑工业出版社,2015., articleTitle=null, refAbstract=null), Reference(id=1276896945935348379, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, doi=null, pmid=null, pmcid=null, year=2001, volume=null, issue=5, pageStart=8, pageEnd=10, url=null, language=null, rfNumber=[43], rfOrder=42, authorNames=中国建筑科学研究院, journalName=上海建材, refType=null, unstructuredReference=中国建筑科学研究院.夏热冬冷地区居住建筑节能设计标准[J].上海建材2001(5):8-10., articleTitle=夏热冬冷地区居住建筑节能设计标准, refAbstract=null), Reference(id=1276896946010845852, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, doi=null, pmid=null, pmcid=null, year=2003, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[44], rfOrder=43, authorNames=中华人民共和国建设部, journalName=null, refType=null, unstructuredReference=中华人民共和国建设部.夏热冬暖地区居住建筑节能设计标准:JGJ 75—2003[S].北京:中国建筑工业出版社,2003., articleTitle=null, refAbstract=null)], funds=null, companyList=[AuthorCompany(id=1276896930735190569, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, xref=1, ext=[AuthorCompanyExt(id=1276896930743579178, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, companyId=1276896930735190569, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1College of Architecture and Urban Planning, Tongji University, Shanghai200092, China), AuthorCompanyExt(id=1276896930751967787, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, companyId=1276896930735190569, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1同济大学建筑与城市规划学院,上海200092)]), AuthorCompany(id=1276896930961682988, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, xref=2, ext=[AuthorCompanyExt(id=1276896930974265901, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, companyId=1276896930961682988, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2International School of Engineering, Tianjin Chengjian University, Tianjin300384, China), AuthorCompanyExt(id=1276896930982654510, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, companyId=1276896930961682988, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2天津城建大学国际工程学院,天津300384)])], figs=[ArticleFig(id=1276896939799081557, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, language=EN, label=Fig.1, caption=Typical construction of bamboo-woven mud walls, figureFileSmall=vdCR+p/jBasE++ajIc5evw==, figureFileBig=hWJ7zZ/Ar9bmp9q38AfLng==, tableContent=null), ArticleFig(id=1276896939874579030, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, language=CN, label=图1, caption=竹编泥墙典型构造, figureFileSmall=vdCR+p/jBasE++ajIc5evw==, figureFileBig=hWJ7zZ/Ar9bmp9q38AfLng==, tableContent=null), ArticleFig(id=1276896940247872087, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, language=EN, label=Fig.2, caption=Traditional bamboo-woven mud walls and wall construction in southern China, figureFileSmall=yvh7P0dVyOBMLnoHVuNh+A==, figureFileBig=d47BE2kTNT5NfcMztxKeWQ==, tableContent=null), ArticleFig(id=1276896940335952472, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, language=CN, label=图2, caption=中国南方传统竹编泥墙和墙体构造, figureFileSmall=yvh7P0dVyOBMLnoHVuNh+A==, figureFileBig=d47BE2kTNT5NfcMztxKeWQ==, tableContent=null), ArticleFig(id=1276896940390478425, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, language=EN, label=Fig.3, caption=Workflow of machine learning for materials, figureFileSmall=rTy7NTlP2isbt4hivvMqxA==, figureFileBig=pR4Npt6aa/f/GujirjH35g==, tableContent=null), ArticleFig(id=1276896940667302490, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, language=CN, label=图3, caption=材料机器学习的工作流程32, figureFileSmall=rTy7NTlP2isbt4hivvMqxA==, figureFileBig=pR4Npt6aa/f/GujirjH35g==, tableContent=null), ArticleFig(id=1276896940734411355, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, language=EN, label=Fig.4, caption=Machine learning modeling process, figureFileSmall=zfTi5ZreLw7cPPVgiGaLNA==, figureFileBig=EDtDldZ15cgPGOuynx6PTg==, tableContent=null), ArticleFig(id=1276896940809908828, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, language=CN, label=图4, caption=机器学习建模流程, figureFileSmall=zfTi5ZreLw7cPPVgiGaLNA==, figureFileBig=EDtDldZ15cgPGOuynx6PTg==, tableContent=null), ArticleFig(id=1276896941048984157, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, language=EN, label=Fig.5, caption=Test analysis workflow and sample preparation process, figureFileSmall=fPofS/tfMkxTEylOhez62g==, figureFileBig=xt2apZuGHe6LZexsds9UcA==, tableContent=null), ArticleFig(id=1276896941120287326, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, language=CN, label=图5, caption=测试分析流程和样品制作过程, figureFileSmall=fPofS/tfMkxTEylOhez62g==, figureFileBig=xt2apZuGHe6LZexsds9UcA==, tableContent=null), ArticleFig(id=1276896941195784799, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, language=EN, label=Fig. 6, caption=Normalized hygrothermal properties of the materials, figureFileSmall=gklXhlQMZpzXZCRLvn+Dxw==, figureFileBig=IZ224l84ybjl3crbKzFQWA==, tableContent=null), ArticleFig(id=1276896941451637344, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, language=CN, label=图6, caption=归一化后的材料热性能和湿性能, figureFileSmall=gklXhlQMZpzXZCRLvn+Dxw==, figureFileBig=IZ224l84ybjl3crbKzFQWA==, tableContent=null), ArticleFig(id=1276896941518746209, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, language=EN, label=Fig. 7, caption=Fitting of the original sample data, figureFileSmall=zNU0oZPvwUZxHNx+slO7Og==, figureFileBig=hGh92TajRVzdiyKrrVJ7eg==, tableContent=null), ArticleFig(id=1276896941594243682, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, language=CN, label=图7, caption=原始样本数据拟合 (a) 训练集 (b) 测试集

注:散点表示模型预测值与实测目标值之间的对应关系;实线表示回归拟合线;虚线Y=T表示预测值Y与实测目标值T完全相等时的理想参考线。

, figureFileSmall=zNU0oZPvwUZxHNx+slO7Og==, figureFileBig=hGh92TajRVzdiyKrrVJ7eg==, tableContent=null), ArticleFig(id=1276896941665546851, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, language=EN, label=Fig. 8, caption=Comparison of original sample data and data generated by GANs, figureFileSmall=TFvNccKZX4Oo5DCeMnDyqQ==, figureFileBig=9A5QGHfAaR1IVeitLlseHw==, tableContent=null), ArticleFig(id=1276896941749432932, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, language=CN, label=图8, caption=原始样本数据与 GANs 生成数据对比, figureFileSmall=TFvNccKZX4Oo5DCeMnDyqQ==, figureFileBig=9A5QGHfAaR1IVeitLlseHw==, tableContent=null), ArticleFig(id=1276896941896233573, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, language=EN, label=Fig. 9, caption=Training process of the predictive model, figureFileSmall=JfHvgHQ2XDSXttDJW+n5zQ==, figureFileBig=B/szd2fXOSoVtSEKq9WMaw==, tableContent=null), ArticleFig(id=1276896941971731046, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, language=CN, label=图9, caption=预测模型的训练过程, figureFileSmall=JfHvgHQ2XDSXttDJW+n5zQ==, figureFileBig=B/szd2fXOSoVtSEKq9WMaw==, tableContent=null), ArticleFig(id=1276896942043034215, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, language=EN, label=Fig. 10, caption=Comparison of results before and after BP neural network prediction, figureFileSmall=Xdg2YeT10L/NvCV54CI9uQ==, figureFileBig=4DWGP14tdNC5Niz+vVvnNQ==, tableContent=null), ArticleFig(id=1276896942114337384, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, language=CN, label=图10, caption=BP 神经网络预测前后的对比

注:图中散点、实线和虚线Y=T的含义同图7。

, figureFileSmall=Xdg2YeT10L/NvCV54CI9uQ==, figureFileBig=4DWGP14tdNC5Niz+vVvnNQ==, tableContent=null), ArticleFig(id=1276896942194029161, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, language=EN, label=Fig.11, caption=Comparison of results before and after prediction by the GA-BP neural network, figureFileSmall=GVhjsXCIrS7TPju/gHgJjw==, figureFileBig=p3sKP9W2Z6SbgMn+Y3ms5w==, tableContent=null), ArticleFig(id=1276896942269526634, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, language=CN, label=图11, caption=GA-BP 神经网络预测前后的对比

注:图中散点、实线和虚线Y=T的含义同图7。

, figureFileSmall=GVhjsXCIrS7TPju/gHgJjw==, figureFileBig=p3sKP9W2Z6SbgMn+Y3ms5w==, tableContent=null), ArticleFig(id=1276896942349218411, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, language=EN, label=Fig.12, caption=Hygrothermal properties of the test set materials, figureFileSmall=0IV3ZwUWh0S1GTJZ6PFH7w==, figureFileBig=WJ0ehvPcjdzs49ZmRUPFdA==, tableContent=null), ArticleFig(id=1276896942420521580, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, language=CN, label=图12, caption=测试集材料热性能和湿性能, figureFileSmall=0IV3ZwUWh0S1GTJZ6PFH7w==, figureFileBig=WJ0ehvPcjdzs49ZmRUPFdA==, tableContent=null), ArticleFig(id=1276896942487630445, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, language=EN, label=Table 1, caption=

Equipment and models

, figureFileSmall=null, figureFileBig=null, tableContent=
名称型号
粉碎机END-200
数字显示土壤液塑限测试仪LP-100D
导热仪Hot Disk TPS 2500S
电加热恒温鼓风干燥箱DHG-9070A
加热培养箱DNP-9272A
砂浆固化箱SJ-40A
扫描电子显微镜Hitachi S4800
), ArticleFig(id=1276896942554739310, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, language=CN, label=表1, caption=

设备及型号

, figureFileSmall=null, figureFileBig=null, tableContent=
名称型号
粉碎机END-200
数字显示土壤液塑限测试仪LP-100D
导热仪Hot Disk TPS 2500S
电加热恒温鼓风干燥箱DHG-9070A
加热培养箱DNP-9272A
砂浆固化箱SJ-40A
扫描电子显微镜Hitachi S4800
), ArticleFig(id=1276896942634431087, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, language=EN, label=Table 2, caption=

Evaluation metrics for GANs algorithms

, figureFileSmall=null, figureFileBig=null, tableContent=
指标评估白水泥

中等砾石

硅藻土稻壳粉热性能Y1湿性能Y2
统计数据(D 值)0.4600.4200.4600.3200.2550.2125
P0.0520.0680.0520.1300.3500.5700
), ArticleFig(id=1276896942709928560, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, language=CN, label=表2, caption=

GANs 算法评估指标

, figureFileSmall=null, figureFileBig=null, tableContent=
指标评估白水泥

中等砾石

硅藻土稻壳粉热性能Y1湿性能Y2
统计数据(D 值)0.4600.4200.4600.3200.2550.2125
P0.0520.0680.0520.1300.3500.5700
)], attaches=null, journal=Journal(id=1276576551509397524, delFlag=0, nameCn=工业建筑, nameEn=Industrial Construction, nameHistory1=null, nameHistory2=null, issn=1000-8993, eissn=null, cn=11-2068/TU, coden=null, periodic=0, language=CN, oaType=null, 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=KHR9x8UxgSX2gqrJN8gfTg==, journalPrice=null, startedYear=null, abbrevIsoEn=Industrial Construction, journalRemark=null, publicationField=null, createdTime=1782289167526, updatedTime=1784021757656, createdBy=18614031015, updatedBy=13041195026, firstLetterCn=G, firstLetterEn=G, subjectCode=Engineering, subjectName=null, subjectCodeEn=Engineering, subjectNameEn=null, picCn=KHR9x8UxgSX2gqrJN8gfTg==, picEn=glrMkaIg87Oz10PZrZOnSg==, jcr=null, cjcr=null, exts=[JournalExt(id=1283843561321894544, language=CN, name=工业建筑, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1784021757679, updatedTime=1784021757679, createdBy=13041195026, updatedBy=13041195026, submissionGuidelinesUrl=, submissionAuthorUrl=https://www.scicloudcenter.com/IC, submissionEditorUrl=https://www.scicloudcenter.com/IC, submissionReviewUrl=https://www.scicloudcenter.com/IC, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1283843561376420497, language=EN, name=Industrial Construction, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1784021757692, updatedTime=1784021757692, createdBy=13041195026, updatedBy=13041195026, submissionGuidelinesUrl=, submissionAuthorUrl=https://www.scicloudcenter.com/IC, submissionEditorUrl=https://www.scicloudcenter.com/IC, submissionReviewUrl=https://www.scicloudcenter.com/IC, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1276577754012160025, websiteList=[Website(id=1276578024992669908, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1276577754012160025, 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/gyjz/CN, language=CN, createTime=1782289518831, createBy=18614031015, updateTime=1782290419260, updateBy=18614031015, name=工业建筑-中文, tplId=1146099689490845704, title=工业建筑, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1276581942745231958, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1276578024992669908, code=articleTextType, value=kx, createTime=1782290452896, updateTime=1782290452896, creator=18614031015, updator=18614031015), WebsiteProps(id=1276581942715871827, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1276578024992669908, code=banner, value=null, createTime=1782290452889, updateTime=1782290452889, creator=18614031015, updator=18614031015), WebsiteProps(id=1276581942778786393, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1276578024992669908, code=grayFlag, value=0, createTime=1782290452904, updateTime=1782290452904, creator=18614031015, updator=18614031015), WebsiteProps(id=1276581942703288914, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1276578024992669908, code=logo, value=https://castjournals.cast.org.cn/joweb/gyjz/CN/file/pic?fileId=ObTw7qIsmguDunMFeBGvBA==, createTime=1782290452886, updateTime=1782290452886, creator=18614031015, updator=18614031015), WebsiteProps(id=1276581942795563611, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1276578024992669908, code=minRunFlag, value=0, createTime=1782290452908, updateTime=1782290452908, creator=18614031015, updator=18614031015), WebsiteProps(id=1276581942736843349, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1276578024992669908, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/gyjz/CN/file/pic, createTime=1782290452894, updateTime=1782290452894, creator=18614031015, updator=18614031015), WebsiteProps(id=1276581942787175002, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1276578024992669908, code=silenceFlag, value=0, createTime=1782290452906, updateTime=1782290452906, creator=18614031015, updator=18614031015), WebsiteProps(id=1276581942724260436, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1276578024992669908, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1782290452891, updateTime=1782290452891, creator=18614031015, updator=18614031015), WebsiteProps(id=1276581942757814871, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1276578024992669908, code=themeColor, value=null, createTime=1782290452899, updateTime=1782290452899, creator=18614031015, updator=18614031015), WebsiteProps(id=1276581942766203480, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1276578024992669908, code=themeStyle, value=null, createTime=1782290452901, updateTime=1782290452901, creator=18614031015, updator=18614031015)]), Website(id=1276578025097527513, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1276577754012160025, 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/gyjz/EN, language=EN, createTime=1782289518856, createBy=18614031015, updateTime=1782290415485, updateBy=18614031015, name=工业建筑-英文, tplId=1146101810881728533, title=Industrial Construction, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1276581912684655179, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1276578025097527513, code=articleTextType, value=kx, createTime=1782290445729, updateTime=1782290445729, creator=18614031015, updator=18614031015), WebsiteProps(id=1276581912659489352, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1276578025097527513, code=banner, value=null, createTime=1782290445723, updateTime=1782290445723, creator=18614031015, updator=18614031015), WebsiteProps(id=1276581912722403918, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1276578025097527513, code=grayFlag, value=0, createTime=1782290445738, updateTime=1782290445738, creator=18614031015, updator=18614031015), WebsiteProps(id=1276581912634323527, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1276578025097527513, code=logo, value=https://castjournals.cast.org.cn/joweb/gyjz/EN/file/pic?fileId=ObTw7qIsmguDunMFeBGvBA==, createTime=1782290445717, updateTime=1782290445717, creator=18614031015, updator=18614031015), WebsiteProps(id=1276581912739181136, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1276578025097527513, code=minRunFlag, value=0, createTime=1782290445742, updateTime=1782290445742, creator=18614031015, updator=18614031015), WebsiteProps(id=1276581912676266570, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1276578025097527513, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/gyjz/EN/file/pic, createTime=1782290445727, updateTime=1782290445727, creator=18614031015, updator=18614031015), WebsiteProps(id=1276581912730792527, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1276578025097527513, code=silenceFlag, value=0, createTime=1782290445740, updateTime=1782290445740, creator=18614031015, updator=18614031015), WebsiteProps(id=1276581912667877961, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1276578025097527513, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_en_623/, createTime=1782290445725, updateTime=1782290445725, creator=18614031015, updator=18614031015), WebsiteProps(id=1276581912693043788, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1276578025097527513, code=themeColor, value=null, createTime=1782290445731, updateTime=1782290445731, creator=18614031015, updator=18614031015), WebsiteProps(id=1276581912709821005, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1276578025097527513, code=themeStyle, value=null, createTime=1782290445735, updateTime=1782290445735, creator=18614031015, updator=18614031015)])], journalTitle=工业建筑, weixinUrl=null, journalUrl=http://gyjz.ic-mag.com/, iacademicId=null, status=1, seqNo=null, journalTitleEn=Industrial Construction, journalPhotoCn=KHR9x8UxgSX2gqrJN8gfTg==, journalPhotoEn=glrMkaIg87Oz10PZrZOnSg==, journalFirstLetter=G, journalRecommend=null, journalNew=null, journalCollection=null, jcrJf=null, cjcrJf=null, jcrJfStr=null, cjcrJfStr=null, submissionFirstDecision=null, sciSubjectClassification=null, casSubjectClassification=null, citeScore=null, totalCitationFrequency=null, icpCode=null, psCode=null, advertisingLicenseCode=null, copyrightInformation=null, country=null, option=, provinceCode=null, provinceName=null, collectFlag=false, interPubPlatform=, interPubPlatformUrl=null), detailUrlCn=https://castjournals.cast.org.cn/joweb/gyjz/CN/10.3724/j.gyjzG25111704, detailUrlEn=https://castjournals.cast.org.cn/joweb/gyjz/EN/10.3724/j.gyjzG25111704, pdfUrlCn=https://castjournals.cast.org.cn/joweb/gyjz/CN/PDF/10.3724/j.gyjzG25111704, pdfUrlEn=https://castjournals.cast.org.cn/joweb/gyjz/EN/PDF/10.3724/j.gyjzG25111704, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, previewStatus=0, delFlag=0, hasFullText=1, orderTime=1779206400000, fullTextJson=null, articleText=null, reference=null)
收藏切换
面向传统建筑墙体材料性能的机器学习预测优化方法研究——以竹编泥墙为例
收藏切换
PDF下载
王乙茜 1 , 郑家祥 1 , 胡柯杨 2 , 傅嘉言 1 , 胡向磊 1
工业建筑 | 工程诊断与性能提升技术 2026,56(5): 167-175
收起
收藏切换
工业建筑 |工程诊断与性能提升技术 2026 , 56 (5) : 167 -175
面向传统建筑墙体材料性能的机器学习预测优化方法研究——以竹编泥墙为例
全屏
[Author(id=1276896931066540593, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=wyxsscici@tongji.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1276896931519525428, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, authorId=1276896931066540593, language=EN, stringName=Yixi WANG, firstName=Yixi, middleName=null, lastName=WANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1College of Architecture and Urban Planning, Tongji University, Shanghai200092, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1276896931817321013, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, authorId=1276896931066540593, language=CN, stringName=王乙茜, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1同济大学建筑与城市规划学院,上海200092, bio={"content":"

王乙茜,博士研究生,主要从事智能建造方向研究,

"}, bioImg=null, bioContent=

王乙茜,博士研究生,主要从事智能建造方向研究,

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1276896930735190569, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, xref=1, ext=[AuthorCompanyExt(id=1276896930743579178, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, companyId=1276896930735190569, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1College of Architecture and Urban Planning, Tongji University, Shanghai200092, China), AuthorCompanyExt(id=1276896930751967787, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, companyId=1276896930735190569, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1同济大学建筑与城市规划学院,上海200092)])]), Author(id=1276896932219974199, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1276896932329026105, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, authorId=1276896932219974199, language=EN, stringName=Jiaxiang ZHENG, firstName=Jiaxiang, middleName=null, lastName=ZHENG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1College of Architecture and Urban Planning, Tongji University, Shanghai200092, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1276896932643598906, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, authorId=1276896932219974199, language=CN, stringName=郑家祥, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1同济大学建筑与城市规划学院,上海200092, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1276896930735190569, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, xref=1, ext=[AuthorCompanyExt(id=1276896930743579178, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, companyId=1276896930735190569, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1College of Architecture and Urban Planning, Tongji University, Shanghai200092, China), AuthorCompanyExt(id=1276896930751967787, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, companyId=1276896930735190569, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1同济大学建筑与城市规划学院,上海200092)])]), Author(id=1276896932740067900, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, 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=1276896933079806526, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, authorId=1276896932740067900, language=EN, stringName=Keyang HU, firstName=Keyang, middleName=null, lastName=HU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2International School of Engineering, Tianjin Chengjian University, Tianjin300384, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1276896934610727487, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, authorId=1276896932740067900, language=CN, stringName=胡柯杨, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2天津城建大学国际工程学院,天津300384, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1276896930961682988, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, xref=2, ext=[AuthorCompanyExt(id=1276896930974265901, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, companyId=1276896930961682988, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2International School of Engineering, Tianjin Chengjian University, Tianjin300384, China), AuthorCompanyExt(id=1276896930982654510, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, companyId=1276896930961682988, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2天津城建大学国际工程学院,天津300384)])]), Author(id=1276896934690419265, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=tongjimail@126.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1276896934782693955, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, authorId=1276896934690419265, language=EN, stringName=Jiayan FU, firstName=Jiayan, middleName=null, lastName=FU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1College of Architecture and Urban Planning, Tongji University, Shanghai200092, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1276896934879162948, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, authorId=1276896934690419265, language=CN, stringName=傅嘉言, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1同济大学建筑与城市规划学院,上海200092, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1276896930735190569, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, xref=1, ext=[AuthorCompanyExt(id=1276896930743579178, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, companyId=1276896930735190569, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1College of Architecture and Urban Planning, Tongji University, Shanghai200092, China), AuthorCompanyExt(id=1276896930751967787, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, companyId=1276896930735190569, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1同济大学建筑与城市规划学院,上海200092)])]), Author(id=1276896935256650310, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, orderNo=4, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=fujiayan@tongji.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1276896935625749064, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, authorId=1276896935256650310, language=EN, stringName=Xianglei HU, firstName=Xianglei, middleName=null, lastName=HU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1College of Architecture and Urban Planning, Tongji University, Shanghai200092, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1276896935722218057, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, authorId=1276896935256650310, language=CN, stringName=胡向磊, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1同济大学建筑与城市规划学院,上海200092, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1276896930735190569, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, xref=1, ext=[AuthorCompanyExt(id=1276896930743579178, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, companyId=1276896930735190569, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1College of Architecture and Urban Planning, Tongji University, Shanghai200092, China), AuthorCompanyExt(id=1276896930751967787, tenantId=1146029695717560320, journalId=1276577754012160025, articleId=1276896925886575114, companyId=1276896930735190569, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1同济大学建筑与城市规划学院,上海200092)])])]
王乙茜1 , 郑家祥1, 胡柯杨2, 傅嘉言1 , 胡向磊1
作者信息
  • 1同济大学建筑与城市规划学院,上海200092
  • 2天津城建大学国际工程学院,天津300384
通讯作者:
胡向磊,副教授,主要从事建筑工业化方向研究,
傅嘉言,博士后,主要从事智能建造方向研究,
Research on Machine Learning-Based Prediction and Optimization Methods for the Performance of Traditional Building Wall Materials: a Case Study of Bamboo-Woven Mud Walls
Yixi WANG1 , Jiaxiang ZHENG1, Keyang HU2, Jiayan FU1 , Xianglei HU1
Affiliations
  • 1College of Architecture and Urban Planning, Tongji University, Shanghai200092, China
  • 2International School of Engineering, Tianjin Chengjian University, Tianjin300384, China
出版时间: 2026-05-20 doi: 10.3724/j.gyjzG25111704
文章导航
收藏切换

聚焦机器学习方法,对竹编泥墙的热湿性能进行预测与优化,挖掘竹编泥墙应对环境挑战的潜力。首先借助生成对抗网络(GANs)扩充试验数据,有效克服小样本数据集的局限;再利用反向传播(BP)神经网络对墙体性能开展预测分析。为提升预测性能,通过遗传算法(GA)对BP神经网络进行优化后,大幅提高预测精度,模型预测系数R²为0.77121,充分显示GA优化BP神经网络模型的预测性能优于原始模型。研究结果验证了机器学习在传统建筑材料再利用领域的可行性,为竹编泥墙的保护更新提供了数字化理论依据与技术支撑。

竹编泥墙  /  机器学习  /  热湿性能  /  生成对抗网络  /  遗传算法

This study applied machine learning to predict and optimize the hygrothermal performance of bamboo-woven mud walls, highlighting their potential in addressing environmental challenges. Generative adversarial networks (GANs) were first used to augment limited experimental data, addressing small-sample constraints. A back propagation (BP) neural network was employed to analyze and predict the performance of the wall materials. After optimization via a genetic algorithm (GA), the model’s R² improved to 0.77, indicating significantly enhanced predictive performance. These findings confirm the feasibility of using machine learning in the reuse of traditional building materials and provide a digital theoretical basis and technical support for the preservation and renewal of bamboo-woven mud walls.

bamboo-woven mud wall  /  machine learning  /  hygrothermal properties  /  generative adversarial networks  /  genetic algorithm
王乙茜, 郑家祥, 胡柯杨, 傅嘉言, 胡向磊. 面向传统建筑墙体材料性能的机器学习预测优化方法研究——以竹编泥墙为例. 工业建筑, 2026 , 56 (5) : 167 -175 . DOI: 10.3724/j.gyjzG25111704
Yixi WANG, Jiaxiang ZHENG, Keyang HU, Jiayan FU, Xianglei HU. Research on Machine Learning-Based Prediction and Optimization Methods for the Performance of Traditional Building Wall Materials: a Case Study of Bamboo-Woven Mud Walls[J]. Industrial Construction, 2026 , 56 (5) : 167 -175 . DOI: 10.3724/j.gyjzG25111704
在材料科学领域,试验测试与数值模拟是表征和分析材料性能的主要手段1,材料的结构、密度等特性直接影响其应用潜力。随着试验技术与模拟方法的不断发展,数据驱动的研究范式为材料性能预测和新材料设计提供了全新路径。相较于传统的试验试错方法,基于机器学习的预测模型因其效率高、适应性强,正日益受到学术界关注。然而,获取材料科学领域数据通常面临成本高昂、周期长的挑战,导致现有数据库规模受限2。尤其是在小样本数据条件下,传统机器学习模型面临精度不足、泛化能力弱等问题,因此,开发适用于小数据集背景下的高效预测方法成为当前研究的重要方向。
自2011年材料基因组计划(Materials Genome Initiative, MGI)提出以来,材料科学领域在试验设备、计算工具与数据资源方面取得显著进展,显著缩短了新材料的研发周期。在MGI的推动下,机器学习逐步成为材料性能预测与设计中的关键技术手段3-4。该方法通过构建高效预测模型,即使在缺乏对物理机制深入理解的情况下,也能快速识别材料性能,显著提升研发效率5-8
在全球化浪潮的推动下,对建筑本体的回归以及对传统文化与地方特性的关注愈发重要。传统建筑材料作为承载地域建造技艺的载体,在低碳建造与环境被动调控方面具有潜在优势。但在当代技术体系中,传统建筑材料往往被简化为单一围护构件,其综合价值被系统削弱。从材料本体出发,结合现代技术手段提升其性能,既是对传统建筑文化的延续与重构,也是增强建筑在复杂环境下适应性的关键路径。同时,现有研究多聚焦于现代墙体材料,仍主要依赖小尺度、离散试验,受限于数据规模、试验成本及模型泛化能力,尚未充分发挥人工智能的优势,面向传统建筑材料的性能优化仍处于起步阶段,基于机器学习的综合优化策略有待进一步完善。
基于既有研究9-14,本研究选取传统竹编泥墙的涂泥材料作为研究对象,围绕其热湿性能展开预测优化分析。由于材料结构复杂,复合材料优化属于典型的多变量非线性问题,常面临收敛缓慢和易陷入局部极值的挑战。针对以上问题,本研究引入生成对抗网络(Generative Adversarial Networks, GANs)进行数据增强,有效扩充小样本数据集,提升模型的泛化能力。同时,结合遗传算法(Genetic Algorithm, GA)优化反向传播神经网络(Back Propagation Neural Network, BP),构建适用于涂泥材料热湿性能进行预测优化的模型,以期为竹编泥墙在现代绿色建筑中的应用提供科学支撑,为推动乡村建筑材料的智能化、可持续发展奠定理论基础。
竹编泥墙是最古老的传统墙体形式之一,广泛分布于南美、南非、东南亚等地区15。在中国,主要集中于长江流域的夏热冬冷和夏热冬暖气候区,常见于传统乡村聚落中的低层住宅及公共建筑。由图12可知,竹编泥墙构造由内向外依次为骨架层、芯层、表层,分别对应竹编层、复合涂泥层、石灰抹面层,形成独特的复合围护构造。该构造凭借高孔隙率实现了对室内热湿环境的被动调节,因而被誉为“可呼吸墙”。近年来,全球极端气候频发,我国极端气候天数也屡创新高,传统竹编泥墙亦面临保温隔热性能受限的挑战。现有研究主要依赖传统试验方法,受限于数据规模不足与试错成本高等问题,难以支撑高效、实时的性能预测。为此,本研究通过改进与优化机器学习算法框架,提升模型在材料性能预测中的精度与效率,为低碳建筑提供可行的智能化技术路径。
作为涵盖计算机科学、数学、统计学与工程学等领域的交叉学科,机器学习致力于通过数据或既有经验不断优化计算模型的性能,也是当前人工智能领域的重要发展方向之一16-17。近年来,机器学习在金融、医疗、工业、生物等诸多领域得到广泛应用,展现出显著的技术优势18-25。机器学习辅助材料设计最直接的目标之一,即运用算法和材料数据构建预测材料性能的模型。材料性能优化本质上属于多变量非线性问题,当前多种智能优化算法可通过调节模型内部节点的连接,实现有效信息处理。既有研究表明,人工智能算法在解决多变量非线性问题求解中具有突出优势。康孟羽等23运用多变量非线性回归与BP神经网络分析滑坡位移,结果表明BP神经网络具有更高的预测精度;Zhou等13提出的三阶段耦合均值扩展递归算法,有效处理了多变量非线性时间序列问题。相关研究亦在建筑能耗预测领域得到了广泛应用与对比分析1126-27,并逐渐拓展至材料数据挖掘、性能预测与优化设计等研究场景28-31。如图3所示,材料机器学习的一般流程包括数据采集、特征工程、模型选择与评估,以及模型应用32。基于该流程,本研究构建墙体材料的机器学习模型,对其热湿性能进行预测分析。图4展示了本研究采用的建模步骤与技术路线。
根据既有研究33的试验流程及样本数据制作流程(图5),采用4种材料作为改性剂(其中A为白水泥,B为中等砾石,C为硅藻土,D为稻壳粉),以不同比率对墙体材料进行正交试验,并采用仪器设备(表1)进行测试分析。正交试验采用L16(4⁴)设计,以4种改性剂的质量分数为控制因素,掺量范围分别为0~31.25%(A)、0~12.50%(B)、0~12.50%(C)和0~20.83%(D),生土与稻壳按35∶3质量比预混。样本均按统一流程制备,即干料充分混合后加入适量水搅拌至均匀黏结状态,装入30 mm×30 mm×30 mm钢模,在规定加载速率下压实成型并标准养护后进行测试33。结果显示,在热性能(导热性能)方面,竹编泥墙样品材料的导热系数为0.4~0.6 W/(m·K),导热系数显著低于混凝土和多孔砖等现代建筑材料,说明涂泥材料具有良好的隔热性能33。在湿性能(等温平衡吸放湿性能)方面,竹编泥墙样品材料的等温平衡吸放湿过程具有显著的动态调节特性。随着环境相对湿度的升高,材料因内外水压差较大而持续吸收环境中的水分33。当材料在相对湿度97.30%的环境中达到吸湿平衡后,材料进入等温解吸阶段,这一过程反映出竹编泥墙材料具有良好的湿度调节能力。通过极差分析与相关性分析,发现竹编泥墙材料的热性能与湿性能相互独立,二者关系复杂且无序33。为进一步量化分析,本研究将热性能设为Y1,湿性能设为Y2(在相对湿度57.57%条件下平衡吸、放湿的平均值),其中Y1Y2直接相关,且彼此的影响不存在优先性。综上所述,竹编泥墙在热湿调节方面具有良好基础性能,但仍需通过材料改性与优化进一步提升其热湿性能,尤其是增强湿度传输与热导率性能之间的协调性。此外,由于试验数据获取复杂且成本较高,试验周期较长,亟需建立机器学习模型对材料性能进行预测与优化,以提前发现潜在问题,减少不必要的重复试验,从而提高研发效率,节约资源。
特征工程是机器学习中不可或缺的一个环节,其主要任务是从原始特征中提取对模型训练与预测最具代表性的信息子集。通过对数据进行处理、转换与筛选,特征工程不仅有助于提升模型性能,还可降低计算复杂度,增强模型的泛化能力,并提高数据的可解释性。本研究采用了特征工程中的数据预处理技术,将4种改性剂的质量分数作为输入特征,将材料的热性能和湿性能作为输出变量,以构建完整的特征空间,为后续的预测建模与优化分析奠定基础。其中,输入向量X=(mAmBmCmD),mA~mD分别表示白水泥(A)、中等砾石(B)、硅藻土(C)和稻壳粉(D)对基体的质量分数,其取值按正交试验在0~31.25%、0~12.50%、0~12.50%、0~20.83%的范围内分级选取;输出向量Y=(Y1Y2),其中Y1为材料导热系数,样本范围为0.4247~0.6089 W/(m·K),表征材料导热能力;Y2为等温平衡吸放湿能力,样本范围为0.3213~0.5591 g/g,表征材料的吸放湿能力。数据预处理的关键步骤包括数据清洗、归一化、特征选择等。归一化处理是为了消除不同特征之间的量纲差异,使得所有特征处于同一量级,从而确保机器学习模型能够有效地学习到数据中的规律。本研究采用标准归一化方法[式(1)],将数据特征值缩放至[0.2,0.8],以确保模型在同一标准下进行有效比较。该方法可以有效避免由于特征值范围差异过大导致的模型训练不稳定或收敛困难问题。图6展示了归一化处理后的材料性能数据分布情况。
xi'=0.6xi-xminxmax-xmin+0.2
式中:xi表示归一化前第i个样本在某一特征上的原始取值;xminxmax分别表示该特征在全部样本中的最小值和最大值;xi'表示归一化后的特征值。
数据归一化后,本研究采用BP神经网络对16组样本数据进行性能预测建模。然而测试集拟合效果较差(图7),决定系数R2值仅为0.32,远低于理想值1。这是由于数据规模较小,且特征维度过高或过低而导致数据出现不平衡问题。相关研究34-37证明,相比传统的基于试验和经验的试错法,机器学习能够迅速从数据中识别出规律和趋势,即使在缺乏物理机制明确认知的情况下,也可用于材料性能预测与设计优化。其核心在于基于有限样本数据,通过合适的算法构建具有较强泛化能力的预测模型,从而实现小样本条件下对目标性能的准确预测。Xu等32指出在样本规模较少时,理解材料成分的描述符与性能之间的关系依然至关重要。此外,Feng34的研究也验证了机器学习在复合材料分析领域的突破性价值。Li等38进一步证实,小样本数据可借助生成对抗网络(GAN)生成与真实样本特征高度相似的合成样本。GAN是一种基于对抗机制实现生成建模的深度学习框架,由生成器(G)与判别器(D)两个神经网络组成。生成器通过学习原始样本的数据分布以生成新样本;判别器则通过估算数据来源概率,判断样本是否来自真实数据集39-40。本研究采用GANs对原始小样本数据进行扩展学习与增强,设置网络训练迭代次数为500,批次大小为64,学习率为 2×10-4,并使用自适应矩估计算法器(Adaptive Moment Estimation,Adam)优化器分别对生成器与判别器进行训练。此后,将GAN生成样本添加到原始数据集中进行建模,形成66组样本量。
为验证生成数据的统计一致性,采用Kolmogorov-Smirnov(K-S)无参数检验方法对增强数据进行评估。结果显示,所有特征的K-S检验P值均大于0.05(表2),表明GAN生成数据与原始数据在统计特性上无显著差异。如图8所示,原始样本值与GANs生成值在整体变化趋势上较为接近,表明生成数据能够较好地保持原始样本数据的分布特征。该结果说明GANs生成数据具有一定统计合理性,可用于缓解小样本条件下模型训练数据不足的问题。
基于上述数据预处理,本研究将66组样本数据分为三个子集:60%作为训练样本,15%作为验证数据,25%作为测试数据用于计算。根据流程(图9),采用MATLAB神经网络工具箱进行建模,将数据依照上述比例输入网络进行训练与测试。其中,输入层包含4个神经元,对应4种改性剂的质量分数A~D,输出层包含2个神经元,对应热性能Y1和湿性能Y2。经多轮预试验对不同拓扑结构进行对比后,最终选取含量层隐藏层的4-2-3-2结构:第一、第二隐藏层分别包含2个和3个神经元,神经网络中隐藏层与输出层的传递函数采用可微分Sigmoid函数Log-sig以及线性传递函数Purelin,以适应连续物理量的回归预测需求。网络训练采用MATLAB内置的Levenberg-Marquardt反向传播(BP)算法训练函数Trainlm,设置最大训练次数为1000,学习率为0.01,目标误差为0.1×10-4。在训练阶段,训练集用于权重调整,验证集用于监控过拟合,测试集则用于最终模型评估,三者在各自阶段独立使用,互不交叉。模型训练过程中,结合不同的隐藏层神经元数量与目标误差进行组合测试,获得预测值与实际值之间的相对误差。相对误差越小,预测值与实际值之间的匹配程度越好,网络训练效果越佳。最终,将样本数据输入至BP神经网络模型中,比较综合性能的预测值与实际值,通过决定系数R2对模型进行评估。
在此基础上,引入遗传算法(GA)对BP网络结构进行全局优化,构建GA-BP 代理模型。GA 采用实数编码,以最多四层隐藏层的神经元数h=[h1h2h3h4]为优化变量,在区间[1,50]内搜索最优组合。优化过程基于 MATLAB 全局优化工具箱的 ga 函数实现,种群规模设置为80,最大进化代数为100,并启用并行计算(UseParallel=true)以提高搜索效率。其余变量均采用ga默认设置。对于每一组候选结构h,在训练集上训练对应拓扑的 BP 神经网络,并在验证集上计算输出指标Y的决定系数R2,再将“最大化R2”转化为“最小化适应度”的问题,适应度函数定义为:
f(h)=1-R2(h)
R2越大,适应度越小、个体越优。GA收敛后,选取适应度最优个体对应的隐藏层神经元数作为最终网络结构,在训练集上重新训练 GA-BP 模型,并通过测试集上的决定系数R2对比结果来评估其泛化性能。
本研究采用BP神经网络算法对材料的综合性能进行迭代优化计算。模型训练结果表明,BP神经网络对样本数据具有一定的拟合能力,其测试集决定系数R²为0.51956(图10),表明模型对样本数据具备一定的拟合能力,能较好地反映性能变化趋势,但整体预测精度仍有提升空间。这一结果验证了代理模型在预测综合性能时的有效性,但也揭示了模型存在进一步提升空间的可能性。基于初步的预测模型,后续的优化工作将集中于提高模型的预测精度和整体表现,特别是在准确捕捉影响综合性能的多种因素间复杂的相互作用方面。为了进一步提高模型的有效性,其关键在于不断调整和优化神经网络的结构、超参数以及训练数据的选择。通过增加更多的训练数据,使用更高效的优化算法,或者采用更复杂的网络结构,模型可以更好地理解和学习不同因素之间的非线性关系,从而提升预测准确性。此外,迭代优化方法的优势在于其灵活性和动态性。通过每次迭代对模型参数进行调整,可以持续改进模型的拟合效果,使其更好地适应不同的样本和性能数据。这种动态调整机制确保了优化过程能够与对性能特征的理解同步演进,从而确保最终模型能够反映出更加准确和全面的综合性能。随着每次迭代的进行,模型将不断得到改进,直到达到所期望的精度水平和泛化能力。通过这一迭代优化过程,能够逐步完善预测模型,提升其在复杂、多变的实际环境中的应用效果,从而为后续竹编泥墙材料的性能优化提供更加可靠的理论基础和数据支持。
通过GA优化 BP 神经网络的参数后,预测模型个体的最优适应度值随着迭代次数的增加持续下降,并在后期逐渐趋于稳定。结果显示,经过遗传算法优化的BP神经网络在测试集上的决定系数(R²)达到了0.77121(图11)。这表明遗传算法能够在设定搜索空间内获得相对较优的参数组合,从而提高 BP 神经网络的预测稳定性。与使用原始数据建模的 BP 神经网络模型相比,遗传算法优化的 BP 神经网络模型在预测材料综合性能时表现出略高的预测准确度。两者均展现了良好的预测性能,但遗传算法优化后的 BP 神经网络模型具有更高的预测精度。这一对比结果强调了在复杂的性能预测场景中,采用遗传算法优化神经网络模型的有效性,尤其是在需要捕捉多种因素相互作用的情况下,优化算法能够显著提升预测模型的准确性。遗传算法通过优化神经网络的结构和参数,能够帮助克服传统BP神经网络在面对复杂数据时可能出现的局部最优解问题,提高了模型的全局优化能力。因此,采用遗传算法优化 BP 神经网络模型,在实际应用中,特别是在涉及到多个因素相互作用和非线性关系的复杂问题时,能够提供更加精确和可靠的预测结果。这进一步证明了遗传算法在神经网络优化中的重要作用,以及其在综合性能预测中的潜力。
综上所述,经机器学习方法预测(图12),墙体材料的导热系数范围为0.4247~0.6089 W/(m·K),等温平衡吸放湿含量范围为0.3213~0.5591 g/g。结合既有实测典型的构造尺寸,中部50 mm竹编骨架、双面各150 mm涂泥层及石灰外饰层,经民用建筑热工计算方法41换算,该竹编泥墙综合传热系数约为0.993 W/(m²·K),该值符合规定的限值要求42-44。预测范围内的等温平衡吸放湿含量将结合石灰饰面层的高碱性与低吸水率,可有效抑制水分渗入与积聚,从而减缓湿度波动对热性能的不利影响。因此,该结果验证了机器学习方法在传统墙体材料热湿性能评估中的有效性与应用潜力。
本研究基于生成对抗网络(GAN)算法对小样本数据进行扩展学习,并结合数值模拟与反向传播(BP)神经网络,构建了材料改性剂与热湿性能之间的预测模型。随后,使用遗传算法对该BP神经网络预测模型进行了优化,测试集决定系数R²值超过了原始预测模型的表现,验证了模型在传统墙体材料热湿性能预测及节能评估中的有效性。主要研究结论如下:
1)通过生成对抗网络(GAN)对16组小样本数据进行学习和扩增,最终生成66组样本数据集。分析结果表明,生成的数据不仅拟合良好,还与理论曲线相符,表明样本扩增有效提升了模型的准确性。
2)BP(反向传播)神经网络具有较强的非线性映射能力,能够有效地从训练样本集中的信息中学习并进行预测。通过建立改性剂剂量与综合热湿性能之间的数学预测模型,展现了较好的预测精度,证明了使用 BP 神经网络预测材料的综合热湿性能的可行性。
3)通过遗传算法(GA)优化 BP 神经网络模型,最终得到了优化后的预测模型,其测试集决定系数(R²=0.77121)超过了未优化模型的决定系数(R²=0.51956),表明遗传算法优化后的 BP 神经网络模型相比未优化的 BP 神经网络模型具有略高的预测准确度。这一改进凸显了遗传算法优化在提升神经网络模型预测能力方面的有效性,特别是在精度要求较高的复杂建模场景中,遗传算法的优化能够显著提升模型的预测精度。
4)机器学习预测表明,涂泥材料导热系数为 0.4247~0.6089 W/(m·K),等温平衡吸放湿含量为 0.3213~0.5591 g/g。等温平衡吸放湿含量在石灰饰面层的抑湿作用下有助于保持热湿耦合条件下的热工稳定性,验证了机器学习在传统墙体热湿性能评估中的有效性,表明该方法不仅在有限样本条件下实现较高精度的性能预测,还可为材料改性试验与节能设计提供理论支持和参考价值。
综上所述,该研究可作为传统墙体材料热湿性能快速预测评估的辅助工具,一方面为地域性传统建筑的绿色更新提供可操作的技术路径,另一方面可为保护与再利用提供可借鉴的数字化方法范式。同时,未来有望引入多种回归与机器学习模型开展系统的横向对比,进一步检验和深化本方法的适用性与优势。

参考文献 引证文献
排序方式:
[1]
AGRAWAL ACHOUDHARY A. Perspective: materials informatics and big data: realization of the “fourth paradigm” of science in materials science[J]. APL Materials20164(5): 053208.
[2]
SHEN CWANG CWEI Xet al. Physical metallurgy-guided machine learning and artificial intelligent design of ultrahigh-strength stainless steel[J]. Acta Materialia2019179: 201-214.
[3]
CAI J ZCHU XXU Ket al. Machine learning-driven new material discovery[J]. Nanoscale Advances20202:3115-3130.
[4]
CHAN C HSUN MHUANG B. Application of machine learning for advanced material prediction and design[J]. EcoMat20224:e12194.
[5]
YANG CREN CJIA Y Fet al. A machine learning-based alloy design system to facilitate the rational design of high entropy alloys with enhanced hardness[J]. Acta Materialia. 2022222:117431.
[6]
TAO Q LXU P CLI M Jet al. Machine learning for perovskite materials design and discovery[J]. NPJ Computational Materials20217:23.
[7]
LIU X JXU P CZHAO J Jet al. Material machine learning for alloys: applications, challenges and perspectives[J]. Journal of Alloys and Compounds2022921:165984.
[8]
XU P CCHEN H MLI M Jet al. New opportunity: machine learning for polymer materials design and discovery[J]. Advanced Theory and Simulations20225:2100565.
[9]
康孟羽, 朱月琴, 陈晨,. 基于多元非线性回归和BP神经网络的滑坡滑动距离预测模型研究 [J]. 地质通报202241(12): 2281-2289.
[10]
魏乐,李承霖,房方,.小样本下基于改进麻雀算法优化卷积神经网络的飞轮储能系统损耗[J].电网技术202549(1):366-372.
[11]
凌薇, 杨遵挥, 张芷薇,. 基于BP神经网络和遗传算法的封闭式厨房污染物模拟与优化[J]. 建筑科学202440(2): 111-119.
[12]
蔡安辉 刘永刚, 孙国雄. 基于正交试验的BP神经网络预测研究 [J]. 中国工程科学2003(7): 67-71.
[13]
ZHOU YDING F. A novel recursive multivariate nonlinear time-series modeling method by using the coupling identification concept[J]. Applied Mathematical Modelling2024127: 571-587.
[14]
MELO A PVERSAGE R SSAWAYA Get al. A novel surrogate model to support building energy labelling system: a new approach to assess cooling energy demand in commercial buildings[J]. Energy and Buildings2016131: 233-247.
[15]
KELCHNER S AGROUP B P. Higher level phylogenetic relationships within the bamboos (Poaceae: Bambusoideae) based on five plastid markers[J]. Molecular Phylogenetics and Evolution201367(2): 404-413.
[16]
JANIESCH CZSCHECH PHEINRICH K. Machine learning and deep learning[J]. Electronic Markets202131:685-695 .
[17]
BI Q FGOODMAN K EKAMINSKY Jet al. What is machine learning? a primer for the epidemiologist[J]. American Journal of Epidemiology2019188:2222-2239.
[18]
WARIN TSTOJKOV A. Machine learning in finance: a metadata-based systematic review of the literature[J]. Journal of Risk and Financial Management202114(7):302.
[19]
AHMED SALSHATER M MAMMARI A Eet al. Artificial intelligence and machine learning in finance: a bibliometric review[J]. Research in International Business and Finance202261:101646.
[20]
MUELLER BKINOSHITA TPEEBLES Aet al. Artificial intelligence and machine learning in emergency medicine: a narrative review[J]. Acute Medicine & Surgery20229:e740.
[21]
SABRY FELTARAS TLABDA Wet al. Machine learning for healthcare wearable devices: the big picture[J]. Joural of Healthcare Engineering20222022(1):4653923.
[22]
OKOROAFOR E RSMITH C MOCHIEET K Iet al. Machine learning in subsurface geothermal energy: two decades in review[J]. Geothermics2022102:102401.
[23]
CIOFFI RTRAVAGLIONI MPISCITELLI Get al. Artificial Intelli gence and machine learning applications in smart production: progress, trends, and directions[J]. Sustainability202012:492.
[24]
CRAMPON KGIORKALLOS ADELDOSSI Met al. Machine learning methods for ligand-protein molecular docking[J]. Drug Discovery Today202227:151-164.
[25]
JIANG Y RLUO JHUANG Det al. Machine learning advances in microbiology: a review of methods and applications[J]. Frontiers in Microbiology202213:925454.
[26]
SHAO Q MZHANG Z S. Berry-Esseen bounds for multivariate nonlinear statistics with applications to M-estimators and stochastic gradient descent algorithms[J]. Bernoulli202228(3): 1548-1576.
[27]
李紫微,林波荣,陈洪钟.建筑方案能耗快速预测方法研究综述[J].暖通空调201848(5):1-8.
[28]
ZHANG QCHANG DZHAI Xet al. OCPMDM: online computation platform for materials data mining[J]. Chemometrics and Intelligent Laboratory Systems2018177:26-34.
[29]
LI LTAO Q LXU P Cet al.Studies on the regularity of perovskite formation via machine learning[J]. Computational Materials Science2021199:110712.
[30]
YANG XLI LTAO Q Let al. Rapid discovery of narrow bandgap oxide double perovskites using machine learning[J]. Computational Materials Science2021196:110528.
[31]
TAO Q LCHANG D PLU Tet al. Multiobjective stepwise design strategy-assisted design of high-performance perovskite oxide photocatalysts[J]. The Journal of Physical Chemistry C2021125:21141-21150.
[32]
XU P CJI X BLI M Jet al. Small data machine learning in materials science[J]. NPJ Computational Materials20239(1):42.
[33]
WANG Y XSHI YZHOU B, Improvement of the Hygrothermal performance of mud-coated material used in traditional bamboo-woven mud walls[J]. International Journal of Architectural Heritage202317:1630-1647.
[34]
FENG H. Machine learning for composite material analysis and optimization[J]. Madison:The University of Wisconsin-Madison Press2023.
[35]
谢建新, 宿彦京, 薛德祯, . 机器学习在材料研发中的应用[J]. 金属学报202157(11): 1343-1361.
[36]
WANG Y QYAO Q MKWOK J Tet al. Generalizing from a few examples: a survey on few-shot learning[J]. ACM computing Surveys202053(3): 1-34.
[37]
LU JGONG PYE Jet al. A survey on machine learning from few samples[J]. Pattern Recognition2023139:109480.
[38]
LI D CCHEN S CLIN Y Set al. A generative adversarial network structure for learning with small numerical data sets[J]. Applied Sciences202111(22): 10823.
[39]
SANCHEZ-LENGELING BASPURU-GUZIK A. Inverse molecular design using machine learn-ing: generative models for matter engineering[J]. Science2018361:360-365.
[40]
BASH DCAI YCHELLAPPAN Vet al.Multi‐fidelity high‐throughput optimization of electrical conductivity in P3HT‐CNT composites[J]. Advanced Functional Materials202131(36): 2102606.
[41]
中华人民共和国建设部.民用建筑热工设计规范:GB/T 50176—1993[S].北京:中国计划出版社,1993.
[42]
中华人民共和国住房和城乡建设部.公共建筑节能设计标准:GB 50189—2015[S].北京:中国建筑工业出版社,2015.
[43]
中国建筑科学研究院.夏热冬冷地区居住建筑节能设计标准[J].上海建材2001(5):8-10.
[44]
中华人民共和国建设部.夏热冬暖地区居住建筑节能设计标准:JGJ 75—2003[S].北京:中国建筑工业出版社,2003.
2026年第56卷第5期
PDF下载
91
37
引用本文
BibTeX
文章信息
doi: 10.3724/j.gyjzG25111704
  • 接收时间:2025-11-17
  • 首发时间:2026-06-25
  • 出版时间:2026-05-20
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2025-11-17
基金
作者信息
    1同济大学建筑与城市规划学院,上海200092
    2天津城建大学国际工程学院,天津300384

通讯作者:

胡向磊,副教授,主要从事建筑工业化方向研究,
傅嘉言,博士后,主要从事智能建造方向研究,
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/gyjz/CN/10.3724/j.gyjzG25111704
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