Article(id=1154049889966220100, tenantId=1146029695717560320, journalId=1146031654075715584, issueId=1154049103748125137, articleNumber=null, orderNo=null, doi=10.13234/j.issn.2095-2805.2024.3.111, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1706716800000, receivedDateStr=2024-02-01, revisedDate=1708272000000, revisedDateStr=2024-02-19, acceptedDate=1708358400000, acceptedDateStr=2024-02-20, onlineDate=1753076534978, onlineDateStr=2025-07-21, pubDate=1716998400000, pubDateStr=2024-05-30, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1753076534978, onlineIssueDateStr=2025-07-21, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1753076534978, creator=13701087609, updateTime=1753076534978, updator=13701087609, issue=Issue{id=1154049103748125137, tenantId=1146029695717560320, journalId=1146031654075715584, year='2024', volume='22', issue='3', pageStart='1', pageEnd='306', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=0, createTime=1753076347529, creator=13701087609, updateTime=1753780989436, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1157004586184695853, tenantId=1146029695717560320, journalId=1146031654075715584, issueId=1154049103748125137, language=EN, specialIssueTitle=, coverIllustrator=, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1157004586184695854, tenantId=1146029695717560320, journalId=1146031654075715584, issueId=1154049103748125137, language=CN, specialIssueTitle=, coverIllustrator=, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=111, endPage=117, ext={EN=ArticleExt(id=1154049890410816325, articleId=1154049889966220100, tenantId=1146029695717560320, journalId=1146031654075715584, language=EN, title=Topology Optimization and Fast Iterative Method for Power Module Heat Sink Based on Neural Network Synchronous Learning, columnId=1154049722709958995, journalTitle=Journal of Power Supply, columnName=Thermal Management and Junction Temperature Monitoring, runingTitle=null, highlight=null, articleAbstract=

With the improvement of the integration degree of power modules, the optimization of their heat transfer structures has become a focus in the development. The topology optimization(TO) can maximize the cooling performance by transforming the morphology and structure of heat sinks, thus receiving extensive attention. However, in the TO process, the temperature distribution of modules and heat sinks needs to be calculated in each iteration step, consuming a large amount of computing resource and calculation time. To accelerate the TO process of traditional heat sinks, a fast iterative method combining neural network (NN) synchronous learning and the traditional solid isotropic material with penalization (SIMP)-based TO methods is put forward. First, an NN prediction model based on the encoder-decoder structure is constructed, which can iteratively evolve the shape of heat sinks to achieve a fast prediction of optimized structures. Second, the NN model is integrated into the TO process of the heat sink based on the SIMP method, and the NN is trained synchronously using the intermediate morphology obtained in the iteration process. Finally, aimed at the single-chip and dual-chip modules, the results obtained by the new method and traditional iterative methods are compared to validate the accuracy and rapidity of the proposed NN synchronous leaning method.

, correspAuthors=null, authorNote=null, correspAuthorsNote=null, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=null, magXml=null, pdfUrl=null, pdf=null, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=null, mapNumber=null, authorCompany=null, fund=null, authors=null, authorsList=Gaojia ZHU, Hanyu HE, Longnü LI, Jianguo ZHU, Yunhui MEI), CN=ArticleExt(id=1154049914175742806, articleId=1154049889966220100, tenantId=1146029695717560320, journalId=1146031654075715584, language=CN, title=基于神经网络同步学习的功率模块散热器拓扑优化快速迭代方法, columnId=1154049722865148247, journalTitle=电源学报, columnName=热管理与结温监测, runingTitle=null, highlight=null, articleAbstract=

随着功率模块集成化程度的提高,其散热结构优化已成为研发中的关键。拓扑优化可通过变换散热器形貌、结构来最大化地提升散热效果,因此受到了广泛关注。但在拓扑优化过程中,每步迭代均需要计算模块与散热器温度分布,占用较庞大的计算资源和计算时间。为加速传统散热器拓扑优化进程,在基于传统固体各向同性材料惩罚 SIMP (solid isotropic material with penalization)散热器拓扑优化方法的基础上,提出一种嵌套神经网络 NN (neural network)同步学习的快速迭代方法。首先,构建散热器基于编码器-解码器结构的 NN 预测模型,即基于散热器形貌迭代进化过程实现优化结构的快速预测;其次,将NN 模型与散热器 SIMP拓扑优化流程相嵌套,利用迭代过程中的中间形貌同步训练 NN;最后,针对单芯片、两芯片模块结构,对比所提方法与传统迭代方法的拓扑优化结果,验证了所提NN同步学习方法的准确性和快速性。

, correspAuthors=null, authorNote=null, correspAuthorsNote=null, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=EZlaG5eCcLVtj8vWaCp+EA==, magXml=71Qepved46EVF37iuPuaVg==, pdfUrl=null, pdf=DcbNHcoYWO/VJj4sRg/TPg==, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=4CWWh5+HAW99pLWXUhLGxA==, mapNumber=null, authorCompany=null, fund=null, authors=

朱高嘉(1989-),男,中国电源学会会员,博士,副教授。研究方向:电气装备多物理场建模与优化。E-mail:zhugaojia@tiangong.edu.cn。

何函宇(2000-),男,硕士研究生。研究方向:模块散热结构优化。E-mail:928505156@qq.com。

李龙女(1988-),女,博士,副教授。研究方向:电气装备多物理场建模与优化。E-mail:lilongnv@tiangong.edu.cn。

朱建国(1958-),男,博士,教授。研究方向:新型电机拓扑结构、优化设计及其控制、新型电力电子技术及智能电网。E-mail:jianguo.zhu@sydney.edu.au。

梅云辉(1985-),男,中国电源学会高级会员,通信作者,博士,教授。研究方向:电力电子器件高可靠封装与材料。E-mail:meiyunhui@tiangong.edu.cn。

, authorsList=朱高嘉, 何函宇, 李龙女, 朱建国, 梅云辉)}, authors=[Author(id=1154049915199152990, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154049889966220100, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=zhugaojia@tiangong.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1154049915262067552, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154049889966220100, authorId=1154049915199152990, language=EN, stringName=Gaojia ZHU, firstName=Gaojia, middleName=null, lastName=ZHU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 School of Electrical Engineering Tiangong University Tianjin 300387 China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1154049915316593505, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154049889966220100, authorId=1154049915199152990, language=CN, stringName=朱高嘉, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 天津工业大学 电气工程学院 天津 300387, bio={"img":"XLw8Mp0homIdfsGzy1cnKA==","content":"

朱高嘉(1989-),男,中国电源学会会员,博士,副教授。研究方向:电气装备多物理场建模与优化。E-mail:zhugaojia@tiangong.edu.cn。

"}, bioImg=XLw8Mp0homIdfsGzy1cnKA==, bioContent=

朱高嘉(1989-),男,中国电源学会会员,博士,副教授。研究方向:电气装备多物理场建模与优化。E-mail:zhugaojia@tiangong.edu.cn。

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1154049915056546647, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154049889966220100, xref=1, ext=[AuthorCompanyExt(id=1154049915060740952, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154049889966220100, companyId=1154049915056546647, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 School of Electrical Engineering Tiangong University Tianjin 300387 China), AuthorCompanyExt(id=1154049915069129561, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154049889966220100, companyId=1154049915056546647, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 天津工业大学 电气工程学院 天津 300387)])]), Author(id=1154049915366925155, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154049889966220100, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=928505156@qq.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1154049915429839717, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154049889966220100, authorId=1154049915366925155, language=EN, stringName=Hanyu HE, firstName=Hanyu, middleName=null, lastName=HE, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 School of Electrical Engineering Tiangong University Tianjin 300387 China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1154049915488559974, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154049889966220100, authorId=1154049915366925155, language=CN, stringName=何函宇, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 天津工业大学 电气工程学院 天津 300387, bio={"content":"

何函宇(2000-),男,硕士研究生。研究方向:模块散热结构优化。E-mail:928505156@qq.com。

"}, bioImg=null, bioContent=

何函宇(2000-),男,硕士研究生。研究方向:模块散热结构优化。E-mail:928505156@qq.com。

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1154049915056546647, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154049889966220100, xref=1, ext=[AuthorCompanyExt(id=1154049915060740952, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154049889966220100, companyId=1154049915056546647, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 School of Electrical Engineering Tiangong University Tianjin 300387 China), AuthorCompanyExt(id=1154049915069129561, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154049889966220100, companyId=1154049915056546647, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 天津工业大学 电气工程学院 天津 300387)])]), Author(id=1154049915543085928, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154049889966220100, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=lilongnv@tiangong.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1154049915597611882, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154049889966220100, authorId=1154049915543085928, language=EN, stringName=Longnü LI, firstName=Longnü, middleName=null, lastName=LI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 School of Electrical Engineering Tiangong University Tianjin 300387 China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1154049915647943531, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154049889966220100, authorId=1154049915543085928, language=CN, stringName=李龙女, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 天津工业大学 电气工程学院 天津 300387, bio={"content":"

李龙女(1988-),女,博士,副教授。研究方向:电气装备多物理场建模与优化。E-mail:lilongnv@tiangong.edu.cn。

"}, bioImg=null, bioContent=

李龙女(1988-),女,博士,副教授。研究方向:电气装备多物理场建模与优化。E-mail:lilongnv@tiangong.edu.cn。

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1154049915056546647, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154049889966220100, xref=1, ext=[AuthorCompanyExt(id=1154049915060740952, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154049889966220100, companyId=1154049915056546647, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 School of Electrical Engineering Tiangong University Tianjin 300387 China), AuthorCompanyExt(id=1154049915069129561, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154049889966220100, companyId=1154049915056546647, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 天津工业大学 电气工程学院 天津 300387)])]), Author(id=1154049915710858093, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154049889966220100, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=jianguo.zhu@sydney.edu.au, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1154049915769578351, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154049889966220100, authorId=1154049915710858093, language=EN, stringName=Jianguo ZHU, firstName=Jianguo, middleName=null, lastName=ZHU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2 School of Electrical and Information Engineering University of Sydney Sydney 2006 Australia, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1154049915840881520, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154049889966220100, authorId=1154049915710858093, language=CN, stringName=朱建国, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2 悉尼大学 电气与信息工程学院 悉尼 2006, bio={"content":"

朱建国(1958-),男,博士,教授。研究方向:新型电机拓扑结构、优化设计及其控制、新型电力电子技术及智能电网。E-mail:jianguo.zhu@sydney.edu.au。

"}, bioImg=null, bioContent=

朱建国(1958-),男,博士,教授。研究方向:新型电机拓扑结构、优化设计及其控制、新型电力电子技术及智能电网。E-mail:jianguo.zhu@sydney.edu.au。

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1154049915127849818, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154049889966220100, xref=2, ext=[AuthorCompanyExt(id=1154049915136238427, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154049889966220100, companyId=1154049915127849818, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 School of Electrical and Information Engineering University of Sydney Sydney 2006 Australia), AuthorCompanyExt(id=1154049915140432732, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154049889966220100, companyId=1154049915127849818, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 悉尼大学 电气与信息工程学院 悉尼 2006)])]), Author(id=1154049915895407474, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154049889966220100, orderNo=4, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=meiyunhui@tiangong.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1154049915962516340, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154049889966220100, authorId=1154049915895407474, language=EN, stringName=Yunhui MEI, firstName=Yunhui, middleName=null, lastName=MEI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 School of Electrical Engineering Tiangong University Tianjin 300387 China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1154049916017042293, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154049889966220100, authorId=1154049915895407474, language=CN, stringName=梅云辉, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 天津工业大学 电气工程学院 天津 300387, bio={"content":"

梅云辉(1985-),男,中国电源学会高级会员,通信作者,博士,教授。研究方向:电力电子器件高可靠封装与材料。E-mail:meiyunhui@tiangong.edu.cn。

"}, bioImg=null, bioContent=

梅云辉(1985-),男,中国电源学会高级会员,通信作者,博士,教授。研究方向:电力电子器件高可靠封装与材料。E-mail:meiyunhui@tiangong.edu.cn。

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1154049915056546647, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154049889966220100, xref=1, ext=[AuthorCompanyExt(id=1154049915060740952, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154049889966220100, companyId=1154049915056546647, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 School of Electrical Engineering Tiangong University Tianjin 300387 China), AuthorCompanyExt(id=1154049915069129561, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154049889966220100, companyId=1154049915056546647, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 天津工业大学 电气工程学院 天津 300387)])])], keywords=[Keyword(id=1154049916256117622, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154049889966220100, language=EN, orderNo=1, keyword=Optimization and design of heat sink structure), Keyword(id=1154049916302254967, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154049889966220100, language=EN, orderNo=2, keyword=topology optimization (TO)), Keyword(id=1154049916356780920, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154049889966220100, language=EN, orderNo=3, keyword=density variation method), Keyword(id=1154049916407112569, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154049889966220100, language=EN, orderNo=4, keyword=neural network synchronous deep learning), Keyword(id=1154049916470027130, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154049889966220100, language=CN, orderNo=1, keyword=散热器结构优化设计), Keyword(id=1154049916524553083, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154049889966220100, language=CN, orderNo=2, keyword=拓扑优化), Keyword(id=1154049916570690428, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154049889966220100, language=CN, orderNo=3, keyword=变密度法), Keyword(id=1154049916629410685, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154049889966220100, language=CN, orderNo=4, keyword=神经网络同步深度学习)], refs=[Reference(id=1154049918974026644, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154049889966220100, doi=null, pmid=null, pmcid=null, year=2023, volume=38, issue=18, pageStart=4947, pageEnd=4962, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=王来利, 赵成, 张彤宇, journalName=电工技术学报, refType=null, unstructuredReference=王来利, 赵成, 张彤宇, 等. 碳化硅功率模块封装技术综述[J]. 电工技术学报, 2023. 38(18): 4947-4962., articleTitle=碳化硅功率模块封装技术综述, refAbstract=null), Reference(id=1154049919036941205, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154049889966220100, doi=null, pmid=null, pmcid=null, year=2023, volume=38, issue=18, pageStart=4947, pageEnd=4962, url=null, language=null, rfNumber=[1], rfOrder=1, authorNames=Wang Laili, Zhao Cheng, Zhang Tongyu, journalName=Transactions of China Electrotechnical Society, refType=null, unstructuredReference=Wang Laili, Zhao Cheng, Zhang Tongyu, et al. Review of packaging technology for silicon carbide power modules[J]. Transactions of China Electrotechnical Society, 2023. 38(18): 4947-4962 (in Chinese)., articleTitle=Review of packaging technology for silicon carbide power modules, refAbstract=null), Reference(id=1154049919083078550, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154049889966220100, doi=null, pmid=null, pmcid=null, year=2019, volume=155, issue=null, pageStart=65, pageEnd=75, url=null, language=null, rfNumber=[2], rfOrder=2, authorNames=Shur M, journalName=Solid-State Electronics, refType=null, unstructuredReference=Shur M. Wide band gap semiconductor technology: State-of-the-art[J]. Solid-State Electronics, 2019. 155: 65-75., articleTitle=Wide band gap semiconductor technology: State-of-the-art, refAbstract=null), Reference(id=1154049919137604503, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154049889966220100, doi=null, pmid=null, pmcid=null, year=2023, volume=259, issue=null, pageStart=108594, pageEnd=null, url=null, language=null, rfNumber=[3], rfOrder=3, authorNames=Sun Chen, Wang Wei, Tian Xiwei, journalName=International Journal of Mechanical Sciences, refType=null, unstructuredReference=Sun Chen, Wang Wei, Tian Xiwei, et al. Thermal design of composite cold plates by topology optimization[J]. International Journal of Mechanical Sciences, 2023. 259: 108594., articleTitle=Thermal design of composite cold plates by topology optimization, refAbstract=null), Reference(id=1154049919200519064, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154049889966220100, doi=null, pmid=null, pmcid=null, year=2021, volume=216, issue=null, pageStart=119223, pageEnd=null, url=null, language=null, rfNumber=[4], rfOrder=4, authorNames=He Ziqiang, Yan Yunfei, Zhang Zhien, journalName=Energy, refType=null, unstructuredReference=He Ziqiang, Yan Yunfei, Zhang Zhien. Thermal management and temperature uniformity enhancement of electronic devices by micro heat sinks: A review[J]. Energy, 2021. 216: 119223., articleTitle=Thermal management and temperature uniformity enhancement of electronic devices by micro heat sinks: A review, refAbstract=null), Reference(id=1154049919259239321, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154049889966220100, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=1317, pageEnd=1322, url=null, language=null, rfNumber=[5], rfOrder=5, authorNames=null, journalName=IECON 2020 the 46th Annual Conference of the IEEE Industrial Electronics Society. Singapore, refType=null, unstructuredReference=Designing thermally uniform heatsink with rectangular pins for high-power automotive SiC inverters[C]// IECON 2020 the 46th Annual Conference of the IEEE Industrial Electronics Society. Singapore, 2020: 1317-1322., articleTitle=Designing thermally uniform heatsink with rectangular pins for high-power automotive SiC inverters, refAbstract=null), Reference(id=1154049919309570970, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154049889966220100, doi=null, pmid=null, pmcid=null, year=1994, volume=31, issue=17, pageStart=2313, pageEnd=2329, url=null, language=null, rfNumber=[6], rfOrder=6, authorNames=Sigmund O, journalName=International Journal of Solids and Structures, refType=null, unstructuredReference=Sigmund O. Materials with prescribed constitutive parameters: An inverse homogenization problem[J]. International Journal of Solids and Structures, 1994. 31(17): 2313-2329., articleTitle=Materials with prescribed constitutive parameters: An inverse homogenization problem, refAbstract=null), Reference(id=1154049919359902619, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154049889966220100, doi=null, pmid=null, pmcid=null, year=1999, volume=42, issue=17, pageStart=3361, pageEnd=3371, url=null, language=null, rfNumber=[7], rfOrder=7, authorNames=Li Qing, Steven G P, Querin O M, journalName=International Journal of Heat and Mass Transfer, refType=null, unstructuredReference=Li Qing, Steven G P, Querin O M, et al. Shape and topology design for heat conduction by evolutionary structural optimization[J]. International Journal of Heat and Mass Transfer, 1999. 42(17): 3361-3371., articleTitle=Shape and topology design for heat conduction by evolutionary structural optimization, refAbstract=null), Reference(id=1154049919401845660, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154049889966220100, doi=null, pmid=null, pmcid=null, year=2022, volume=101, issue=null, pageStart=276, pageEnd=308, url=null, language=null, rfNumber=[8], rfOrder=8, authorNames=Li Hao, Kondoh T, Jolivet P, journalName=Applied Mathematical Modelling, refType=null, unstructuredReference=Li Hao, Kondoh T, Jolivet P, et al. Three-dimensional topology optimization of a fluid-structure system using body-fitted mesh adaption based on the level-set method[J]. Applied Mathematical Modelling, 2022. 101: 276-308., articleTitle=Three-dimensional topology optimization of a fluid-structure system using body-fitted mesh adaption based on the level-set method, refAbstract=null), Reference(id=1154049919452177309, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154049889966220100, doi=null, pmid=null, pmcid=null, year=1999, volume=69, issue=null, pageStart=635, pageEnd=654, url=null, language=null, rfNumber=[9], rfOrder=9, authorNames=Bendsøe M P, Sigmund O, journalName=Archive of Applied Mechanics, refType=null, unstructuredReference=Bendsøe M P, Sigmund O. Material interpolation schemes in topology optimization[J]. Archive of Applied Mechanics, 1999. 69: 635-654., articleTitle=Material interpolation schemes in topology optimization, refAbstract=null), Reference(id=1154049919515091870, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154049889966220100, doi=null, pmid=null, pmcid=null, year=2022, volume=8, issue=null, pageStart=718, pageEnd=726, url=null, language=null, rfNumber=[10], rfOrder=10, authorNames=Xie Liyao, Zhang Yan, Ge Minghui, journalName=Energy Reports, refType=null, unstructuredReference=Xie Liyao, Zhang Yan, Ge Minghui, et al. Topology optimization of heat sink based on variable density method[J]. Energy Reports, 2022. 8: 718-726., articleTitle=Topology optimization of heat sink based on variable density method, refAbstract=null), Reference(id=1154049919565423519, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154049889966220100, doi=null, pmid=null, pmcid=null, year=2019, volume=34, issue=4, pageStart=215, pageEnd=223, url=null, language=null, rfNumber=[11], rfOrder=11, authorNames=Sosnovik I, Oseledets I, journalName=Russian Journal of Numerical Analysis and Mathematical Modelling, refType=null, unstructuredReference=Sosnovik I, Oseledets I. Neural networks for topology optimization[J]. Russian Journal of Numerical Analysis and Mathematical Modelling, 2019. 34(4): 215-223., articleTitle=Neural networks for topology optimization, refAbstract=null), Reference(id=1154049919624143776, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154049889966220100, doi=null, pmid=null, pmcid=null, year=2020, volume=62, issue=3, pageStart=1185, pageEnd=1212, url=null, language=null, rfNumber=[12], rfOrder=12, authorNames=Kallioras N A, Kazakis G, Lagaros N D, journalName=Structural and Multidisciplinary Optimization, refType=null, unstructuredReference=Kallioras N A, Kazakis G, Lagaros N D. Accelerated topology optimization by means of deep learning[J]. Structural and Multidisciplinary Optimization, 2020. 62(3): 1185-1212., articleTitle=Accelerated topology optimization by means of deep learning, refAbstract=null), Reference(id=1154049919682864033, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154049889966220100, doi=null, pmid=null, pmcid=null, year=2022, volume=42, issue=2, pageStart=715, pageEnd=728, url=null, language=null, rfNumber=[13], rfOrder=13, authorNames=陈宇, 吴强, 周宇, journalName=中国电机工程学报, refType=null, unstructuredReference=陈宇, 吴强, 周宇, 等. 基于傅里叶级数解析热扩散角的功率模块热阻抗物理模型[J]. 中国电机工程学报, 2022. 42(2): 715-728., articleTitle=基于傅里叶级数解析热扩散角的功率模块热阻抗物理模型, refAbstract=null), Reference(id=1154049919741584290, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154049889966220100, doi=null, pmid=null, pmcid=null, year=2022, volume=42, issue=2, pageStart=715, pageEnd=728, url=null, language=null, rfNumber=[13], rfOrder=14, authorNames=Chen Yu, Wu Qiang, Zhou Yu, journalName=Proceedings of the CSEE, refType=null, unstructuredReference=Chen Yu, Wu Qiang, Zhou Yu, et al. Physics-based thermal impedance model for power module by analytic fourier series based heat spreading angle[J]. Proceedings of the CSEE, 2022. 42(2): 715-728 (in Chinese)., articleTitle=Physics-based thermal impedance model for power module by analytic fourier series based heat spreading angle, refAbstract=null), Reference(id=1154049919791915939, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154049889966220100, doi=null, pmid=null, pmcid=null, year=2023, volume=55, issue=8, pageStart=1336, pageEnd=1351, url=null, language=null, rfNumber=[14], rfOrder=15, authorNames=Yan Jun, Xu Qi, Fan Zhirui, journalName=Engineering Optimization, refType=null, unstructuredReference=Yan Jun, Xu Qi, Fan Zhirui, et al. A study on topology optimization of heat dissipation structures with different objective functions based on an explicit moving morphable components method[J]. Engineering Optimization, 2023. 55(8): 1336-1351., articleTitle=A study on topology optimization of heat dissipation structures with different objective functions based on an explicit moving morphable components method, refAbstract=null), Reference(id=1154049919846441892, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154049889966220100, doi=null, pmid=null, pmcid=null, year=2020, volume=119, issue=null, pageStart=13, pageEnd=24, url=null, language=null, rfNumber=[15], rfOrder=16, authorNames=Zhao Qinghai, Fan C M, Wang Fajie, journalName=Engineering Analysis with Boundary Elements, refType=null, unstructuredReference=Zhao Qinghai, Fan C M, Wang Fajie, et al. Topology optimization of steady-state heat conduction structures using meshless generalized finite difference method[J]. Engineering Analysis with Boundary Elements, 2020. 119: 13-24., articleTitle=Topology optimization of steady-state heat conduction structures using meshless generalized finite difference method, refAbstract=null), Reference(id=1154049919900967845, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154049889966220100, doi=null, pmid=null, pmcid=null, year=2021, volume=63, issue=null, pageStart=39, pageEnd=58, url=null, language=null, rfNumber=[16], rfOrder=17, authorNames=Han Haitao, Guo Yuchen, Chen Shikui, journalName=Structural and Multidisciplinary Optimization, refType=null, unstructuredReference=Han Haitao, Guo Yuchen, Chen Shikui, et al. Topological constraints in 2D structural topology optimization[J]. Structural and Multidisciplinary Optimization, 2021. 63: 39-58., articleTitle=Topological constraints in 2D structural topology optimization, refAbstract=null), Reference(id=1154049919959688102, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154049889966220100, doi=null, pmid=null, pmcid=null, year=2019, volume=59, issue=3, pageStart=787, pageEnd=799, url=null, language=null, rfNumber=[17], rfOrder=18, authorNames=Yu Y, Hur T, Jung J, journalName=Structural and Multidisciplinary Optimization, refType=null, unstructuredReference=Yu Y, Hur T, Jung J, et al. Deep learning for determining a near-optimal topological design without any iteration[J]. Structural and Multidisciplinary Optimization, 2019. 59(3): 787-799., articleTitle=Deep learning for determining a near-optimal topological design without any iteration, refAbstract=null)], funds=[Fund(id=1154049918609122190, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154049889966220100, awardId=52177189, language=EN, fundingSource=National Natural Science Foundation of China(52177189), fundOrder=null, country=null), Fund(id=1154049918667842447, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154049889966220100, awardId=52177189, language=CN, fundingSource=国家自然科学基金资助项目(52177189), fundOrder=null, country=null), Fund(id=1154049918718174096, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154049889966220100, awardId=21JCJQJC00150, language=EN, fundingSource=Tianjin Outstanding Youth Fundation(21JCJQJC00150), fundOrder=null, country=null), Fund(id=1154049918768505745, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154049889966220100, awardId=21JCJQJC00150, language=CN, fundingSource=天津市杰出青年基金资助项目(21JCJQJC00150), fundOrder=null, country=null), Fund(id=1154049918823031698, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154049889966220100, awardId=HZKY20220604, language=EN, fundingSource="Chunhui Plan" Collaborative Research Project of Ministry of Education of China(HZKY20220604), fundOrder=null, country=null), Fund(id=1154049918885946259, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154049889966220100, awardId=HZKY20220604, language=CN, fundingSource=教育部“春晖计划”国际合作科研项目(HZKY20220604), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1154049915056546647, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154049889966220100, xref=1, ext=[AuthorCompanyExt(id=1154049915060740952, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154049889966220100, companyId=1154049915056546647, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 School of Electrical Engineering Tiangong University Tianjin 300387 China), AuthorCompanyExt(id=1154049915069129561, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154049889966220100, companyId=1154049915056546647, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 天津工业大学 电气工程学院 天津 300387)]), AuthorCompany(id=1154049915127849818, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154049889966220100, xref=2, ext=[AuthorCompanyExt(id=1154049915136238427, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154049889966220100, companyId=1154049915127849818, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 School of Electrical and Information Engineering University of Sydney Sydney 2006 Australia), AuthorCompanyExt(id=1154049915140432732, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154049889966220100, companyId=1154049915127849818, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 悉尼大学 电气与信息工程学院 悉尼 2006)])], figs=[ArticleFig(id=1154049917606683518, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154049889966220100, language=EN, label=Fig. 1, caption=Iteration process of typical heat transfer topology optimization problem, figureFileSmall=xVUJyNwpHRKI6L7ENqyHXw==, figureFileBig=DbNckYrsFe9U0ha+yDMLLg==, tableContent=null), ArticleFig(id=1154049917669598079, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154049889966220100, language=CN, label=图1, caption=典型传热拓扑优化问题迭代过程, figureFileSmall=xVUJyNwpHRKI6L7ENqyHXw==, figureFileBig=DbNckYrsFe9U0ha+yDMLLg==, tableContent=null), ArticleFig(id=1154049917740901248, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154049889966220100, language=EN, label=Fig. 2, caption=Structure of neural network model, figureFileSmall=QIZ2owqRAYYxuQ4NgASbxQ==, figureFileBig=RmArr3cuY2aXPPeYECks1g==, tableContent=null), ArticleFig(id=1154049917791232897, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154049889966220100, language=CN, label=图2, caption=神经网络模型结构, figureFileSmall=QIZ2owqRAYYxuQ4NgASbxQ==, figureFileBig=RmArr3cuY2aXPPeYECks1g==, tableContent=null), ArticleFig(id=1154049917849953154, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154049889966220100, language=EN, label=Fig. 3, caption=Flow chart of topology optimization program using neural network nested method, figureFileSmall=NXeBwxB3KG3gU5yEemLiWw==, figureFileBig=wrptvSmOuBChSOxY7LPxGw==, tableContent=null), ArticleFig(id=1154049917921256323, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154049889966220100, language=CN, label=图3, caption=神经网络嵌套方法拓扑优化程序流程, figureFileSmall=NXeBwxB3KG3gU5yEemLiWw==, figureFileBig=wrptvSmOuBChSOxY7LPxGw==, tableContent=null), ArticleFig(id=1154049917984170884, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154049889966220100, language=EN, label=Fig. 4, caption=Training data including intermediate results, figureFileSmall=3NtD/7Vgx6e/GZVpXbmLEg==, figureFileBig=uA2Zr8dJX4O3qNn7D0bdBA==, tableContent=null), ArticleFig(id=1154049918047085445, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154049889966220100, language=CN, label=图4, caption=包含中间结果的训练数据, figureFileSmall=3NtD/7Vgx6e/GZVpXbmLEg==, figureFileBig=uA2Zr8dJX4O3qNn7D0bdBA==, tableContent=null), ArticleFig(id=1154049918110000006, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154049889966220100, language=EN, label=Fig. 5, caption=Comparison between structures obtained by nested method and SIMP method in Example 1 under two grid sizes, figureFileSmall=JEbFl/L1nJVNAULdJykyPw==, figureFileBig=lfeRzn2tENZfFZW46iWC4w==, tableContent=null), ArticleFig(id=1154049918168720263, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154049889966220100, language=CN, label=图5, caption=两种网格大小下算例 1 嵌套方法与 SIMP 法所得结构对比, figureFileSmall=JEbFl/L1nJVNAULdJykyPw==, figureFileBig=lfeRzn2tENZfFZW46iWC4w==, tableContent=null), ArticleFig(id=1154049918227440520, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154049889966220100, language=EN, label=Fig. 6, caption=Description of heat transfer optimization problem in Example 2, figureFileSmall=sDhlhZXVzkBGsxWAqPRv9A==, figureFileBig=LofP6xbPhRXYmMlTuS9o6A==, tableContent=null), ArticleFig(id=1154049918277772169, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154049889966220100, language=CN, label=图6, caption=算例 2 传热优化问题描述, figureFileSmall=sDhlhZXVzkBGsxWAqPRv9A==, figureFileBig=LofP6xbPhRXYmMlTuS9o6A==, tableContent=null), ArticleFig(id=1154049918328103818, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154049889966220100, language=EN, label=Fig. 7, caption=Comparison between structures obtained by nested method and SIMP method in Example 2, figureFileSmall=oRu0C+RClIg218aXqtZjGQ==, figureFileBig=pBkeL9znWcp82ZTueQarow==, tableContent=null), ArticleFig(id=1154049918378435467, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154049889966220100, language=CN, label=图7, caption=算例 2 嵌套方法与 SIMP 法所得结构对比, figureFileSmall=oRu0C+RClIg218aXqtZjGQ==, figureFileBig=pBkeL9znWcp82ZTueQarow==, tableContent=null), ArticleFig(id=1154049918437155724, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154049889966220100, language=EN, label=Tab. 1, caption=Objective function error and time saving percentage of nested methods, figureFileSmall=null, figureFileBig=null, tableContent=
使用 方法 迭代 次数 迭代 时间/s 目标 函数 目标函数误 差百分比/% 节省时间 百分比/%
SIMP (40x40) 134 12.95 368.05 - -
嵌套 (40x40) 78 6.90 369.43 0.37 46.72
SIMP$\left({{80}\times {80}}\right)$ 334 251.68 5216.71 - -
嵌套$\left({{80}\times {80}}\right)$ 232 173.59 5205.08 0.22 31.02
), ArticleFig(id=1154049918495875981, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1154049889966220100, language=CN, label=表1, caption=嵌套方法的目标函数误差及节省时间百分比, figureFileSmall=null, figureFileBig=null, tableContent=
使用 方法 迭代 次数 迭代 时间/s 目标 函数 目标函数误 差百分比/% 节省时间 百分比/%
SIMP (40x40) 134 12.95 368.05 - -
嵌套 (40x40) 78 6.90 369.43 0.37 46.72
SIMP$\left({{80}\times {80}}\right)$ 334 251.68 5216.71 - -
嵌套$\left({{80}\times {80}}\right)$ 232 173.59 5205.08 0.22 31.02
)], attaches=null, journal=Journal(id=1046111678587809797, delFlag=0, nameCn=电源学报, nameEn=Journal of Power Supply, nameHistory1=null, nameHistory2=null, issn=2095-2805, eissn=, cn=12-1420/TM, coden=null, periodic=bio-monthly, language=CN, oaType=是, ccby=null, superviseOffice=null, ownerOffice=null, pubOffice=null, editorOffice=null, officeType=null, aims=null, clcCode=null, officeProv=null, officeCity=null, officeAddr=null, officeZip=null, officeEmail=null, officePhone=null, editDirector=null, officeDirector=null, officeDirectorPhone=null, officeStaffNum=null, officeEmpNum=null, coverPicUrl=Mx+A2dn+ULnPHuEAI1LruQ==, journalPrice=null, startedYear=null, abbrevIsoEn=J Power Supp, journalRemark=null, publicationField=null, createdTime=null, updatedTime=1759802942253, createdBy=null, updatedBy=18614031015, firstLetterCn=J, firstLetterEn=J, subjectCode=Engineering, subjectName=工程, subjectCodeEn=Engineering, subjectNameEn=null, picCn=Mx+A2dn+ULnPHuEAI1LruQ==, picEn=yHt2vwjzkDgqh+JDCfJKoQ==, jcr=null, cjcr=null, exts=[JournalExt(id=1162453073839375337, language=CN, name=电源学报, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=null, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=http://www.jops.cn/EN/home, createdTime=1755080010137, updatedTime=1755080010137, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=http://www.jops.cn/CN/column/column7.shtml, submissionAuthorUrl=https://mc03.manuscriptcentral.com/jops, submissionEditorUrl=https://mc03.manuscriptcentral.com/jops, submissionReviewUrl=https://mc03.manuscriptcentral.com/jops, submissionCeEditorUrl=https://mc03.manuscriptcentral.com/jops, submissionAeEditorUrl=https://mc03.manuscriptcentral.com/jops, option={"copyright":""}), JournalExt(id=1162453073902289898, language=EN, name=Journal of Power Supply, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=null, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=http://www.jops.cn/CN/home, createdTime=1755080010152, updatedTime=1755080010152, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=http://www.jops.cn/EN/column/column7.shtml, submissionAuthorUrl=https://mc03.manuscriptcentral.com/jops, submissionEditorUrl=https://mc03.manuscriptcentral.com/jops, submissionReviewUrl=https://mc03.manuscriptcentral.com/jops, submissionCeEditorUrl=https://mc03.manuscriptcentral.com/jops, submissionAeEditorUrl=https://mc03.manuscriptcentral.com/jops, option={"copyright":""})], databaseList=null, tenantJournalId=1146031654075715584, websiteList=[Website(id=1146832214672683008, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146031654075715584, 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/dyxb/EN, language=EN, createTime=1751355707101, createBy=18614031015, updateTime=1753435268747, updateBy=18614031015, name=电源学报-英文站点, tplId=1146101810881728533, title=电源学报, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1155559379819679852, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1146832214672683008, code=articleTextType, value=kx, createTime=1753436425404, updateTime=1753436425404, creator=18614031015, updator=18614031015), WebsiteProps(id=1155559379798708329, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1146832214672683008, code=banner, value=null, createTime=1753436425399, updateTime=1753436425399, creator=18614031015, updator=18614031015), WebsiteProps(id=1155559379781931112, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1146832214672683008, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=efYTu4aDDzS8GgTA1MjEKw==, createTime=1753436425396, updateTime=1753436425396, creator=18614031015, updator=18614031015), WebsiteProps(id=1155559379811291243, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1146832214672683008, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1753436425402, updateTime=1753436425402, creator=18614031015, updator=18614031015), WebsiteProps(id=1155559379802902634, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1146832214672683008, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1753436425400, updateTime=1753436425400, creator=18614031015, updator=18614031015)]), Website(id=1148243202240405915, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146031654075715584, 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/dyxb/CN, language=CN, createTime=1751692112741, createBy=18614031015, updateTime=1753435242839, updateBy=18614031015, name=电源学报-中文站点, tplId=1146099689490845704, title=电源学报, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1148618015060553758, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202240405915, code=articleTextType, value=kx, createTime=1751781475081, updateTime=1751781475081, creator=18614031015, updator=18614031015), WebsiteProps(id=1148618015035387931, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202240405915, code=banner, value=null, createTime=1751781475075, updateTime=1751781475075, creator=18614031015, updator=18614031015), WebsiteProps(id=1148618015022805018, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202240405915, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=efYTu4aDDzS8GgTA1MjEKw==, createTime=1751781475072, updateTime=1751781475072, creator=18614031015, updator=18614031015), WebsiteProps(id=1148618015052165149, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202240405915, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1751781475079, updateTime=1751781475079, creator=18614031015, updator=18614031015), WebsiteProps(id=1148618015043776540, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202240405915, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1751781475077, updateTime=1751781475077, creator=18614031015, updator=18614031015)])], journalTitle=电源学报, weixinUrl=null, journalUrl=http://www.jops.cn/CN/home, iacademicId=null, status=0, seqNo=null, journalTitleEn=Journal of Power Supply, journalPhotoCn=Mx+A2dn+ULnPHuEAI1LruQ==, journalPhotoEn=yHt2vwjzkDgqh+JDCfJKoQ==, 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=null, provinceCode=null, provinceName=null, collectFlag=false), detailUrlCn=https://castjournals.cast.org.cn/joweb/dyxb/CN/10.13234/j.issn.2095-2805.2024.3.111, detailUrlEn=https://castjournals.cast.org.cn/joweb/dyxb/EN/10.13234/j.issn.2095-2805.2024.3.111, pdfUrlCn=https://castjournals.cast.org.cn/joweb/dyxb/CN/PDF/10.13234/j.issn.2095-2805.2024.3.111, pdfUrlEn=https://castjournals.cast.org.cn/joweb/dyxb/EN/PDF/10.13234/j.issn.2095-2805.2024.3.111, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于神经网络同步学习的功率模块散热器拓扑优化快速迭代方法
收藏切换
PDF下载
朱高嘉 1 , 何函宇 1 , 李龙女 1 , 朱建国 2 , 梅云辉 1
电源学报 | 热管理与结温监测 2024,22(3): 111-117
收起
收藏切换
电源学报 | 热管理与结温监测 2024, 22(3): 111-117
基于神经网络同步学习的功率模块散热器拓扑优化快速迭代方法
全屏
朱高嘉1 , 何函宇1 , 李龙女1 , 朱建国2 , 梅云辉1
作者信息
  • 1 天津工业大学 电气工程学院 天津 300387
  • 2 悉尼大学 电气与信息工程学院 悉尼 2006
  • 朱高嘉(1989-),男,中国电源学会会员,博士,副教授。研究方向:电气装备多物理场建模与优化。E-mail:zhugaojia@tiangong.edu.cn。

    何函宇(2000-),男,硕士研究生。研究方向:模块散热结构优化。E-mail:928505156@qq.com。

    李龙女(1988-),女,博士,副教授。研究方向:电气装备多物理场建模与优化。E-mail:lilongnv@tiangong.edu.cn。

    朱建国(1958-),男,博士,教授。研究方向:新型电机拓扑结构、优化设计及其控制、新型电力电子技术及智能电网。E-mail:jianguo.zhu@sydney.edu.au。

    梅云辉(1985-),男,中国电源学会高级会员,通信作者,博士,教授。研究方向:电力电子器件高可靠封装与材料。E-mail:meiyunhui@tiangong.edu.cn。

Topology Optimization and Fast Iterative Method for Power Module Heat Sink Based on Neural Network Synchronous Learning
Gaojia ZHU1 , Hanyu HE1 , Longnü LI1 , Jianguo ZHU2 , Yunhui MEI1
Affiliations
  • 1 School of Electrical Engineering Tiangong University Tianjin 300387 China
  • 2 School of Electrical and Information Engineering University of Sydney Sydney 2006 Australia
出版时间: 2024-05-30 doi: 10.13234/j.issn.2095-2805.2024.3.111
文章导航
收藏切换

随着功率模块集成化程度的提高,其散热结构优化已成为研发中的关键。拓扑优化可通过变换散热器形貌、结构来最大化地提升散热效果,因此受到了广泛关注。但在拓扑优化过程中,每步迭代均需要计算模块与散热器温度分布,占用较庞大的计算资源和计算时间。为加速传统散热器拓扑优化进程,在基于传统固体各向同性材料惩罚 SIMP (solid isotropic material with penalization)散热器拓扑优化方法的基础上,提出一种嵌套神经网络 NN (neural network)同步学习的快速迭代方法。首先,构建散热器基于编码器-解码器结构的 NN 预测模型,即基于散热器形貌迭代进化过程实现优化结构的快速预测;其次,将NN 模型与散热器 SIMP拓扑优化流程相嵌套,利用迭代过程中的中间形貌同步训练 NN;最后,针对单芯片、两芯片模块结构,对比所提方法与传统迭代方法的拓扑优化结果,验证了所提NN同步学习方法的准确性和快速性。

散热器结构优化设计  /  拓扑优化  /  变密度法  /  神经网络同步深度学习

With the improvement of the integration degree of power modules, the optimization of their heat transfer structures has become a focus in the development. The topology optimization(TO) can maximize the cooling performance by transforming the morphology and structure of heat sinks, thus receiving extensive attention. However, in the TO process, the temperature distribution of modules and heat sinks needs to be calculated in each iteration step, consuming a large amount of computing resource and calculation time. To accelerate the TO process of traditional heat sinks, a fast iterative method combining neural network (NN) synchronous learning and the traditional solid isotropic material with penalization (SIMP)-based TO methods is put forward. First, an NN prediction model based on the encoder-decoder structure is constructed, which can iteratively evolve the shape of heat sinks to achieve a fast prediction of optimized structures. Second, the NN model is integrated into the TO process of the heat sink based on the SIMP method, and the NN is trained synchronously using the intermediate morphology obtained in the iteration process. Finally, aimed at the single-chip and dual-chip modules, the results obtained by the new method and traditional iterative methods are compared to validate the accuracy and rapidity of the proposed NN synchronous leaning method.

Optimization and design of heat sink structure  /  topology optimization (TO)  /  density variation method  /  neural network synchronous deep learning
朱高嘉, 何函宇, 李龙女, 朱建国, 梅云辉. 基于神经网络同步学习的功率模块散热器拓扑优化快速迭代方法. 电源学报, 2024 , 22 (3) : 111 -117 . DOI: 10.13234/j.issn.2095-2805.2024.3.111
Gaojia ZHU, Hanyu HE, Longnü LI, Jianguo ZHU, Yunhui MEI. Topology Optimization and Fast Iterative Method for Power Module Heat Sink Based on Neural Network Synchronous Learning[J]. Journal of Power Supply, 2024 , 22 (3) : 111 -117 . DOI: 10.13234/j.issn.2095-2805.2024.3.111
以碳化硅 SiC(silicon carbide) 和氮化镓 GaN (gallium nitride)为代表的第三代半导体材料具备宽禁带宽度、低导通压和高热导率的优势,因此在电气化交通、工业制造和航空航天等领域得到了广泛应用[1-2]。然而,随着器件功率密度的不断提高,高效散热技术已成为限制其进一步发展的关键因素[34]。针对该问题, 国内外学者积极探索诸多散热系统的设计与优化手段[5],但传统优化方法仅能计及散热结构尺寸与数量的变化, 难以克服工程经验限制以实现散热器形貌的彻底优化设计, 从而无法发挥有限空间内的最大化散热性能。
自 1994 年 Sigmund${\mathrm{O}}^{\left\lbrack 6\right\rbrack }$ 首先使用逆均匀化方法获得具有极端热膨胀系数的复合材料后,出现了许多拓扑优化技术在热传导问题中的应用方法, 如进化结构优化法、水平集法等[7-8]。目前,应用最广泛的是固体各向同性材料惩罚法 SIMP (solid isotropic material with penalization${)}^{\left\lbrack 9 -{10}\right\rbrack }$,其通过定义材料相对密度得到材料在设计域中的最优分布,但大型结构拓扑优化需重复进行有限元计算且计算效率较低, 而深度学习法因其更强大的数据处理能力, 被广泛应用于拓扑优化研究。Sosnovik I 等[1] 首先利用深度学习作为有效的逐图像标记技术来执行拓扑优化,减少了总时间消耗;Kallioras NA 等[12] 将深度置信网络集成到 SIMP 方法中,将所需的迭代次数减少一个数量级以上。然而, 现有模型需通过大量拓扑优化运算来收集训练样本, 并在此基础上独立进行神经网络训练,因而训练时间需与拓扑优化时间相叠加,限制了全流程总体效率的提升。
针对该问题, 本文在 SIMP 方法的框架下, 提出一种将编码器-解码器神经网络模型与 SIMP 法嵌套的模块散热器同步学习快速拓扑优化方法, 利用传统 SIMP 法优化过程中的中间迭代结果, 在后续拓扑优化迭代的过程中同步训练神经网络;在神经网络预测结果与后续拓扑优化迭代结果差别小于预设值后, 应用神经网络替代拓扑优化迭代, 从而有效降低总体优化时间。
典型单芯片模块散热器设计域简化拓扑优化模型如图1(a) 所示。其中,由于模块内芯片发出的热量延热扩散角传递至散热器[13],为了计算简便, 在设计域左侧以均匀单体热源$\mathrm{Q}$ 等效。设计域中, 散热器部分为自然对流散热, 需通过拓扑优化区分散热器(铜)和冷却介质(空气)。当设计域中某区域为散热器时, 其具备较高热传导性能; 而当其为冷却介质 (空气) 时,铜制散热齿可向该冷却介质通过自然对流换热。因此, 若设计域中散热器部分过多, 势必造成对流换热面积不足,限制散热能力;反之, 若冷却介质区域过大, 则存在热源发出的热量难以有效传导至自然对流换热面的问题。针对该问题, 需通过拓扑优化得到散热器与冷却介质的最优分布结构与散热器形貌。此外, 为了保证优化目标的全局性,在稳态热传导问题中通常以散热弱度为目标函数, 散热弱度越小, 结构向周围介质散热的能力越强[14]
$ x =\left\{{{x}_{1},{x}_{2},\cdots,{x}_{n}}\right\}\in {R}^{n}$
$ C ={\mathbf{T}}^{\mathrm{T}}\mathbf{K}\left( x\right)\mathbf{T}= \mathop{\sum }\limits_{{e = 1}}^{n}{\mathbf{T}}_{\mathrm{e}}^{\mathrm{T}}{\mathbf{K}}_{\mathrm{e}}{\mathbf{T}}_{\mathrm{e}}$
$\mathop{\sum }\limits_{{e = 1}}^{n}{x}_{\mathrm{e}}{v}_{\mathrm{e}}\leq f \cdot {V}_{0}$
$ K\mathbf{T}= \mathbf{P}$
$ 0 <{x}_{\min }\leq {x}_{\mathrm{e}}\leq 1 $
式中:$C$ 为结构散热弱度;$\mathbf{T}$ 为节点温度向量;$\mathbf{K}$ 为整体结构热传导矩阵;$\mathbf{P}$ 为整体结构的热载荷向量;$x$ 为单元密度,即设计变量;${\mathbf{T}}_{\mathrm{e}}$ 为单元节点温度向量;${x}_{\mathrm{e}}$ 为各材料单元的相对密度;${v}_{\mathrm{e}}$ 为单元体积;${V}_{0}$ 为设计域的总体积;$f$ 为材料体积分数;$n$ 为单元总数;${x}_{\min }$ 为单元密度最小值,用于防止计算时出现奇异矩阵,一般取 0.001。单元热传导矩阵${\mathbf{K}}_{\mathrm{e}}$ 的定义[15]为
${\mathbf{K}}_{\mathrm{e}}= {f}_{\mathrm{e}}\left({x}_{\mathrm{e}}\right){\mathbf{K}}_{0}$
式中,${\mathbf{K}}_{0}$ 为结构拓扑空间中相对密度为 1 时的单元热传导矩阵。${f}_{\mathrm{e}}\left({x}_{\mathrm{e}}\right)$ 为人为定义的指数函数模型[16], 可表示为
${f}_{\mathrm{e}}\left({x}_{\mathrm{e}}\right)= {x}_{\mathrm{e}}^{p}$
式中:$p$ 为 SIMP 插值模型中的惩罚因子,可使设计变量趋近于 “ 0 ”或 “ 1 ”,从而减少求解过程中出现的灰度单元现象,其趋近程度随$p$ 的增大而增大。$p$ 一般设定为 2~5。
基于上述算法理论, 可得图1(a) 所示简化模型的拓扑优化迭代过程与最终收敛结果, 分别如图1(b)~(e)所示。
图1 可见, 随着拓扑优化迭代的进行, 散热器与空气界面逐渐清晰,最终得到树状结构,能够最大化地提升散热效果。此外,由优化过程可见,仅通过 30 步迭代,基本的散热器树状结构已形成,但即使针对图1(a) 所示的简化结构, 优化算法仍需通过约 100 步迭代来精细化优化结果、明确散热器与冷却介质的截面,这导致了优化时间的增大。因此,当设计问题复杂度提高时,限制了其的优化效率。
建立与 SIMP 法程序相嵌套的深度全卷积神经网络模型, 如图2 所示。模型的输入为 1 个单通道灰度图像,输出为对此灰度结构的预测图像。模型由 1 个编码器网络和 1 个解码器网络组成, 其中编码器网络包含 2 个卷积层, 每层的卷积核大小均为$3 \times 3$,采用 relu 激活函数保证其非线性,接着通过内核大小为$2 \times 2$ 的最大池化层将特征图像尺寸减半,减少训练过程中学习参数的数量。在其之后插入最大池化层, 并通过池化最大元素得到 64 张特征图。解码器结构则将编码器结构反转,包含 2 个卷积层,将池化层替换为上采样层,采用$2 \times 2$ 的内核, 并与编码器中对应的池化层相连, 融合深层和浅层的特征信息。同时,为了减少输出设计变量中的灰度单元,采用双曲正切滤波器,可表示为
${x}_{\text{new }}= \frac{{e}^{{x}_{out}}- {e}^{-{x}_{out}}}{{e}^{{x}_{out}}+ {e}^{-{x}_{out}}}$
式中:${x}_{\text{out }}$ 为自动编码器的输出值;${x}_{\text{new }}$ 为最终输出的预测密度值。解码器通过逐步增加图像的空间尺寸将数据恢复到原始大小, 同时减少特征深度, 最后的回归输出层用于计算损失函数。
建立嵌套同步学习神经网络的拓扑优化计算流程, 如图3 所示。其中, 不需专有数据集对神经网络进行训练,而是采用传统 SIMP 法程序中获得的中间结果作为样本, 同步训练神经网络, 在其达到足够预测精度后,替代拓扑优化迭代来提高收敛速度。如图4 所示,将第$n + 5$ 次迭代结构作为第$n$ 次迭代结构的样本标签,标签样本为对应样本更进一步的迭代结构。神经网络通过学习从非清晰图像到清晰图像的映射,达到预测迭代结构的目的。
为了保证优化程序与训练的同步进行, 在拓扑优化开始运行后首先保存 5 组初始训练数据, 自动编码器利用优化程序初始迭代得到 5 组数据进行训练,新的训练样本按照每次训练迭代增加 5 组进行补充, 直到达到设定的训练样本数量上限, 使训练过程不会因为中间结构补充过慢而延误。在设计域网格大小为${40}\times {40}$ 的情况下,保存初始训练数据所需时间少于$1\mathrm{\;s}$。达到设定的样本上限后,神经网络利用整组数据重复进行训练,当达到误差条件 (2 次训练过程损失函数之差小于 0.0001 )后,调用自动编码器对当前迭代进行预测,并利用预测结构替代当前拓扑优化迭代结构, 使用更接近最终解的预测值进行拓扑优化, 以使后续操作能更早地获得最终结构, 从而减少传统拓扑优化程序所需的迭代次数。
在训练过程中, 采用的损失函数被定义为
$ L =\alpha \cdot {L}_{\mathrm{{RMSE}}}+ \beta \cdot {L}_{\text{vol }}$
${L}_{\text{RMSE }}= \sqrt{\frac{1}{NM}\mathop{\sum }\limits_{{i = 1}}^{N}\mathop{\sum }\limits_{{j = 1}}^{M}{\left({\mathrm{x}}_{\text{true }}^{ij}- {\mathrm{x}}_{\text{pred }}^{ij}\right)}^{2}}$
${L}_{\text{vol }}= {\left({\bar{x}}_{\text{pred }}- {\bar{x}}_{\text{true }}\right)}^{2}$
式中:${L}_{\text{RMSE }}$ 为重构损失,即均方根误差;$N$$M$ 的乘积为图像总像素数量;${x}_{\text{true }}$${x}_{\text{pred }}$ 分别为真实样本和神经网络的预测样本;${L}_{\mathrm{{vol}}}$ 为体积分数约束,用以保证预测结果的准确性。由于重构损失较小时的体积分数损失也同样较小, 因此选择重构损失占总损失函数的较大比例,即将$\alpha$$\beta$ 分别取值为 0.7 和${0.3}^{\left\lbrack {17}\right\rbrack }$
训练优化过程使用 ADAM 默认优化器, 训练过程借助 MATLAB 的并行计算工具箱 PCT(parallel computing toolbox) 进行并行计算, 拓扑优化程序在 CPU 进行, 训练过程被分配到 GPU 进行, 当数据集大小为 30 组样本时, 在 NVIDIA RTX 3060 上重复训练 100 次迭代约需$4 \sim 5\mathrm{s}$
本文研究目的是验证所提嵌套方法对于加速传统拓扑优化程序的作用,即比较所提方法与传统 SIMP 法在减少迭代时间方面的性能来验证所提方法的有效性。所得最终结构的散热弱度直接表征结构的散热能力, 所提嵌套方法与传统 SIMP 所得目标函数差异决定结构散热能力的差异。误差函数百分比越小, 说明 2 种方法所得结构散热能力的差异越小。计算嵌套方法最终所得结构目标函数的误差,验证其准确性。
以单芯片模块散热拓扑优化为算例 1, 体积分数设置为 0.5。当网格数量为${40}\times {40}$ 、仅使用 SIMP 拓扑优化程序时得到的最终结构如图5(c) 所示, 第 134 次迭代时达到收敛,总耗费时间为${12.95}\mathrm{\;s}$。 在使用嵌套方法时,分别选取 1~15 次和 6~20 次迭代样本作为训练数据。当拓扑优化程序进行到第 31 次迭代时,训练满足训练收敛条件,自动编码器自行预测第 31 次迭代图像,输入图像和预测结构图像分别如图5(a) 和 (b) 所示, 可见预测图像虽有较多的灰度单元,但具有较为细化的分支结构, 此时拓扑优化程序历时${3.67}\mathrm{\;s}$。而后利用预测图像继续进行后续拓扑优化进程, 最终在第 78 次迭代达到收敛,耗时${3.23}\mathrm{\;s}$,因此采用嵌套程序从开始运行到获得最终结构总耗时为${6.9}\mathrm{\;s}$,最终结构如图5(d) 所示, 与单独使用 SIMP 法拓扑优化程序时的输出结构拓扑基本相同。在网格大小为${80}\times {80}$ 的情况下,所得结构分别如图5(e)~(h)所示,选取 1~25 次和 6~30 次迭代作为训练数据,当程序进行到第 37 次迭代时神经网络训练完成, 耗时${11.34}\mathrm{\;s}$。传统 SIMP 法和嵌套方法所需迭代时间及所得最终结构的目标函数(散热弱度)误差见表1, 结果表明, 在目标函数几乎不变的情况下, 本文方法减少了传统 SIMP 拓扑优化程序所需的迭代次数及总耗时。当网格数量增大时, SIMP 法整个迭代进程所需总时间增加,与此同时每次迭代所需时间的增加会导致使用嵌套方法节省的总时间也在增加, 即在网格数量过大时, 同样能够保证嵌套方法在节省时间方面的作用。
为验证本文算法的泛化能力, 针对多芯片模块散热需求进行拓扑优化设计。此时,假设模块内多芯片位置经过合理设计, 传导至散热器时, 各芯片对应热扩散角完全无交叠(即无热耦合作用)且布满连接面 (最大化散热能力), 以该问题为算例 2, 如图6 所示。
使用 SIMP 法与使用嵌套程序所得最终结构分别如图7(c)和(d)所示。选取 1~25 次和 6~30 次,第 35 次迭代作为训练数据。第 35 次迭代图像及预测结构分别如图7(a)和(b)所示。迭代次数由 221 次减少到 141 次,得到最终结构所需时间由${134.14}\mathrm{\;s}$ 减少至 86.38 s,总时间减少约 35.60%。
针对功率模块散热器的拓扑优化, 本文将神经网络同步学习与 SIMP 拓扑优化迭代相结合, 通过迭代数据保存、神经网络训练、当前迭代结构预测及后续拓扑优化的基本流程, 建立嵌套神经网络同步学习的 SIMP 高效迭代方法, 实现散热器形貌结构的快速迭代优化。研究结果表明,针对单芯片、两芯片模块散热需求, 单芯片使用神经网络嵌套方法在网格大小为${40}\times {40}$ 下,与传统 SIMP 方法相比, 拓扑迭代所需总时间减少了 46.72%,在网格大小为${80}\times {80}$ 下,拓扑迭代所需总时间减少了 31.02%; 针对两芯片散热算例,拓扑迭代所需总时间减少了 35.60%, 同时目标函数误差百分比约为 0.30%。研究结果验证了本文所提方法的准确性与高效性。
  • 国家自然科学基金资助项目(52177189)
  • 天津市杰出青年基金资助项目(21JCJQJC00150)
  • 教育部“春晖计划”国际合作科研项目(HZKY20220604)
参考文献 引证文献
排序方式:
[1]
王来利, 赵成, 张彤宇, 等. 碳化硅功率模块封装技术综述[J]. 电工技术学报, 2023. 38(18): 4947-4962.
Wang Laili, Zhao Cheng, Zhang Tongyu, et al. Review of packaging technology for silicon carbide power modules[J]. Transactions of China Electrotechnical Society, 2023. 38(18): 4947-4962 (in Chinese).
[2]
Shur M. Wide band gap semiconductor technology: State-of-the-art[J]. Solid-State Electronics, 2019. 155: 65-75.
[3]
Sun Chen, Wang Wei, Tian Xiwei, et al. Thermal design of composite cold plates by topology optimization[J]. International Journal of Mechanical Sciences, 2023. 259: 108594.
[4]
He Ziqiang, Yan Yunfei, Zhang Zhien. Thermal management and temperature uniformity enhancement of electronic devices by micro heat sinks: A review[J]. Energy, 2021. 216: 119223.
[5]
Designing thermally uniform heatsink with rectangular pins for high-power automotive SiC inverters[C]// IECON 2020 the 46th Annual Conference of the IEEE Industrial Electronics Society. Singapore, 2020: 1317-1322.
[6]
Sigmund O. Materials with prescribed constitutive parameters: An inverse homogenization problem[J]. International Journal of Solids and Structures, 1994. 31(17): 2313-2329.
[7]
Li Qing, Steven G P, Querin O M, et al. Shape and topology design for heat conduction by evolutionary structural optimization[J]. International Journal of Heat and Mass Transfer, 1999. 42(17): 3361-3371.
[8]
Li Hao, Kondoh T, Jolivet P, et al. Three-dimensional topology optimization of a fluid-structure system using body-fitted mesh adaption based on the level-set method[J]. Applied Mathematical Modelling, 2022. 101: 276-308.
[9]
Bendsøe M P, Sigmund O. Material interpolation schemes in topology optimization[J]. Archive of Applied Mechanics, 1999. 69: 635-654.
[10]
Xie Liyao, Zhang Yan, Ge Minghui, et al. Topology optimization of heat sink based on variable density method[J]. Energy Reports, 2022. 8: 718-726.
[11]
Sosnovik I, Oseledets I. Neural networks for topology optimization[J]. Russian Journal of Numerical Analysis and Mathematical Modelling, 2019. 34(4): 215-223.
[12]
Kallioras N A, Kazakis G, Lagaros N D. Accelerated topology optimization by means of deep learning[J]. Structural and Multidisciplinary Optimization, 2020. 62(3): 1185-1212.
[13]
陈宇, 吴强, 周宇, 等. 基于傅里叶级数解析热扩散角的功率模块热阻抗物理模型[J]. 中国电机工程学报, 2022. 42(2): 715-728.
Chen Yu, Wu Qiang, Zhou Yu, et al. Physics-based thermal impedance model for power module by analytic fourier series based heat spreading angle[J]. Proceedings of the CSEE, 2022. 42(2): 715-728 (in Chinese).
[14]
Yan Jun, Xu Qi, Fan Zhirui, et al. A study on topology optimization of heat dissipation structures with different objective functions based on an explicit moving morphable components method[J]. Engineering Optimization, 2023. 55(8): 1336-1351.
[15]
Zhao Qinghai, Fan C M, Wang Fajie, et al. Topology optimization of steady-state heat conduction structures using meshless generalized finite difference method[J]. Engineering Analysis with Boundary Elements, 2020. 119: 13-24.
[16]
Han Haitao, Guo Yuchen, Chen Shikui, et al. Topological constraints in 2D structural topology optimization[J]. Structural and Multidisciplinary Optimization, 2021. 63: 39-58.
[17]
Yu Y, Hur T, Jung J, et al. Deep learning for determining a near-optimal topological design without any iteration[J]. Structural and Multidisciplinary Optimization, 2019. 59(3): 787-799.
2024年第22卷第3期
PDF下载
309
117
引用本文
BibTeX
文章信息
doi: 10.13234/j.issn.2095-2805.2024.3.111
  • 接收时间:2024-02-01
  • 首发时间:2025-07-21
  • 出版时间:2024-05-30
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2024-02-01
  • 修回日期:2024-02-19
  • 录用日期:2024-02-20
基金
National Natural Science Foundation of China(52177189)
国家自然科学基金资助项目(52177189)
Tianjin Outstanding Youth Fundation(21JCJQJC00150)
天津市杰出青年基金资助项目(21JCJQJC00150)
"Chunhui Plan" Collaborative Research Project of Ministry of Education of China(HZKY20220604)
教育部“春晖计划”国际合作科研项目(HZKY20220604)
作者信息
    1 天津工业大学 电气工程学院 天津 300387
    2 悉尼大学 电气与信息工程学院 悉尼 2006
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/dyxb/CN/10.13234/j.issn.2095-2805.2024.3.111
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