Article(id=1228279670324524017, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1228279664221815452, articleNumber=null, orderNo=null, doi=10.12404/j.issn.1671-1815.2408240, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=research-article, receivedDate=1730736000000, receivedDateStr=2024-11-05, revisedDate=1747238400000, revisedDateStr=2025-05-15, acceptedDate=null, acceptedDateStr=null, onlineDate=1770774293738, onlineDateStr=2026-02-11, pubDate=1754582400000, pubDateStr=2025-08-08, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1770774293738, onlineIssueDateStr=2026-02-11, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1770774293738, creator=13701087609, updateTime=1770774293738, updator=13701087609, issue=Issue{id=1228279664221815452, tenantId=1146029695717560320, journalId=1146123166801305609, year='2025', volume='25', issue='22', pageStart='9211', pageEnd='9648', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=1, specialIssue=null, createTime=1770774292283, creator=13701087609, updateTime=1770777611996, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1228293588207992892, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1228279664221815452, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1228293588207992893, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1228279664221815452, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=9505, endPage=9513, ext={EN=ArticleExt(id=1228279673814184029, articleId=1228279670324524017, tenantId=1146029695717560320, journalId=1146123166801305609, language=EN, title=Chiller Fault Diagnosis Method Based on IDBO-HKELM, columnId=1228279670542627833, journalTitle=Science Technology and Engineering, columnName=Papers·Architectural Science, runingTitle=null, highlight=null, articleAbstract=

As a key equipment and a major source of energy consumption in a building, chiller plant, if it fails, it will not only affect the normal operation of the system, but also cause serious energy waste. In order to improve the reliability of chiller system operation. A multi-strategy IDBO(improved dung beetle optimization algorithm) combined with a HKELM(hybrid kernel extreme learning machine) fusion fault diagnosis model was constructed to achieve accurate diagnosis of early faults in chiller systems. The model firstly employs hybrid kernel functions to improve the learning ability and generalization of KELM(kernel-extreme learning machine). Secondly, Bernoulli mapping, adaptive inertia factor, and Levy flight fusion dynamic weight coefficients strategies were used to improve the DBO(dung beetle optimization) algorithm in order to balance the global exploration performance of the DBO algorithm. Finally, the effectiveness of the IDBO algorithm was verified by benchmark functions, and the HKELM hyperparameters are optimized using the IDBO algorithm to construct a data-driven model for early fault diagnosis of chiller units. Through relevant training simulations and experimental validation, the accuracy of the proposed IDBO-HKELM model for early fault diagnosis of chillers is improved to 99.71%, which is an obvious advantage over other algorithms.

, correspAuthors=Da-song GUAN, authorNote=null, correspAuthorsNote=null, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=null, magXml=null, pdfUrl=null, pdf=null, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=null, mapNumber=null, authorCompany=null, fund=null, authors=null, authorsList=Hong WANG, Pan CHU, Da-song GUAN, Yang GUO, Zeng-rui TIAN, Ying-jie SHENG), CN=ArticleExt(id=1228279675940696269, articleId=1228279670324524017, tenantId=1146029695717560320, journalId=1146123166801305609, language=CN, title=基于IDBO-HKELM的冷水机组故障诊断方法, columnId=1228279671742197785, journalTitle=科学技术与工程, columnName=论文·建筑科学, runingTitle=null, highlight=null, articleAbstract=

冷水机组作为建筑中的关键设备和主要能耗源,若其发生故障不仅会影响系统的正常运行,还会造成严重的能源浪费。为提升冷水机组系统运行的可靠性,构建了一种多策略改进蜣螂优化算法(improve dung beetle optimizer,IDBO)和混合核极限学习机(hybrid kernel extreme learning machine,HKELM)融合的故障诊断模型,用于实现冷水机组早期故障的精确诊断。该模型首先采用混合核函数提高核极限学习机(kernel extreme learning machine,KELM)的学习能力和泛化性,其次将Bernoulli映射、自适应惯性因子和Levy飞行融合动态权重系数策略用于改进蜣螂优化算法(dung beetle optimizer,DBO),以平衡DBO算法的全局探索性能。最后通过基准函数验证IDBO算法的有效性,利用IDBO算法对HKELM超参数进行优化,从而构建用于冷水机组早期故障诊断的数据驱动模型。通过相关训练仿真和实验验证,所提出的IDBO-HKELM模型对冷水机组的早期故障诊断准确率提高到99.71%,对比其他算法具有明显优势。

, correspAuthors=管大松, authorNote=null, correspAuthorsNote=
* 管大松(1969—),男,汉族,北京人,教授级高级工程师。研究方向:建筑设备节能、智能化控制。E-mail:
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=UlPD3zuHKNp/U/gmE+x1jw==, magXml=8VOR4ivtpic71iVrGH7qFQ==, pdfUrl=null, pdf=Xu6G3wtI7AJkGUyQ8ruFwQ==, pdfFileSize=5676577, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=F1ymsk5ALLG0nd0lDNZbcA==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=ueHo8BGg5zIjh/ZuFfFRTg==, mapNumber=null, authorCompany=null, fund=null, authors=

王宏(1977—),男,汉族,河南平顶山人,硕士,教授。研究方向:智能建筑设备节能优化控制、故障诊断及智慧运维。E-mail:

, authorsList=王宏, 储盼, 管大松, 郭洋, 田增瑞, 盛英杰)}, authors=[Author(id=1228369858971238617, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=wanghong@zzuli.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1228369859080290531, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, authorId=1228369858971238617, language=EN, stringName=Hong WANG, firstName=Hong, middleName=null, lastName=WANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1 College of Building Environment Engineering, Zhengzhou University of Light Industry, Zhengzhou 450000, China
2 Henan Engineering Research Center of Intelligent Buildings and Human Settlements, Zhengzhou 450000, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1228369859189342445, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, authorId=1228369858971238617, language=CN, stringName=王宏, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1 郑州轻工业大学建筑环境工程学院, 郑州 450000
2 河南省智慧建筑与人居环境工程技术研究中心, 郑州 450000, bio={"content":"

王宏(1977—),男,汉族,河南平顶山人,硕士,教授。研究方向:智能建筑设备节能优化控制、故障诊断及智慧运维。E-mail:

"}, bioImg=null, bioContent=

王宏(1977—),男,汉族,河南平顶山人,硕士,教授。研究方向:智能建筑设备节能优化控制、故障诊断及智慧运维。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1228369858606334141, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, xref=1, ext=[AuthorCompanyExt(id=1228369858614722750, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, companyId=1228369858606334141, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 College of Building Environment Engineering, Zhengzhou University of Light Industry, Zhengzhou 450000, China), AuthorCompanyExt(id=1228369858623111359, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, companyId=1228369858606334141, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 郑州轻工业大学建筑环境工程学院, 郑州 450000)]), AuthorCompany(id=1228369858740551879, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, xref=2, ext=[AuthorCompanyExt(id=1228369858748940487, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, companyId=1228369858740551879, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 Henan Engineering Research Center of Intelligent Buildings and Human Settlements, Zhengzhou 450000, China), AuthorCompanyExt(id=1228369858757329096, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, companyId=1228369858740551879, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 河南省智慧建筑与人居环境工程技术研究中心, 郑州 450000)])]), Author(id=1228369859264839925, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, 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=1228369859428417792, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, authorId=1228369859264839925, language=EN, stringName=Pan CHU, firstName=Pan, middleName=null, lastName=CHU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1 College of Building Environment Engineering, Zhengzhou University of Light Industry, Zhengzhou 450000, China
2 Henan Engineering Research Center of Intelligent Buildings and Human Settlements, Zhengzhou 450000, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1228369859541664010, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, authorId=1228369859264839925, language=CN, stringName=储盼, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1 郑州轻工业大学建筑环境工程学院, 郑州 450000
2 河南省智慧建筑与人居环境工程技术研究中心, 郑州 450000, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1228369858606334141, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, xref=1, ext=[AuthorCompanyExt(id=1228369858614722750, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, companyId=1228369858606334141, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 College of Building Environment Engineering, Zhengzhou University of Light Industry, Zhengzhou 450000, China), AuthorCompanyExt(id=1228369858623111359, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, companyId=1228369858606334141, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 郑州轻工业大学建筑环境工程学院, 郑州 450000)]), AuthorCompany(id=1228369858740551879, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, xref=2, ext=[AuthorCompanyExt(id=1228369858748940487, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, companyId=1228369858740551879, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 Henan Engineering Research Center of Intelligent Buildings and Human Settlements, Zhengzhou 450000, China), AuthorCompanyExt(id=1228369858757329096, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, companyId=1228369858740551879, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 河南省智慧建筑与人居环境工程技术研究中心, 郑州 450000)])]), Author(id=1228369859663298836, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=C960850C@163.com, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1228369859801710883, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, authorId=1228369859663298836, language=EN, stringName=Da-song GUAN, firstName=Da-song, middleName=null, lastName=GUAN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, *, address=3 China Construction Technology Group Ltd., Beijing 100013, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1228369859931734317, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, authorId=1228369859663298836, language=CN, stringName=管大松, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, *, address=3 中国建筑技术集团有限公司, 北京 100013, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1228369858853798096, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, xref=3, ext=[AuthorCompanyExt(id=1228369858857992399, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, companyId=1228369858853798096, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 China Construction Technology Group Ltd., Beijing 100013, China), AuthorCompanyExt(id=1228369858866381008, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, companyId=1228369858853798096, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 中国建筑技术集团有限公司, 北京 100013)])]), Author(id=1228369860053369141, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1228369860170809669, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, authorId=1228369860053369141, language=EN, stringName=Yang GUO, firstName=Yang, middleName=null, lastName=GUO, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1 College of Building Environment Engineering, Zhengzhou University of Light Industry, Zhengzhou 450000, China
2 Henan Engineering Research Center of Intelligent Buildings and Human Settlements, Zhengzhou 450000, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1228369860267278668, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, authorId=1228369860053369141, language=CN, stringName=郭洋, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1 郑州轻工业大学建筑环境工程学院, 郑州 450000
2 河南省智慧建筑与人居环境工程技术研究中心, 郑州 450000, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1228369858606334141, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, xref=1, ext=[AuthorCompanyExt(id=1228369858614722750, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, companyId=1228369858606334141, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 College of Building Environment Engineering, Zhengzhou University of Light Industry, Zhengzhou 450000, China), AuthorCompanyExt(id=1228369858623111359, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, companyId=1228369858606334141, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 郑州轻工业大学建筑环境工程学院, 郑州 450000)]), AuthorCompany(id=1228369858740551879, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, xref=2, ext=[AuthorCompanyExt(id=1228369858748940487, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, companyId=1228369858740551879, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 Henan Engineering Research Center of Intelligent Buildings and Human Settlements, Zhengzhou 450000, China), AuthorCompanyExt(id=1228369858757329096, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, companyId=1228369858740551879, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 河南省智慧建筑与人居环境工程技术研究中心, 郑州 450000)])]), Author(id=1228369860376330579, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, orderNo=4, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1228369860514742627, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, authorId=1228369860376330579, language=EN, stringName=Zeng-rui TIAN, firstName=Zeng-rui, middleName=null, lastName=TIAN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1 College of Building Environment Engineering, Zhengzhou University of Light Industry, Zhengzhou 450000, China
2 Henan Engineering Research Center of Intelligent Buildings and Human Settlements, Zhengzhou 450000, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1228369860682514795, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, authorId=1228369860376330579, language=CN, stringName=田增瑞, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1 郑州轻工业大学建筑环境工程学院, 郑州 450000
2 河南省智慧建筑与人居环境工程技术研究中心, 郑州 450000, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1228369858606334141, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, xref=1, ext=[AuthorCompanyExt(id=1228369858614722750, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, companyId=1228369858606334141, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 College of Building Environment Engineering, Zhengzhou University of Light Industry, Zhengzhou 450000, China), AuthorCompanyExt(id=1228369858623111359, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, companyId=1228369858606334141, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 郑州轻工业大学建筑环境工程学院, 郑州 450000)]), AuthorCompany(id=1228369858740551879, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, xref=2, ext=[AuthorCompanyExt(id=1228369858748940487, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, companyId=1228369858740551879, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 Henan Engineering Research Center of Intelligent Buildings and Human Settlements, Zhengzhou 450000, China), AuthorCompanyExt(id=1228369858757329096, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, companyId=1228369858740551879, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 河南省智慧建筑与人居环境工程技术研究中心, 郑州 450000)])]), Author(id=1228369860783178102, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, orderNo=5, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1228369860917395845, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, authorId=1228369860783178102, language=EN, stringName=Ying-jie SHENG, firstName=Ying-jie, middleName=null, lastName=SHENG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1 College of Building Environment Engineering, Zhengzhou University of Light Industry, Zhengzhou 450000, China
2 Henan Engineering Research Center of Intelligent Buildings and Human Settlements, Zhengzhou 450000, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1228369861047419284, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, authorId=1228369860783178102, language=CN, stringName=盛英杰, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1 郑州轻工业大学建筑环境工程学院, 郑州 450000
2 河南省智慧建筑与人居环境工程技术研究中心, 郑州 450000, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1228369858606334141, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, xref=1, ext=[AuthorCompanyExt(id=1228369858614722750, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, companyId=1228369858606334141, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 College of Building Environment Engineering, Zhengzhou University of Light Industry, Zhengzhou 450000, China), AuthorCompanyExt(id=1228369858623111359, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, companyId=1228369858606334141, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 郑州轻工业大学建筑环境工程学院, 郑州 450000)]), AuthorCompany(id=1228369858740551879, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, xref=2, ext=[AuthorCompanyExt(id=1228369858748940487, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, companyId=1228369858740551879, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 Henan Engineering Research Center of Intelligent Buildings and Human Settlements, Zhengzhou 450000, China), AuthorCompanyExt(id=1228369858757329096, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, companyId=1228369858740551879, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 河南省智慧建筑与人居环境工程技术研究中心, 郑州 450000)])])], keywords=[Keyword(id=1228369861290688939, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, language=EN, orderNo=1, keyword=chiller), Keyword(id=1228369861399740854, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, language=EN, orderNo=2, keyword=swarm algorithm), Keyword(id=1228369861517181375, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, language=EN, orderNo=3, keyword=HKELM(hybrid kernel extreme learning machine)), Keyword(id=1228369861647204809, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, language=EN, orderNo=4, keyword=fault diagnosis), Keyword(id=1228369863069073875, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, language=EN, orderNo=5, keyword=IDBO(improved dung beetle optimization) algorithm), Keyword(id=1228369863194903003, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, language=CN, orderNo=1, keyword=冷水机组), Keyword(id=1228369863287177699, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, language=CN, orderNo=2, keyword=群体算法), Keyword(id=1228369863417201130, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, language=CN, orderNo=3, keyword=HKELM), Keyword(id=1228369863530447346, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, language=CN, orderNo=4, keyword=IDBO算法), Keyword(id=1228369863643693561, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, language=CN, orderNo=5, keyword=故障诊断)], refs=[Reference(id=1228369867485676164, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, doi=null, pmid=null, pmcid=null, year=2018, volume=24, issue=1, pageStart=3, pageEnd=21, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=Kim W, Katipamula S, journalName=Science and Technology for the Built Environment, refType=null, unstructuredReference=Kim W, Katipamula S. A review of fault detection and diagnostics methods for building systems[J]. Science and Technology for the Built Environment, 2018, 24(1): 3-21., articleTitle=A review of fault detection and diagnostics methods for building systems, refAbstract=null), Reference(id=1228369867598922377, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, doi=null, pmid=null, pmcid=null, year=2016, volume=42, issue=9, pageStart=1285, pageEnd=1299, url=null, language=null, rfNumber=[2], rfOrder=1, authorNames=文成林, 吕菲亚, 包哲静, journalName=自动化学报, refType=null, unstructuredReference=文成林, 吕菲亚, 包哲静, 等. 基于数据驱动的微小故障诊断方法综述[J]. 自动化学报, 2016, 42(9): 1285-1299., articleTitle=基于数据驱动的微小故障诊断方法综述, refAbstract=null), Reference(id=1228369867703779982, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, doi=null, pmid=null, pmcid=null, year=2016, volume=42, issue=9, pageStart=1285, pageEnd=1299, url=null, language=null, rfNumber=[2], rfOrder=2, authorNames=Wen Chenglin, Lu Feiya, Bao Zhejing, journalName=Acta Automatica Sinica, refType=null, unstructuredReference=Wen Chenglin, Lu Feiya, Bao Zhejing, et al. A review of data-driven methods for diagnosis of small faults[J]. Acta Automatica Sinica, 2016, 42(9): 1285-1299., articleTitle=A review of data-driven methods for diagnosis of small faults, refAbstract=null), Reference(id=1228369867787666064, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, doi=null, pmid=null, pmcid=null, year=2024, volume=24, issue=13, pageStart=5626, pageEnd=5633, url=null, language=null, rfNumber=[3], rfOrder=3, authorNames=戴洪德, 张志亮, 崔伟成, journalName=科学技术与工程, refType=null, unstructuredReference=戴洪德, 张志亮, 崔伟成, 等. 基于SSA-SVM的航空电弧故障检测[J]. 科学技术与工程, 2024, 24(13): 5626-5633., articleTitle=基于SSA-SVM的航空电弧故障检测, refAbstract=null), Reference(id=1228369867892523667, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, doi=null, pmid=null, pmcid=null, year=2024, volume=24, issue=13, pageStart=5626, pageEnd=5633, url=null, language=null, rfNumber=[3], rfOrder=4, authorNames=Dai Hongde, Zhang Zhiliang, Cui Weicheng, journalName=Science Technology and Engineering, refType=null, unstructuredReference=Dai Hongde, Zhang Zhiliang, Cui Weicheng, et al. Aerial arc fault detection based on SSA-SVM[J]. Science Technology and Engineering, 2024, 24(13): 5626-5633., articleTitle=Aerial arc fault detection based on SSA-SVM, refAbstract=null), Reference(id=1228369868001575579, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, doi=null, pmid=null, pmcid=null, year=2022, volume=41, issue=9, pageStart=151, pageEnd=155, url=null, language=null, rfNumber=[4], rfOrder=5, authorNames=宋玉生, 刘光宇, 朱凌, journalName=传感器与微系统, refType=null, unstructuredReference=宋玉生, 刘光宇, 朱凌, 等. 改进的灰狼优化算法在SVM参数优化中的应用[J]. 传感器与微系统, 2022, 41(9): 151-155., articleTitle=改进的灰狼优化算法在SVM参数优化中的应用, refAbstract=null), Reference(id=1228369868106433184, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, doi=null, pmid=null, pmcid=null, year=2022, volume=41, issue=9, pageStart=151, pageEnd=155, url=null, language=null, rfNumber=[4], rfOrder=6, authorNames=Song Yusheng, Liu Guangyu, Zhu Ling, journalName=Transducer and Microsystem Technologies, refType=null, unstructuredReference=Song Yusheng, Liu Guangyu, Zhu Ling, et al. Application of improved GWO algorithm in SVM parameter optimization[J]. Transducer and Microsystem Technologies, 2022, 41(9): 151-155., articleTitle=Application of improved GWO algorithm in SVM parameter optimization, refAbstract=null), Reference(id=1228369868202902178, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, doi=null, pmid=null, pmcid=null, year=2022, volume=41, issue=11, pageStart=134, pageEnd=137, url=null, language=null, rfNumber=[5], rfOrder=7, authorNames=宋旭彤, 刘卓元, 金毅, journalName=传感器与微系统, refType=null, unstructuredReference=宋旭彤, 刘卓元, 金毅, 等. 基于CNN和预处理机制的球磨机故障诊断方法[J]. 传感器与微系统, 2022, 41(11): 134-137, 142., articleTitle=基于CNN和预处理机制的球磨机故障诊断方法, refAbstract=null), Reference(id=1228369868303565479, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, doi=null, pmid=null, pmcid=null, year=2022, volume=41, issue=11, pageStart=134, pageEnd=137, url=null, language=null, rfNumber=[5], rfOrder=8, authorNames=Song Xutong, Liu Zhuoyuan, Jin Yi, journalName=Transducer and Microsystem Technologies, refType=null, unstructuredReference=Song Xutong, Liu Zhuoyuan, Jin Yi, et al. Fault diagnosis method for ball mill based on CNN and preprocessing mechanism[J]. Transducer and Microsystem Technologies, 2022, 41(11): 134-137, 142., articleTitle=Fault diagnosis method for ball mill based on CNN and preprocessing mechanism, refAbstract=null), Reference(id=1228369868400034473, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, doi=null, pmid=null, pmcid=null, year=2023, volume=42, issue=2, pageStart=126, pageEnd=131, url=null, language=null, rfNumber=[6], rfOrder=9, authorNames=赵志宏, 李春秀, 窦广鉴, journalName=振动与冲击, refType=null, unstructuredReference=赵志宏, 李春秀, 窦广鉴, 等. 基于MTF-CNN的轴承故障诊断研究[J]. 振动与冲击, 2023, 42(2): 126-131., articleTitle=基于MTF-CNN的轴承故障诊断研究, refAbstract=null), Reference(id=1228369868500697775, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, doi=null, pmid=null, pmcid=null, year=2023, volume=42, issue=2, pageStart=126, pageEnd=131, url=null, language=null, rfNumber=[6], rfOrder=10, authorNames=Zhao Zhihong, Li Chunxiu, Dou Guangjian, journalName=Journal of Vibration and Shock, refType=null, unstructuredReference=Zhao Zhihong, Li Chunxiu, Dou Guangjian, et al. Bearing fault dia-gnosis method based on MTF-CNN[J]. Journal of Vibration and Shock, 2023, 42(2): 126-131., articleTitle=Bearing fault dia-gnosis method based on MTF-CNN, refAbstract=null), Reference(id=1228369868605555375, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, doi=null, pmid=null, pmcid=null, year=2022, volume=41, issue=12, pageStart=72, pageEnd=80, url=null, language=null, rfNumber=[7], rfOrder=11, authorNames=吴经锋, 王文森, 张璐, journalName=电工电能新技术, refType=null, unstructuredReference=吴经锋, 王文森, 张璐, 等. 基于CNN算法的并联电抗器机械故障诊断方法[J]. 电工电能新技术, 2022, 41(12): 72-80., articleTitle=基于CNN算法的并联电抗器机械故障诊断方法, refAbstract=null), Reference(id=1228369868722995893, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, doi=null, pmid=null, pmcid=null, year=2022, volume=41, issue=12, pageStart=72, pageEnd=80, url=null, language=null, rfNumber=[7], rfOrder=12, authorNames=Wu Jingfeng, Wang Wensen, Zhang Lu, journalName=Advanced Technology of Electrical Engineering and Energy, refType=null, unstructuredReference=Wu Jingfeng, Wang Wensen, Zhang Lu, et al. Mechanical fault dia-gnosis methodof shunt reactor based on CNN algorithm[J]. Advanced Technology of Electrical Engineering and Energy, 2022, 41(12): 72-80., articleTitle=Mechanical fault dia-gnosis methodof shunt reactor based on CNN algorithm, refAbstract=null), Reference(id=1228369868819464888, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, doi=null, pmid=null, pmcid=null, year=2004, volume=2, issue=null, pageStart=985, pageEnd=990, url=null, language=null, rfNumber=[8], rfOrder=13, authorNames=Huang G B, Zhu Q Y, Siew C K, journalName=IEEE Internation Joint Conference on Neural Networks, refType=null, unstructuredReference=Huang G B, Zhu Q Y, Siew C K. Extreme learning machine: a new learning scheme of feedforward neural networks[J]. IEEE Internation Joint Conference on Neural Networks, 2004, 2: 985-990., articleTitle=Extreme learning machine: a new learning scheme of feedforward neural networks, refAbstract=null), Reference(id=1228369868936905409, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, doi=null, pmid=null, pmcid=null, year=2013, volume=28, issue=6, pageStart=30, pageEnd=59, url=null, language=null, rfNumber=[9], rfOrder=14, authorNames=Cambria E, Huang G B, Kasun L L C, journalName=IEEE Intelligent Systems, refType=null, unstructuredReference=Cambria E, Huang G B, Kasun L L C. Extreme learning machines[J]. IEEE Intelligent Systems, 2013, 28(6): 30-59., articleTitle=Extreme learning machines, refAbstract=null), Reference(id=1228369869054345922, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, doi=null, pmid=null, pmcid=null, year=2015, volume=58, issue=2, pageStart=1, pageEnd=16, url=null, language=null, rfNumber=[10], rfOrder=15, authorNames=Deng C W, Huang G B, Xu J, journalName=Science China Information Sciences, refType=null, unstructuredReference=Deng C W, Huang G B, Xu J, et al. Extreme learning machines: new trends and applications[J]. Science China Information Sciences, 2015, 58(2): 1-16., articleTitle=Extreme learning machines: new trends and applications, refAbstract=null), Reference(id=1228369869155009222, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, doi=null, pmid=null, pmcid=null, year=2017, volume=2017, issue=null, pageStart=809, pageEnd=821, url=null, language=null, rfNumber=[11], rfOrder=16, authorNames=Tang J, Deng C, Huang G B, journalName=IEEE Transactions on Neural Networks & Learning Systems, refType=null, unstructuredReference=Tang J, Deng C, Huang G B. Extreme learning machine for multilayer perceptron[J]. IEEE Transactions on Neural Networks & Learning Systems, 2017, 2017: 809-821., articleTitle=Extreme learning machine for multilayer perceptron, refAbstract=null), Reference(id=1228369869264061130, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, doi=null, pmid=null, pmcid=null, year=2024, volume=53, issue=4, pageStart=36, pageEnd=40, url=null, language=null, rfNumber=[12], rfOrder=17, authorNames=李花宁, 吴生彪, 冯丽, journalName=机电工程技术, refType=null, unstructuredReference=李花宁, 吴生彪, 冯丽, 等. 基于AdaBoost-WOA-HKELM的下肢关节角度预测[J]. 机电工程技术, 2024, 53(4): 36-40., articleTitle=基于AdaBoost-WOA-HKELM的下肢关节角度预测, refAbstract=null), Reference(id=1228369869398278860, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, doi=null, pmid=null, pmcid=null, year=2024, volume=53, issue=4, pageStart=36, pageEnd=40, url=null, language=null, rfNumber=[12], rfOrder=18, authorNames=Li Huaning, Wu Shengbiao, Feng Li, journalName=Mechatro-nics Engineering Technology, refType=null, unstructuredReference=Li Huaning, Wu Shengbiao, Feng Li, et al. Lower limb joint angle prediction based on AdaBoost-WOA-HKELM[J]. Mechatro-nics Engineering Technology, 2024, 53(4): 36-40., articleTitle=Lower limb joint angle prediction based on AdaBoost-WOA-HKELM, refAbstract=null), Reference(id=1228369869528302288, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, doi=null, pmid=null, pmcid=null, year=2024, volume=52, issue=6, pageStart=120, pageEnd=130, url=null, language=null, rfNumber=[13], rfOrder=19, authorNames=赵鑫, 王东丽, 彭泓, journalName=电力系统保护与控制, refType=null, unstructuredReference=赵鑫, 王东丽, 彭泓, 等. 基于多策略改进蜣螂算法优化的变压器故障诊断[J]. 电力系统保护与控制, 2024, 52(6): 120-130., articleTitle=基于多策略改进蜣螂算法优化的变压器故障诊断, refAbstract=null), Reference(id=1228369869633159893, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, doi=null, pmid=null, pmcid=null, year=2024, volume=52, issue=6, pageStart=120, pageEnd=130, url=null, language=null, rfNumber=[13], rfOrder=20, authorNames=Zhao Xin, Wang Dongli, Peng Hong, journalName=Power System Protection and Control, refType=null, unstructuredReference=Zhao Xin, Wang Dongli, Peng Hong, et al. Transformer fault diagnosis based on multi-strategy improved dung beetle algorithm optimization[J]. Power System Protection and Control, 2024, 52(6): 120-130., articleTitle=Transformer fault diagnosis based on multi-strategy improved dung beetle algorithm optimization, refAbstract=null), Reference(id=1228369869750600411, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, doi=null, pmid=null, pmcid=null, year=2023, volume=23, issue=2, pageStart=640, pageEnd=647, url=null, language=null, rfNumber=[14], rfOrder=21, authorNames=范小虎, 赵爱罡, 许强, journalName=科学技术与工程, refType=null, unstructuredReference=范小虎, 赵爱罡, 许强, 等. 基于ELM-SVR模型的装备关键部件寿命预测[J]. 科学技术与工程, 2023, 23(2): 640-647., articleTitle=基于ELM-SVR模型的装备关键部件寿命预测, refAbstract=null), Reference(id=1228369869859652319, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, doi=null, pmid=null, pmcid=null, year=2023, volume=23, issue=2, pageStart=640, pageEnd=647, url=null, language=null, rfNumber=[14], rfOrder=22, authorNames=Fan Xiaohu, Zhao Aigang, Xu Qiang, journalName=Science Technology and Engineering, refType=null, unstructuredReference=Fan Xiaohu, Zhao Aigang, Xu Qiang, et al. Life prediction of key equipment components based on ELM-SVR model[J]. Science Technology and Engineering, 2023, 23(2): 640-647., articleTitle=Life prediction of key equipment components based on ELM-SVR model, refAbstract=null), Reference(id=1228369869964509925, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, doi=null, pmid=null, pmcid=null, year=2024, volume=24, issue=11, pageStart=4599, pageEnd=4606, url=null, language=null, rfNumber=[15], rfOrder=23, authorNames=宋永献, 王祥祥, 李媛媛, journalName=科学技术与工程, refType=null, unstructuredReference=宋永献, 王祥祥, 李媛媛, 等. 基于核极限学习机的下肢关节力矩预测方法[J]. 科学技术与工程, 2024, 24(11): 4599-4606., articleTitle=基于核极限学习机的下肢关节力矩预测方法, refAbstract=null), Reference(id=1228369870065173224, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, doi=null, pmid=null, pmcid=null, year=2024, volume=24, issue=11, pageStart=4599, pageEnd=4606, url=null, language=null, rfNumber=[15], rfOrder=24, authorNames=Song Yongxian, Wang Xiangxiang, Li Yuanyuan, journalName=Science Technology and Engineering, refType=null, unstructuredReference=Song Yongxian, Wang Xiangxiang, Li Yuanyuan, et al. A method for lower limb joint moment prediction based on nuclear limit learning machine[J]. Science Technology and Engineering, 2024, 24(11): 4599-4606., articleTitle=A method for lower limb joint moment prediction based on nuclear limit learning machine, refAbstract=null), Reference(id=1228369870157447915, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, doi=null, pmid=null, pmcid=null, year=2024, volume=24, issue=23, pageStart=9842, pageEnd=9847, url=null, language=null, rfNumber=[16], rfOrder=25, authorNames=李彦阳, 王金东, 曲孝海, journalName=科学技术与工程, refType=null, unstructuredReference=李彦阳, 王金东, 曲孝海. 基于GMPE和GWO-MKELM算法的往复压缩机轴承故障诊断[J]. 科学技术与工程, 2024, 24(23): 9842-9847., articleTitle=基于GMPE和GWO-MKELM算法的往复压缩机轴承故障诊断, refAbstract=null), Reference(id=1228369870232945389, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, doi=null, pmid=null, pmcid=null, year=2024, volume=24, issue=23, pageStart=9842, pageEnd=9847, url=null, language=null, rfNumber=[16], rfOrder=26, authorNames=Li Yanyang, Wang Jindong, Qu Xiaohai, journalName=Science Technology and Engineering, refType=null, unstructuredReference=Li Yanyang, Wang Jindong, Qu Xiaohai. Fault diagnosis of reciprocating compressor bearings based on GMPE and GWO-MKELM algorithms[J]. Science Technology and Engineering, 2024, 24(23): 9842-9847., articleTitle=Fault diagnosis of reciprocating compressor bearings based on GMPE and GWO-MKELM algorithms, refAbstract=null), Reference(id=1228369870316831472, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, doi=null, pmid=null, pmcid=null, year=2023, volume=79, issue=7, pageStart=7305, pageEnd=7336, url=null, language=null, rfNumber=[17], rfOrder=27, authorNames=Xue J, Shen B, journalName=The Journal of Supercomputing, refType=null, unstructuredReference=Xue J, Shen B. Dung beetle optimizer: a new meta-heuristic algorithm for global optimization[J]. The Journal of Supercomputing, 2023, 79(7): 7305-7336., articleTitle=Dung beetle optimizer: a new meta-heuristic algorithm for global optimization, refAbstract=null), Reference(id=1228369870396523254, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, doi=null, pmid=null, pmcid=null, year=2024, volume=24, issue=14, pageStart=5882, pageEnd=5891, url=null, language=null, rfNumber=[18], rfOrder=28, authorNames=汤兆平, 孟鑫, 孙剑萍, journalName=科学技术与工程, refType=null, unstructuredReference=汤兆平, 孟鑫, 孙剑萍, 等. 基于改进鲸鱼优化算法的码垛机器人时间最优轨迹规划[J]. 科学技术与工程, 2024, 24(14): 5882-5891., articleTitle=基于改进鲸鱼优化算法的码垛机器人时间最优轨迹规划, refAbstract=null), Reference(id=1228369870480409338, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, doi=null, pmid=null, pmcid=null, year=2024, volume=24, issue=14, pageStart=5882, pageEnd=5891, url=null, language=null, rfNumber=[18], rfOrder=29, authorNames=Tang Zhaoping, Meng Xin, Sun Jianping, journalName=Science Technology and Engineering, refType=null, unstructuredReference=Tang Zhaoping, Meng Xin, Sun Jianping, et al. Time-optimal trajectory planning for palletizing robot based on improved whaleoptimization algorithm[J]. Science Technology and Engineering, 2024, 24(14): 5882-5891., articleTitle=Time-optimal trajectory planning for palletizing robot based on improved whaleoptimization algorithm, refAbstract=null), Reference(id=1228369870602044159, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, doi=null, pmid=null, pmcid=null, year=2023, volume=51, issue=11, pageStart=96, pageEnd=102, url=null, language=null, rfNumber=[19], rfOrder=30, authorNames=王宏, 袁伯阳, 韩晨, journalName=低温与超导, refType=null, unstructuredReference=王宏, 袁伯阳, 韩晨, 等. 基于机器学习的冷水机组早期故障诊断[J]. 低温与超导, 2023, 51(11): 96-102., articleTitle=基于机器学习的冷水机组早期故障诊断, refAbstract=null), Reference(id=1228369872002941701, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, doi=null, pmid=null, pmcid=null, year=2023, volume=51, issue=11, pageStart=96, pageEnd=102, url=null, language=null, rfNumber=[19], rfOrder=31, authorNames=Wang Hong, Yuan Boyang, Han Chen, journalName=Cryogenics and Superconductivity, refType=null, unstructuredReference=Wang Hong, Yuan Boyang, Han Chen, et al. Early fault diagnosis of chiller based on machine learning[J]. Cryogenics and Superconductivity, 2023, 51(11): 96-102., articleTitle=Early fault diagnosis of chiller based on machine learning, refAbstract=null), Reference(id=1228369872107799308, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, doi=null, pmid=null, pmcid=null, year=2011, volume=34, issue=2, pageStart=586, pageEnd=599, url=null, language=null, rfNumber=[20], rfOrder=32, authorNames=Han H, Gu B, Wang T, journalName=International Journal of Refrigeration, refType=null, unstructuredReference=Han H, Gu B, Wang T, et al. Important sensors for chiller fault detection and diagnosis(FDD) from the perspective of feature selection and machine learning[J]. International Journal of Refrigeration, 2011, 34(2): 586-599., articleTitle=Important sensors for chiller fault detection and diagnosis(FDD) from the perspective of feature selection and machine learning, refAbstract=null)], funds=[Fund(id=1228369865677931115, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, awardId=232102211050, language=CN, fundingSource=河南省科技攻关项目(232102211050), fundOrder=null, country=null), Fund(id=1228369865740845680, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, awardId=252102241002, language=CN, fundingSource=河南省科技攻关项目(252102241002), fundOrder=null, country=null), Fund(id=1228369865849897590, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, awardId=YJYGNYZ-2024005, language=CN, fundingSource=郑州轻工业大学产业技术研究院2024年度概念验证项目(YJYGNYZ-2024005), fundOrder=null, country=null), Fund(id=1228369865917006460, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, awardId=13501050025, language=CN, fundingSource=郑州轻工业大学博士科研基金资助项目(13501050025), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1228369858606334141, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, xref=1, ext=[AuthorCompanyExt(id=1228369858614722750, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, companyId=1228369858606334141, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 College of Building Environment Engineering, Zhengzhou University of Light Industry, Zhengzhou 450000, China), AuthorCompanyExt(id=1228369858623111359, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, companyId=1228369858606334141, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 郑州轻工业大学建筑环境工程学院, 郑州 450000)]), AuthorCompany(id=1228369858740551879, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, xref=2, ext=[AuthorCompanyExt(id=1228369858748940487, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, companyId=1228369858740551879, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 Henan Engineering Research Center of Intelligent Buildings and Human Settlements, Zhengzhou 450000, China), AuthorCompanyExt(id=1228369858757329096, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, companyId=1228369858740551879, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 河南省智慧建筑与人居环境工程技术研究中心, 郑州 450000)]), AuthorCompany(id=1228369858853798096, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, xref=3, ext=[AuthorCompanyExt(id=1228369858857992399, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, companyId=1228369858853798096, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 China Construction Technology Group Ltd., Beijing 100013, China), AuthorCompanyExt(id=1228369858866381008, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, companyId=1228369858853798096, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 中国建筑技术集团有限公司, 北京 100013)])], figs=[ArticleFig(id=1228369863975043594, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, language=EN, label=Fig.1, caption=Diagnostic flowchart of the IDBO-HKELM model, figureFileSmall=QhPG3jepUgoAIaC3ZkSb9Q==, figureFileBig=u1Apd/SwCGFzNiY+9sXIRw==, tableContent=null), ArticleFig(id=1228369864096678415, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, language=CN, label=图1, caption=IDBO-HKELM模型诊断流程图, figureFileSmall=QhPG3jepUgoAIaC3ZkSb9Q==, figureFileBig=u1Apd/SwCGFzNiY+9sXIRw==, tableContent=null), ArticleFig(id=1228369864235090456, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, language=EN, label=Fig.2, caption=Convergence curves for different function values, figureFileSmall=SuDjRAHBPFTsEXiLhq25Dg==, figureFileBig=6Oj4aXedLmCSoJXAqocTmw==, tableContent=null), ArticleFig(id=1228369864318976542, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, language=CN, label=图2, caption=不同函数值收敛曲线, figureFileSmall=SuDjRAHBPFTsEXiLhq25Dg==, figureFileBig=6Oj4aXedLmCSoJXAqocTmw==, tableContent=null), ArticleFig(id=1228369864423834147, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, language=EN, label=Fig.3, caption=Confusion matrix of each fault diagnosis model, figureFileSmall=htCFNZmtC6qAsvomqzt1CQ==, figureFileBig=DYFSpZUHpLTV3yK4cbYfUQ==, tableContent=null), ArticleFig(id=1228369864524497452, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, language=CN, label=图3, caption=各故障诊断模型混淆矩阵, figureFileSmall=htCFNZmtC6qAsvomqzt1CQ==, figureFileBig=DYFSpZUHpLTV3yK4cbYfUQ==, tableContent=null), ArticleFig(id=1228369864620966446, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, language=EN, label=Table 1, caption=

Benchmark functions

, figureFileSmall=null, figureFileBig=null, tableContent=
函数 搜索范围 理论值 参数含义
${F}_{1}\left(x\right)=\stackrel{n}{\sum _{i=1}}{x}_{i}^{2}$ [-100,100] 0 $-100\le {x}_{i}\le 100$
${F}_{2}\left(x\right)=\stackrel{n}{\sum _{i=1}}\left|{x}_{i}\right|+\stackrel{n}{\underset{i=1}{\mathrm{\Pi }}}\left|{x}_{i}\right|$ [-10,10] 0 $-10\le {x}_{i}\le 10$
${F}_{3}\left(x\right)=\stackrel{n}{\sum _{i=1}}(\stackrel{j}{\sum _{j=1}}{x}_{i}{)}^{2}$ [-100,100] 0 $-100\le {x}_{i}\le 100$
${F}_{8}\left(x\right)=\stackrel{n}{\sum _{i=1}}-{x}_{i}\mathrm{s}\mathrm{i}\mathrm{n}\sqrt{\left|{x}_{i}\right|}$ [-500,500] -418.98×dim $-500\le {x}_{i}\le 500;$
dim为维度
${F}_{9}\left(x\right)=\stackrel{n}{\sum _{i=1}}[{x}_{i}^{2}-10\mathrm{c}\mathrm{o}\mathrm{s}(2\mathrm{\pi }{x}_{i})+10]$ [-5.12,5.12] 0 $-5.12\le {x}_{i}\le 5.12$
${F}_{10}\left(x\right)=-20\mathrm{e}\mathrm{x}\mathrm{p}\left(-0.2\sqrt{\frac{1}{n}\stackrel{n}{\sum _{i=1}}{x}_{i}^{2}}\right)-\mathrm{e}\mathrm{x}\mathrm{p}\left[\frac{1}{n}\stackrel{n}{\sum _{i=1}}\mathrm{c}\mathrm{o}\mathrm{s}\left(2\mathrm{\pi }{x}_{i}\right)\right]+20+\mathrm{e}$ [-32,32] 0 $-32\le {x}_{i}\le 32$
${F}_{15}\left(x\right)=\stackrel{11}{\sum _{i=1}}{\left[{a}_{i}-\frac{{x}_{1}({b}_{i}^{2}+{b}_{1}{x}_{2})}{{b}_{i}^{2}+{b}_{1}{x}_{3}+{x}_{4}}\right]}^{2}$ [-5,5] 0.148 4 $-5\le {x}_{i}\le 5;$ai为权重参数;
bi为影响分子和分母的线性组合
${F}_{20}\left(x\right)=\stackrel{4}{\sum _{i=1}}{c}_{i}\mathrm{e}\mathrm{x}\mathrm{p}[-\stackrel{6}{\sum _{j=1}}{a}_{ij}({x}_{j}-{p}_{ij}{)}^{2}]$ [0,1] -3.32 $0\le {x}_{i}\le 1;$ci为权重;
aij为惩罚系数;pij为位置参数
), ArticleFig(id=1228369864704852531, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, language=CN, label=表1, caption=

基准测试函数表

, figureFileSmall=null, figureFileBig=null, tableContent=
函数 搜索范围 理论值 参数含义
${F}_{1}\left(x\right)=\stackrel{n}{\sum _{i=1}}{x}_{i}^{2}$ [-100,100] 0 $-100\le {x}_{i}\le 100$
${F}_{2}\left(x\right)=\stackrel{n}{\sum _{i=1}}\left|{x}_{i}\right|+\stackrel{n}{\underset{i=1}{\mathrm{\Pi }}}\left|{x}_{i}\right|$ [-10,10] 0 $-10\le {x}_{i}\le 10$
${F}_{3}\left(x\right)=\stackrel{n}{\sum _{i=1}}(\stackrel{j}{\sum _{j=1}}{x}_{i}{)}^{2}$ [-100,100] 0 $-100\le {x}_{i}\le 100$
${F}_{8}\left(x\right)=\stackrel{n}{\sum _{i=1}}-{x}_{i}\mathrm{s}\mathrm{i}\mathrm{n}\sqrt{\left|{x}_{i}\right|}$ [-500,500] -418.98×dim $-500\le {x}_{i}\le 500;$
dim为维度
${F}_{9}\left(x\right)=\stackrel{n}{\sum _{i=1}}[{x}_{i}^{2}-10\mathrm{c}\mathrm{o}\mathrm{s}(2\mathrm{\pi }{x}_{i})+10]$ [-5.12,5.12] 0 $-5.12\le {x}_{i}\le 5.12$
${F}_{10}\left(x\right)=-20\mathrm{e}\mathrm{x}\mathrm{p}\left(-0.2\sqrt{\frac{1}{n}\stackrel{n}{\sum _{i=1}}{x}_{i}^{2}}\right)-\mathrm{e}\mathrm{x}\mathrm{p}\left[\frac{1}{n}\stackrel{n}{\sum _{i=1}}\mathrm{c}\mathrm{o}\mathrm{s}\left(2\mathrm{\pi }{x}_{i}\right)\right]+20+\mathrm{e}$ [-32,32] 0 $-32\le {x}_{i}\le 32$
${F}_{15}\left(x\right)=\stackrel{11}{\sum _{i=1}}{\left[{a}_{i}-\frac{{x}_{1}({b}_{i}^{2}+{b}_{1}{x}_{2})}{{b}_{i}^{2}+{b}_{1}{x}_{3}+{x}_{4}}\right]}^{2}$ [-5,5] 0.148 4 $-5\le {x}_{i}\le 5;$ai为权重参数;
bi为影响分子和分母的线性组合
${F}_{20}\left(x\right)=\stackrel{4}{\sum _{i=1}}{c}_{i}\mathrm{e}\mathrm{x}\mathrm{p}[-\stackrel{6}{\sum _{j=1}}{a}_{ij}({x}_{j}-{p}_{ij}{)}^{2}]$ [0,1] -3.32 $0\le {x}_{i}\le 1;$ci为权重;
aij为惩罚系数;pij为位置参数
), ArticleFig(id=1228369864784544311, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, language=EN, label=Table 2, caption=

Optimization results of benchmark test functions

, figureFileSmall=null, figureFileBig=null, tableContent=
函数名 指标 GWO SSA DBO IDBO
最优值 1.470 4×10-29 1.337 6×10-231 7.779 1×10-167 0
F1 平均值 1.125 9×10-27 1.454 5×10-55 3.837 9×10-105 0
标准差 1.804 2×10-27 7.965 5×10-55 2.059 8×10-104 0
最优值 3.137 9×10-30 0 6.389 3×10-171 0
F2 平均值 1.050 6×10-28 6.044 3×10-59 1.150 4×10-119 0
标准差 1.668 2×10-28 3.308 6×10-58 6.301 1×10-119 0
最优值 9.592 2×10-18 1.068 7×10-133 1.425 0×10-84 0
F3 平均值 1.230 2×10-16 2.051 5×10-31 2.163 9×10-59 0
标准差 1.125 1×10-16 7.940 1×10-31 8.937 8×10-59 0
最优值 7.939 9×10-55 0 1.318 5×10-304 0
F8 平均值 2.618 1×10-51 5.529 2×10-119 8.333 6×10-197 0
标准差 7.493 2×10-51 2.520 1×10-118 0 0
最优值 5.861 6×10-4 1.105 2×10-4 1.418 4×10-4 3.112 4×10-5
F9 平均值 2.314 7×10-3 1.634 4×10-3 1.015 2×10-3 7.385 8×10-4
标准差 1.113 9×10-3 9.791 8×10-4 7.676 2×10-4 5.360 9×10-4
最优值 5.010×10-107 1.118 7×10-209 1.766 7×10-187 0
F10 平均值 1.512×10-96 7.576 3×10-49 1.306 5×10-119 0
标准差 8.132×10-96 2.885 8×10-48 7.156 0×10-119 0
最优值 1.393 8×10-16 2.308 7×10-110 1.485 6×10-77 0
F15 平均值 4.111 5×10-4 2.559 8×10-9 2.519 6×10-1 0
标准差 5.437 1×10-4 7.428 5×10-9 1.377 8 0
最优值 9.298 2×10-26 0 1.286 5×10-159 0
F20 平均值 3.318 8×10-24 2.842 1×10-24 2.284 0×10-99 0
标准差 1.039 5×10-23 1.425 3×10-23 1.194 1×10-98 0
), ArticleFig(id=1228369864893596222, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, language=CN, label=表2, caption=

基准测试函数优化结果

, figureFileSmall=null, figureFileBig=null, tableContent=
函数名 指标 GWO SSA DBO IDBO
最优值 1.470 4×10-29 1.337 6×10-231 7.779 1×10-167 0
F1 平均值 1.125 9×10-27 1.454 5×10-55 3.837 9×10-105 0
标准差 1.804 2×10-27 7.965 5×10-55 2.059 8×10-104 0
最优值 3.137 9×10-30 0 6.389 3×10-171 0
F2 平均值 1.050 6×10-28 6.044 3×10-59 1.150 4×10-119 0
标准差 1.668 2×10-28 3.308 6×10-58 6.301 1×10-119 0
最优值 9.592 2×10-18 1.068 7×10-133 1.425 0×10-84 0
F3 平均值 1.230 2×10-16 2.051 5×10-31 2.163 9×10-59 0
标准差 1.125 1×10-16 7.940 1×10-31 8.937 8×10-59 0
最优值 7.939 9×10-55 0 1.318 5×10-304 0
F8 平均值 2.618 1×10-51 5.529 2×10-119 8.333 6×10-197 0
标准差 7.493 2×10-51 2.520 1×10-118 0 0
最优值 5.861 6×10-4 1.105 2×10-4 1.418 4×10-4 3.112 4×10-5
F9 平均值 2.314 7×10-3 1.634 4×10-3 1.015 2×10-3 7.385 8×10-4
标准差 1.113 9×10-3 9.791 8×10-4 7.676 2×10-4 5.360 9×10-4
最优值 5.010×10-107 1.118 7×10-209 1.766 7×10-187 0
F10 平均值 1.512×10-96 7.576 3×10-49 1.306 5×10-119 0
标准差 8.132×10-96 2.885 8×10-48 7.156 0×10-119 0
最优值 1.393 8×10-16 2.308 7×10-110 1.485 6×10-77 0
F15 平均值 4.111 5×10-4 2.559 8×10-9 2.519 6×10-1 0
标准差 5.437 1×10-4 7.428 5×10-9 1.377 8 0
最优值 9.298 2×10-26 0 1.286 5×10-159 0
F20 平均值 3.318 8×10-24 2.842 1×10-24 2.284 0×10-99 0
标准差 1.039 5×10-23 1.425 3×10-23 1.194 1×10-98 0
), ArticleFig(id=1228369864973288002, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, language=EN, label=Table 3, caption=

Types of failures

, figureFileSmall=null, figureFileBig=null, tableContent=
故障编号 故障类型 缩写
1 润滑油过量 EO
2 冷凝器结垢 CF
3 制冷剂泄露 RL
4 制冷剂过量 RO
5 不凝气体 NC
6 冷却水不足 FWC
7 冷冻水不足 FWE
), ArticleFig(id=1228369865040396872, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, language=CN, label=表3, caption=

故障类型

, figureFileSmall=null, figureFileBig=null, tableContent=
故障编号 故障类型 缩写
1 润滑油过量 EO
2 冷凝器结垢 CF
3 制冷剂泄露 RL
4 制冷剂过量 RO
5 不凝气体 NC
6 冷却水不足 FWC
7 冷冻水不足 FWE
), ArticleFig(id=1228369865149448784, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, language=EN, label=Table 4, caption=

Schematic diagram of the confusion matrix

, figureFileSmall=null, figureFileBig=null, tableContent=
类别 预测类
1 2 3
真实类 1 a b C
2 d e f
3 g h i
), ArticleFig(id=1228369865250112088, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, language=CN, label=表4, caption=

混淆矩阵示意表

, figureFileSmall=null, figureFileBig=null, tableContent=
类别 预测类
1 2 3
真实类 1 a b C
2 d e f
3 g h i
), ArticleFig(id=1228369865350775388, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, language=EN, label=Table 5, caption=

Fault diagnosis effects of each diagnostic model

, figureFileSmall=null, figureFileBig=null, tableContent=
状态种类 KELM HKELM DBO-HKELM IDBO-HKELM
UR/
%
FAR/
%
UR/
%
FAR/
%
UR/
%
FAR/
%
UR/
%
FAR/
%
NO 7.6 14.4 3.3 5 0.5 0.3 0.1 0.7
CF 8 16.1 1 2.9 0.3 0 0 0
EO 7.3 3.1 0 0 0 0 0 0
NC 11.3 7.6 1.3 1 0 0.3 0.3 0
FWC 37.3 14.2 16.7 9.1 1 1.3 2 1
FWE 0.3 0 0.3 0 0 0.3 0 0
RL 14 7.2 2.7 1 0.7 0 1 0
RO 0 1.6 0.3 2 0 1 0.3 0
准确率/% 90.54 96.76 98.92 99.71
), ArticleFig(id=1228369865455632995, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1228279670324524017, language=CN, label=表5, caption=

各诊断模型的故障诊断效果

, figureFileSmall=null, figureFileBig=null, tableContent=
状态种类 KELM HKELM DBO-HKELM IDBO-HKELM
UR/
%
FAR/
%
UR/
%
FAR/
%
UR/
%
FAR/
%
UR/
%
FAR/
%
NO 7.6 14.4 3.3 5 0.5 0.3 0.1 0.7
CF 8 16.1 1 2.9 0.3 0 0 0
EO 7.3 3.1 0 0 0 0 0 0
NC 11.3 7.6 1.3 1 0 0.3 0.3 0
FWC 37.3 14.2 16.7 9.1 1 1.3 2 1
FWE 0.3 0 0.3 0 0 0.3 0 0
RL 14 7.2 2.7 1 0.7 0 1 0
RO 0 1.6 0.3 2 0 1 0.3 0
准确率/% 90.54 96.76 98.92 99.71
)], attaches=null, journal=Journal(id=1146119176004939786, delFlag=0, nameCn=科学技术与工程, nameEn=Science Technology and Engineering, nameHistory1=null, nameHistory2=null, issn=1671-1815, eissn=, cn=11-4688/T, coden=null, periodic=4, language=CN, oaType=是, ccby=null, superviseOffice=null, ownerOffice=null, pubOffice=null, editorOffice=null, officeType=null, aims=null, clcCode=null, officeProv=null, officeCity=null, officeAddr=null, officeZip=null, officeEmail=null, officePhone=null, editDirector=null, officeDirector=null, officeDirectorPhone=null, officeStaffNum=null, officeEmpNum=null, coverPicUrl=UKU/O7GSka5polgCTkbIIw==, journalPrice=null, startedYear=null, abbrevIsoEn=Sci Technol Eng, journalRemark=null, publicationField=null, createdTime=null, updatedTime=1754445529766, createdBy=null, updatedBy=13701087609, firstLetterCn=S, firstLetterEn=S, subjectCode=Natural Sciences, subjectName=自然科学, subjectCodeEn=Natural Sciences, subjectNameEn=null, picCn=UKU/O7GSka5polgCTkbIIw==, picEn=5hwlULoNwcbj3xUmVi9MAQ==, jcr=null, cjcr=null, exts=[JournalExt(id=1159791870395564357, language=CN, name=科学技术与工程, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=null, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=http://www.stae.com.cn/jsygc/home, createdTime=1754445529793, updatedTime=1754445529793, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=http://www.stae.com.cn/jsygc/site/menus/20090429150146001, submissionAuthorUrl=http://www.stae.com.cn/jsygc/author/login, submissionEditorUrl=http://www.stae.com.cn/jsygc/editor/login, submissionReviewUrl=http://www.stae.com.cn/jsygc/reviewer/login, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1159791870441701702, language=EN, name=Science Technology and Engineering, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=null, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=http://www.stae.com.cn/jsygc/home, createdTime=1754445529804, updatedTime=1754445529804, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=http://www.stae.com.cn/jsygc/author/login, submissionEditorUrl=http://www.stae.com.cn/jsygc/editor/login, submissionReviewUrl=http://www.stae.com.cn/jsygc/reviewer/login, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1146123166801305609, websiteList=[Website(id=1148243202391400884, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146123166801305609, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/kxjsygc/CN, language=CN, createTime=1751692112777, createBy=18614031015, updateTime=1753520965431, updateBy=18614031015, name=科学技术与工程-中文站点, tplId=1146099689490845704, title=科学技术与工程, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1148622798802673703, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=articleTextType, value=kx, createTime=1751782615614, updateTime=1751782615614, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622798781702180, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=banner, value=null, createTime=1751782615609, updateTime=1751782615609, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622798769119267, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=j86gbwi+p0Idkyl5SzIlmQ==, createTime=1751782615606, updateTime=1751782615606, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622798794285094, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1751782615612, updateTime=1751782615612, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622798790090789, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1751782615611, updateTime=1751782615611, creator=18614031015, updator=18614031015)]), Website(id=1155914124811976731, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146123166801305609, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/kxjsygc/EN, language=EN, createTime=1753521003206, createBy=18614031015, updateTime=1753521003206, updateBy=18614031015, name=科学技术与工程-英文站点, tplId=1146101810881728533, title=Science Technology and Engineering, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1155914371227308235, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=articleTextType, value=kx, createTime=1753521061952, updateTime=1753521061952, creator=18614031015, updator=18614031015), WebsiteProps(id=1155914371210531016, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=banner, value=null, createTime=1753521061947, updateTime=1753521061947, creator=18614031015, updator=18614031015), WebsiteProps(id=1155914371202142407, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=j86gbwi+p0Idkyl5SzIlmQ==, createTime=1753521061945, updateTime=1753521061945, creator=18614031015, updator=18614031015), WebsiteProps(id=1155914371223113930, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1753521061950, updateTime=1753521061950, creator=18614031015, updator=18614031015), WebsiteProps(id=1155914371218919625, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1753521061949, updateTime=1753521061949, creator=18614031015, updator=18614031015)])], journalTitle=科学技术与工程, weixinUrl=null, journalUrl=null, iacademicId=null, status=0, seqNo=null, journalTitleEn=Science Technology and Engineering, journalPhotoCn=UKU/O7GSka5polgCTkbIIw==, journalPhotoEn=5hwlULoNwcbj3xUmVi9MAQ==, journalFirstLetter=S, journalRecommend=null, journalNew=null, journalCollection=null, jcrJf=null, cjcrJf=null, jcrJfStr=null, cjcrJfStr=null, submissionFirstDecision=null, sciSubjectClassification=null, casSubjectClassification=null, citeScore=null, totalCitationFrequency=null, icpCode=null, psCode=null, advertisingLicenseCode=null, copyrightInformation=null, country=null, option=null, provinceCode=null, provinceName=null, collectFlag=false), detailUrlCn=https://castjournals.cast.org.cn/joweb/kxjsygc/CN/10.12404/j.issn.1671-1815.2408240, detailUrlEn=https://castjournals.cast.org.cn/joweb/kxjsygc/EN/10.12404/j.issn.1671-1815.2408240, pdfUrlCn=https://castjournals.cast.org.cn/joweb/kxjsygc/CN/PDF/10.12404/j.issn.1671-1815.2408240, pdfUrlEn=https://castjournals.cast.org.cn/joweb/kxjsygc/EN/PDF/10.12404/j.issn.1671-1815.2408240, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于IDBO-HKELM的冷水机组故障诊断方法
收藏切换
PDF下载
王宏 1, 2 , 储盼 1, 2 , 管大松 3, * , 郭洋 1, 2 , 田增瑞 1, 2 , 盛英杰 1, 2
科学技术与工程 | 论文·建筑科学 2025,25(22): 9505-9513
收起
收藏切换
科学技术与工程 | 论文·建筑科学 2025, 25(22): 9505-9513
基于IDBO-HKELM的冷水机组故障诊断方法
全屏
王宏1, 2 , 储盼1, 2, 管大松3, * , 郭洋1, 2, 田增瑞1, 2, 盛英杰1, 2
作者信息
  • 1 郑州轻工业大学建筑环境工程学院, 郑州 450000
  • 2 河南省智慧建筑与人居环境工程技术研究中心, 郑州 450000
  • 3 中国建筑技术集团有限公司, 北京 100013
  • 王宏(1977—),男,汉族,河南平顶山人,硕士,教授。研究方向:智能建筑设备节能优化控制、故障诊断及智慧运维。E-mail:

通讯作者:

* 管大松(1969—),男,汉族,北京人,教授级高级工程师。研究方向:建筑设备节能、智能化控制。E-mail:
Chiller Fault Diagnosis Method Based on IDBO-HKELM
Hong WANG1, 2 , Pan CHU1, 2, Da-song GUAN3, * , Yang GUO1, 2, Zeng-rui TIAN1, 2, Ying-jie SHENG1, 2
Affiliations
  • 1 College of Building Environment Engineering, Zhengzhou University of Light Industry, Zhengzhou 450000, China
  • 2 Henan Engineering Research Center of Intelligent Buildings and Human Settlements, Zhengzhou 450000, China
  • 3 China Construction Technology Group Ltd., Beijing 100013, China
出版时间: 2025-08-08 doi: 10.12404/j.issn.1671-1815.2408240
文章导航
收藏切换

冷水机组作为建筑中的关键设备和主要能耗源,若其发生故障不仅会影响系统的正常运行,还会造成严重的能源浪费。为提升冷水机组系统运行的可靠性,构建了一种多策略改进蜣螂优化算法(improve dung beetle optimizer,IDBO)和混合核极限学习机(hybrid kernel extreme learning machine,HKELM)融合的故障诊断模型,用于实现冷水机组早期故障的精确诊断。该模型首先采用混合核函数提高核极限学习机(kernel extreme learning machine,KELM)的学习能力和泛化性,其次将Bernoulli映射、自适应惯性因子和Levy飞行融合动态权重系数策略用于改进蜣螂优化算法(dung beetle optimizer,DBO),以平衡DBO算法的全局探索性能。最后通过基准函数验证IDBO算法的有效性,利用IDBO算法对HKELM超参数进行优化,从而构建用于冷水机组早期故障诊断的数据驱动模型。通过相关训练仿真和实验验证,所提出的IDBO-HKELM模型对冷水机组的早期故障诊断准确率提高到99.71%,对比其他算法具有明显优势。

冷水机组  /  群体算法  /  HKELM  /  IDBO算法  /  故障诊断

As a key equipment and a major source of energy consumption in a building, chiller plant, if it fails, it will not only affect the normal operation of the system, but also cause serious energy waste. In order to improve the reliability of chiller system operation. A multi-strategy IDBO(improved dung beetle optimization algorithm) combined with a HKELM(hybrid kernel extreme learning machine) fusion fault diagnosis model was constructed to achieve accurate diagnosis of early faults in chiller systems. The model firstly employs hybrid kernel functions to improve the learning ability and generalization of KELM(kernel-extreme learning machine). Secondly, Bernoulli mapping, adaptive inertia factor, and Levy flight fusion dynamic weight coefficients strategies were used to improve the DBO(dung beetle optimization) algorithm in order to balance the global exploration performance of the DBO algorithm. Finally, the effectiveness of the IDBO algorithm was verified by benchmark functions, and the HKELM hyperparameters are optimized using the IDBO algorithm to construct a data-driven model for early fault diagnosis of chiller units. Through relevant training simulations and experimental validation, the accuracy of the proposed IDBO-HKELM model for early fault diagnosis of chillers is improved to 99.71%, which is an obvious advantage over other algorithms.

chiller  /  swarm algorithm  /  HKELM(hybrid kernel extreme learning machine)  /  fault diagnosis  /  IDBO(improved dung beetle optimization) algorithm
王宏, 储盼, 管大松, 郭洋, 田增瑞, 盛英杰. 基于IDBO-HKELM的冷水机组故障诊断方法. 科学技术与工程, 2025 , 25 (22) : 9505 -9513 . DOI: 10.12404/j.issn.1671-1815.2408240
Hong WANG, Pan CHU, Da-song GUAN, Yang GUO, Zeng-rui TIAN, Ying-jie SHENG. Chiller Fault Diagnosis Method Based on IDBO-HKELM[J]. Science Technology and Engineering, 2025 , 25 (22) : 9505 -9513 . DOI: 10.12404/j.issn.1671-1815.2408240
当前,在中国“3060”双碳目标背景下,节能减排与可持续发展是中国建筑行业所面临的巨大挑战,有效降低建筑能耗和提高能源利用率已成为中国建筑行业转型发展的新态势。据统计,空调系统的能源消耗占据建筑总能耗的40%~50%[1],而冷水机组作为空调系统的核心设备,性能下降和出现故障会导致大量的能源浪费。因此,提升冷水机组的故障分类性能,保证冷水机组高效、安全、稳定的工作是提高能源利用率的有效途径。
基于数据驱动的故障诊断方法已经成为一个重要的研究方向[2],为提升故障检测效率和准确性提供了新途径。支持向量机[3-4]和人工神经网络[5-7]等方法已用于建立冷水机组的故障诊断模型,但支持向量机难以训练大规模的样本。相比之下,虽然人工神经网络具备大规模样本学习的能力,但其训练速度较慢。极限学习机(extreme learning machine,ELM)是一种单隐藏层前向神经网络,具有简单、快速学习的特点[8],然而,ELM的输入权重和阈值的隐藏层是随机确定的,这使得建立正确数量的隐藏层具有挑战性[9]。核极限学习机(kernel extreme learning machine,KELM)使用核映射而不是随机映射,降低了网络的复杂度,显著提高了模型的预测和泛化能力[10],但是,KELM通常在应用过程中使用单个核函数,难以适应具有各种数据属性的样本。近年来,通过对不同的核函数进行加权,学者们提出了混合核极限学习机(hybrid kernel extreme learning machine,HKELM),该混合核极限学习机可以解决KELM中的单个核函数难以检索多维样本的问题[11-12]。然而,混合核极限学习机的泛化能力与分类能力却受到核函数类型与超参数的强烈影响。蜣螂优化算法(dung beetle optimizer,DBO)可用于优化混合核极限学习机的超参数,其具有结构简单,调节参数少,操作简单,全局优化能力强等特点。但DBO在寻优过程中,仍存在收敛速度较慢,容易陷入局部最优等问题[13]
针对上述问题,现提出一种多策略改进蜣螂优化算法(improved dung beetle optimizer,IDBO)和HKELM融合的冷水机组故障诊断方法。首先,将 Bernoulli 映射、自适应惯性因子和Levy飞行融合动态权重系数策略引入DBO,提出IDBO算法,通过多个基准函数测试,证明IDBO具有良好的收敛性与稳定性。其次,选择多种核函数组成的HKELM模型,并使用IDBO对HKELM超参数寻优,解决HKELM参数较多且性能受参数影响较大的问题。最后采用ASHRAE 1043-RP的数据集进行对比实验,验证所提出故障诊断模型的优越性。
ELM虽然具有训练速度快、克服了传统梯度算法的局部极小等优点,但在较复杂的分类、回归等非线性模式识别任务往往需要更多的隐层神经元,导致网络的结构非常复杂[14]。针对ELM的不足,研究者们提出了一种核极限学习机[15]。该方法不需要显式地定义映射函数,也不需要设置隐层神经元个数,从而节省了隐层神经元个数优化的时间。核矩阵定义为
${\Omega }_{\mathrm{K}\mathrm{E}\mathrm{L}\mathrm{M}}\left(X\right)=h\left(X\right){H}^{\mathrm{T}}$
式(1)中:h(X)为隐藏层的输入到输出的映射;X为输入数据矩阵;H为隐藏层输出矩阵。
矩阵中第i行和第j列的元素表示为
${\Omega }_{\mathrm{K}\mathrm{E}\mathrm{L}\mathrm{M}ij}({x}_{i},{x}_{j})=h\left({x}_{i}\right)h\left({x}_{j}\right)\triangleq K\left({x}_{i}{x}_{j}\right)$
式(2)中:${\Omega }_{\mathrm{K}\mathrm{E}\mathrm{L}\mathrm{M}ij}({x}_{i},{x}_{j})$表示核矩阵中的元素,衡量输入样本xixj间的相似性;h(xi)和h(xj)分别为输入数据xixj映射到高维空间的表示;$\stackrel{\mathrm{\Delta }}{=}$表示等价;K(xixj)为数据xixj在高维特征空间的内积。
$\begin{array}{l}{f}_{KELM}\left(X\right)=\left[K\right(X{x}_{1})\dots K(X{x}_{N}\left)\right]\times \\ [{\Omega }_{KELM}{\left(X\right)]}^{-1}Y\end{array}$
式(3)中:fKELM(X)为模型KELM的输出;K(Xx1)K(XxN)为输入数据X和样本x1xN在特征空间的相似性;Y为目标输出矩阵。
引入正则化后,公式为
$\begin{array}{l}{f}_{KELM}\left(X\right)=\left[K\right(X{x}_{1})\dots K(X{x}_{\mathrm{N}}\left)\right]\times \\ {\left[\frac{I}{C}+{\Omega }_{KELM}\left(X\right)\right]}^{-1}Y\end{array}$
KELM的网络输出fKELM(Xk)可写为
$\begin{array}{l}{f}_{KELM}\left({X}_{k}\right)=\stackrel{n}{\sum _{k=1}}{\Omega }_{\mathrm{K}\mathrm{E}\mathrm{L}\mathrm{M}}\left(X{x}_{k}\right)[{\left(\frac{I}{C}\right)}_{k}+\\ {\Omega }_{\mathrm{K}\mathrm{E}\mathrm{L}\mathrm{M}}\left(X{x}_{k}\right)]{}^{-1}{Y}_{k}\end{array}$
式(5)中:${f}_{\mathrm{K}\mathrm{E}\mathrm{L}\mathrm{M}}\left({X}_{k}\right)$为KELM模型对输入数据X中第k个样本的函数输出;${\Omega }_{KELM}\left(X{x}_{k}\right)$为核矩阵;C为正则化系数;I为单位矩阵。
KELM通过使用核函数将低维空间转化为高维空间,大大降低了网络的复杂性,提高了预测和泛化能力。然而,典型的KELM算法的单核函数难以处理各种样本数据,由此采用了混合核极限学习机的方法。通过引入混合核函数,可以弥补单核ELM的缺陷,解决泛化能力差和预测精度低等问题。
核函数的类型很多,综合常见核函数的特性,权衡模型精度与计算复杂度。本文采用将多项式函数(polynomial function,Poly)和径向基函数(radial basis function,Rbf)进行加权组合的混合核极限学习机,并构造其两种组合的等效核函数。使模型可以兼具Poly核函数与Rbf核函数的优点,进一步提高KELM的学习能力和泛化性能[16]。相较于其他核函数得到更好的泛化性能,其输出模型为
$f\left(x\right)=h\left(x\right)\beta =H\beta $
式(6)中:x为样本数据;f(x)为输出;h(x)为隐含层输入;H为特征映射矩阵;β为输出权重矩阵。
$\beta ={H}^{\mathrm{T}}{\left(H{H}^{\mathrm{T}}+\frac{I}{C}\right)}^{-1}A$
式(7)中:A为训练集目标矩阵。
KELM核函数定义为
$\left\{\begin{array}{l}\Omega =H{H}^{\mathrm{T}}\\ {\Omega }_{i,j}=h\left({x}_{i}\right)h\left({x}_{j}\right)=K({x}_{i},{x}_{j})\end{array}\right.$
式(8)中:$\Omega $表示矩阵;${\Omega }_{i,j}$为核矩阵中的第i行和第j列的元素。
因此可得出输出模型为
$\begin{array}{l}f\left(x\right)=\left[\begin{array}{l}K(x,{x}_{1})\\ K(x,{x}_{2})\\ ︙\\ K(x,{x}_{\mathrm{N}})\end{array}\right]A{\left(\frac{I}{C}+\Omega \right)}^{-1}A\\ =\left[\begin{array}{l}K(x,{x}_{1})\\ K(x,{x}_{2})\\ ︙\\ K(x,{x}_{\mathrm{N}})\end{array}\right]A\beta \end{array}$
采用的混合核函数可以表示为
${K}_{\mathrm{m}\mathrm{i}\mathrm{x}}(x,{x}_{j})=r{K}_{\mathrm{p}\mathrm{o}\mathrm{l}\mathrm{y}}(x,{x}_{i})+(1-r){K}_{\mathrm{r}\mathrm{b}\mathrm{f}}(x,{x}_{i}),r\in \left[\mathrm{0,1}\right]$
式(10)中:KpolyKrbf 分别为Poly和Rbf的核函数;r为线性平衡因子。
${K}_{\mathrm{p}\mathrm{o}\mathrm{l}\mathrm{y}}({x}_{i},{x}_{j})=(x,{x}_{i}+{\mathrm{c}}_{1}{)}^{d}$
${K}_{\mathrm{r}\mathrm{b}\mathrm{f}}\left({x}_{i},{x}_{j}\right)=\mathrm{e}\mathrm{x}\mathrm{p}\left(-\frac{\Vert {x}_{i}-{x}_{j}{\Vert }^{2}}{{\sigma }^{2}}\right)$
式中:σc1d为Poly核函数与Rbf核函数的核参数。
由此可见,HKELM需求参数较多,故需要对模型中的参数进行寻优,提升分类性能。
Xue等[17]受到自然界中蜣螂的生存行为启发,提出了DBO算法。该算法模拟了蜣螂的滚球、跳舞、觅食、偷窃和繁殖行为。
在滚动过程中,滚球蜣螂依靠天气线索进行导航,以确保粪球沿直线方向滚动。蜣螂在滚动时位置变化的表示为
${x}_{i}(t+1)={x}_{i}\left(t\right)+\alpha k{x}_{i}(t-1)+b\mathrm{\Delta }x$
$\mathrm{\Delta }x=\left|{x}_{i}\left(t\right)-{X}^{\mathrm{w}}\right|$
式中:xi(t)为迭代所对应第i只蜣螂的位置信息;$\alpha $为是否偏离原来位置;k为偏转系数;Xw为整体的最差位置;$\mathrm{\Delta }x$为模拟自然光的强弱。
蜣螂产卵时的迭代位置更新公式为
$\begin{array}{l}{B}_{i}(t+1)={X}^{\mathrm{*}}+{b}_{1}\left[{B}_{i}\right(t)-{L}_{\mathrm{b}}^{\mathrm{*}}]+\\ {b}_{2}\left[{B}_{i}\right(t)-{U}_{\mathrm{b}}^{\mathrm{*}}]\end{array}$
式(15)中:X*为局部最佳位置;Bi(t)为第t次迭代时第i个卵球的位置;L*bU*b为产卵区域的下界和上界;b1b2为两个独立大小为1×d的随机量;d为解决问题的维数。
DBO在寻优过程中,仍存在收敛速度较慢,容易陷入局部最优等问题。因此,为提升该算法的精度和收敛性能,提出了一种多策略改进蜣螂优化算法,从而对HKELM模型中的参数进行寻优,提升其分类性能。
Bernoulli映射是一种混沌系统,其轨迹对初始条件极为敏感,微小的初始变化会迅速导致不同的结果[18]。因此本文研究中采用Bernoulli混沌映射,通过遵循特定的规律来遍历搜索空间,避免了初始化种群分布不均匀的问题。Bernoulli映射模型为
${Z}_{t+1}=\left\{\begin{array}{ll}\frac{{Z}_{t}}{1-\lambda },& {Z}_{t}\in (\mathrm{0,1}-\lambda )\\ \frac{{Z}_{t}-1+\lambda }{\lambda },& {Z}_{t}\in (\mathrm{0,1}-\lambda )\end{array}\right.$
${X}_{td}={X}_{\mathrm{L}}+({X}_{\mathrm{U}}-{X}_{\mathrm{L}}){Z}_{td}$
式中:Zt为产生的第t代混沌序列的当前值;Zt+1为在第t+1代时所产生的混沌值;λ为调节系数;Xtd为第t个元素在d维的位置;${X}_{\mathrm{U}}、{X}_{\mathrm{L}}$为搜索空间的上、下限;Ztd为第t个元素在d维上产生的混沌值。
钻出地面寻找食物的为小蜣螂。其最佳觅食区的边界定义为
$\begin{array}{l}{{L}^{\mathrm{b}}}_{\mathrm{b}}=\mathrm{m}\mathrm{a}\mathrm{x}\left[{X}^{\mathrm{b}}\right(1-R),{L}_{\mathrm{b}}]\\ {{U}^{\mathrm{b}}}_{\mathrm{b}}=\mathrm{m}\mathrm{i}\mathrm{n}\left[{X}^{\mathrm{b}}\right(1-R),{U}_{\mathrm{b}}]\end{array}$
式(18)中:Xb为最优位置;LbbUbb分别为最佳寻找食物范围的下限和上限;LbUb分别为寻找空间下限和上限;$R=1-(t/{T}_{\mathrm{m}\mathrm{a}\mathrm{x}});t$为当前迭代次数;Tmax为最大迭代次数。
位置更新为
$\begin{array}{l}{x}_{i}(t+1)={x}_{i}\left(t\right)+{C}_{1}\left[{x}_{i}\right(t)-{{L}^{\mathrm{b}}}_{\mathrm{b}})]+\\ {C}_{2}\left[{x}_{i}\right(t)-{{U}^{\mathrm{b}}}_{\mathrm{b}}]\end{array}$
但觅食小蜣螂在面对位置更新陷入局部最优时,会使得种群不再进行遍历搜索。为了解决这一问题,本文在此阶段引入了自适应因子mn,算法表达式为
$\left\{\begin{array}{l}m=2{r}_{\mathrm{a}\mathrm{n}\mathrm{d}}-1\\ n=\mathrm{e}\mathrm{x}\mathrm{p}\left\{5\mathrm{c}\mathrm{o}\mathrm{s}\left[\mathrm{\pi }\left(\frac{1-t}{{T}_{\mathrm{m}\mathrm{a}\mathrm{x}}}\right)\right]\right\}\end{array}\right.$
$\begin{aligned}\boldsymbol{x}_{i}(t+1) & =\exp(mn)\cos(2\pi n)\boldsymbol{x}_{i}(t)+ \\ & C_{1}[\boldsymbol{x}_{i}(t)-\boldsymbol{L}_{\mathrm{b}}^{\mathrm{b}}]+\boldsymbol{C}_{2}[\boldsymbol{x}_{i}(t)-\boldsymbol{U}_{\mathrm{b}}^{\mathrm{b}}]\end{aligned}$
式中:rand为0~1的随机数;C1为服从正态分布的随机数;C2为0~1范围内的随机向量。
若所有蜣螂个体都集中在当前最优解附近,随着迭代的继续,算法会陷入停滞,此时得到的解并非全局最优。为了克服算法易陷入局部最优的问题,本文研究将莱维(Levy)飞行引入到偷窃蜣螂的位置信息更新过程中[19],在加强局部邻域搜索的同时,也可探测到算法空间中的较远解。
Levy飞行的公式为
$L=\frac{\tau u}{\left(\left|{v}^{1/\beta }\right|\right)}$
$u~N(0,{\sigma }^{2}),v~N\left(\mathrm{0,1}\right)$
$\sigma ={\left[\frac{\Gamma (1+\beta )\mathrm{s}\mathrm{i}\mathrm{n}\frac{\mathrm{\pi }\beta }{2}}{\Gamma \left(\frac{1+\beta }{2}\right)\beta \left({2}^{\beta -1}\right)}\right]}^{1/\beta }$
式中:uv为服从正太分布的随机数;$\tau $为(0,1)中随机值:β为设置为(0,2)的随机值;Γ为伽马函数。
为解决在迭代时陷入局部最优这一问题,引入动态权重系数。
$\omega =\frac{\mu -{\mu }^{-1}}{\mu +{\mu }^{-1}}$
$\mu =\mathrm{e}\mathrm{x}\mathrm{p}\left[2\left(1-\frac{t}{{T}_{\mathrm{m}\mathrm{a}\mathrm{x}}}\right)\right]$
更新后的迭代公式为
$\begin{array}{l}{x}_{i}(t+1)=L{x}^{\mathrm{b}}+Sg\omega [\left|{x}_{i}\left(t\right)-{X}^{\mathrm{*}}\right|+\\ {x}_{i}\left(t\right)-{X}^{\mathrm{b}}]\end{array}$
式中:S为常数值;g为随机向量;Xb为最佳位置。
IDBO-HKELM模型的故障诊断流程图如图1所示,具体步骤如下。
步骤1 获取并划分故障数据。
步骤2 设定种群规模、最大迭代次数。
步骤3 通过式(17)初始化种群。
步骤4 计算种群中个体适应度值。
步骤5 根据式(13)、式(15)、式(19)、式(21)和式(27)更新滚球行为、繁殖行为、觅食行为和偷窃行为的个体位置,获得更新后的种群,并计算新位置的适应度值,若前者更优则保持原个体位置不变,若当前更优则更新为当前个体。
步骤6 判断是否满足最大迭代数,若满足则输入到最优HKELM模型,若不满足则返回步骤4。
步骤7 将获得最优值的参数输入HKELM模型中。
步骤8 输出最终结果并结束。
为验证本文所提出IDBO算法改进的有效性,采用基准测试函数进行实验,并将麻雀搜索算法(sparrow search slgorithm,SSA)、灰狼优化算法(grey wolf optimizer,GWO)与原始蜣螂优化算法作为对照组。表1为本文选择的基准测试函数,其中F1~F3为单峰测试函数、F8~F10为多峰测试函数、F15F20为复合测试函数。
每个算法种群规模设置为30,迭代次数为500,独立运行30次,分别求其最优值、平均值和标准差。最优值用于评价算法寻优能力,平均值用于评价算法收敛精度,标准差用于评价算法寻优的稳定性。具体测试结果如表2所示。
算法的平均适应度收敛曲线如图2所示,IDBO算法在收敛精度和速度上明显优于其他3种对照组。特别是在单峰测试函数F1~F3、多峰函数F8F10以及复合函数F15F20中,IDBO都展示出最高的收敛速度和最佳的稳定性。对于多峰基准函数F9来说,在收敛速度相同的情况下,IDBO算法在收敛精度上也优于其他3种对照组。此外,由图2收敛曲线可看出,IDBO算法避免了种群分布不均匀的问题,证明了在初始化阶段引入Bernoulli混沌映射的有效性;同时也可看出IDBO算法展现出最快的收敛速度和精度,证明了在觅食阶段引入自适应因子以及在偷窃阶段引入莱维飞行融合动态权重系数策略的有效性,使得算法跳出局部最优,增强了蜣螂快速探索的能力。由此说明,IDBO算法具有优越的全局探索能力和跳出局部最优的开发能力。
使用ASHRE RP-1043报告中冷水机组的运行数据作为实验数据集。实验系统共有冷冻水回路、冷却水回路、热水回路、城市供水和蒸汽供水5条回路,模拟了冷水机组的正常运行状态和7种典型故障类别,故障类型如表3所示。
另外RP-1043数据集对不同的故障划分了4个等级,依次由轻微到严重(SL1、SL2、SL3、SL4)。本文研究使用了最低故障等级SL1的数据作为样本,以更准确地反映冷水机组的运行和早期微故障问题。从表3的7种故障类型中各选取了1 000条,正常运行数据选取4 000条,共11 000条数据构建本文数据集样本,按7∶3的比例划分为训练集和测试集。为避免数据特征对故障不敏感,后续影响实验准确度。本文研究选择了16个传感器成本较低且对故障敏感度较高的特征进行分析[20]
多分类混淆矩阵作为故障诊断的性能评估依据,具体如表4所示,其中字母a~i表示分类的个数。根据该混淆矩阵,定义模型总体准确率(Acc)、单个类别故障诊断准确率(AR)、误报率(FAR)、漏报率(UR)。
故障模型总体准确率(Acc)定义为
Acc=$\frac{a+e+i}{a+b+c+d+e+f+g+h+i}$×100
以类别1为例,单个类别故障诊断AR
${A}_{\mathrm{R}}=\frac{a}{a+b+c}\times 100$
单个类别的诊断UR定义为
${U}_{\mathrm{R}}=\frac{b+c}{a+b+c}\times 100$
单个类别的FAR定义为
${F}_{\mathrm{A}\mathrm{R}}=\frac{d+g}{a+d+g}\times 100$
为了验证本文所提出的故障诊断模型的有效性,设置了3个对照组:KELM、HKELM、DBO-HKELM。KELM、HKELM、DBO-HKELM、IDBO-HKELM的混淆矩阵如图3所示,表5为各算法诊断不同故障类型的误报率(FAR)、漏报率(UR)。
表5可知,KELM、HKELM、DBO-HKELM和IDBO-HKELM模型的准确率分别为90.54%、96.76%、98.92%和99.71%,可见HKELM比KELM具备更好的学习能力和泛化性能。其中经过IDBO优化后的HKELM模型准确率最高,较其他几种故障诊断模型分别提升了9.17%、2.95%、0.79%。尤其针对EO、FWE、RO 3种故障类型,IDBO-HKELM可达到100%准确率。这表明了经过本文改进的IDBO优化HKELM模型的准确性大幅提高,验证了IDBO具有良好的寻优能力,进一步证明了改进算法的优越性以及本文提出的IDBO-HKELM模型可以更好地针对冷水机组早期故障进行诊断分类。
针对冷水机组早期故障的识别问题,提出了一种基于IDBO-HKELM的故障诊断方案,得出如下结论。
(1)将HKELM与KELM进行实验对比,证明了poly核函数与rbf核函数相结合的HKELM提高了KELM的学习能力和泛化性能。
(2)本文提出的融合Bernoulli混沌映射初始化、自适应惯性因子和Levy飞行融合动态权重系数策略的IDBO改进算法,通过基准函数测试,相较于改进前的DBO算法与SSA算法、GWO算法收敛精度和速度得到明显优化。
(3)通过IDBO算法对HKELM模型超参数的优化,实验结果表明:本文设计的IDBO-HKELM的模型对冷水机组早期故障诊断的整体准确率高达99.71%;针对EO、FWE、RO 3种故障类型,IDBO-HKELM可达到100%准确率。验证了本文方案在解决冷水机组故障分类性能上的有效性。
  • 河南省科技攻关项目(232102211050)
  • 河南省科技攻关项目(252102241002)
  • 郑州轻工业大学产业技术研究院2024年度概念验证项目(YJYGNYZ-2024005)
  • 郑州轻工业大学博士科研基金资助项目(13501050025)
参考文献 引证文献
排序方式:
[1]
Kim W, Katipamula S. A review of fault detection and diagnostics methods for building systems[J]. Science and Technology for the Built Environment, 2018, 24(1): 3-21.
[2]
文成林, 吕菲亚, 包哲静, 等. 基于数据驱动的微小故障诊断方法综述[J]. 自动化学报, 2016, 42(9): 1285-1299.
Wen Chenglin, Lu Feiya, Bao Zhejing, et al. A review of data-driven methods for diagnosis of small faults[J]. Acta Automatica Sinica, 2016, 42(9): 1285-1299.
[3]
戴洪德, 张志亮, 崔伟成, 等. 基于SSA-SVM的航空电弧故障检测[J]. 科学技术与工程, 2024, 24(13): 5626-5633.
Dai Hongde, Zhang Zhiliang, Cui Weicheng, et al. Aerial arc fault detection based on SSA-SVM[J]. Science Technology and Engineering, 2024, 24(13): 5626-5633.
[4]
宋玉生, 刘光宇, 朱凌, 等. 改进的灰狼优化算法在SVM参数优化中的应用[J]. 传感器与微系统, 2022, 41(9): 151-155.
Song Yusheng, Liu Guangyu, Zhu Ling, et al. Application of improved GWO algorithm in SVM parameter optimization[J]. Transducer and Microsystem Technologies, 2022, 41(9): 151-155.
[5]
宋旭彤, 刘卓元, 金毅, 等. 基于CNN和预处理机制的球磨机故障诊断方法[J]. 传感器与微系统, 2022, 41(11): 134-137, 142.
Song Xutong, Liu Zhuoyuan, Jin Yi, et al. Fault diagnosis method for ball mill based on CNN and preprocessing mechanism[J]. Transducer and Microsystem Technologies, 2022, 41(11): 134-137, 142.
[6]
赵志宏, 李春秀, 窦广鉴, 等. 基于MTF-CNN的轴承故障诊断研究[J]. 振动与冲击, 2023, 42(2): 126-131.
Zhao Zhihong, Li Chunxiu, Dou Guangjian, et al. Bearing fault dia-gnosis method based on MTF-CNN[J]. Journal of Vibration and Shock, 2023, 42(2): 126-131.
[7]
吴经锋, 王文森, 张璐, 等. 基于CNN算法的并联电抗器机械故障诊断方法[J]. 电工电能新技术, 2022, 41(12): 72-80.
Wu Jingfeng, Wang Wensen, Zhang Lu, et al. Mechanical fault dia-gnosis methodof shunt reactor based on CNN algorithm[J]. Advanced Technology of Electrical Engineering and Energy, 2022, 41(12): 72-80.
[8]
Huang G B, Zhu Q Y, Siew C K. Extreme learning machine: a new learning scheme of feedforward neural networks[J]. IEEE Internation Joint Conference on Neural Networks, 2004, 2: 985-990.
[9]
Cambria E, Huang G B, Kasun L L C. Extreme learning machines[J]. IEEE Intelligent Systems, 2013, 28(6): 30-59.
[10]
Deng C W, Huang G B, Xu J, et al. Extreme learning machines: new trends and applications[J]. Science China Information Sciences, 2015, 58(2): 1-16.
[11]
Tang J, Deng C, Huang G B. Extreme learning machine for multilayer perceptron[J]. IEEE Transactions on Neural Networks & Learning Systems, 2017, 2017: 809-821.
[12]
李花宁, 吴生彪, 冯丽, 等. 基于AdaBoost-WOA-HKELM的下肢关节角度预测[J]. 机电工程技术, 2024, 53(4): 36-40.
Li Huaning, Wu Shengbiao, Feng Li, et al. Lower limb joint angle prediction based on AdaBoost-WOA-HKELM[J]. Mechatro-nics Engineering Technology, 2024, 53(4): 36-40.
[13]
赵鑫, 王东丽, 彭泓, 等. 基于多策略改进蜣螂算法优化的变压器故障诊断[J]. 电力系统保护与控制, 2024, 52(6): 120-130.
Zhao Xin, Wang Dongli, Peng Hong, et al. Transformer fault diagnosis based on multi-strategy improved dung beetle algorithm optimization[J]. Power System Protection and Control, 2024, 52(6): 120-130.
[14]
范小虎, 赵爱罡, 许强, 等. 基于ELM-SVR模型的装备关键部件寿命预测[J]. 科学技术与工程, 2023, 23(2): 640-647.
Fan Xiaohu, Zhao Aigang, Xu Qiang, et al. Life prediction of key equipment components based on ELM-SVR model[J]. Science Technology and Engineering, 2023, 23(2): 640-647.
[15]
宋永献, 王祥祥, 李媛媛, 等. 基于核极限学习机的下肢关节力矩预测方法[J]. 科学技术与工程, 2024, 24(11): 4599-4606.
Song Yongxian, Wang Xiangxiang, Li Yuanyuan, et al. A method for lower limb joint moment prediction based on nuclear limit learning machine[J]. Science Technology and Engineering, 2024, 24(11): 4599-4606.
[16]
李彦阳, 王金东, 曲孝海. 基于GMPE和GWO-MKELM算法的往复压缩机轴承故障诊断[J]. 科学技术与工程, 2024, 24(23): 9842-9847.
Li Yanyang, Wang Jindong, Qu Xiaohai. Fault diagnosis of reciprocating compressor bearings based on GMPE and GWO-MKELM algorithms[J]. Science Technology and Engineering, 2024, 24(23): 9842-9847.
[17]
Xue J, Shen B. Dung beetle optimizer: a new meta-heuristic algorithm for global optimization[J]. The Journal of Supercomputing, 2023, 79(7): 7305-7336.
[18]
汤兆平, 孟鑫, 孙剑萍, 等. 基于改进鲸鱼优化算法的码垛机器人时间最优轨迹规划[J]. 科学技术与工程, 2024, 24(14): 5882-5891.
Tang Zhaoping, Meng Xin, Sun Jianping, et al. Time-optimal trajectory planning for palletizing robot based on improved whaleoptimization algorithm[J]. Science Technology and Engineering, 2024, 24(14): 5882-5891.
[19]
王宏, 袁伯阳, 韩晨, 等. 基于机器学习的冷水机组早期故障诊断[J]. 低温与超导, 2023, 51(11): 96-102.
Wang Hong, Yuan Boyang, Han Chen, et al. Early fault diagnosis of chiller based on machine learning[J]. Cryogenics and Superconductivity, 2023, 51(11): 96-102.
[20]
Han H, Gu B, Wang T, et al. Important sensors for chiller fault detection and diagnosis(FDD) from the perspective of feature selection and machine learning[J]. International Journal of Refrigeration, 2011, 34(2): 586-599.
2025年第25卷第22期
PDF下载
128
52
引用本文
BibTeX
文章信息
doi: 10.12404/j.issn.1671-1815.2408240
  • 接收时间:2024-11-05
  • 首发时间:2026-02-11
  • 出版时间:2025-08-08
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2024-11-05
  • 修回日期:2025-05-15
基金
河南省科技攻关项目(232102211050)
河南省科技攻关项目(252102241002)
郑州轻工业大学产业技术研究院2024年度概念验证项目(YJYGNYZ-2024005)
郑州轻工业大学博士科研基金资助项目(13501050025)
作者信息
    1 郑州轻工业大学建筑环境工程学院, 郑州 450000
    2 河南省智慧建筑与人居环境工程技术研究中心, 郑州 450000
    3 中国建筑技术集团有限公司, 北京 100013

通讯作者:

* 管大松(1969—),男,汉族,北京人,教授级高级工程师。研究方向:建筑设备节能、智能化控制。E-mail:
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/kxjsygc/CN/10.12404/j.issn.1671-1815.2408240
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