Article(id=1239215313082962399, tenantId=1146029695717560320, journalId=1238823019242635269, issueId=1239215308985136031, articleNumber=null, orderNo=null, doi=10.12465/j.issn.0253-4339.2025.04.061, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=research-article, receivedDate=1706630400000, receivedDateStr=2024-01-31, revisedDate=1711555200000, revisedDateStr=2024-03-28, acceptedDate=1716307200000, acceptedDateStr=2024-05-22, onlineDate=1773381554146, onlineDateStr=2026-03-13, pubDate=1755273600000, pubDateStr=2025-08-16, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1773381554146, onlineIssueDateStr=2026-03-13, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1773381554146, creator=13701087609, updateTime=1773381554146, updator=13701087609, issue=Issue{id=1239215308985136031, tenantId=1146029695717560320, journalId=1238823019242635269, year='2025', volume='46', issue='4', pageStart='1', pageEnd='170', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1773381553169, creator=13701087609, updateTime=1773381893131, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1239216734947824534, tenantId=1146029695717560320, journalId=1238823019242635269, issueId=1239215308985136031, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1239216734947824535, tenantId=1146029695717560320, journalId=1238823019242635269, issueId=1239215308985136031, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=61, endPage=74, ext={EN=ArticleExt(id=1239215314039263749, articleId=1239215313082962399, tenantId=1146029695717560320, journalId=1238823019242635269, language=EN, title=Comparison of High Adaptability and Low-Cost Intelligent Recognition Method for Evaporator Frosting Status Based on Image Texture Features, columnId=null, journalTitle=Journal of Refrigeration, columnName=null, runingTitle=null, highlight=null, articleAbstract=

Unnecessary or delayed defrosting results in increased energy consumption, reduced stability, and increased failure rates in refrigeration and heat pump units. Accurately identifying the frost status and timely defrosting are important for improving the performance of refrigeration and heat pumps. Frost status identification methods based on digital and intelligent technologies have shown significant potential. However, existing technologies have significantly reduced accuracy in complex real-world conditions and require urgent improvement. In this paper, we proposed an intelligent recognition method based on the texture features of evaporator surface images. We used a gray-level co-occurrence matrix to extract texture features and combine them with the extreme learning machine optimized by the sparrow algorithm for classification. This is expected to mitigate the impact of external conditions, such as shooting angles and light intensity, thereby achieving strong adaptability. An experimental setup was established to collect 4 125 images of the evaporator in three different frost states under complex working conditions, and the proposed method was validated and compared. The results showed that the accuracy of the method in identifying different conditions can reach 95%, which is significantly higher than that of existing methods by 5-35%. Furthermore, this method has high stability and low cost thereby demonstrating great potential for practical applications.

, correspAuthors=null, authorNote=null, correspAuthorsNote=
Han Xiaohong, female, professor, doctoral advisor, Institute of Refrigeration and Cryogenics, Zhejiang University, 86-571-87953944, E-mail: . Research fields: high heat flux heat dissipation technology (mainly heat pipe heat dissipation, microchannel heat dissipation and immersion liquid cooling technology), immersion liquid cooling of power battery, refrigerant replacement technology, refrigerant leakage, refrigerant recovery, recycling and reclamation.
, 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=Yingjie Xu, Hengrui Zhang, Yunyu Liu, Xiaoxiao Zhou, Xiaohong Han, Guangming Chen), CN=ArticleExt(id=1239215320305554276, articleId=1239215313082962399, tenantId=1146029695717560320, journalId=1238823019242635269, language=CN, title=基于图像纹理特征的高适应性低成本蒸发器结霜状态智能识别方法对比, columnId=0, journalTitle=制冷学报, columnName=, runingTitle=null, highlight=null, articleAbstract=

误除霜或除霜不及时将导致制冷/热泵机组能耗增加、稳定性降低、故障率提升。精准识别结霜状态从而及时除霜是提升制冷/热泵性能的重要方向。基于数字/智能技术的结霜状态识别方法展现出较好的潜力,但现有技术在实际应用的复杂条件下,识别准确率明显降低,亟待改善。基于此,以蒸发器表面图像的纹理特征为切入点,提出以灰度共生矩阵提取纹理特征并结合麻雀算法优化后的极限学习机进行分类的智能识别方法。有望规避拍摄角度、光照强度等外部条件的影响,实现较强的适应性。建立实验装置,实验采集4 125张复杂工况下3种结霜状态的蒸发器图像样本,对新方法进行了验证和对比研究。结果表明,该方法在不同工况下识别准确率可接近或高于95%,显著高于现有的方法5%~35%。该方法的稳定性较高,成本较低,表现出良好的应用潜力。

, correspAuthors=null, authorNote=null, correspAuthorsNote=
韩晓红,女,教授,博士生导师,浙江大学制冷与低温研究所,(0571)87953944,E-mail:。研究方向:高热流散热技术(主要指热管散热、微通道散热及浸没液体冷却技术)、动力电池浸没液冷热管理技术、制冷剂替代技术、制冷剂泄漏与回收及再利用技术。
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=giFcAFNgRhV/hFdpjN62TQ==, magXml=YNZmuF6dcw1G7coz9VD0qQ==, pdfUrl=null, pdf=QDKd24A7DJbb0yoRJJwY6w==, pdfFileSize=22632817, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=vwjTn70PKiSd0H8nhER5hQ==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=ptb124HPyXRhocohAZer1g==, mapNumber=null, authorCompany=null, fund=null, authors=null, authorsList=徐英杰, 张恒瑞, 柳云宇, 周晓晓, 韩晓红, 陈光明)}, authors=[Author(id=1239232335535722570, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, orderNo=0, 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=1239232335611220046, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, authorId=1239232335535722570, language=EN, stringName=Yingjie Xu, firstName=Yingjie, middleName=null, lastName=Xu, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.College of Mechanical Engineering, Zhejiang University of Technology, Hangzhou, 310023, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1239232335690911828, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, authorId=1239232335535722570, language=CN, stringName=徐英杰, firstName=英杰, middleName=null, lastName=徐, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1浙江工业大学机械工程学院 杭州 310023, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1239232335242121263, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, xref=1., ext=[AuthorCompanyExt(id=1239232335250509872, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, companyId=1239232335242121263, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.College of Mechanical Engineering, Zhejiang University of Technology, Hangzhou, 310023, China), AuthorCompanyExt(id=1239232335254704177, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, companyId=1239232335242121263, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1浙江工业大学机械工程学院 杭州 310023)])]), Author(id=1239232335787380825, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, 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=1239232335875461214, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, authorId=1239232335787380825, language=EN, stringName=Hengrui Zhang, firstName=Hengrui, middleName=null, lastName=Zhang, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.College of Mechanical Engineering, Zhejiang University of Technology, Hangzhou, 310023, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1239232335942570085, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, authorId=1239232335787380825, language=CN, stringName=张恒瑞, firstName=恒瑞, middleName=null, lastName=张, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1浙江工业大学机械工程学院 杭州 310023, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1239232335242121263, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, xref=1., ext=[AuthorCompanyExt(id=1239232335250509872, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, companyId=1239232335242121263, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.College of Mechanical Engineering, Zhejiang University of Technology, Hangzhou, 310023, China), AuthorCompanyExt(id=1239232335254704177, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, companyId=1239232335242121263, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1浙江工业大学机械工程学院 杭州 310023)])]), Author(id=1239232336013873258, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, 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=1239232336093565039, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, authorId=1239232336013873258, language=EN, stringName=Yunyu Liu, firstName=Yunyu, middleName=null, lastName=Liu, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.College of Mechanical Engineering, Zhejiang University of Technology, Hangzhou, 310023, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1239232336190034038, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, authorId=1239232336013873258, language=CN, stringName=柳云宇, firstName=云宇, middleName=null, lastName=柳, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1浙江工业大学机械工程学院 杭州 310023, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1239232335242121263, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, xref=1., ext=[AuthorCompanyExt(id=1239232335250509872, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, companyId=1239232335242121263, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.College of Mechanical Engineering, Zhejiang University of Technology, Hangzhou, 310023, China), AuthorCompanyExt(id=1239232335254704177, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, companyId=1239232335242121263, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1浙江工业大学机械工程学院 杭州 310023)])]), Author(id=1239232336282308733, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, 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=1239232336362000516, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, authorId=1239232336282308733, language=EN, stringName=Xiaoxiao Zhou, firstName=Xiaoxiao, middleName=null, lastName=Zhou, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.Zhejiang Dun'an Artificial Environment Co., Ltd., Shaoxing, 311835, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1239232336441692299, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, authorId=1239232336282308733, language=CN, stringName=周晓晓, firstName=晓晓, middleName=null, lastName=周, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2浙江盾安人工环境股份有限公司 绍兴 311835, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1239232335330201658, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, xref=2., ext=[AuthorCompanyExt(id=1239232335334395962, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, companyId=1239232335330201658, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.Zhejiang Dun'an Artificial Environment Co., Ltd., Shaoxing, 311835, China), AuthorCompanyExt(id=1239232335342784571, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, companyId=1239232335330201658, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2浙江盾安人工环境股份有限公司 绍兴 311835)])]), Author(id=1239232336508801168, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, orderNo=4, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=hanxh66@zju.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1239232336609464471, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, authorId=1239232336508801168, language=EN, stringName=Xiaohong Han, firstName=Xiaohong, middleName=null, lastName=Han, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3.Institute of Refrigeration and Cryogenics, Zhejiang University, Hangzhou, 310007, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1239232336693350554, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, authorId=1239232336508801168, language=CN, stringName=韩晓红, firstName=晓红, middleName=null, lastName=韩, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3浙江大学制冷与低温研究所 杭州 310007, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1239232335422476354, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, xref=3., ext=[AuthorCompanyExt(id=1239232335426670659, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, companyId=1239232335422476354, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3.Institute of Refrigeration and Cryogenics, Zhejiang University, Hangzhou, 310007, China), AuthorCompanyExt(id=1239232335435059268, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, companyId=1239232335422476354, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3浙江大学制冷与低温研究所 杭州 310007)])]), Author(id=1239232336802402462, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, 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=1239232336907260069, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, authorId=1239232336802402462, language=EN, stringName=Guangming Chen, firstName=Guangming, middleName=null, lastName=Chen, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3.Institute of Refrigeration and Cryogenics, Zhejiang University, Hangzhou, 310007, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1239232336970174631, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, authorId=1239232336802402462, language=CN, stringName=陈光明, firstName=光明, middleName=null, lastName=陈, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3浙江大学制冷与低温研究所 杭州 310007, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1239232335422476354, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, xref=3., ext=[AuthorCompanyExt(id=1239232335426670659, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, companyId=1239232335422476354, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3.Institute of Refrigeration and Cryogenics, Zhejiang University, Hangzhou, 310007, China), AuthorCompanyExt(id=1239232335435059268, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, companyId=1239232335422476354, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3浙江大学制冷与低温研究所 杭州 310007)])])], keywords=[Keyword(id=1239232338584981679, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, language=EN, orderNo=1, keyword=frosting state recognition), Keyword(id=1239232338702422195, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, language=EN, orderNo=2, keyword=gray level co-occurrence matrix), Keyword(id=1239232338815668409, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, language=EN, orderNo=3, keyword=digital image processing), Keyword(id=1239232338949886139, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, language=EN, orderNo=4, keyword=texture features), Keyword(id=1239232339037966528, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, language=EN, orderNo=5, keyword=defrost), Keyword(id=1239232339113464004, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, language=CN, orderNo=1, keyword=结霜状态识别), Keyword(id=1239232339222515913, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, language=CN, orderNo=2, keyword=灰度共生矩阵), Keyword(id=1239232339331567823, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, language=CN, orderNo=3, keyword=数字图像), Keyword(id=1239232339415453907, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, language=CN, orderNo=4, keyword=纹理特征), Keyword(id=1239232339532894425, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, language=CN, orderNo=5, keyword=除霜)], refs=[Reference(id=1239232344381510035, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, doi=null, pmid=null, pmcid=null, year=2009, volume=9, issue=3, pageStart=8, pageEnd=14, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=郭宪民, journalName=制冷与空调(北京), refType=null, unstructuredReference=郭宪民. 空气源热泵结霜问题的研究现状及进展(Ⅱ)[J]. 制冷与空调(北京), 2009, 9(3): 8-14., articleTitle=空气源热泵结霜问题的研究现状及进展(Ⅱ), refAbstract=null), Reference(id=1239232344465396120, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, doi=null, pmid=null, pmcid=null, year=2009, volume=9, issue=3, pageStart=8, pageEnd=14, url=null, language=null, rfNumber=[1], rfOrder=1, authorNames=GUO Xianmin, journalName=Refrigeration and Air-conditioning, refType=null, unstructuredReference=(GUO Xianmin. Current status and progress of air source heat pump under frosting conditions: part Ⅱ[J]. Refrigeration and Air-conditioning, 2009, 9(3): 8-14.), articleTitle=Current status and progress of air source heat pump under frosting conditions: part Ⅱ, refAbstract=null), Reference(id=1239232344528310684, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, doi=null, pmid=null, pmcid=null, year=2017, volume=74, issue=null, pageStart=385, pageEnd=398, url=null, language=null, rfNumber=[2], rfOrder=2, authorNames=LIU Jingdong, SUN Yuying, WANG Wei, journalName=International Journal of Refrigeration, refType=null, unstructuredReference=LIU Jingdong, SUN Yuying, WANG Wei, et al. Performance evaluation of air source heat pump under unnecessary defrosting phenomena for nine typical cities in China[J]. International Journal of Refrigeration, 2017, 74: 385-398., articleTitle=Performance evaluation of air source heat pump under unnecessary defrosting phenomena for nine typical cities in China, refAbstract=null), Reference(id=1239232344595419552, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, doi=null, pmid=null, pmcid=null, year=2020, volume=109, issue=null, pageStart=161, pageEnd=171, url=null, language=null, rfNumber=[3], rfOrder=3, authorNames=LIANG Shimin, WANG Wei, SUN Yuying, journalName=International Journal of Refrigeration, refType=null, unstructuredReference=LIANG Shimin, WANG Wei, SUN Yuying, et al. A novel characteristic index for frosting suppression based on the configuration and operation of air source heat pumps[J]. International Journal of Refrigeration, 2020, 109: 161-171., articleTitle=A novel characteristic index for frosting suppression based on the configuration and operation of air source heat pumps, refAbstract=null), Reference(id=1239232344704471459, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, doi=null, pmid=null, pmcid=null, year=2014, volume=30, issue=null, pageStart=538, pageEnd=554, url=null, language=null, rfNumber=[4], rfOrder=4, authorNames=RAFATI NASR M, FAUCHOUX M, BESANT R W, journalName=Renewable and Sustainable Energy Reviews, refType=null, unstructuredReference=RAFATI NASR M, FAUCHOUX M, BESANT R W, et al. A review of frosting in air-to-air energy exchangers[J]. Renewable and Sustainable Energy Reviews, 2014, 30: 538-554., articleTitle=A review of frosting in air-to-air energy exchangers, refAbstract=null), Reference(id=1239232344792551845, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, doi=null, pmid=null, pmcid=null, year=2009, volume=null, issue=23, pageStart=55, pageEnd=57, url=null, language=null, rfNumber=[5], rfOrder=5, authorNames=肖彪, journalName=家电科技, refType=null, unstructuredReference=肖彪. 风冷热泵商用空调除霜控制分析[J]. 家电科技, 2009(23): 55-57., articleTitle=风冷热泵商用空调除霜控制分析, refAbstract=null), Reference(id=1239232344863855015, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, doi=null, pmid=null, pmcid=null, year=2009, volume=null, issue=23, pageStart=55, pageEnd=57, url=null, language=null, rfNumber=[5], rfOrder=6, authorNames=XIAO Biao, journalName=China Appliance Technology, refType=null, unstructuredReference=(XIAO Biao. Analysis on defrosting control of air-cooled heat pump commercial air conditioner[J]. China Appliance Technology, 2009(23): 55-57.), articleTitle=Analysis on defrosting control of air-cooled heat pump commercial air conditioner, refAbstract=null), Reference(id=1239232344951935403, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, doi=null, pmid=null, pmcid=null, year=2011, volume=88, issue=12, pageStart=4470, pageEnd=4480, url=null, language=null, rfNumber=[6], rfOrder=7, authorNames=WANG W, XIAO J, GUO Q C, journalName=Applied Energy, refType=null, unstructuredReference=WANG W, XIAO J, GUO Q C, et al. Field test investigation of the characteristics for the air source heat pump under two typical mal-defrost phenomena[J]. Applied Energy, 2011, 88(12): 4470-4480., articleTitle=Field test investigation of the characteristics for the air source heat pump under two typical mal-defrost phenomena, refAbstract=null), Reference(id=1239232345035821484, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, doi=null, pmid=null, pmcid=null, year=2013, volume=112, issue=null, pageStart=1138, pageEnd=1145, url=null, language=null, rfNumber=[7], rfOrder=8, authorNames=WANG W, FENG Y C, ZHU J H, journalName=Applied Energy, refType=null, unstructuredReference=WANG W, FENG Y C, ZHU J H, et al. Performances of air source heat pump system for a kind of mal-defrost phenomenon appearing in moderate climate conditions[J]. Applied Energy, 2013, 112: 1138-1145., articleTitle=Performances of air source heat pump system for a kind of mal-defrost phenomenon appearing in moderate climate conditions, refAbstract=null), Reference(id=1239232345128096174, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, doi=null, pmid=null, pmcid=null, year=2013, volume=102, issue=null, pageStart=571, pageEnd=581, url=null, language=null, rfNumber=[8], rfOrder=9, authorNames=GONG Guangcai, TANG Jinchen, LYU Dongyan, journalName=Applied Energy, refType=null, unstructuredReference=GONG Guangcai, TANG Jinchen, LYU Dongyan, et al. Research on frost formation in air source heat pump at cold-moist conditions in central-South China[J]. Applied Energy, 2013, 102: 571-581., articleTitle=Research on frost formation in air source heat pump at cold-moist conditions in central-South China, refAbstract=null), Reference(id=1239232345207787954, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, doi=null, pmid=null, pmcid=null, year=2021, volume=42, issue=5, pageStart=27, pageEnd=35, url=null, language=null, rfNumber=[9], rfOrder=10, authorNames=王沣浩, 马龙霞, 王志华, journalName=制冷学报, refType=null, unstructuredReference=王沣浩, 马龙霞, 王志华, 等. 空气源热泵除霜控制方法研究现状及展望[J]. 制冷学报, 2021, 42(5): 27-35., articleTitle=空气源热泵除霜控制方法研究现状及展望, refAbstract=null), Reference(id=1239232345287479735, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, doi=null, pmid=null, pmcid=null, year=2021, volume=42, issue=5, pageStart=27, pageEnd=35, url=null, language=null, rfNumber=[9], rfOrder=11, authorNames=WANG Fenghao, MA Longxia, WANG Zhihua, journalName=Journal of Refrigeration, refType=null, unstructuredReference=(WANG Fenghao, MA Longxia, WANG Zhihua, et al. Research status and prospect on defrosting control method of air source heat pump[J]. Journal of Refrigeration, 2021, 42(5): 27-35.), articleTitle=Research status and prospect on defrosting control method of air source heat pump, refAbstract=null), Reference(id=1239232345362977209, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, doi=null, pmid=null, pmcid=null, year=2018, volume=18, issue=9, pageStart=1, pageEnd=6, url=null, language=null, rfNumber=[10], rfOrder=12, authorNames=何亚屏, 胡家喜, 文宇良, journalName=制冷与空调(北京), refType=null, unstructuredReference=何亚屏, 胡家喜, 文宇良, 等. 中央空调高速永磁直驱变频传动系统关键技术研究及应用[J]. 制冷与空调(北京), 2018, 18(9): 1-6., articleTitle=中央空调高速永磁直驱变频传动系统关键技术研究及应用, refAbstract=null), Reference(id=1239232345501389243, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, doi=null, pmid=null, pmcid=null, year=2018, volume=18, issue=9, pageStart=1, pageEnd=6, url=null, language=null, rfNumber=[10], rfOrder=13, authorNames=HE Yaping, HU Jiaxi, WEN Yuliang, journalName=Refrigeration and Air-conditioning, refType=null, unstructuredReference=(HE Yaping, HU Jiaxi, WEN Yuliang, et al. Researchand application of key technologies for high speed PMSM direct drive VFD system of central air-conditioning[J]. Refrigeration and Air-conditioning, 2018, 18(9): 1-6.), articleTitle=Researchand application of key technologies for high speed PMSM direct drive VFD system of central air-conditioning, refAbstract=null), Reference(id=1239232345597858240, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, doi=null, pmid=null, pmcid=null, year=2022, volume=43, issue=5, pageStart=24, pageEnd=32, url=null, language=null, rfNumber=[11], rfOrder=14, authorNames=梁士民, 王伟, 孙育英, journalName=制冷学报, refType=null, unstructuredReference=梁士民, 王伟, 孙育英, 等. 抑霜型空气源热泵机组应用实测研究[J]. 制冷学报, 2022, 43(5): 24-32., articleTitle=抑霜型空气源热泵机组应用实测研究, refAbstract=null), Reference(id=1239232345681744322, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, doi=null, pmid=null, pmcid=null, year=2022, volume=43, issue=5, pageStart=24, pageEnd=32, url=null, language=null, rfNumber=[11], rfOrder=15, authorNames=LIANG Shimin, WANG Wei, SUN Yuying, journalName=Journal of Refrigeration, refType=null, unstructuredReference=(LIANG Shimin, WANG Wei, SUN Yuying, et al. Field study on the application of frost-suppression air-source heat pump units[J]. Journal of Refrigeration, 2022, 43(5): 24-32.), articleTitle=Field study on the application of frost-suppression air-source heat pump units, refAbstract=null), Reference(id=1239232345769824708, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, doi=null, pmid=null, pmcid=null, year=2022, volume=43, issue=3, pageStart=78, pageEnd=86, url=null, language=null, rfNumber=[12], rfOrder=16, authorNames=刘耀, 盛伟, 方永强, journalName=制冷学报, refType=null, unstructuredReference=刘耀, 盛伟, 方永强, 等. 铝基波纹表面结霜特性实验研究[J]. 制冷学报, 2022, 43(3): 78-86., articleTitle=铝基波纹表面结霜特性实验研究, refAbstract=null), Reference(id=1239232345845322185, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, doi=null, pmid=null, pmcid=null, year=2022, volume=43, issue=3, pageStart=78, pageEnd=86, url=null, language=null, rfNumber=[12], rfOrder=17, authorNames=LIU Yao, SHENG Wei, FANG Yongqiang, journalName=Journal of Refrigeration, refType=null, unstructuredReference=(LIU Yao, SHENG Wei, FANG Yongqiang, et al. Experimental study on frosting characteristics of wavy aluminum surfaces[J]. Journal of Refrigeration, 2022, 43(3): 78-86.), articleTitle=Experimental study on frosting characteristics of wavy aluminum surfaces, refAbstract=null), Reference(id=1239232345933402574, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, doi=null, pmid=null, pmcid=null, year=2016, volume=37, issue=3, pageStart=17, pageEnd=21, url=null, language=null, rfNumber=[13], rfOrder=18, authorNames=邢震, 郭宪民, 李景善, journalName=制冷学报, refType=null, unstructuredReference=邢震, 郭宪民, 李景善. 基于平均性能最优的空气源热泵除霜控制方法的研究[J]. 制冷学报, 2016, 37(3): 17-21., articleTitle=基于平均性能最优的空气源热泵除霜控制方法的研究, refAbstract=null), Reference(id=1239232347418186193, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, doi=null, pmid=null, pmcid=null, year=2016, volume=37, issue=3, pageStart=17, pageEnd=21, url=null, language=null, rfNumber=[13], rfOrder=19, authorNames=XING Zhen, GUO Xianmin, LI Jingshan, journalName=Journal of Refrigeration, refType=null, unstructuredReference=(XING Zhen, GUO Xianmin, LI Jingshan. Study on the defrosting control method based on the optimal average performance of an air source heat pump[J]. Journal of Refrigeration, 2016, 37(3): 17-21.), articleTitle=Study on the defrosting control method based on the optimal average performance of an air source heat pump, refAbstract=null), Reference(id=1239232347485295057, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, doi=null, pmid=null, pmcid=null, year=2002, volume=26, issue=6/7, pageStart=661, pageEnd=668, url=null, language=null, rfNumber=[14], rfOrder=20, authorNames=FOSSA M, TANDA G, journalName=Experimental Thermal and Fluid Science, refType=null, unstructuredReference=FOSSA M, TANDA G. Study of free convection frost formation on a vertical plate[J]. Experimental Thermal and Fluid Science, 2002, 26(6/7): 661-668., articleTitle=Study of free convection frost formation on a vertical plate, refAbstract=null), Reference(id=1239232347573375446, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, doi=null, pmid=null, pmcid=null, year=2000, volume=24, issue=3, pageStart=179, pageEnd=181, url=null, language=null, rfNumber=[15], rfOrder=21, authorNames=董金锠, 王玮, 董振强, journalName=激光技术, refType=null, unstructuredReference=董金锠, 王玮, 董振强. 蒸发器结霜速率实时测定[J]. 激光技术, 2000, 24(3): 179-181., articleTitle=蒸发器结霜速率实时测定, refAbstract=null), Reference(id=1239232347648872922, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, doi=null, pmid=null, pmcid=null, year=2000, volume=24, issue=3, pageStart=179, pageEnd=181, url=null, language=null, rfNumber=[15], rfOrder=22, authorNames=DONG Jinchang, WANG Wei, DONG Zhenqiang, journalName=Laser Technology, refType=null, unstructuredReference=(DONG Jinchang, WANG Wei, DONG Zhenqiang. Real-time measurement for evaporator frosting rate[J]. Laser Technology, 2000, 24(3): 179-181.), articleTitle=Real-time measurement for evaporator frosting rate, refAbstract=null), Reference(id=1239232347762119135, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, doi=null, pmid=null, pmcid=null, year=2013, volume=50, issue=1, pageStart=177, pageEnd=186, url=null, language=null, rfNumber=[16], rfOrder=23, authorNames=WANG Wei, XIAO Jing, FENG Yingchao, journalName=Applied Thermal Engineering, refType=null, unstructuredReference=WANG Wei, XIAO Jing, FENG Yingchao, et al. Characteristics of an air source heat pump with novel photoelectric sensors during periodic frost-defrost cycles[J]. Applied Thermal Engineering, 2013, 50(1): 177-186., articleTitle=Characteristics of an air source heat pump with novel photoelectric sensors during periodic frost-defrost cycles, refAbstract=null), Reference(id=1239232347900531172, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, doi=null, pmid=null, pmcid=null, year=2001, volume=35, issue=8, pageStart=1175, pageEnd=1177, url=null, language=null, rfNumber=[17], rfOrder=24, authorNames=周冲, 程惠尔, journalName=上海交通大学学报, refType=null, unstructuredReference=周冲, 程惠尔. 图像处理在管内结霜厚度测量中的应用[J]. 上海交通大学学报, 2001, 35(8): 1175-1177., articleTitle=图像处理在管内结霜厚度测量中的应用, refAbstract=null), Reference(id=1239232347997000168, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, doi=null, pmid=null, pmcid=null, year=2001, volume=35, issue=8, pageStart=1175, pageEnd=1177, url=null, language=null, rfNumber=[17], rfOrder=25, authorNames=ZHOU Chong, CHENG Huier, journalName=Journal of Shanghai Jiao Tong University, refType=null, unstructuredReference=(ZHOU Chong, CHENG Huier. Dynamic height-detecting system for growing frost in a tube[J]. Journal of Shanghai Jiao Tong University, 2001, 35(8): 1175-1177.), articleTitle=Dynamic height-detecting system for growing frost in a tube, refAbstract=null), Reference(id=1239232348059914732, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, doi=null, pmid=null, pmcid=null, year=2006, volume=45, issue=2, pageStart=116, pageEnd=123, url=null, language=null, rfNumber=[18], rfOrder=26, authorNames=QU Kaiyang, KOMORI S, JIANG Yi, journalName=International Journal of Thermal Sciences, refType=null, unstructuredReference=QU Kaiyang, KOMORI S, JIANG Yi. Local variation of frost layer thickness and morphology[J]. International Journal of Thermal Sciences, 2006, 45(2): 116-123., articleTitle=Local variation of frost layer thickness and morphology, refAbstract=null), Reference(id=1239232348135412208, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, doi=null, pmid=null, pmcid=null, year=2006, volume=29, issue=7, pageStart=1066, pageEnd=1079, url=null, language=null, rfNumber=[19], rfOrder=27, authorNames=XIA Y, ZHONG Y, HRNJAK P S, journalName=International Journal of Refrigeration, refType=null, unstructuredReference=XIA Y, ZHONG Y, HRNJAK P S, et al. Frost, defrost, and refrost and its impact on the air-side thermal-hydraulic performance of louvered-fin, flat-tube heat exchangers[J]. International Journal of Refrigeration, 2006, 29(7): 1066-1079., articleTitle=Frost, defrost, and refrost and its impact on the air-side thermal-hydraulic performance of louvered-fin, flat-tube heat exchangers, refAbstract=null), Reference(id=1239232348227686900, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, doi=null, pmid=null, pmcid=null, year=2019, volume=155, issue=null, pageStart=461, pageEnd=469, url=null, language=null, rfNumber=[20], rfOrder=28, authorNames=CHUNG Y, NA S I, CHOI J, journalName=Applied Thermal Engineering, refType=null, unstructuredReference=CHUNG Y, NA S I, CHOI J, et al. Feasibility and optimization of defrosting control method with differential pressure sensor for air source heat pump systems[J]. Applied Thermal Engineering, 2019, 155: 461-469., articleTitle=Feasibility and optimization of defrosting control method with differential pressure sensor for air source heat pump systems, refAbstract=null), Reference(id=1239232348340933111, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, doi=null, pmid=null, pmcid=null, year=1999, volume=27, issue=2, pageStart=55, pageEnd=57, url=null, language=null, rfNumber=[21], rfOrder=29, authorNames=陈汝东, 许东晟, journalName=流体机械, refType=null, unstructuredReference=陈汝东, 许东晟. 风冷热泵空调器除霜控制的研究[J]. 流体机械, 1999, 27(2): 55-57., articleTitle=风冷热泵空调器除霜控制的研究, refAbstract=null), Reference(id=1239232348420624890, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, doi=null, pmid=null, pmcid=null, year=1999, volume=27, issue=2, pageStart=55, pageEnd=57, url=null, language=null, rfNumber=[21], rfOrder=30, authorNames=CHEN Rudong, XU Dongsheng, journalName=Fluid Machinery, refType=null, unstructuredReference=(CHEN Rudong, XU Dongsheng. Study on defrosting control of air-cooled heat pump air conditioner[J]. Fluid Machinery, 1999, 27(2): 55-57.), articleTitle=Study on defrosting control of air-cooled heat pump air conditioner, refAbstract=null), Reference(id=1239232348508705279, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, doi=null, pmid=null, pmcid=null, year=2007, volume=26, issue=2, pageStart=14, pageEnd=17, url=null, language=null, rfNumber=[22], rfOrder=31, authorNames=葛住军, 许文斌, 付彬, journalName=制冷, refType=null, unstructuredReference=葛住军, 许文斌, 付彬, 等. 最大平均制热量控制除霜方法的实验研究[J]. 制冷, 2007, 26(2): 14-17., articleTitle=最大平均制热量控制除霜方法的实验研究, refAbstract=null), Reference(id=1239232348592591363, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, doi=null, pmid=null, pmcid=null, year=2007, volume=26, issue=2, pageStart=14, pageEnd=17, url=null, language=null, rfNumber=[22], rfOrder=32, authorNames=GE Zhujun, XU Wenbin, FU Bin, journalName=Refrigeration, refType=null, unstructuredReference=(GE Zhujun, XU Wenbin, FU Bin, et al. Research on a kind of defrosting control method-maximum average heating capacity[J]. Refrigeration, 2007, 26(2): 14-17.), articleTitle=Research on a kind of defrosting control method-maximum average heating capacity, refAbstract=null), Reference(id=1239232348701643270, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, doi=null, pmid=null, pmcid=null, year=2024, volume=291, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[23], rfOrder=33, authorNames=XU Yingjie, ZHAO Ruiying, WU Kai, journalName=Energy, refType=null, unstructuredReference=XU Yingjie, ZHAO Ruiying, WU Kai, et al. Experimental investigation and validation on an air-source heat pump frosting state recognition method based on fan current fluctuation signal and machine learning[J]. Energy, 2024, 291: 130372., articleTitle=Experimental investigation and validation on an air-source heat pump frosting state recognition method based on fan current fluctuation signal and machine learning, refAbstract=null), Reference(id=1239232348810695180, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, doi=null, pmid=null, pmcid=null, year=2018, volume=124, issue=null, pageStart=586, pageEnd=614, url=null, language=null, rfNumber=[24], rfOrder=34, authorNames=SONG Mengjie, DANG Chaobin, journalName=International Journal of Heat and Mass Transfer, refType=null, unstructuredReference=SONG Mengjie, DANG Chaobin. Review on the measurement and calculation of frost characteristics[J]. International Journal of Heat and Mass Transfer, 2018, 124: 586-614., articleTitle=Review on the measurement and calculation of frost characteristics, refAbstract=null), Reference(id=1239232348881998350, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, doi=null, pmid=null, pmcid=null, year=2021, volume=233, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[25], rfOrder=35, authorNames=LI Zhaoyang, WANG Wei, SUN Yuying, journalName=Energy, refType=null, unstructuredReference=LI Zhaoyang, WANG Wei, SUN Yuying, et al. Applying image recognition to frost built-up detection in air source heat pumps[J]. Energy, 2021, 233: 121004., articleTitle=Applying image recognition to frost built-up detection in air source heat pumps, refAbstract=null), Reference(id=1239232348978467346, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, doi=null, pmid=null, pmcid=null, year=2022, volume=138, issue=null, pageStart=259, pageEnd=269, url=null, language=null, rfNumber=[26], rfOrder=36, authorNames=MIAO Hongfei, YANG Xueqing, YIN Dazhen, journalName=International Journal of Refrigeration, refType=null, unstructuredReference=MIAO Hongfei, YANG Xueqing, YIN Dazhen, et al. A novel defrosting control strategy with image processing technique and fractal theory[J]. International Journal of Refrigeration, 2022, 138: 259-269., articleTitle=A novel defrosting control strategy with image processing technique and fractal theory, refAbstract=null), Reference(id=1239232349053964822, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, doi=null, pmid=null, pmcid=null, year=2022, volume=139, issue=null, pageStart=214, pageEnd=224, url=null, language=null, rfNumber=[27], rfOrder=37, authorNames=SUN Huan, ZHU Junda, LIU Xinghua, journalName=International Journal of Refrigeration, refType=null, unstructuredReference=SUN Huan, ZHU Junda, LIU Xinghua, et al. Theoretical and experimental study of a new defrost control strategy based on gray scale graph theory[J]. International Journal of Refrigeration, 2022, 139: 214-224., articleTitle=Theoretical and experimental study of a new defrost control strategy based on gray scale graph theory, refAbstract=null), Reference(id=1239232349133656601, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, doi=null, pmid=null, pmcid=null, year=2022, volume=324, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[28], rfOrder=38, authorNames=CHEN Siliang, CHEN Kang, ZHU Xu, journalName=Applied Energy, refType=null, unstructuredReference=CHEN Siliang, CHEN Kang, ZHU Xu, et al. Deep learning-based image recognition method for on-demand defrosting control to save energy in commercial energy systems[J]. Applied Energy, 2022, 324: 119702., articleTitle=Deep learning-based image recognition method for on-demand defrosting control to save energy in commercial energy systems, refAbstract=null), Reference(id=1239232349196571165, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, doi=null, pmid=null, pmcid=null, year=2023, volume=292, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[29], rfOrder=39, authorNames=XU Yingjie, XIE Yong, WANG Xiaopo, journalName=Energy and Buildings, refType=null, unstructuredReference=XU Yingjie, XIE Yong, WANG Xiaopo, et al. Study on a novel defrost control method based on the surface texture of evaporator image with gray-level cooccurrence matrix, new characterization parameter combination and machine learning[J]. Energy and Buildings, 2023, 292: 113173., articleTitle=Study on a novel defrost control method based on the surface texture of evaporator image with gray-level cooccurrence matrix, new characterization parameter combination and machine learning, refAbstract=null), Reference(id=1239232349280457247, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, doi=null, pmid=null, pmcid=null, year=2006, volume=70, issue=1-3, pageStart=489, pageEnd=501, url=null, language=null, rfNumber=[30], rfOrder=40, authorNames=HUANG Guangbin, ZHU Qinyu, SIEW C K, journalName=Neurocomputing, refType=null, unstructuredReference=HUANG Guangbin, ZHU Qinyu, SIEW C K. Extreme learning machine: theory and applications[J]. Neurocomputing, 2006, 70(1-3): 489-501., articleTitle=Extreme learning machine: theory and applications, refAbstract=null), Reference(id=1239232349385314850, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, doi=null, pmid=null, pmcid=null, year=2024, volume=152, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[31], rfOrder=41, authorNames=ZHANG Mengxuan, LIU Long, JIN Yaochu, journalName=Applied Soft Computing, refType=null, unstructuredReference=ZHANG Mengxuan, LIU Long, JIN Yaochu, et al. Tree-shaped multiobjective evolutionary CNN for hyperspectral image classification[J]. Applied Soft Computing, 2024, 152: 111176., articleTitle=Tree-shaped multiobjective evolutionary CNN for hyperspectral image classification, refAbstract=null), Reference(id=1239232349494366759, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, doi=null, pmid=null, pmcid=null, year=2024, volume=168, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[32], rfOrder=42, authorNames=HAN Qi, QIAN Xin, XU Hongxiang, journalName=Computers in Biology and Medicine, refType=null, unstructuredReference=HAN Qi, QIAN Xin, XU Hongxiang, et al. DM-CNN: Dynamic multi-scale convolutional neural network with uncertainty quantification for medical image classification[J]. Computers in Biology and Medicine, 2024, 168: 107758., articleTitle=DM-CNN: Dynamic multi-scale convolutional neural network with uncertainty quantification for medical image classification, refAbstract=null), Reference(id=1239232349603418664, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, doi=null, pmid=null, pmcid=null, year=2023, volume=167, issue=null, pageStart=22, pageEnd=35, url=null, language=null, rfNumber=[33], rfOrder=43, authorNames=LI Guangfei, GAO Quanxue, YANG Ming, journalName=Neural Networks, refType=null, unstructuredReference=LI Guangfei, GAO Quanxue, YANG Ming, et al. Active learning based on similarity level histogram and adaptive-scale sampling for very high resolution image classification[J]. Neural Networks, 2023, 167: 22-35., articleTitle=Active learning based on similarity level histogram and adaptive-scale sampling for very high resolution image classification, refAbstract=null)], funds=[Fund(id=1239232344117268869, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, awardId=52076185, language=EN, fundingSource=National Natural Science Foundation of China(52076185), fundOrder=null, country=null), Fund(id=1239232344201154953, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, awardId=52076185, language=CN, fundingSource=国家自然科学基金(52076185), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1239232335242121263, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, xref=1., ext=[AuthorCompanyExt(id=1239232335250509872, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, companyId=1239232335242121263, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.College of Mechanical Engineering, Zhejiang University of Technology, Hangzhou, 310023, China), AuthorCompanyExt(id=1239232335254704177, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, companyId=1239232335242121263, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1浙江工业大学机械工程学院 杭州 310023)]), AuthorCompany(id=1239232335330201658, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, xref=2., ext=[AuthorCompanyExt(id=1239232335334395962, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, companyId=1239232335330201658, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.Zhejiang Dun'an Artificial Environment Co., Ltd., Shaoxing, 311835, China), AuthorCompanyExt(id=1239232335342784571, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, companyId=1239232335330201658, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2浙江盾安人工环境股份有限公司 绍兴 311835)]), AuthorCompany(id=1239232335422476354, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, xref=3., ext=[AuthorCompanyExt(id=1239232335426670659, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, companyId=1239232335422476354, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3.Institute of Refrigeration and Cryogenics, Zhejiang University, Hangzhou, 310007, China), AuthorCompanyExt(id=1239232335435059268, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, companyId=1239232335422476354, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3浙江大学制冷与低温研究所 杭州 310007)])], figs=[ArticleFig(id=1239232339792941291, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, language=EN, label=Fig.1, caption=Flow schematic of GLCM-SELM method, figureFileSmall=sckgOg5PYYErKSLBV8raPQ==, figureFileBig=XDTq8C2x94DE+qnJVl5sPw==, tableContent=null), ArticleFig(id=1239232339885215986, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, language=CN, label=图1, caption=GLCM-SELM方法的流程原理, figureFileSmall=sckgOg5PYYErKSLBV8raPQ==, figureFileBig=XDTq8C2x94DE+qnJVl5sPw==, tableContent=null), ArticleFig(id=1239232339994267903, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, language=EN, label=Fig.2, caption=Solution for grayscale co-occurrence matrix, figureFileSmall=Zt0nDyQAXBrRtEgixk01ew==, figureFileBig=9QVBLUf70MC2Uht8j91ZSQ==, tableContent=null), ArticleFig(id=1239232340094931203, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, language=CN, label=图2, caption=灰度共生矩阵求解, figureFileSmall=Zt0nDyQAXBrRtEgixk01ew==, figureFileBig=9QVBLUf70MC2Uht8j91ZSQ==, tableContent=null), ArticleFig(id=1239232340178817288, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, language=EN, label=Fig.3, caption=Frost layer comparison, figureFileSmall=pexX3+CpFKQn/UgBclenSA==, figureFileBig=J6NmVmW2JpHHMBFn4b8Kaw==, tableContent=null), ArticleFig(id=1239232340300452112, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, language=CN, label=图3, caption=霜层对比, figureFileSmall=pexX3+CpFKQn/UgBclenSA==, figureFileBig=J6NmVmW2JpHHMBFn4b8Kaw==, tableContent=null), ArticleFig(id=1239232340371755283, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, language=EN, label=Fig.4, caption=Histograms of images with different frosting states, figureFileSmall=CYNwqPEwx/KKFBhirPo05g==, figureFileBig=whKbLBn5+TxyznXUD8rliA==, tableContent=null), ArticleFig(id=1239232340455641368, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, language=CN, label=图4, caption=不同结霜状态图像的直方图, figureFileSmall=CYNwqPEwx/KKFBhirPo05g==, figureFileBig=whKbLBn5+TxyznXUD8rliA==, tableContent=null), ArticleFig(id=1239232340531138845, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, language=EN, label=Fig.5, caption=Frost layer classification, figureFileSmall=lcHAmS3ra5qvAJ9GIpOF3w==, figureFileBig=lpfwrYKCVqSU7Lufzufzdw==, tableContent=null), ArticleFig(id=1239232340640190754, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, language=CN, label=图5, caption=霜层分型, figureFileSmall=lcHAmS3ra5qvAJ9GIpOF3w==, figureFileBig=lpfwrYKCVqSU7Lufzufzdw==, tableContent=null), ArticleFig(id=1239232340711493926, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, language=EN, label=Fig.6, caption=Experimental system plan, figureFileSmall=iofXCqFLPr9G1mW3Xm1aTw==, figureFileBig=VBDRCQtEZ1Bi+fFpS6bojw==, tableContent=null), ArticleFig(id=1239232340778602798, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, language=CN, label=图6, caption=实验系统, figureFileSmall=iofXCqFLPr9G1mW3Xm1aTw==, figureFileBig=VBDRCQtEZ1Bi+fFpS6bojw==, tableContent=null), ArticleFig(id=1239232340879266098, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, language=EN, label=Fig.7, caption=Image acquisition device, figureFileSmall=GbNgpAFcUmacGGSH4x/biQ==, figureFileBig=wZMCwGms92luBrZp5cmq2Q==, tableContent=null), ArticleFig(id=1239232340979929397, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, language=CN, label=图7, caption=图像采集设备, figureFileSmall=GbNgpAFcUmacGGSH4x/biQ==, figureFileBig=wZMCwGms92luBrZp5cmq2Q==, tableContent=null), ArticleFig(id=1239232341101564220, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, language=EN, label=Fig.8, caption=Frost layer images at different shooting angles and distances, figureFileSmall=oylj8BY6YlMaQ/y1lk9zPw==, figureFileBig=2uUCWsT+0C4qfjQguXz0tg==, tableContent=null), ArticleFig(id=1239232341193838913, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, language=CN, label=图8, caption=不同拍摄角度及距离霜层图像, figureFileSmall=oylj8BY6YlMaQ/y1lk9zPw==, figureFileBig=2uUCWsT+0C4qfjQguXz0tg==, tableContent=null), ArticleFig(id=1239232341298696516, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, language=EN, label=Fig.9, caption=Optimization of construction parameters for GLCM-SELM, figureFileSmall=6ayTWrjEcZvMygdC0BmsWQ==, figureFileBig=N0jCRwXooSK0qvmhvOAqow==, tableContent=null), ArticleFig(id=1239232341395165511, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, language=CN, label=图9, caption=GLCM-SELM的构造参数的优化, figureFileSmall=6ayTWrjEcZvMygdC0BmsWQ==, figureFileBig=N0jCRwXooSK0qvmhvOAqow==, tableContent=null), ArticleFig(id=1239232341470662984, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, language=EN, label=Fig.10, caption=Parameter optimization process, figureFileSmall=dWAUfyCGKyRbCaKAq5MsIA==, figureFileBig=Vt9c5v6NrrcOnBv4w0J+Ig==, tableContent=null), ArticleFig(id=1239232342951252300, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, language=CN, label=图10, caption=参数优化过程, figureFileSmall=dWAUfyCGKyRbCaKAq5MsIA==, figureFileBig=Vt9c5v6NrrcOnBv4w0J+Ig==, tableContent=null), ArticleFig(id=1239232343035138381, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, language=EN, label=Fig.11, caption=Accuracy of recognition methods under different lighting conditions, figureFileSmall=gQ8AR3I831w3HjFtcmLLcw==, figureFileBig=UiBngiwPKYDzj0CbfZQl5Q==, tableContent=null), ArticleFig(id=1239232343102247250, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, language=CN, label=图11, caption=不同光照下识别方法的准确率, figureFileSmall=gQ8AR3I831w3HjFtcmLLcw==, figureFileBig=UiBngiwPKYDzj0CbfZQl5Q==, tableContent=null), ArticleFig(id=1239232343173550421, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, language=EN, label=Fig.12, caption=Average recognition accuracy of different methods under different lighting conditions, figureFileSmall=IP6EPve8uJFhVlnkTSaz1w==, figureFileBig=LW4PciVqJjPoGKa+NMesJA==, tableContent=null), ArticleFig(id=1239232343249047897, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, language=CN, label=图12, caption=不同光照下不同方法平均识别准确率, figureFileSmall=IP6EPve8uJFhVlnkTSaz1w==, figureFileBig=LW4PciVqJjPoGKa+NMesJA==, tableContent=null), ArticleFig(id=1239232343316156765, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, language=EN, label=Fig.13, caption=The confusion matrices of matrix diagrams identified by different recognition methods, figureFileSmall=6gclZuCfxwO6XWNvuIywNQ==, figureFileBig=ywWEUN6c0IainaLAToSnpw==, tableContent=null), ArticleFig(id=1239232343412625761, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, language=CN, label=图13, caption=不同识别方法矩阵图混淆矩阵, figureFileSmall=6gclZuCfxwO6XWNvuIywNQ==, figureFileBig=ywWEUN6c0IainaLAToSnpw==, tableContent=null), ArticleFig(id=1239232343509094758, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, language=EN, label=Fig.14, caption=Different methods for identifying the number of classifications, figureFileSmall=e/u91j16YvRGWAYL1L/bwg==, figureFileBig=Rw9BJCmjAeYqSudfTSJMsw==, tableContent=null), ArticleFig(id=1239232343622340972, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, language=CN, label=图14, caption=不同方法识别分类数量, figureFileSmall=e/u91j16YvRGWAYL1L/bwg==, figureFileBig=Rw9BJCmjAeYqSudfTSJMsw==, tableContent=null), ArticleFig(id=1239232343718809970, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, language=EN, label=Tab.1, caption=Number of image samples, figureFileSmall=null, figureFileBig=null, tableContent=
结霜程度样本数量分类标签
无霜1 7490
中霜9571
重霜1 4192
), ArticleFig(id=1239232343823667572, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, language=CN, label=表1, caption=图像样本数量, figureFileSmall=null, figureFileBig=null, tableContent=
结霜程度样本数量分类标签
无霜1 7490
中霜9571
重霜1 4192
), ArticleFig(id=1239232343899165048, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, language=EN, label=Tab.2, caption=Identification accuracy of different methods, figureFileSmall=null, figureFileBig=null, tableContent=
方法低光照强度中光照强度高光照强度混合光照强度
标准差方差标准差方差标准差方差标准差方差
GLCM-SELM1.311.550.950.881.993.852.347.49
CNN3.9514.081.371.691.943.392.174.25
直方图5.0923.384.0915.062.736.741.141.17
分型理论1.692.571.632.391.923.342.045.21
阈值分割6.133.853.6211.854.014.923.5111.10
), ArticleFig(id=1239232343974662525, tenantId=1146029695717560320, journalId=1238823019242635269, articleId=1239215313082962399, language=CN, label=表2, caption=不同方法识别准确率的标准差, figureFileSmall=null, figureFileBig=null, tableContent=
方法低光照强度中光照强度高光照强度混合光照强度
标准差方差标准差方差标准差方差标准差方差
GLCM-SELM1.311.550.950.881.993.852.347.49
CNN3.9514.081.371.691.943.392.174.25
直方图5.0923.384.0915.062.736.741.141.17
分型理论1.692.571.632.391.923.342.045.21
阈值分割6.133.853.6211.854.014.923.5111.10
)], attaches=null, journal=Journal(id=1238822513841586179, delFlag=0, nameCn=制冷学报, nameEn=Journal of Refrigeration, nameHistory1=null, nameHistory2=null, issn=0253-4339, eissn=2097-650X, cn=11-2182/TB, coden=null, periodic=1, 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=JDTT9dhyhNYd/ugabP90Kg==, journalPrice=null, startedYear=null, abbrevIsoEn=Journal of Refrigeration, journalRemark=null, publicationField=null, createdTime=1773287903512, updatedTime=1773299932329, createdBy=18614031015, updatedBy=13701087609, firstLetterCn=J, firstLetterEn=J, subjectCode=Engineering, subjectName=null, subjectCodeEn=Engineering, subjectNameEn=null, picCn=JDTT9dhyhNYd/ugabP90Kg==, picEn=CikjJLRTlyHZsUAWPKsBaw==, jcr=null, cjcr=null, exts=[JournalExt(id=1238872966457520458, language=CN, name=制冷学报, 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=1773299932350, updatedTime=1773299932350, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=https://journal.ids.fzyun.cn/auth/realms/journal/protocol/openid-connect/auth?client_id=journal-zhilengxuebao-author&redirect_uri=https%3A%2F%2Fzhilengxuebao.portal.founderss.cn%2Foauth%2Fcallback&response_type=code&scope=phone+openid+email+profile&state=, submissionEditorUrl=https://journal.ids.fzyun.cn/auth/realms/journal/protocol/openid-connect/auth?client_id=journal-portal&redirect_uri=https%3A%2F%2Fjournal.portal.founderss.cn%2Foauth%2Fcallback&response_type=code&scope=phone+openid+email+profile&state=3899b7f4-47a5-4fb5-8, submissionReviewUrl=https://journal.ids.fzyun.cn/auth/realms/journal/protocol/openid-connect/auth?client_id=journal-zhilengxuebao-author&redirect_uri=https%3A%2F%2Fzhilengxuebao.portal.founderss.cn%2Foauth%2Fcallback&response_type=code&scope=phone+openid+email+profile&state=, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1238872966507852107, language=EN, name=Journal of Refrigeration, 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=1773299932362, updatedTime=1773299932362, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=https://journal.ids.fzyun.cn/auth/realms/journal/protocol/openid-connect/auth?client_id=journal-zhilengxuebao-author&redirect_uri=https%3A%2F%2Fzhilengxuebao.portal.founderss.cn%2Foauth%2Fcallback&response_type=code&scope=phone+openid+email+profile&state=, submissionEditorUrl=https://journal.ids.fzyun.cn/auth/realms/journal/protocol/openid-connect/auth?client_id=journal-portal&redirect_uri=https%3A%2F%2Fjournal.portal.founderss.cn%2Foauth%2Fcallback&response_type=code&scope=phone+openid+email+profile&state=3899b7f4-47a5-4fb5-8, submissionReviewUrl=https://journal.ids.fzyun.cn/auth/realms/journal/protocol/openid-connect/auth?client_id=journal-zhilengxuebao-author&redirect_uri=https%3A%2F%2Fzhilengxuebao.portal.founderss.cn%2Foauth%2Fcallback&response_type=code&scope=phone+openid+email+profile&state=, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1238823019242635269, websiteList=[Website(id=1238843830003356342, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1238823019242635269, 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/zlxb/CN, language=CN, createTime=1773292985679, createBy=18614031015, updateTime=1773293389655, updateBy=18614031015, name=制冷学报-中文, tplId=1146099689490845704, title=制冷学报, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1238876063237992790, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1238843830003356342, code=articleTextType, value=kx, createTime=1773300670680, updateTime=1773300670680, creator=18614031015, updator=18614031015), WebsiteProps(id=1238876063217021267, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1238843830003356342, code=banner, value=null, createTime=1773300670675, updateTime=1773300670675, creator=18614031015, updator=18614031015), WebsiteProps(id=1238876063258964313, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1238843830003356342, code=grayFlag, value=0, createTime=1773300670685, updateTime=1773300670685, creator=18614031015, updator=18614031015), WebsiteProps(id=1238876063208632658, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1238843830003356342, code=logo, value=https://castjournals.cast.org.cn/joweb/zlxb/CN/file/pic?fileId=4PlxZN/EdYc/tGPHGzZ0fw==, createTime=1773300670673, updateTime=1773300670673, creator=18614031015, updator=18614031015), WebsiteProps(id=1238876063271547227, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1238843830003356342, code=minRunFlag, value=0, createTime=1773300670688, updateTime=1773300670688, creator=18614031015, updator=18614031015), WebsiteProps(id=1238876063233798485, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1238843830003356342, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/zlxb/CN/file/pic, createTime=1773300670679, updateTime=1773300670679, creator=18614031015, updator=18614031015), WebsiteProps(id=1238876063263158618, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1238843830003356342, code=silenceFlag, value=0, createTime=1773300670687, updateTime=1773300670687, creator=18614031015, updator=18614031015), WebsiteProps(id=1238876063225409876, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1238843830003356342, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1773300670677, updateTime=1773300670677, creator=18614031015, updator=18614031015), WebsiteProps(id=1238876063246381399, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1238843830003356342, code=themeColor, value=null, createTime=1773300670682, updateTime=1773300670682, creator=18614031015, updator=18614031015), WebsiteProps(id=1238876063250575704, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1238843830003356342, code=themeStyle, value=null, createTime=1773300670683, updateTime=1773300670683, creator=18614031015, updator=18614031015)]), Website(id=1238843830074659514, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1238823019242635269, 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/zlxb/EN, language=EN, createTime=1773292985695, createBy=18614031015, updateTime=1773293420654, updateBy=18614031015, name=制冷学报-英文, tplId=1146101810881728533, title=Journal of Refrigeration, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1238876091918643554, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1238843830074659514, code=articleTextType, value=kx, createTime=1773300677518, updateTime=1773300677518, creator=18614031015, updator=18614031015), WebsiteProps(id=1238876091893477727, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1238843830074659514, code=banner, value=null, createTime=1773300677512, updateTime=1773300677512, creator=18614031015, updator=18614031015), WebsiteProps(id=1238876091935420773, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1238843830074659514, code=grayFlag, value=0, createTime=1773300677522, updateTime=1773300677522, creator=18614031015, updator=18614031015), WebsiteProps(id=1238876091885089118, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1238843830074659514, code=logo, value=https://castjournals.cast.org.cn/joweb/zlxb/EN/file/pic?fileId=4PlxZN/EdYc/tGPHGzZ0fw==, createTime=1773300677510, updateTime=1773300677510, creator=18614031015, updator=18614031015), WebsiteProps(id=1238876091952197991, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1238843830074659514, code=minRunFlag, value=0, createTime=1773300677526, updateTime=1773300677526, creator=18614031015, updator=18614031015), WebsiteProps(id=1238876091910254945, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1238843830074659514, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/zlxb/EN/file/pic, createTime=1773300677516, updateTime=1773300677516, creator=18614031015, updator=18614031015), WebsiteProps(id=1238876091948003686, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1238843830074659514, code=silenceFlag, value=0, createTime=1773300677525, updateTime=1773300677525, creator=18614031015, updator=18614031015), WebsiteProps(id=1238876091897672032, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1238843830074659514, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_en_623/, createTime=1773300677513, updateTime=1773300677513, creator=18614031015, updator=18614031015), WebsiteProps(id=1238876091927032163, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1238843830074659514, code=themeColor, value=null, createTime=1773300677520, updateTime=1773300677520, creator=18614031015, updator=18614031015), WebsiteProps(id=1238876091931226468, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1238843830074659514, code=themeStyle, value=null, createTime=1773300677521, updateTime=1773300677521, creator=18614031015, updator=18614031015)])], journalTitle=制冷学报, weixinUrl=null, journalUrl=https://www.zhilengxuebao.com/, iacademicId=null, status=1, seqNo=null, journalTitleEn=Journal of Refrigeration, journalPhotoCn=JDTT9dhyhNYd/ugabP90Kg==, journalPhotoEn=CikjJLRTlyHZsUAWPKsBaw==, journalFirstLetter=J, 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), detailUrlCn=https://castjournals.cast.org.cn/joweb/zlxb/CN/10.12465/j.issn.0253-4339.2025.04.061, detailUrlEn=https://castjournals.cast.org.cn/joweb/zlxb/EN/10.12465/j.issn.0253-4339.2025.04.061, pdfUrlCn=https://castjournals.cast.org.cn/joweb/zlxb/CN/PDF/10.12465/j.issn.0253-4339.2025.04.061, pdfUrlEn=https://castjournals.cast.org.cn/joweb/zlxb/EN/PDF/10.12465/j.issn.0253-4339.2025.04.061, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于图像纹理特征的高适应性低成本蒸发器结霜状态智能识别方法对比
收藏切换
PDF下载
徐英杰 1 , 张恒瑞 1 , 柳云宇 1 , 周晓晓 2 , 韩晓红 3 , 陈光明 3
制冷学报 | 2025,46(4): 61-74
收起
收藏切换
制冷学报 | 2025, 46(4): 61-74
基于图像纹理特征的高适应性低成本蒸发器结霜状态智能识别方法对比
全屏
徐英杰1, 张恒瑞1, 柳云宇1, 周晓晓2, 韩晓红3 , 陈光明3
作者信息
  • 1浙江工业大学机械工程学院 杭州 310023
  • 2浙江盾安人工环境股份有限公司 绍兴 311835
  • 3浙江大学制冷与低温研究所 杭州 310007

通讯作者:

韩晓红,女,教授,博士生导师,浙江大学制冷与低温研究所,(0571)87953944,E-mail:。研究方向:高热流散热技术(主要指热管散热、微通道散热及浸没液体冷却技术)、动力电池浸没液冷热管理技术、制冷剂替代技术、制冷剂泄漏与回收及再利用技术。
Comparison of High Adaptability and Low-Cost Intelligent Recognition Method for Evaporator Frosting Status Based on Image Texture Features
Yingjie Xu1, Hengrui Zhang1, Yunyu Liu1, Xiaoxiao Zhou2, Xiaohong Han3 , Guangming Chen3
Affiliations
  • 1.College of Mechanical Engineering, Zhejiang University of Technology, Hangzhou, 310023, China
  • 2.Zhejiang Dun'an Artificial Environment Co., Ltd., Shaoxing, 311835, China
  • 3.Institute of Refrigeration and Cryogenics, Zhejiang University, Hangzhou, 310007, China
出版时间: 2025-08-16 doi: 10.12465/j.issn.0253-4339.2025.04.061
文章导航
收藏切换

误除霜或除霜不及时将导致制冷/热泵机组能耗增加、稳定性降低、故障率提升。精准识别结霜状态从而及时除霜是提升制冷/热泵性能的重要方向。基于数字/智能技术的结霜状态识别方法展现出较好的潜力,但现有技术在实际应用的复杂条件下,识别准确率明显降低,亟待改善。基于此,以蒸发器表面图像的纹理特征为切入点,提出以灰度共生矩阵提取纹理特征并结合麻雀算法优化后的极限学习机进行分类的智能识别方法。有望规避拍摄角度、光照强度等外部条件的影响,实现较强的适应性。建立实验装置,实验采集4 125张复杂工况下3种结霜状态的蒸发器图像样本,对新方法进行了验证和对比研究。结果表明,该方法在不同工况下识别准确率可接近或高于95%,显著高于现有的方法5%~35%。该方法的稳定性较高,成本较低,表现出良好的应用潜力。

结霜状态识别  /  灰度共生矩阵  /  数字图像  /  纹理特征  /  除霜

Unnecessary or delayed defrosting results in increased energy consumption, reduced stability, and increased failure rates in refrigeration and heat pump units. Accurately identifying the frost status and timely defrosting are important for improving the performance of refrigeration and heat pumps. Frost status identification methods based on digital and intelligent technologies have shown significant potential. However, existing technologies have significantly reduced accuracy in complex real-world conditions and require urgent improvement. In this paper, we proposed an intelligent recognition method based on the texture features of evaporator surface images. We used a gray-level co-occurrence matrix to extract texture features and combine them with the extreme learning machine optimized by the sparrow algorithm for classification. This is expected to mitigate the impact of external conditions, such as shooting angles and light intensity, thereby achieving strong adaptability. An experimental setup was established to collect 4 125 images of the evaporator in three different frost states under complex working conditions, and the proposed method was validated and compared. The results showed that the accuracy of the method in identifying different conditions can reach 95%, which is significantly higher than that of existing methods by 5-35%. Furthermore, this method has high stability and low cost thereby demonstrating great potential for practical applications.

frosting state recognition  /  gray level co-occurrence matrix  /  digital image processing  /  texture features  /  defrost
徐英杰, 张恒瑞, 柳云宇, 周晓晓, 韩晓红, 陈光明. 基于图像纹理特征的高适应性低成本蒸发器结霜状态智能识别方法对比. 制冷学报, 2025 , 46 (4) : 61 -74 . DOI: 10.12465/j.issn.0253-4339.2025.04.061
Yingjie Xu, Hengrui Zhang, Yunyu Liu, Xiaoxiao Zhou, Xiaohong Han, Guangming Chen. Comparison of High Adaptability and Low-Cost Intelligent Recognition Method for Evaporator Frosting Status Based on Image Texture Features[J]. Journal of Refrigeration, 2025 , 46 (4) : 61 -74 . DOI: 10.12465/j.issn.0253-4339.2025.04.061
空气源热泵是未来实现零/近零碳供热的关键技术,而冷链制冷系统是节能减排的重点对象。二者的蒸发器与空气换热时均存在结霜问题,影响系统性能。蒸发器上的霜层较厚[1]时,会显著降低传热效率,从而导致换热量减少30%~57%[2-4],COP(性能系数,coefficient of performance)下降35%~60%[5-9],能耗急剧上升。还会使压缩机吸气压力下降,导致制冷量或制热量不足[10-11]。结霜进一步严重时,还会造成机组停机、设备损坏[12]等事故。因而,及时准确地对蒸发器进行除霜非常重要,而此项工作得以实施的必要前提就是对结霜状态实现精确识别。
制冷/热泵系统蒸发器结霜状态的识别方法传统上可以分为2类。第1类是直接法,即直接测量霜层自身的参数,如厚度[13]、覆盖面积等,来确定结霜程度。主要包括:以千分尺[14]直接测量霜层厚度的方法,厚度误差低至0.1 mm;采用激光测量法[15]测量霜层厚度,误差仅0.5 mm;使用光电耦合技术[16]测量霜层厚度;利用电荷耦合器件[17]]观察冰晶的高度,误差为0.002 mm;使用干涉测量法[18]分析霜层厚度,其测量不确定度为±0.01 mm等。这些方法对霜层测量精度高,但操作复杂、成本高,且局部测量不能反映蒸发器整体的结霜状态,因而直接法很难实际应用。
第2类是间接法,即测量霜层自身参数以外的信号来判断结霜程度。主要包括:测量运行时间参数的定时法[5,19],其误除霜率高达60%;结合系统运行时间蒸发器盘管温度的T-T法[7],在北方城市的误除霜率为53%,中部城市为38%,南方城市为15%;测量室外换热器空气压差[20]的除霜控制法,其准确率为72%~85%;结合最大平均供热能力[21-22]的除霜控制法,其相对于T-T除霜控制方法的准确率约有5%的提升;测量风机电流[23]的除霜控制方法,但长期使用风机会产生污垢,导致准确率下降。间接法因结构简单、成本低廉是当前热泵/制冷系统除霜中采用的主要方法,但其最大的弊端是影响因素复杂,识别准确率低,一般不足75%。
随着计算机科学的发展,数字图像技术的处理能力提升、设备成本下降,已逐渐应用于医学、交通等领域,也正在成为蒸发器结霜识别的第3类方法。Song Mengjie等[24]对图像处理在霜层测量中的应用进行了调研。调研表明,图像处理技术可以直接用来检测霜层厚度,但受到一些干扰因素的影响,效果仍有提升空间。Li Zhaoyang等[25]提出一种多阈值分割方法,使用阈值对图像中的像素点进行特征化处理,预测当前的结霜阶段,准确率约为70%。Miao Hongfei等[26]使用图像分层理论与图像数字处理技术结合的方法进行除霜控制,与传统T-T方法相比,可使“有霜不除”和“无霜除霜”的误除霜现象造成的能耗分别降低10.6%和22.3%。Sun Huan等[27]提出一种基于灰度对比度振幅的霜厚检测方法,利用提出的新特征参数评价蒸发器盘管结霜量。该方法的精度有一定的提高,但改变光照条件时,准确率会大幅下降。Chen Siliang等[28]直接使用卷积神经网络,将实验所得图片直接放入神经网络中,对霜层状态进行分类。但当改变拍摄角度和光照条件时,结霜状态识别准确率为75%,比额定工况下降21%。
综上所述,现有的具有实用价值的蒸发器结霜状态识别方法的识别准确率多在50%~75%,仍有较大概率导致误除霜,可引起约40%[7]能源浪费,造成温度波动。因而开发具有高准确性、高适应性、高实用价值的结霜状态识别方法十分必要和紧迫。同时也可以看到,数字图像结霜识别方法在准确性和实用性上具有较好的基础,展现出巨大的潜力。但在复杂的光照强度、图像尺寸、拍摄角度和传感器性能等实际工况下,其性能仍需进一步提升。
基于此,本文从卫星遥感数字图像技术中受到启发,提出以改进的灰度共生矩阵(gray level co-occurrence matrix,GLCM)提取蒸发器表面结霜图像的纹理特征[29],构建新型特征向量简化特征的表征,结合经麻雀搜索算法(sparrow search algorithm,SSA)优化的极限学习机(extreme learning machine,ELM)最终实现准确分类的结霜状态识别方法。为研究与验证上述新方法(gray level co-occurrence matrix-supervised extreme learning machine,GLCM-SELM),搭建了蒸发器结霜模拟实验系统,实验得到不同光照等条件下的不同程度的结霜图像,并分析了其经济性。依据这些图像与现有的若干数字图像结霜识别方法进行对比,确认GLCM-SELM方法的准确性和适应性。
GLCM-SELM方法的流程原理如图1所示。将预处理后的蒸发器图像经过计算和转换,得到了保存有图像纹理特征的灰度共生矩阵(GLCM)。再用8个特征参数进一步简化表征GLCM中的图像纹理特征。最后以特征参数作为麻雀搜索优化的极限学习机(SELM)的输入量,实现图像的分类。
在图像的传输和采集过程中,常受到噪声干扰,从而导致图像数据失真。针对霜层图像,其噪声主要来源于温度突变和光照不足等因素所引发的高斯噪声。因此,本文首先采用高斯滤波的方法对图像进行处理,为后续的分析和识别奠定基础,该过程可表述为:
式中:Gij)为坐标(ij)处的函数值,能体现该点在高斯分布里的权重或概率密度;ij为像素坐标;k为高斯卷积核的大小;σ为高斯分布的标准差。
然后,将图像转化为灰度格式,如式(2)所示。
式中:G为转换后的灰度值,范围一般为0~255;RGB分别为像素点的红、绿、蓝通道值,范围为0~ 255。最后,将灰度图像进行压缩和量化处理,以降低计算复杂度并节省存储空间。即将连续的亮度值分成若干个区间,并将同一区间内的像素值映射为相同的数值。将灰度图像0~255的灰度值,按照8、16、32、64个等级别平均划分为若干个区间,并将同一区间内的像素值映射为相同的数值。
通过使用灰度共生矩阵(GLCM)对霜层的纹理特征进行量化统计。具体而言就是将蒸发器表面霜层的图像转换为黑白图像,并将其分成小块。对于每个小块,计算它与周围像素之间的灰度级别共生关系,然后根据这些关系计算出一系列统计特征,例如能量、对比度和相关性等。最后,将整个图像的所有小块的纹理特征进行汇总,并得到代表整个图像的纹理特征向量,该过程如图2(a)所示。图2(b)所示为在不同方向上对纹理特征进行统计的过程。
通过GLCM计算可得14种Haralick纹理特征,其维数较大,一般不能直接进行纹理特征的区分。需要针对不同的应用场景和任务选取不同的Haralick纹理特征进行分析。本文选取对比度、同质性、相关性和能量作为特征值进行研究。
1)角二阶矩(angular second moment,ASM):角二阶矩也被称为能量,能量是指图像中纹理的规则程度,也可以理解为纹理的强度。高能量值表示图像中的纹理相对较强、规则性较高,低能量值表示纹理较弱、规则性较低。
式中:S为角二阶矩的值。
2)同质性(Homogeneity,Hom):同质性反映了图像中纹理的一致性或均匀性。高同质性值表示图像中的纹理相互间相似度较高,低同质性值表示纹理之间差异较大。
式中:H为同质性的值。
3)相关性(Correlation,Cor):相关性描述了图像中纹理的线性关系程度。高相关性值表示纹理在不同位置间具有较强的线性关联,低相关性值表示纹理之间的线性关联较弱。
式中:O为相关性的值;uiuj分别为ij的均值;σiσj分别为ij的标准差。
4)对比度(Contrast,Con):对比度衡量了图像中明暗或颜色的变化程度。高对比度值表示图像中明暗或颜色差异明显,低对比度值表示图像中明暗或颜色变化较小。
式中:Q为对比度的值;nij的差值。
通过上述计算方法,分别求解了4个方向上的相关统计参数。然而,获得的4×4矩阵保存的图像信息将过于冗余,增加了后续机器学习的计算量。本文由4×4矩阵计算得到4个非线性相关统计参数在4个方向上的均差和标准差以简化机器学习中的输入信息。
极限学习机(extreme learning machine,ELM)是Huang Guangbin等[30]提出的一种单隐层前馈神经网络模型。通过解方程组的方法可以直接计算输出层与隐含层之间的连接权值,在保证模型精准性的同时,具有较快的学习速度,已经在各种领域得到广泛应用。此外,将麻雀优化算法(sparrow search algorithm,SSA)和ELM结合可以提升ELM的性能和泛化能力,SSA模拟了麻雀在寻找食物、避免危险和群体合作等方面的行为规律。利用SSA寻找最优的输入层与隐含层权重矩阵和偏置向量,可使ELM的性能最优化。
1)基于多阈值分割的结霜状态识别方法。多阈值分割是在将不同光照强度、像素和拍摄角度的图像数据转化为灰度图像的基础上,使每个像素的灰度值与预设的阈值进行对比[21]。通过对比为每个像素重新赋予新的特征值。该过程表述为式(7),其中,阈值K1用于区分非结霜区域和中等结霜区域,阈值K2用于区分中度结霜区域和重度结霜区域。图3所示为赋予新特征值前、后的图像对比。
通过赋值霜层图片中的像素点全部拥有新的特征数,计算整张图像的特征值平均值,同时引入结霜系数P,将特征值平均值与P进行对比,从而判断霜层状态。
式中:N为图像中像素点的个数。
2)基于卷积神经网络的结霜状态识别方法。卷积神经网络(convolutional neural network,CNN)可逐层提取图像特征,通过共享参数减少过拟合风险,在大规模数据集上具有优异表现,广泛应用于图像分类[31]、目标检测[32]和图像生成等。根据不同需求,可以通过设置激活函数、卷积核大小、隐含层和池化层数量等参数来构建卷积神经网络。本文在MATLAB环境下建立基于卷积神经网络的结霜图像识别模型。
3)基于灰度直方图的BP(back propagation)神经网络识别方法。通过统计图像像素在不同颜色的分布情况,可以得到对应的直方图。当不同灰度图像灰度级分布相同时,可能具有相同的灰度直方图[32]。在该情况下,利用灰度直方图的一对多特性可以对结霜状态的图像进行分类。图4所示为无霜、中霜和重霜3种不同结霜状态图像的直方图,可以明显看出它们之间的差异。
其次,将直方图中的灰度数据加载至BP神经网络中。针对实验得到的3种结霜状态下的灰度直方图,分别给予标签,按照一定比例划分为训练集和测试集,通过BP神经网络进行学习和预测,实现对结霜状态的预测。
4)基于分型理论的结霜状态识别方法。在霜层图形识别中可以使用分形维数来描述和分析霜层的自相似性和长程依赖性。分形维数是一种用于描述分形对象几何结构复杂性的度量指标。常用的分形维数[33]定义方式包括盒维数、信息维数和谱维数等。图5所示为霜层经过分型处理后的三维视图。
分形维数的计算可以通过将几何体分解成若干个粗略相同的子部分,并计算每个子部分需要被分解的次数,然后将得到的结果进行加权平均,得到整个几何体的分形维数。该过程可以通过计算盒计数-盒尺寸关系曲线的斜率来实现。将不同霜层状态下的分形维数作为特征,并设置标签,利用深度机器学习来识别不同光照强度下的霜层结冰状态。
为了验证和评估该方法的准确性和可行性,建立了一个空气源热泵换热器结霜模拟实验系统,并在实验过程中收集了不同阶段霜层发展的图像。这些图像对于分析和理解结霜过程中的变化非常重要。实验系统如图6所示,该系统包括一个空气源热泵换热器,用于模拟真实工况下的结霜过程。在实验过程中,使用高清摄像机捕捉了不同阶段霜层发展的图像。这些图像作为后续分析的数据源,可以用于评估提出的方法在结霜图像识别和分析中的效果。
实验系统分为2个主要区域:冷凝侧和蒸发侧。这些区域各自承担不同的功能,以模拟真实工况并实现对实验系统的有效控制。在蒸发侧,使用型号为DF100-720P的CMOS摄像机,这是一款具有高集成度相机系统的设备。采用0.635 cm的CMOS,最大分辨率可达1 280×720。同时,配备一个棒灯作为辅助光源,以此满足不同光照强度、拍摄角度及拍摄距离的要求,具体情况如图7所示。
本方法的经济性分析:相比原换热系统,本方法需要一个CMOS摄像机和图像视觉识别模块,价值57元,用于图像的获取;将原有价值约90元的控制板芯片升级为价值150元的图像处理芯片。额定输入功率为3 600 W的制冷系统,成本约为1万~3万元,额定输入功率为7 355 W的制冷系统成本约为5万~15万元,额定输入功率为14 700 W的系统成本约为10万~30万元。额外增加的设备约相当于原系统价值的3%。所以GLCM-SELM方法的成本相当低。
为了采集不同复杂工况下蒸发器表面的结霜图片,实验中模拟的蒸发侧环境温度为-20~-10 ℃,相对湿度在75%~100%之间变化;光照强度在5~ 2 370 lx之间变化;拍摄角度分为左、中、右。具体实验步骤如下:
1)在开始实验前,检查设备的连接和安装情况,确保设备能够安全运行,同时排除制冷剂泄漏、传感器和数据采集装置连接异常等问题。
2)设置相机的拍摄角度,以获取不同角度下的蒸发器霜层图像。同时,通过可调节的辅助光源,在不同光照条件下获取结霜图像。
3)调整好相机位置后,启动设备进行实验,并打开上位机中的系统运行参数数据采集装置。通过电脑用户界面进行控制,可以实时采集系统的数据,并记录温度、电流等参数的变化。
4)随着系统的运行,蒸发器翅片表面逐渐结霜并生长。选择每180 s采集一次图像,并在辅助光源的帮助下采集不同光照下的图像。一直进行图像采集,直至蒸发器表面的霜层完全覆盖后停止采集。
5)在系统运行结束后,启动强制除霜系统。
6)重新设定新的目标温度,并调整光照强度和拍摄角度。重复执行步骤2~5的操作。在同一温湿度下,多次重复实验,以消除偶然误差。
实验中光照强度为5~2 370 lx;角度为-45°~ 45°,实验所得的典型图像如图8所示。通过测量所摄图像中霜层厚度,结合制冷系统制冷性能下降比例,经综合判断将蒸发器对应的结霜状态分为无霜、中霜和重霜3类,并分别标记为1、2、3。
图像识别模型中的参数取值影响识别准确率,为确保对比的公平,先将各模型的参数均优化至最佳值。
1)GLCM-SELM模型的参数优化:GLCM-SELM模型存在一些关键参数的确定,如机器学习中隐含层节点数和激活函数的选取,以及图像量化等级g、扫描角度和扫描步长d的选择。本文在量化等级8、16、32、64,扫描步长1、2、3、4范围内搜寻最优参数。运行结果如图9所示。
2)基于多阈值分割的结霜状态识别模型的参数优化:阈值是决定将图像中的像素分为目标和背景的界限。较高的阈值会导致漏检增多,将一些真正的目标误分类为背景;较低的阈值也会导致误检增多,将一些背景误分类为目标。因此,合理选择阈值是提高准确率的关键,阈值不同导致同一张图像的结霜系数P不同,从而影响结霜状态的识别率。因此多次循环使用不同的阈值计算识别准确率,以得到最佳阈值,结果如图10(a)所示。
3)基于卷积神经网络的结霜状态识别模型的参数优化:卷积神经网络需要设置激活函数、卷积核大小、隐含层和池化层数量等参数来构建卷积神经网络。本文中使用VGG(visual geometry group)卷积神经网络,VGG网络的核心思想是通过多层堆叠的卷积层和池化层来增加网络的深度。基本架构包括几个相同的块,每块由连续的卷积层(使用小尺寸的卷积核)和池化层组成。这种简单的设计使网络具有非常深的结构,有助于提取更高级别的特征。本文采用优化的卷积核为3×3,最大池化层为2×2,卷积层数为13,全连接层数为3,组成结果如图10(b)所示。
4)基于灰度直方图的结霜状态识别模型的参数优化:基于灰度直方图的结霜状态识别方法通过计算统计不同结霜状态下图像的灰度值,以此作为机器学习的输入特征值,从而进行分类判断。在确认输入的特征值后,对分类器的结构以及参数进行优化可以不同程度地提升模型的准确度。本文采用BP神经网络进行分类判断,对其关键参数隐含层节点数和训练迭代次数进行了优化。如图10(c)所示,基于灰度直方图和BP网络的结霜状态识别模型在迭代次数为50,隐含层节点数为5时,准确率最高。
5)基于分型理论的结霜状态识别模型的参数优化:基于分型理论的结霜状态识别方法是提取霜层图像的分形维数作为特征值,同样运用BP神经网络分类器进行分类判断。图10(d)所示为该方法在考虑隐藏层节点数和迭代次数的优化过程,当迭代次数为15,隐含层节点数为13时,准确率最高。
本文通过实验获得了在不同拍摄角度、不同光照强度的复杂工况下的蒸发器结霜图像4 125张,如表1所示。并随机将数据集分为70%的训练集和30%的测试集。
为了验证GLCM-SELM方法的有效性,将样本输入不同的图像识别模型,得到各霜冻状态的训练精度、测试精度和识别率。并且对每种识别方法进行10次测试,以减少训练时的随机性,准确率的结果如图11所示。此处准确率是指分类器测试集中正确分类的样本数占总样本数比例(式(9))。可以看出GLCM-SELM方法的准确率稳定性较高,无论在低光照强度还是高光照强度下,波动均较小,并且高光照强度下单次测试准确率可达100%。而基于直方图的方法在低光照强度下波动性很明显,为5种方法中最大。在高光照强度下,5种方法的准确率均较为稳定。总体而言,10次测试中,GLCM-SELM方法的稳定性优于其他4种方法。
式中:A为准确率的值;C为正确分类的样本数;M为所有的样本个数。
图12所示为5种方法分别在低光照强度、高光照强度和混合光照强度下的识别准确率。除去卷积神经网络识别方法和直方图识别方法。无论是高光照强度(1 172 lx以上)、中光照强度(252~1 172 lx)、低光照强度(4.6~252 lx)还是混合光照的条件下,GLCM-SELM方法均有较高的识别准确率,分别为93.58%、96.58%、98.89%和95.48%,可见其在复杂光照条件下的高适应性。对于CNN卷积网络识别法其在低光照强度下有较好的识别准确率,但当光照强度提高时,准确率下降,且混合光照时,准确率仅有61.85%,受到光照强度的严重影响。对于直方图识别法,在不同光照强度下均略低于GLCM-SELM,特别是在高光照强度下识别率相对于GLCM-SELM方法低约8%。基于分形理论的识别方法,由于分形维数主要说明图像自身的相似性,重霜和无霜时的分形维数较为接近,在不同光照强度下,该方法的准确率低于GLCM-SELM方法10%~30%。基于阈值分割的识别方法,在不同光照强度下,使用同一阈值进行状态识别时,就会出现准确率的大幅度波动,所以在低光照强度下其准确率相对于GLCM-SELM方法低约15%,而在高光照强度,准确率低约30%,混合光照强度准确率仅有66.63%。表2所示为不同方法在不同光照强度下的识别准确率的方差及标准差,GLCM-SELM方法及分型理论方法的方差及标准差均较低,说明这2种方法的稳定性最好,而直方图方法的稳定性最差。
取无霜、中霜和重霜3种结霜状态下的图像样本各50个,共150个组成新的测试集。在高光照强度(2 370 lx)和低光照强度(35 lx)2种光照下分别构建上述测试集,且测试集中随机混入不同拍摄角度的样本。5种方法分别对上述测试集进行识别。图13以混淆矩阵的形式给出了不同识别方法对结霜图像进行分类的结果。混淆矩阵中0、1、2分别代表了无霜、中霜和重霜状态。混淆矩阵中对角线所在数值越大,说明该方法对于该状态下的识别越准确,对应方格的颜色也越接近深红色。对角线上某一格的水平方向上其他方格中的数据则表示将当前结霜状态错误地识别为其他状态的数量。
纵观图13中5种方法的混淆矩阵图,只有本文的GLCM-SELM方法在高、低光照强度下均呈现出完整的深红色对角线,说明其识别结果几乎完全正确。图14进一步给出了2种光照下总的识别准确率,其对重霜状态的准确率达到了100%,而对无霜和中霜状态的识别率也分别达到了98%和97%,展现出很高的精度和适应性。
基于阈值分割的方法,对于不同光照强度下的霜层图像,需要不同的阈值进行区分,当阈值满足低光照强度时,阈值偏低,导致该方法易将在高光照强度下获取的无霜状态和中霜状态的图像错误地分类至中霜状态或重霜状态,使准确率降低,反之亦然。本文通过优化将阈值控制在高低光照下识别较均衡的状态。但可以看到无论是哪种状态其对角线颜色均处于较浅的水平。由图14可知,其对无霜、中霜、重霜的总识别准确率分别仅为73%、72%、59%,为5种方法中最低的。
基于分形理论方法,在低光照强度下,易将中霜和重霜状态误认为无霜,从而霜状态的识别率较高;而高光照强度下则相反,易将无霜状态误认为重霜。其对3种状态总的识别准确率分别为73%、73%和76%。对于卷积神经网络方法在高、低光照下也有非常明显的差异,但错误方向与分型理论正好相反,其对3种状态总的识别准确率分别为68%、85%和70%。显示出光照对这2种方法的影响非常大,即这2种方法对光照的适应性较差。总体而言,这2种方法的准确率在中等水平,但很难突破75%。
基于直方图的方法,虽然与本文提出的新方法存在明显差距(对3种状态准确率分别为85%、85%、92%),但相比其他方法具有一定优势。其特点是高光照下的识别准确率明显低于低光照下的准确率,对于晴朗天气下的应用较为不利。
上述结果直观地体现出GLCM-SELM方法对于其他4种结霜状态识别方法的优势。
本文提出并研究了一种基于优化灰度共生矩阵、新型表征参数组合和极限学习机(OGLCM-SELM)的蒸发器结霜状态识别新方法。可采用低成本设备,实现较高的识别精度和对不同工况的适应性,得到结论如下:
1)搭建了蒸发器结霜实验系统,实验采集了不同光照强度和拍摄角度下的不同结霜程度的图像样本。基于实验装置分析,本方法的硬件成本相比现有设备仅增加约117元,相比大型制冷/热泵系统的成本较低,具有实用性。
2)混合拍摄角度和不同光照强度的复杂工况下,GLCM-SELM的识别准确率可达97%~100%,高于阈值分割方法的59%~73%,分型理论方法的73%~76%,卷积神经网络的68%~85%以及基于直方图方法的85%~92%,显著提升了结霜状态识别的技术水平。
3)GLCM-SELM识别方法在复杂应用条件下的稳定性也处于较高水平,其在不同工况下识别准确率的方差为0.88~7.49,与分型理论方法的2.39~5.21相近,明显优于阈值分割方法的11.1~33.85,卷积神经网络方法的1.69~14.08,以及基于直方图方法的1.17~23.38。
综上所述,GLCM-SELM表现出对不同工况的高适应性,同时也将成本保持在较低水平,是一种具有应用潜力的结霜状态识别技术。
  • 国家自然科学基金(52076185)
参考文献 引证文献
排序方式:
[1]
郭宪民. 空气源热泵结霜问题的研究现状及进展(Ⅱ)[J]. 制冷与空调(北京), 2009, 9(3): 8-14.
(GUO Xianmin. Current status and progress of air source heat pump under frosting conditions: part Ⅱ[J]. Refrigeration and Air-conditioning, 2009, 9(3): 8-14.)
[2]
LIU Jingdong, SUN Yuying, WANG Wei, et al. Performance evaluation of air source heat pump under unnecessary defrosting phenomena for nine typical cities in China[J]. International Journal of Refrigeration, 2017, 74: 385-398.
[3]
LIANG Shimin, WANG Wei, SUN Yuying, et al. A novel characteristic index for frosting suppression based on the configuration and operation of air source heat pumps[J]. International Journal of Refrigeration, 2020, 109: 161-171.
[4]
RAFATI NASR M, FAUCHOUX M, BESANT R W, et al. A review of frosting in air-to-air energy exchangers[J]. Renewable and Sustainable Energy Reviews, 2014, 30: 538-554.
[5]
肖彪. 风冷热泵商用空调除霜控制分析[J]. 家电科技, 2009(23): 55-57.
(XIAO Biao. Analysis on defrosting control of air-cooled heat pump commercial air conditioner[J]. China Appliance Technology, 2009(23): 55-57.)
[6]
WANG W, XIAO J, GUO Q C, et al. Field test investigation of the characteristics for the air source heat pump under two typical mal-defrost phenomena[J]. Applied Energy, 2011, 88(12): 4470-4480.
[7]
WANG W, FENG Y C, ZHU J H, et al. Performances of air source heat pump system for a kind of mal-defrost phenomenon appearing in moderate climate conditions[J]. Applied Energy, 2013, 112: 1138-1145.
[8]
GONG Guangcai, TANG Jinchen, LYU Dongyan, et al. Research on frost formation in air source heat pump at cold-moist conditions in central-South China[J]. Applied Energy, 2013, 102: 571-581.
[9]
王沣浩, 马龙霞, 王志华, 等. 空气源热泵除霜控制方法研究现状及展望[J]. 制冷学报, 2021, 42(5): 27-35.
(WANG Fenghao, MA Longxia, WANG Zhihua, et al. Research status and prospect on defrosting control method of air source heat pump[J]. Journal of Refrigeration, 2021, 42(5): 27-35.)
[10]
何亚屏, 胡家喜, 文宇良, 等. 中央空调高速永磁直驱变频传动系统关键技术研究及应用[J]. 制冷与空调(北京), 2018, 18(9): 1-6.
(HE Yaping, HU Jiaxi, WEN Yuliang, et al. Researchand application of key technologies for high speed PMSM direct drive VFD system of central air-conditioning[J]. Refrigeration and Air-conditioning, 2018, 18(9): 1-6.)
[11]
梁士民, 王伟, 孙育英, 等. 抑霜型空气源热泵机组应用实测研究[J]. 制冷学报, 2022, 43(5): 24-32.
(LIANG Shimin, WANG Wei, SUN Yuying, et al. Field study on the application of frost-suppression air-source heat pump units[J]. Journal of Refrigeration, 2022, 43(5): 24-32.)
[12]
刘耀, 盛伟, 方永强, 等. 铝基波纹表面结霜特性实验研究[J]. 制冷学报, 2022, 43(3): 78-86.
(LIU Yao, SHENG Wei, FANG Yongqiang, et al. Experimental study on frosting characteristics of wavy aluminum surfaces[J]. Journal of Refrigeration, 2022, 43(3): 78-86.)
[13]
邢震, 郭宪民, 李景善. 基于平均性能最优的空气源热泵除霜控制方法的研究[J]. 制冷学报, 2016, 37(3): 17-21.
(XING Zhen, GUO Xianmin, LI Jingshan. Study on the defrosting control method based on the optimal average performance of an air source heat pump[J]. Journal of Refrigeration, 2016, 37(3): 17-21.)
[14]
FOSSA M, TANDA G. Study of free convection frost formation on a vertical plate[J]. Experimental Thermal and Fluid Science, 2002, 26(6/7): 661-668.
[15]
董金锠, 王玮, 董振强. 蒸发器结霜速率实时测定[J]. 激光技术, 2000, 24(3): 179-181.
(DONG Jinchang, WANG Wei, DONG Zhenqiang. Real-time measurement for evaporator frosting rate[J]. Laser Technology, 2000, 24(3): 179-181.)
[16]
WANG Wei, XIAO Jing, FENG Yingchao, et al. Characteristics of an air source heat pump with novel photoelectric sensors during periodic frost-defrost cycles[J]. Applied Thermal Engineering, 2013, 50(1): 177-186.
[17]
周冲, 程惠尔. 图像处理在管内结霜厚度测量中的应用[J]. 上海交通大学学报, 2001, 35(8): 1175-1177.
(ZHOU Chong, CHENG Huier. Dynamic height-detecting system for growing frost in a tube[J]. Journal of Shanghai Jiao Tong University, 2001, 35(8): 1175-1177.)
[18]
QU Kaiyang, KOMORI S, JIANG Yi. Local variation of frost layer thickness and morphology[J]. International Journal of Thermal Sciences, 2006, 45(2): 116-123.
[19]
XIA Y, ZHONG Y, HRNJAK P S, et al. Frost, defrost, and refrost and its impact on the air-side thermal-hydraulic performance of louvered-fin, flat-tube heat exchangers[J]. International Journal of Refrigeration, 2006, 29(7): 1066-1079.
[20]
CHUNG Y, NA S I, CHOI J, et al. Feasibility and optimization of defrosting control method with differential pressure sensor for air source heat pump systems[J]. Applied Thermal Engineering, 2019, 155: 461-469.
[21]
陈汝东, 许东晟. 风冷热泵空调器除霜控制的研究[J]. 流体机械, 1999, 27(2): 55-57.
(CHEN Rudong, XU Dongsheng. Study on defrosting control of air-cooled heat pump air conditioner[J]. Fluid Machinery, 1999, 27(2): 55-57.)
[22]
葛住军, 许文斌, 付彬, 等. 最大平均制热量控制除霜方法的实验研究[J]. 制冷, 2007, 26(2): 14-17.
(GE Zhujun, XU Wenbin, FU Bin, et al. Research on a kind of defrosting control method-maximum average heating capacity[J]. Refrigeration, 2007, 26(2): 14-17.)
[23]
XU Yingjie, ZHAO Ruiying, WU Kai, et al. Experimental investigation and validation on an air-source heat pump frosting state recognition method based on fan current fluctuation signal and machine learning[J]. Energy, 2024, 291: 130372.
[24]
SONG Mengjie, DANG Chaobin. Review on the measurement and calculation of frost characteristics[J]. International Journal of Heat and Mass Transfer, 2018, 124: 586-614.
[25]
LI Zhaoyang, WANG Wei, SUN Yuying, et al. Applying image recognition to frost built-up detection in air source heat pumps[J]. Energy, 2021, 233: 121004.
[26]
MIAO Hongfei, YANG Xueqing, YIN Dazhen, et al. A novel defrosting control strategy with image processing technique and fractal theory[J]. International Journal of Refrigeration, 2022, 138: 259-269.
[27]
SUN Huan, ZHU Junda, LIU Xinghua, et al. Theoretical and experimental study of a new defrost control strategy based on gray scale graph theory[J]. International Journal of Refrigeration, 2022, 139: 214-224.
[28]
CHEN Siliang, CHEN Kang, ZHU Xu, et al. Deep learning-based image recognition method for on-demand defrosting control to save energy in commercial energy systems[J]. Applied Energy, 2022, 324: 119702.
[29]
XU Yingjie, XIE Yong, WANG Xiaopo, et al. Study on a novel defrost control method based on the surface texture of evaporator image with gray-level cooccurrence matrix, new characterization parameter combination and machine learning[J]. Energy and Buildings, 2023, 292: 113173.
[30]
HUANG Guangbin, ZHU Qinyu, SIEW C K. Extreme learning machine: theory and applications[J]. Neurocomputing, 2006, 70(1-3): 489-501.
[31]
ZHANG Mengxuan, LIU Long, JIN Yaochu, et al. Tree-shaped multiobjective evolutionary CNN for hyperspectral image classification[J]. Applied Soft Computing, 2024, 152: 111176.
[32]
HAN Qi, QIAN Xin, XU Hongxiang, et al. DM-CNN: Dynamic multi-scale convolutional neural network with uncertainty quantification for medical image classification[J]. Computers in Biology and Medicine, 2024, 168: 107758.
[33]
LI Guangfei, GAO Quanxue, YANG Ming, et al. Active learning based on similarity level histogram and adaptive-scale sampling for very high resolution image classification[J]. Neural Networks, 2023, 167: 22-35.
2025年第46卷第4期
PDF下载
100
44
引用本文
BibTeX
文章信息
doi: 10.12465/j.issn.0253-4339.2025.04.061
  • 接收时间:2024-01-31
  • 首发时间:2026-03-13
  • 出版时间:2025-08-16
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2024-01-31
  • 修回日期:2024-03-28
  • 录用日期:2024-05-22
基金
National Natural Science Foundation of China(52076185)
国家自然科学基金(52076185)
作者信息
    1浙江工业大学机械工程学院 杭州 310023
    2浙江盾安人工环境股份有限公司 绍兴 311835
    3浙江大学制冷与低温研究所 杭州 310007

通讯作者:

韩晓红,女,教授,博士生导师,浙江大学制冷与低温研究所,(0571)87953944,E-mail:。研究方向:高热流散热技术(主要指热管散热、微通道散热及浸没液体冷却技术)、动力电池浸没液冷热管理技术、制冷剂替代技术、制冷剂泄漏与回收及再利用技术。
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/zlxb/CN/10.12465/j.issn.0253-4339.2025.04.061
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