Article(id=1228805366801166411, tenantId=1146029695717560320, journalId=1225147924628267009, issueId=1228805359561802007, articleNumber=null, orderNo=null, doi=10.16385/j.cnki.issn.1004-4523.2025.06.002, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1743350400000, receivedDateStr=2025-03-31, revisedDate=1746806400000, revisedDateStr=2025-05-10, acceptedDate=null, acceptedDateStr=null, onlineDate=1770899629545, onlineDateStr=2026-02-12, pubDate=1749484800000, pubDateStr=2025-06-10, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1770899629545, onlineIssueDateStr=2026-02-12, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1770899629545, creator=13701087609, updateTime=1770899629545, updator=13701087609, issue=Issue{id=1228805359561802007, tenantId=1146029695717560320, journalId=1225147924628267009, year='2025', volume='38', issue='6', pageStart='1133', pageEnd='1362', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1770899627819, creator=13701087609, updateTime=1770901542852, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1228813391846896476, tenantId=1146029695717560320, journalId=1225147924628267009, issueId=1228805359561802007, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1228813391846896477, tenantId=1146029695717560320, journalId=1225147924628267009, issueId=1228805359561802007, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=1134, endPage=1144, ext={EN=ArticleExt(id=1228805367161876576, articleId=1228805366801166411, tenantId=1146029695717560320, journalId=1225147924628267009, language=EN, title=Online monitoring and intelligent internal quality discrimination method for laser powder bed fusion based on acoustic emission signals, columnId=null, journalTitle=Journal of Vibration Engineering, columnName=null, runingTitle=null, highlight=null, articleAbstract=

Laser powder bed fusion (LPBF) technology, a cutting-edge process in metal additive manufacturing, has been successfully applied in high-end manufacturing sectors like aerospace. However, strong multi-physical field coupling effects frequently lead to dynamic instability in the molten pool, causing widespread porosity defects within fabricated parts and severely impacting forming quality stability. Traditional monitoring methods face limitations such as high cost and deployment difficulties, struggling to meet industrial production demands. To address these challenges, this paper proposes an online monitoring and intelligent internal quality discrimination method based on acoustic emission (AE)-deep learning fusion. An AE sensor-based online monitoring system for the LPBF process was developed. By continously monitoring AE signals throughout the entire process, the mapping relationship between AE signal characteristics and forming quality was revealed, creating a molten pool AE dataset comprising over 80,000 samples. To tackle the difficulty of extracting weak fluctuation features from the molten pool, a frequency domain feature extraction network based on the adaptive Fourier neural operator (AFNO) and a high-dimensional feature mapping classifier based on the Kolmogorov-Arnold network (KAN) were constructed. This approach analyzes molten pool dynamic characteristics through a multi-scale time domain feature fusion mechanism. By precisely mapping high-dimensional features using high-dimensional manifolds, the method achieves enhanced characterization of weak fluctuation features in AE signals and high-precision quality discrimination. Experimental results demonstrate that developed monitoring system effectively captures the dynamic behavior of the molten pool, and the proposed method achieves a quality discrimination accuracy exceeding 97%.

, 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=Xingwu ZHANG, Jiafeng TANG, Kunpeng TAN, Zhibin ZHAO, Xuefeng CHEN, Yinghong Li), CN=ArticleExt(id=1228805369728790822, articleId=1228805366801166411, tenantId=1146029695717560320, journalId=1225147924628267009, language=CN, title=基于声发射信号的激光粉末床熔融在线监测与内部质量智能判别方法, columnId=0, journalTitle=振动工程学报, columnName=, runingTitle=null, highlight=null, articleAbstract=

激光粉末床熔融(laser powder bed fusion, LPBF)技术作为金属增材制造领域的前沿工艺,已被成功应用于航空航天等高端制造领域。然而多物理场强耦合效应易引发熔池动态失稳,导致制件内部孔隙缺陷频发,严重影响成形质量稳定性。传统监测手段受限于成本高、部署困难等瓶颈,难以满足工业化生产需求。为此,提出声发射-深度学习融合的在线监测与内部质量智能判别方法。研制了基于声发射传感器的LPBF过程在线监测系统,通过工艺过程全周期声发射信号监测揭示声发射信号特征与成形质量间的映射规律,构建了包含逾8万组样本的熔池声发射数据。针对熔池微弱波动特征提取难题,构建了基于自适应傅里叶神经算子(AFNO)的频域特征提取网络和Kolmogorov-Arnold网络(KAN)的高维特征映射分类器,通过多尺度时域特征融合机制解析熔池动态特性,并借助高维流形精确映射高维特征,实现了声发射信号中微弱波动特征的增强表征和高精度质量判别。试验结果表明:研制的监测系统可有效捕获熔池的动态行为,所提方法质量判别精度达97%以上。

, correspAuthors=null, authorNote=null, correspAuthorsNote=
赵志斌(1993—),男,博士,副教授。E-mail:
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=4mVS4eOeCb7S5XG+0UvPbg==, magXml=v3T2VAbdjy6yLHcNMbEqYA==, pdfUrl=null, pdf=q0rJX0i+dKjN0ZpbPDB7LA==, pdfFileSize=1649543, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=uMCyVu3RIMEFTkUYBLk/1g==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=BzQJazrPmQkrJ/FWUf5zCQ==, mapNumber=null, authorCompany=null, fund=null, authors=

张兴武(1984—),男,博士,教授。E-mail:

, authorsList=张兴武, 唐甲锋, 谭鲲鹏, 赵志斌, 陈雪峰, 李应红)}, authors=[Author(id=1228805370215330133, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=xwzhang@xjtu.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1228805370341159266, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, authorId=1228805370215330133, language=EN, stringName=Xingwu ZHANG, firstName=Xingwu, middleName=null, lastName=ZHANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1.National Key Lab of Aerospace Power System and Plasma Technology,Xi’an Jiaotong University,Xi’an 710049,China
2.School of Mechanical Engineering,Xi’an Jiaotong University,Xi’an 710049,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1228805370425045354, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, authorId=1228805370215330133, language=CN, stringName=张兴武, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1.西安交通大学航空动力系统与等离子体技术全国重点实验室,陕西 西安 710049
2.西安交通大学机械工程学院,陕西 西安 710049, bio={"content":"

张兴武(1984—),男,博士,教授。E-mail:

"}, bioImg=null, bioContent=

张兴武(1984—),男,博士,教授。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1228805369938506044, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, xref=1., ext=[AuthorCompanyExt(id=1228805369946894653, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, companyId=1228805369938506044, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.National Key Lab of Aerospace Power System and Plasma Technology,Xi’an Jiaotong University,Xi’an 710049,China), AuthorCompanyExt(id=1228805369951088958, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, companyId=1228805369938506044, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.西安交通大学航空动力系统与等离子体技术全国重点实验室,陕西 西安 710049)]), AuthorCompany(id=1228805370026586438, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, xref=2., ext=[AuthorCompanyExt(id=1228805370034975046, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, companyId=1228805370026586438, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.School of Mechanical Engineering,Xi’an Jiaotong University,Xi’an 710049,China), AuthorCompanyExt(id=1228805370039169353, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, companyId=1228805370026586438, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.西安交通大学机械工程学院,陕西 西安 710049)])]), Author(id=1228805370496348531, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, 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=1228805370571846014, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, authorId=1228805370496348531, language=EN, stringName=Jiafeng TANG, firstName=Jiafeng, middleName=null, lastName=TANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1.National Key Lab of Aerospace Power System and Plasma Technology,Xi’an Jiaotong University,Xi’an 710049,China
2.School of Mechanical Engineering,Xi’an Jiaotong University,Xi’an 710049,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1228805370676703624, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, authorId=1228805370496348531, language=CN, stringName=唐甲锋, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1.西安交通大学航空动力系统与等离子体技术全国重点实验室,陕西 西安 710049
2.西安交通大学机械工程学院,陕西 西安 710049, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1228805369938506044, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, xref=1., ext=[AuthorCompanyExt(id=1228805369946894653, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, companyId=1228805369938506044, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.National Key Lab of Aerospace Power System and Plasma Technology,Xi’an Jiaotong University,Xi’an 710049,China), AuthorCompanyExt(id=1228805369951088958, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, companyId=1228805369938506044, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.西安交通大学航空动力系统与等离子体技术全国重点实验室,陕西 西安 710049)]), AuthorCompany(id=1228805370026586438, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, xref=2., ext=[AuthorCompanyExt(id=1228805370034975046, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, companyId=1228805370026586438, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.School of Mechanical Engineering,Xi’an Jiaotong University,Xi’an 710049,China), AuthorCompanyExt(id=1228805370039169353, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, companyId=1228805370026586438, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.西安交通大学机械工程学院,陕西 西安 710049)])]), Author(id=1228805370768978318, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, 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=1228805370865447321, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, authorId=1228805370768978318, language=EN, stringName=Kunpeng TAN, firstName=Kunpeng, middleName=null, lastName=TAN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1.National Key Lab of Aerospace Power System and Plasma Technology,Xi’an Jiaotong University,Xi’an 710049,China
2.School of Mechanical Engineering,Xi’an Jiaotong University,Xi’an 710049,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1228805370957722014, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, authorId=1228805370768978318, language=CN, stringName=谭鲲鹏, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1.西安交通大学航空动力系统与等离子体技术全国重点实验室,陕西 西安 710049
2.西安交通大学机械工程学院,陕西 西安 710049, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1228805369938506044, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, xref=1., ext=[AuthorCompanyExt(id=1228805369946894653, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, companyId=1228805369938506044, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.National Key Lab of Aerospace Power System and Plasma Technology,Xi’an Jiaotong University,Xi’an 710049,China), AuthorCompanyExt(id=1228805369951088958, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, companyId=1228805369938506044, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.西安交通大学航空动力系统与等离子体技术全国重点实验室,陕西 西安 710049)]), AuthorCompany(id=1228805370026586438, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, xref=2., ext=[AuthorCompanyExt(id=1228805370034975046, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, companyId=1228805370026586438, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.School of Mechanical Engineering,Xi’an Jiaotong University,Xi’an 710049,China), AuthorCompanyExt(id=1228805370039169353, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, companyId=1228805370026586438, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.西安交通大学机械工程学院,陕西 西安 710049)])]), Author(id=1228805371070968233, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=zhaozhibin@xjtu.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1228805371184214450, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, authorId=1228805371070968233, language=EN, stringName=Zhibin ZHAO, firstName=Zhibin, middleName=null, lastName=ZHAO, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1.National Key Lab of Aerospace Power System and Plasma Technology,Xi’an Jiaotong University,Xi’an 710049,China
2.School of Mechanical Engineering,Xi’an Jiaotong University,Xi’an 710049,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1228805371284877756, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, authorId=1228805371070968233, language=CN, stringName=赵志斌, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1.西安交通大学航空动力系统与等离子体技术全国重点实验室,陕西 西安 710049
2.西安交通大学机械工程学院,陕西 西安 710049, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1228805369938506044, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, xref=1., ext=[AuthorCompanyExt(id=1228805369946894653, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, companyId=1228805369938506044, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.National Key Lab of Aerospace Power System and Plasma Technology,Xi’an Jiaotong University,Xi’an 710049,China), AuthorCompanyExt(id=1228805369951088958, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, companyId=1228805369938506044, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.西安交通大学航空动力系统与等离子体技术全国重点实验室,陕西 西安 710049)]), AuthorCompany(id=1228805370026586438, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, xref=2., ext=[AuthorCompanyExt(id=1228805370034975046, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, companyId=1228805370026586438, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.School of Mechanical Engineering,Xi’an Jiaotong University,Xi’an 710049,China), AuthorCompanyExt(id=1228805370039169353, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, companyId=1228805370026586438, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.西安交通大学机械工程学院,陕西 西安 710049)])]), Author(id=1228805371410706888, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, orderNo=4, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1228805371536536019, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, authorId=1228805371410706888, language=EN, stringName=Xuefeng CHEN, firstName=Xuefeng, middleName=null, lastName=CHEN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1.National Key Lab of Aerospace Power System and Plasma Technology,Xi’an Jiaotong University,Xi’an 710049,China
2.School of Mechanical Engineering,Xi’an Jiaotong University,Xi’an 710049,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1228805371649782234, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, authorId=1228805371410706888, language=CN, stringName=陈雪峰, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1.西安交通大学航空动力系统与等离子体技术全国重点实验室,陕西 西安 710049
2.西安交通大学机械工程学院,陕西 西安 710049, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1228805369938506044, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, xref=1., ext=[AuthorCompanyExt(id=1228805369946894653, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, companyId=1228805369938506044, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.National Key Lab of Aerospace Power System and Plasma Technology,Xi’an Jiaotong University,Xi’an 710049,China), AuthorCompanyExt(id=1228805369951088958, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, companyId=1228805369938506044, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.西安交通大学航空动力系统与等离子体技术全国重点实验室,陕西 西安 710049)]), AuthorCompany(id=1228805370026586438, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, xref=2., ext=[AuthorCompanyExt(id=1228805370034975046, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, companyId=1228805370026586438, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.School of Mechanical Engineering,Xi’an Jiaotong University,Xi’an 710049,China), AuthorCompanyExt(id=1228805370039169353, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, companyId=1228805370026586438, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.西安交通大学机械工程学院,陕西 西安 710049)])]), Author(id=1228805371729474017, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, 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=1228805371821748712, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, authorId=1228805371729474017, language=EN, stringName=Yinghong Li, firstName=Yinghong, middleName=null, lastName=Li, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3.National Key Lab of Aerospace Power System and Plasma Technology,Air Force Engineering University,Xi’an 710038,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1228805371939189231, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, authorId=1228805371729474017, language=CN, stringName=李应红, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3.空军工程大学航空动力系统与等离子体技术全国重点实验室,陕西 西安 710038, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1228805370114666828, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, xref=3., ext=[AuthorCompanyExt(id=1228805370123055438, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, companyId=1228805370114666828, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3.National Key Lab of Aerospace Power System and Plasma Technology,Air Force Engineering University,Xi’an 710038,China), AuthorCompanyExt(id=1228805370127249743, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, companyId=1228805370114666828, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3.空军工程大学航空动力系统与等离子体技术全国重点实验室,陕西 西安 710038)])])], keywords=[Keyword(id=1228805372060824060, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, language=EN, orderNo=1, keyword=laser powder bed fusion), Keyword(id=1228805372148904451, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, language=EN, orderNo=2, keyword=process monitoring), Keyword(id=1228805372236984837, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, language=EN, orderNo=3, keyword=acoustic emission), Keyword(id=1228805372371202573, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, language=EN, orderNo=4, keyword=quality evaluation), Keyword(id=1228805372442505749, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, language=EN, orderNo=5, keyword=deep learning), Keyword(id=1228805372538974748, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, language=CN, orderNo=1, keyword=激光粉末床熔融), Keyword(id=1228805372643832354, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, language=CN, orderNo=2, keyword=过程监测), Keyword(id=1228805372736107047, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, language=CN, orderNo=3, keyword=声发射), Keyword(id=1228805372836770348, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, language=CN, orderNo=4, keyword=质量判别), Keyword(id=1228805372941627953, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, language=CN, orderNo=5, keyword=深度学习)], refs=[Reference(id=1228805376112521900, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, doi=null, pmid=null, pmcid=null, year=2020, volume=108, issue=1, pageStart=191, pageEnd=209, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=KHORASANI A, GIBSON I, VEETIL J K, journalName=The International Journal of Advanced Manufacturing Technology, refType=null, unstructuredReference=KHORASANI A, GIBSON I, VEETIL J K, et al.A review of technological improvements in laser-based powder bed fusion of metal printers[J]. The International Journal of Advanced Manufacturing Technology, 2020, 108(1): 191-209., articleTitle=A review of technological improvements in laser-based powder bed fusion of metal printers, refAbstract=null), Reference(id=1228805376196407983, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, doi=null, pmid=null, pmcid=null, year=2021, volume=46, issue=null, pageStart=350, pageEnd=355, url=null, language=null, rfNumber=[2], rfOrder=1, authorNames=SINGH D D, MAHENDER T, REDDY A R, journalName=Materials Today: Proceedings, refType=null, unstructuredReference=SINGH D D, MAHENDER T, REDDY A R. Powder bed fusion process: a brief review[J]. Materials Today: Proceedings, 2021, 46: 350-355., articleTitle=Powder bed fusion process: a brief review, refAbstract=null), Reference(id=1228805376280294067, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, doi=null, pmid=null, pmcid=null, year=2022, volume=75, issue=null, pageStart=375, pageEnd=414, url=null, language=null, rfNumber=[3], rfOrder=2, authorNames=NARASIMHARAJU S R, ZENG W H, SEE T L, journalName=Journal of Manufacturing Processes, refType=null, unstructuredReference=NARASIMHARAJU S R, ZENG W H, SEE T L, et al.A comprehensive review on laser powder bed fusion of steels: processing, microstructure, defects and control methods, mechanical properties, current challenges and future trends[J]. Journal of Manufacturing Processes, 2022, 75: 375-414., articleTitle=A comprehensive review on laser powder bed fusion of steels: processing, microstructure, defects and control methods, mechanical properties, current challenges and future trends, refAbstract=null), Reference(id=1228805376368374457, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, doi=null, pmid=null, pmcid=null, year=2020, volume=26, issue=null, pageStart=3058, pageEnd=3070, url=null, language=null, rfNumber=[4], rfOrder=3, authorNames=SINGH R, GUPTA A, TRIPATHI O, journalName=Materials Today: Proceedings, refType=null, unstructuredReference=SINGH R, GUPTA A, TRIPATHI O, et al.Powder bed fusion process in additive manufacturing: an overview[J]. Materials Today: Proceedings,2020,26: 3058-3070., articleTitle=Powder bed fusion process in additive manufacturing: an overview, refAbstract=null), Reference(id=1228805376460649149, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, doi=null, pmid=null, pmcid=null, year=2022, volume=20, issue=null, pageStart=2109, pageEnd=2172, url=null, language=null, rfNumber=[5], rfOrder=4, authorNames=CHOWDHURY S, YADAIAH N, PRAKASH C, journalName=Journal of Materials Research and Technology, refType=null, unstructuredReference=CHOWDHURY S, YADAIAH N, PRAKASH C, et al.Laser powder bed fusion: a state-of-the-art review of the technology, materials, properties & defects, and numerical modelling[J]. Journal of Materials Research and Technology, 2022, 20: 2109-2172., articleTitle=Laser powder bed fusion: a state-of-the-art review of the technology, materials, properties & defects, and numerical modelling, refAbstract=null), Reference(id=1228805376552923845, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, doi=null, pmid=null, pmcid=null, year=2020, volume=370, issue=6520, pageStart=1080, pageEnd=1086, url=null, language=null, rfNumber=[6], rfOrder=5, authorNames=ZHAO C, PARAB N D, LI X X, journalName=Science, refType=null, unstructuredReference=ZHAO C, PARAB N D, LI X X, et al.Critical instability at moving keyhole tip generates porosity in laser melting[J]. Science, 2020, 370(6520): 1080-1086., articleTitle=Critical instability at moving keyhole tip generates porosity in laser melting, refAbstract=null), Reference(id=1228805376657781447, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, doi=null, pmid=null, pmcid=null, year=2022, volume=13, issue=1, pageStart=2959, pageEnd=null, url=null, language=null, rfNumber=[7], rfOrder=6, authorNames=BITHARAS I, PARAB N, ZHAO C, journalName=Nature Communications, refType=null, unstructuredReference=BITHARAS I, PARAB N, ZHAO C, et al.The interplay between vapour, liquid, and solid phases in laser powder bed fusion[J]. Nature Communications, 2022, 13(1): 2959., articleTitle=The interplay between vapour, liquid, and solid phases in laser powder bed fusion, refAbstract=null), Reference(id=1228805376758444749, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, doi=null, pmid=null, pmcid=null, year=2021, volume=45, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[8], rfOrder=7, authorNames=MCCANN R, OBEIDI M A, HUGHES C, journalName=Additive Manufacturing, refType=null, unstructuredReference=MCCANN R, OBEIDI M A, HUGHES C, et al.In-situ sensing, process monitoring and machine control in Laser Powder Bed Fusion: a review[J]. Additive Manufacturing, 2021, 45: 102058., articleTitle=In-situ sensing, process monitoring and machine control in Laser Powder Bed Fusion: a review, refAbstract=null), Reference(id=1228805376884273875, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, doi=null, pmid=null, pmcid=null, year=2020, volume=35, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[9], rfOrder=8, authorNames=YEUNG H, YANG Z, YAN L, journalName=Additive Manufacturing, refType=null, unstructuredReference=YEUNG H, YANG Z, YAN L. A meltpool prediction based scan strategy for powder bed fusion additive manufacturing[J]. Additive Manufacturing, 2020, 35: 101383., articleTitle=A meltpool prediction based scan strategy for powder bed fusion additive manufacturing, refAbstract=null), Reference(id=1228805377026880216, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, doi=null, pmid=null, pmcid=null, year=2020, volume=31, issue=2, pageStart=375, pageEnd=386, url=null, language=null, rfNumber=[10], rfOrder=9, authorNames=KWON O, KIM H G, HAM M J, journalName=Journal of Intelligent Manufacturing, refType=null, unstructuredReference=KWON O, KIM H G, HAM M J, et al.A deep neural network for classification of melt-pool images in metal additive manufacturing[J]. Journal of Intelligent Manufacturing, 2020, 31(2): 375-386., articleTitle=A deep neural network for classification of melt-pool images in metal additive manufacturing, refAbstract=null), Reference(id=1228805377127543516, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, doi=null, pmid=null, pmcid=null, year=2024, volume=93, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[11], rfOrder=10, authorNames=SAMAEI A, PORTER C, KOZJEK D, journalName=Additive Manufacturing, refType=null, unstructuredReference=SAMAEI A, PORTER C, KOZJEK D, et al.Understanding coaxial photodiode-based multispectral pyrometer measurements at the overhang regions in laser powder bed fusion for part qualification[J]. Additive Manufacturing, 2024, 93: 104398., articleTitle=Understanding coaxial photodiode-based multispectral pyrometer measurements at the overhang regions in laser powder bed fusion for part qualification, refAbstract=null), Reference(id=1228805377228206815, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, doi=null, pmid=null, pmcid=null, year=2023, volume=106, issue=null, pageStart=214, pageEnd=222, url=null, language=null, rfNumber=[12], rfOrder=11, authorNames=YANG W M, QIU Y B, LIU W W, journalName=Journal of Manufacturing Processes, refType=null, unstructuredReference=YANG W M, QIU Y B, LIU W W, et al.Defect prediction in laser powder bed fusion with the combination of simulated melt pool images and thermal images[J]. Journal of Manufacturing Processes, 2023, 106: 214-222., articleTitle=Defect prediction in laser powder bed fusion with the combination of simulated melt pool images and thermal images, refAbstract=null), Reference(id=1228805377303704290, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, doi=null, pmid=null, pmcid=null, year=2022, volume=3, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[13], rfOrder=12, authorNames=SELEZNEV M, GUSTMANN T, FRIEBEL J M, journalName=Additive Manufacturing Letters, refType=null, unstructuredReference=SELEZNEV M, GUSTMANN T, FRIEBEL J M, et al.In situ detection of cracks during laser powder bed fusion using acoustic emission monitoring[J]. Additive Manufacturing Letters, 2022, 3: 100099., articleTitle=In situ detection of cracks during laser powder bed fusion using acoustic emission monitoring, refAbstract=null), Reference(id=1228805377395978982, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, doi=null, pmid=null, pmcid=null, year=2023, volume=5, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[14], rfOrder=13, authorNames=KONONENKO D Y, NIKONOVA V, SELEZNEV M, journalName=Additive Manufacturing Letters, refType=null, unstructuredReference=KONONENKO D Y, NIKONOVA V, SELEZNEV M, et al.An in situ crack detection approach in additive manufacturing based on acoustic emission and machine learning[J]. Additive Manufacturing Letters,2023,5: 100130., articleTitle=An in situ crack detection approach in additive manufacturing based on acoustic emission and machine learning, refAbstract=null), Reference(id=1228805377517613805, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, doi=null, pmid=null, pmcid=null, year=2024, volume=79, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[15], rfOrder=14, authorNames=DE FORMANOIR C, NASAB M H, SCHLENGER L, journalName=Additive Manufacturing, refType=null, unstructuredReference=DE FORMANOIR C, NASAB M H, SCHLENGER L, et al.Healing of keyhole porosity by means of defocused laser beam remelting: operando observation by X-ray imaging and acoustic emission-based detection[J]. Additive Manufacturing, 2024, 79: 103880., articleTitle=Healing of keyhole porosity by means of defocused laser beam remelting: operando observation by X-ray imaging and acoustic emission-based detection, refAbstract=null), Reference(id=1228805377605694193, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, doi=null, pmid=null, pmcid=null, year=2024, volume=80, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[16], rfOrder=15, authorNames=PANDIYAN V, WRÓBEL R, RICHTER R A, journalName=Additive Manufacturing, refType=null, unstructuredReference=PANDIYAN V, WRÓBEL R, RICHTER R A, et al.Monitoring of Laser Powder Bed Fusion process by bridging dissimilar process maps using deep learning-based domain adaptation on acoustic emissions[J]. Additive Manufacturing, 2024, 80: 103974., articleTitle=Monitoring of Laser Powder Bed Fusion process by bridging dissimilar process maps using deep learning-based domain adaptation on acoustic emissions, refAbstract=null), Reference(id=1228805377714746103, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, doi=null, pmid=null, pmcid=null, year=2023, volume=14, issue=1, pageStart=8008, pageEnd=null, url=null, language=null, rfNumber=[17], rfOrder=16, authorNames=HAMIDI NASAB M, MASINELLI G, DE FORMANOIR C, journalName=Nature Communications, refType=null, unstructuredReference=HAMIDI NASAB M, MASINELLI G, DE FORMANOIR C, et al.Harmonizing sound and light: X-ray imaging unveils acoustic signatures of stochastic inter-regime instabilities during laser melting[J]. Nature Communications, 2023, 14(1): 8008., articleTitle=Harmonizing sound and light: X-ray imaging unveils acoustic signatures of stochastic inter-regime instabilities during laser melting, refAbstract=null), Reference(id=1228805377807020796, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, doi=null, pmid=null, pmcid=null, year=2024, volume=37, issue=12, pageStart=2148, pageEnd=2157, url=null, language=null, rfNumber=[18], rfOrder=17, authorNames=张亚军, 潘东辉, 张先杰, journalName=振动工程学报, refType=null, unstructuredReference=张亚军,潘东辉, 张先杰,等.多尺度图池化特征融合的集成智能故障诊断方法[J]. 振动工程学报, 2024, 37(12):2148-2157., articleTitle=多尺度图池化特征融合的集成智能故障诊断方法, refAbstract=null), Reference(id=1228805377895101183, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, doi=null, pmid=null, pmcid=null, year=2024, volume=37, issue=12, pageStart=2148, pageEnd=2157, url=null, language=null, rfNumber=[18], rfOrder=18, authorNames=ZHANG Yajun, PAN Donghui, ZHANG Xianjie, journalName=Journal of Vibration Engineering, refType=null, unstructuredReference=ZHANG Yajun, PAN Donghui, ZHANG Xianjie, et al.Ensemble intelligent fault diagnosis method based on multi-scale graph pooling feature fusion[J]. Journal of Vibration Engineering, 2024, 37(12): 2148-2157., articleTitle=Ensemble intelligent fault diagnosis method based on multi-scale graph pooling feature fusion, refAbstract=null), Reference(id=1228805377970598659, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, doi=null, pmid=null, pmcid=null, year=2025, volume=38, issue=1, pageStart=96, pageEnd=108, url=null, language=null, rfNumber=[19], rfOrder=19, authorNames=郭盼盼, 张文斌, 崔奔, journalName=振动工程学报, refType=null, unstructuredReference=郭盼盼,张文斌, 崔奔,等.基于增强深度卷积神经网络的滚动轴承多工况故障诊断方法[J]. 振动工程学报, 2025, 38(1):96-108., articleTitle=基于增强深度卷积神经网络的滚动轴承多工况故障诊断方法, refAbstract=null), Reference(id=1228805378058679049, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, doi=null, pmid=null, pmcid=null, year=2025, volume=38, issue=1, pageStart=96, pageEnd=108, url=null, language=null, rfNumber=[19], rfOrder=20, authorNames=GUO Panpan, ZHANG Wenbin, CUI Ben, journalName=Journal of Vibration Engineering, refType=null, unstructuredReference=GUO Panpan, ZHANG Wenbin, CUI Ben, et al.Multi-condition fault diagnosis method of rolling bearing based on enhanced deep convolutional neural network[J]. Journal of Vibration Engineering, 2025, 38(1): 96-108., articleTitle=Multi-condition fault diagnosis method of rolling bearing based on enhanced deep convolutional neural network, refAbstract=null), Reference(id=1228805378163536650, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, doi=null, pmid=null, pmcid=null, year=2024, volume=89, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[20], rfOrder=21, authorNames=TANG J F, ZHAO Z B, GUO Y J, journalName=Robotics and Computer-Integrated Manufacturing, refType=null, unstructuredReference=TANG J F, ZHAO Z B, GUO Y J, et al.Privacy-preserving federated transfer learning for defect identification from highly imbalanced image data in additive manufacturing[J]. Robotics and Computer-Integrated Manufacturing, 2024, 89: 102779., articleTitle=Privacy-preserving federated transfer learning for defect identification from highly imbalanced image data in additive manufacturing, refAbstract=null), Reference(id=1228805378251617042, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, doi=null, pmid=null, pmcid=null, year=2024, volume=255, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[21], rfOrder=22, authorNames=TAN K P, TANG J F, ZHAO Z B, journalName=Expert Systems with Applications, refType=null, unstructuredReference=TAN K P, TANG J F, ZHAO Z B, et al.Efficient and lightweight layer-wise in-situ defect detection in laser powder bed fusion via knowledge distillation and structural re-parameterization[J]. Expert Systems with Applications, 2024, 255: 124628., articleTitle=Efficient and lightweight layer-wise in-situ defect detection in laser powder bed fusion via knowledge distillation and structural re-parameterization, refAbstract=null), Reference(id=1228805378360668947, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, doi=null, pmid=null, pmcid=null, year=2024, volume=252, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[22], rfOrder=23, authorNames=LI J C, HU J X, ZHOU Q, journalName=Expert Systems with Applications, refType=null, unstructuredReference=LI J C, HU J X, ZHOU Q, et al.Transfer learning-based quality monitoring of laser powder bed fusion across materials[J]. Expert Systems with Applications, 2024, 252: 124150., articleTitle=Transfer learning-based quality monitoring of laser powder bed fusion across materials, refAbstract=null), Reference(id=1228805378448749337, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, doi=null, pmid=null, pmcid=null, year=2024, volume=72, issue=null, pageStart=59, pageEnd=73, url=null, language=null, rfNumber=[23], rfOrder=24, authorNames=ZHAO Z B, LIU W L, REN J X, journalName=Journal of Manufacturing Systems, refType=null, unstructuredReference=ZHAO Z B, LIU W L, REN J X, et al.Uncertainty-driven trustworthy defect detection for high-resolution powder bed images in selective laser melting[J]. Journal of Manufacturing Systems, 2024, 72: 59-73., articleTitle=Uncertainty-driven trustworthy defect detection for high-resolution powder bed images in selective laser melting, refAbstract=null), Reference(id=1228805378524246812, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, doi=null, pmid=null, pmcid=null, year=2024, volume=88, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[24], rfOrder=25, authorNames=KOZJEK D, PORTER C, CARTER F M, journalName=Additive Manufacturing, refType=null, unstructuredReference=KOZJEK D, PORTER C, CARTER F M, et al.Data-driven prediction of inter-layer process condition variations in laser powder bed fusion[J]. Additive Manufacturing, 2024, 88: 104230., articleTitle=Data-driven prediction of inter-layer process condition variations in laser powder bed fusion, refAbstract=null), Reference(id=1228805378629104416, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, doi=null, pmid=null, pmcid=null, year=2023, volume=67, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[25], rfOrder=26, authorNames=DRISSI-DAOUDI R, MASINELLI G, DE FORMANOIR C, journalName=Additive Manufacturing, refType=null, unstructuredReference=DRISSI-DAOUDI R, MASINELLI G, DE FORMANOIR C, et al.Acoustic emission for the prediction of processing regimes in Laser Powder Bed Fusion, and the generation of processing maps[J]. Additive Manufacturing, 2023, 67: 103484., articleTitle=Acoustic emission for the prediction of processing regimes in Laser Powder Bed Fusion, and the generation of processing maps, refAbstract=null), Reference(id=1228805378725573412, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, doi=null, pmid=null, pmcid=null, year=2024, volume=38, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[26], rfOrder=27, authorNames=WANG H J, ZHANG S F, LI B, journalName=Materials Today Communications, refType=null, unstructuredReference=WANG H J, ZHANG S F, LI B. Machine learning-assisted acoustic emission monitoring for track formability prediction of laser powder bed fusion[J]. Materials Today Communications, 2024, 38: 108522., articleTitle=Machine learning-assisted acoustic emission monitoring for track formability prediction of laser powder bed fusion, refAbstract=null), Reference(id=1228805378817848104, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[27], rfOrder=28, authorNames=GUIBAS J, MARDANI M, LI Z Y, journalName=null, refType=null, unstructuredReference=GUIBAS J, MARDANI M, LI Z Y, et al.Adaptive fourier neural operators: efficient token mixers for transformers[EB/OL]. (2021-11-24)[2025-03-31]. https://arXiv.org/abs/2111.13587v2., articleTitle=Adaptive fourier neural operators: efficient token mixers for transformers, refAbstract=null), Reference(id=1228805378905928489, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[28], rfOrder=29, authorNames=LIU Z, WANG Y, VAIDYA S, journalName=null, refType=null, unstructuredReference=LIU Z, WANG Y, VAIDYA S, et al.Kan: Kolmogorov-arnold networks[EB/OL]. (2024-04-30)[2025-03-31]. https://arXiv.org/abs/2404.19756., articleTitle=Kan: Kolmogorov-arnold networks, refAbstract=null), Reference(id=1228805378968843051, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, doi=null, pmid=null, pmcid=null, year=2016, volume=null, issue=null, pageStart=770, pageEnd=778, url=null, language=null, rfNumber=[29], rfOrder=30, authorNames=HE K M, ZHANG X Y, REN S Q, journalName=null, refType=null, unstructuredReference=HE K M, ZHANG X Y, REN S Q, et al.Deep residual learning for image recognition[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 2016: 770-778., articleTitle=Deep residual learning for image recognition, refAbstract=null), Reference(id=1228805379023369006, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[30], rfOrder=31, authorNames=LI Z Y, KOVACHKI N, AZIZZADENESHELI K, journalName=null, refType=null, unstructuredReference=LI Z Y, KOVACHKI N, AZIZZADENESHELI K, et al.Fourier neural operator for parametric partial differential equations[EB/OL]. (2020-10-18)[2025-03-31]. https://arXiv.org/abs/2010.08895v3., articleTitle=Fourier neural operator for parametric partial differential equations, refAbstract=null), Reference(id=1228805379098866481, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, doi=null, pmid=null, pmcid=null, year=2023, volume=8, issue=2, pageStart=265, pageEnd=283, url=null, language=null, rfNumber=[31], rfOrder=32, authorNames=BUHAIRI M A, FOUDZI F M, JAMHARI F I, journalName=Progress in Additive Manufacturing, refType=null, unstructuredReference=BUHAIRI M A, FOUDZI F M, JAMHARI F I, et al.Review on volumetric energy density: influence on morphology and mechanical properties of Ti6Al4V manufactured via laser powder bed fusion[J]. Progress in Additive Manufacturing, 2023, 8(2): 265-283., articleTitle=Review on volumetric energy density: influence on morphology and mechanical properties of Ti6Al4V manufactured via laser powder bed fusion, refAbstract=null)], funds=[Fund(id=1228805375999275686, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, awardId=JCKY2023110C044, language=CN, fundingSource=国防基础科研计划资助项目(JCKY2023110C044), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1228805369938506044, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, xref=1., ext=[AuthorCompanyExt(id=1228805369946894653, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, companyId=1228805369938506044, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.National Key Lab of Aerospace Power System and Plasma Technology,Xi’an Jiaotong University,Xi’an 710049,China), AuthorCompanyExt(id=1228805369951088958, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, companyId=1228805369938506044, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.西安交通大学航空动力系统与等离子体技术全国重点实验室,陕西 西安 710049)]), AuthorCompany(id=1228805370026586438, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, xref=2., ext=[AuthorCompanyExt(id=1228805370034975046, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, companyId=1228805370026586438, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.School of Mechanical Engineering,Xi’an Jiaotong University,Xi’an 710049,China), AuthorCompanyExt(id=1228805370039169353, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, companyId=1228805370026586438, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.西安交通大学机械工程学院,陕西 西安 710049)]), AuthorCompany(id=1228805370114666828, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, xref=3., ext=[AuthorCompanyExt(id=1228805370123055438, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, companyId=1228805370114666828, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3.National Key Lab of Aerospace Power System and Plasma Technology,Air Force Engineering University,Xi’an 710038,China), AuthorCompanyExt(id=1228805370127249743, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, companyId=1228805370114666828, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3.空军工程大学航空动力系统与等离子体技术全国重点实验室,陕西 西安 710038)])], figs=[ArticleFig(id=1228805373063262774, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, language=EN, label=Fig. 1, caption=Overview diagram of intelligent evaluation method for internal quality in LPBF, figureFileSmall=n64pL+efXXcfxNO+sp5t9Q==, figureFileBig=uMCyVu3RIMEFTkUYBLk/1g==, tableContent=null), ArticleFig(id=1228805373147148857, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, language=CN, label=图1, caption=LPBF内部质量智能判别方法概述图, figureFileSmall=n64pL+efXXcfxNO+sp5t9Q==, figureFileBig=uMCyVu3RIMEFTkUYBLk/1g==, tableContent=null), ArticleFig(id=1228805373314921023, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, language=EN, label=Fig. 2, caption=Schematic diagram of FNO module, figureFileSmall=LzH14KvWCrDotA28VmAeoA==, figureFileBig=k1nw6HCYmibJxl8AXfKG6w==, tableContent=null), ArticleFig(id=1228805373390418497, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, language=CN, label=图2, caption=FNO模块示意图, figureFileSmall=LzH14KvWCrDotA28VmAeoA==, figureFileBig=k1nw6HCYmibJxl8AXfKG6w==, tableContent=null), ArticleFig(id=1228805373478498886, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, language=EN, label=Fig. 3, caption=Schematic diagram of AFNO module, figureFileSmall=5VtMlQ8JPmpPJWMhADp5MQ==, figureFileBig=P2n6uzjLnKd2x2jeWQlKlg==, tableContent=null), ArticleFig(id=1228805373604328011, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, language=CN, label=图3, caption=AFNO模块示意图, figureFileSmall=5VtMlQ8JPmpPJWMhADp5MQ==, figureFileBig=P2n6uzjLnKd2x2jeWQlKlg==, tableContent=null), ArticleFig(id=1228805373721768527, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, language=EN, label=Fig. 4, caption=Schematic diagram of training and inference process of AFNO-based quality evaluation model, figureFileSmall=Io5Ezi5nqZN4fKfnXldo8A==, figureFileBig=UGaKlkzlfjMVVmaS19hRew==, tableContent=null), ArticleFig(id=1228805373847597653, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, language=CN, label=图4, caption=基于AFNO的质量判别模型训练与推断过程示意图, figureFileSmall=Io5Ezi5nqZN4fKfnXldo8A==, figureFileBig=UGaKlkzlfjMVVmaS19hRew==, tableContent=null), ArticleFig(id=1228805373939872343, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, language=EN, label=Fig. 5, caption=Schematic diagram of online monitoring system in LPBF based on AE sensor, figureFileSmall=jC4X9UmxzwBfCiDzy58ycg==, figureFileBig=d+bzsQRlV3oTOzAOrtH8iQ==, tableContent=null), ArticleFig(id=1228805374019564124, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, language=CN, label=图5, caption=基于AE传感器的LPBF在线监测系统示意图, figureFileSmall=jC4X9UmxzwBfCiDzy58ycg==, figureFileBig=d+bzsQRlV3oTOzAOrtH8iQ==, tableContent=null), ArticleFig(id=1228805374103450211, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, language=EN, label=Fig. 6, caption=Installation schematic diagram of AE sensor, figureFileSmall=Bb9lRw+ce2mZK0ciz87svA==, figureFileBig=7XMcQj3eHVVIHSIq/I/Dug==, tableContent=null), ArticleFig(id=1228805374187336292, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, language=CN, label=图6, caption=AE传感器安装示意图, figureFileSmall=Bb9lRw+ce2mZK0ciz87svA==, figureFileBig=7XMcQj3eHVVIHSIq/I/Dug==, tableContent=null), ArticleFig(id=1228805374262833767, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, language=EN, label=Fig. 7, caption=36 sets of process parameter conbination test parts, figureFileSmall=iMrdL4W+xdi7b7Dv/xCgmg==, figureFileBig=wLba/nBCAcY3O1j8io9g1g==, tableContent=null), ArticleFig(id=1228805374329942632, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, language=CN, label=图7, caption=36组工艺参数组合试验件, figureFileSmall=iMrdL4W+xdi7b7Dv/xCgmg==, figureFileBig=wLba/nBCAcY3O1j8io9g1g==, tableContent=null), ArticleFig(id=1228805374472548972, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, language=EN, label=Fig. 8, caption=Internal quality metallographic results, figureFileSmall=t2/6WTAikbfMpdO5qxUUHg==, figureFileBig=P1z/g4FHmVA/xbhyickD1A==, tableContent=null), ArticleFig(id=1228805374522880624, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, language=CN, label=图8, caption=内部质量金相结果, figureFileSmall=t2/6WTAikbfMpdO5qxUUHg==, figureFileBig=P1z/g4FHmVA/xbhyickD1A==, tableContent=null), ArticleFig(id=1228805374589989490, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, language=EN, label=Fig. 9, caption=The pre-processing of melt-pool AE data, figureFileSmall=0bCO4jfhBuAUr/4i9iOgzA==, figureFileBig=hAZelhalDfjJxIBIsQeQNw==, tableContent=null), ArticleFig(id=1228805374665486964, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, language=CN, label=图9, caption=熔池AE数据预处理, figureFileSmall=0bCO4jfhBuAUr/4i9iOgzA==, figureFileBig=hAZelhalDfjJxIBIsQeQNw==, tableContent=null), ArticleFig(id=1228805374740984439, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, language=EN, label=Fig. 10, caption=Test results of proposed method on dataset B and C, figureFileSmall=Pj+sZIu+fK5PevWb14xGoA==, figureFileBig=0brGmZFqaMU8CP4/OcVbGA==, tableContent=null), ArticleFig(id=1228805374837453436, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, language=CN, label=图10, caption=所提方法在数据集B和C上的试验结果, figureFileSmall=Pj+sZIu+fK5PevWb14xGoA==, figureFileBig=0brGmZFqaMU8CP4/OcVbGA==, tableContent=null), ArticleFig(id=1228805374921339520, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, language=EN, label=Fig. 11, caption=Results of t-SNE clustering of proposed method on dataset B and C, figureFileSmall=KZQV7uit2rTmK/PTgiSj6A==, figureFileBig=TIvtuAEYA2bkDWXoVK5ptA==, tableContent=null), ArticleFig(id=1228805375013614209, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, language=CN, label=图11, caption=所提方法在数据集B和C上的t-SNE聚类结果, figureFileSmall=KZQV7uit2rTmK/PTgiSj6A==, figureFileBig=TIvtuAEYA2bkDWXoVK5ptA==, tableContent=null), ArticleFig(id=1228805375118471814, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, language=EN, label=Fig. 12, caption=The confusion matrix of proposed method on dataset D, figureFileSmall=W6h4KoKvcPHXcqUVmIjcnw==, figureFileBig=C6b5DvU9aTAmUWmiQafKcw==, tableContent=null), ArticleFig(id=1228805375202357897, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, language=CN, label=图12, caption=所提方法在数据集D上的混淆矩阵, figureFileSmall=W6h4KoKvcPHXcqUVmIjcnw==, figureFileBig=C6b5DvU9aTAmUWmiQafKcw==, tableContent=null), ArticleFig(id=1228805375294632588, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, language=EN, label=Tab.1, caption=

The detail of datasets

, figureFileSmall=null, figureFileBig=null, tableContent=
数据集总量训练集数量验证集数量测试集数量
A56574525566566
B66095287661661
C48413871485485
D167081336616711671
), ArticleFig(id=1228805375416267408, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, language=CN, label=表1, caption=

数据集详情

, figureFileSmall=null, figureFileBig=null, tableContent=
数据集总量训练集数量验证集数量测试集数量
A56574525566566
B66095287661661
C48413871485485
D167081336616711671
), ArticleFig(id=1228805375525319314, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, language=EN, label=Tab.2, caption=

Test results of proposed method on baseline dataset A (Unit: %)

, figureFileSmall=null, figureFileBig=null, tableContent=
方法AccPreRecF1
ResNet18-1d99.8099.8099.8599.83
所提方法100.00100.00100.00100.00
), ArticleFig(id=1228805375617594007, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, language=CN, label=表2, caption=

所提方法在基准数据集A上的试验结果(单位:%)

, figureFileSmall=null, figureFileBig=null, tableContent=
方法AccPreRecF1
ResNet18-1d99.8099.8099.8599.83
所提方法100.00100.00100.00100.00
), ArticleFig(id=1228805375718257305, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, language=EN, label=Tab.3, caption=

Results of ablation test

, figureFileSmall=null, figureFileBig=null, tableContent=
数据集方法参数量/MBAcc/%Pre/%Rec/%F1/%
BResNet18-1d8.7398.5998.5498.6298.58
ResNet34-1d16.5998.5998.5498.6698.59
ResNet50-1d20.9996.2596.2596.3596.25
+KAN8.7498.1298.1098.2198.14
+AFNO8.9197.8197.7597.8797.81
所提方法8.9299.2299.1999.3099.46
CResNet18-1d8.7398.4498.4298.5098.44
ResNet34-1d16.5998.4498.4598.4598.44
ResNet50-1d20.9996.4396.7396.3996.48
+KAN8.7497.1097.1197.1497.11
+AFNO8.9198.2198.1998.2598.21
所提方法8.9298.8898.8798.8898.87
DResNet18-1d8.7396.5796.5296.4196.45
ResNet34-1d16.5997.2497.1397.1397.13
ResNet50-1d20.9993.8793.7293.6393.65
+KAN8.7496.9496.9996.8396.87
+AFNO8.9197.0697.0196.9296.94
所提方法8.9297.6097.5697.5097.51
), ArticleFig(id=1228805375869252255, tenantId=1146029695717560320, journalId=1225147924628267009, articleId=1228805366801166411, language=CN, label=表3, caption=

消融试验结果

, figureFileSmall=null, figureFileBig=null, tableContent=
数据集方法参数量/MBAcc/%Pre/%Rec/%F1/%
BResNet18-1d8.7398.5998.5498.6298.58
ResNet34-1d16.5998.5998.5498.6698.59
ResNet50-1d20.9996.2596.2596.3596.25
+KAN8.7498.1298.1098.2198.14
+AFNO8.9197.8197.7597.8797.81
所提方法8.9299.2299.1999.3099.46
CResNet18-1d8.7398.4498.4298.5098.44
ResNet34-1d16.5998.4498.4598.4598.44
ResNet50-1d20.9996.4396.7396.3996.48
+KAN8.7497.1097.1197.1497.11
+AFNO8.9198.2198.1998.2598.21
所提方法8.9298.8898.8798.8898.87
DResNet18-1d8.7396.5796.5296.4196.45
ResNet34-1d16.5997.2497.1397.1397.13
ResNet50-1d20.9993.8793.7293.6393.65
+KAN8.7496.9496.9996.8396.87
+AFNO8.9197.0697.0196.9296.94
所提方法8.9297.6097.5697.5097.51
)], attaches=null, journal=Journal(id=1225147830491308032, delFlag=0, nameCn=振动工程学报, nameEn=Journal of Vibration Engineering, nameHistory1=null, nameHistory2=null, issn=1004-4523, eissn=null, cn=32-1349/TB, coden=null, periodic=0, language=CN, oaType=null, ccby=null, superviseOffice=null, ownerOffice=null, pubOffice=null, editorOffice=null, officeType=null, aims=null, clcCode=null, officeProv=null, officeCity=null, officeAddr=null, officeZip=null, officeEmail=null, officePhone=null, editDirector=null, officeDirector=null, officeDirectorPhone=null, officeStaffNum=null, officeEmpNum=null, coverPicUrl=null, journalPrice=null, startedYear=null, abbrevIsoEn=Journal of Vibration Engineering, journalRemark=null, publicationField=null, createdTime=1770027604939, updatedTime=1770169610881, createdBy=18614031015, updatedBy=18614031015, firstLetterCn=J, firstLetterEn=J, subjectCode=Engineering, subjectName=null, subjectCodeEn=Engineering, subjectNameEn=null, picCn=null, picEn=null, jcr=null, cjcr=null, exts=[JournalExt(id=1225743346702925905, language=CN, name=振动工程学报, nameHistory1=null, nameHistory2=null, managedBy=中国科学技术协会, sponsoredBy=中国振动工程学会, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1770169587064, updatedTime=1770169587064, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=https://www.manuscripts.com.cn/zdgcxb, submissionEditorUrl=https://www.manuscripts.com.cn/zdgcxb, submissionReviewUrl=https://www.manuscripts.com.cn/zdgcxb, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1225743346765840466, language=EN, name=Journal of Vibration Engineering, 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=1770169587079, updatedTime=1770169587079, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=https://www.manuscripts.com.cn/zdgcxb, submissionEditorUrl=https://www.manuscripts.com.cn/zdgcxb, submissionReviewUrl=https://www.manuscripts.com.cn/zdgcxb, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1225147924628267009, websiteList=[Website(id=1225150618881404985, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1225147924628267009, 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/zdgcxb/CN, language=CN, createTime=1770028269739, createBy=18614031015, updateTime=1770028293069, updateBy=18614031015, name=振动工程学报-中文, tplId=1146099689490845704, title=振动工程学报, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1225151164178673750, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225150618881404985, code=articleTextType, value=kx, createTime=1770028399748, updateTime=1770028399748, creator=18614031015, updator=18614031015), WebsiteProps(id=1225151164157702227, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225150618881404985, code=banner, value=null, createTime=1770028399743, updateTime=1770028399743, creator=18614031015, updator=18614031015), WebsiteProps(id=1225151164203839577, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225150618881404985, code=grayFlag, value=0, createTime=1770028399754, updateTime=1770028399754, creator=18614031015, updator=18614031015), WebsiteProps(id=1225151164145119314, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225150618881404985, code=logo, value=https://castjournals.cast.org.cn/joweb/zdgcxb/EN/file/pic?fileId=L7mSU8YPwm66NWFMoTG4aQ==, createTime=1770028399740, updateTime=1770028399740, creator=18614031015, updator=18614031015), WebsiteProps(id=1225151164212228187, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225150618881404985, code=minRunFlag, value=0, createTime=1770028399756, updateTime=1770028399756, creator=18614031015, updator=18614031015), WebsiteProps(id=1225151164170285141, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225150618881404985, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/zdgcxb/CN/file/pic, createTime=1770028399746, updateTime=1770028399746, creator=18614031015, updator=18614031015), WebsiteProps(id=1225151164208033882, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225150618881404985, code=silenceFlag, value=0, createTime=1770028399755, updateTime=1770028399755, creator=18614031015, updator=18614031015), WebsiteProps(id=1225151164166090836, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225150618881404985, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1770028399745, updateTime=1770028399745, creator=18614031015, updator=18614031015), WebsiteProps(id=1225151164187062359, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225150618881404985, code=themeColor, value=null, createTime=1770028399750, updateTime=1770028399750, creator=18614031015, updator=18614031015), WebsiteProps(id=1225151164195450968, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225150618881404985, code=themeStyle, value=null, createTime=1770028399752, updateTime=1770028399752, creator=18614031015, updator=18614031015)]), Website(id=1225150619003039804, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1225147924628267009, 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/zdgcxb/EN, language=EN, createTime=1770028269768, createBy=18614031015, updateTime=1770028309190, updateBy=18614031015, name=振动工程学报-英文, tplId=1146101810881728533, title=Journal of Vibration Engineering, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1225151193366835296, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225150619003039804, code=articleTextType, value=kx, createTime=1770028406707, updateTime=1770028406707, creator=18614031015, updator=18614031015), WebsiteProps(id=1225151193350058077, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225150619003039804, code=banner, value=null, createTime=1770028406703, updateTime=1770028406703, creator=18614031015, updator=18614031015), WebsiteProps(id=1225151193387806819, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225150619003039804, code=grayFlag, value=0, createTime=1770028406712, updateTime=1770028406712, creator=18614031015, updator=18614031015), WebsiteProps(id=1225151193341669468, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225150619003039804, code=logo, value=https://castjournals.cast.org.cn/joweb/zdgcxb/EN/file/pic?fileId=L7mSU8YPwm66NWFMoTG4aQ==, createTime=1770028406701, updateTime=1770028406701, creator=18614031015, updator=18614031015), WebsiteProps(id=1225151193400389733, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225150619003039804, code=minRunFlag, value=0, createTime=1770028406715, updateTime=1770028406715, creator=18614031015, updator=18614031015), WebsiteProps(id=1225151193362640991, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225150619003039804, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/zdgcxb/EN/file/pic, createTime=1770028406706, updateTime=1770028406706, creator=18614031015, updator=18614031015), WebsiteProps(id=1225151193392001124, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225150619003039804, code=silenceFlag, value=0, createTime=1770028406713, updateTime=1770028406713, creator=18614031015, updator=18614031015), WebsiteProps(id=1225151193354252382, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225150619003039804, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_en_623/, createTime=1770028406704, updateTime=1770028406704, creator=18614031015, updator=18614031015), WebsiteProps(id=1225151193371029601, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225150619003039804, code=themeColor, value=null, createTime=1770028406708, updateTime=1770028406708, creator=18614031015, updator=18614031015), WebsiteProps(id=1225151193379418210, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1225150619003039804, code=themeStyle, value=null, createTime=1770028406710, updateTime=1770028406710, creator=18614031015, updator=18614031015)])], journalTitle=振动工程学报, weixinUrl=null, journalUrl=http://zdgcxb.csve.org.cn/, iacademicId=null, status=1, seqNo=null, journalTitleEn=Journal of Vibration Engineering, journalPhotoCn=null, journalPhotoEn=null, 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/zdgcxb/CN/10.16385/j.cnki.issn.1004-4523.2025.06.002, detailUrlEn=https://castjournals.cast.org.cn/joweb/zdgcxb/EN/10.16385/j.cnki.issn.1004-4523.2025.06.002, pdfUrlCn=https://castjournals.cast.org.cn/joweb/zdgcxb/CN/PDF/10.16385/j.cnki.issn.1004-4523.2025.06.002, pdfUrlEn=https://castjournals.cast.org.cn/joweb/zdgcxb/EN/PDF/10.16385/j.cnki.issn.1004-4523.2025.06.002, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于声发射信号的激光粉末床熔融在线监测与内部质量智能判别方法
收藏切换
PDF下载
张兴武 1, 2 , 唐甲锋 1, 2 , 谭鲲鹏 1, 2 , 赵志斌 1, 2 , 陈雪峰 1, 2 , 李应红 3
振动工程学报 | 2025,38(6): 1134-1144
收起
收藏切换
振动工程学报 | 2025, 38(6): 1134-1144
基于声发射信号的激光粉末床熔融在线监测与内部质量智能判别方法
全屏
张兴武1, 2 , 唐甲锋1, 2, 谭鲲鹏1, 2, 赵志斌1, 2 , 陈雪峰1, 2, 李应红3
作者信息
  • 1.西安交通大学航空动力系统与等离子体技术全国重点实验室,陕西 西安 710049
  • 2.西安交通大学机械工程学院,陕西 西安 710049
  • 3.空军工程大学航空动力系统与等离子体技术全国重点实验室,陕西 西安 710038
  • 张兴武(1984—),男,博士,教授。E-mail:

通讯作者:

赵志斌(1993—),男,博士,副教授。E-mail:
Online monitoring and intelligent internal quality discrimination method for laser powder bed fusion based on acoustic emission signals
Xingwu ZHANG1, 2 , Jiafeng TANG1, 2, Kunpeng TAN1, 2, Zhibin ZHAO1, 2 , Xuefeng CHEN1, 2, Yinghong Li3
Affiliations
  • 1.National Key Lab of Aerospace Power System and Plasma Technology,Xi’an Jiaotong University,Xi’an 710049,China
  • 2.School of Mechanical Engineering,Xi’an Jiaotong University,Xi’an 710049,China
  • 3.National Key Lab of Aerospace Power System and Plasma Technology,Air Force Engineering University,Xi’an 710038,China
出版时间: 2025-06-10 doi: 10.16385/j.cnki.issn.1004-4523.2025.06.002
文章导航
收藏切换

激光粉末床熔融(laser powder bed fusion, LPBF)技术作为金属增材制造领域的前沿工艺,已被成功应用于航空航天等高端制造领域。然而多物理场强耦合效应易引发熔池动态失稳,导致制件内部孔隙缺陷频发,严重影响成形质量稳定性。传统监测手段受限于成本高、部署困难等瓶颈,难以满足工业化生产需求。为此,提出声发射-深度学习融合的在线监测与内部质量智能判别方法。研制了基于声发射传感器的LPBF过程在线监测系统,通过工艺过程全周期声发射信号监测揭示声发射信号特征与成形质量间的映射规律,构建了包含逾8万组样本的熔池声发射数据。针对熔池微弱波动特征提取难题,构建了基于自适应傅里叶神经算子(AFNO)的频域特征提取网络和Kolmogorov-Arnold网络(KAN)的高维特征映射分类器,通过多尺度时域特征融合机制解析熔池动态特性,并借助高维流形精确映射高维特征,实现了声发射信号中微弱波动特征的增强表征和高精度质量判别。试验结果表明:研制的监测系统可有效捕获熔池的动态行为,所提方法质量判别精度达97%以上。

激光粉末床熔融  /  过程监测  /  声发射  /  质量判别  /  深度学习

Laser powder bed fusion (LPBF) technology, a cutting-edge process in metal additive manufacturing, has been successfully applied in high-end manufacturing sectors like aerospace. However, strong multi-physical field coupling effects frequently lead to dynamic instability in the molten pool, causing widespread porosity defects within fabricated parts and severely impacting forming quality stability. Traditional monitoring methods face limitations such as high cost and deployment difficulties, struggling to meet industrial production demands. To address these challenges, this paper proposes an online monitoring and intelligent internal quality discrimination method based on acoustic emission (AE)-deep learning fusion. An AE sensor-based online monitoring system for the LPBF process was developed. By continously monitoring AE signals throughout the entire process, the mapping relationship between AE signal characteristics and forming quality was revealed, creating a molten pool AE dataset comprising over 80,000 samples. To tackle the difficulty of extracting weak fluctuation features from the molten pool, a frequency domain feature extraction network based on the adaptive Fourier neural operator (AFNO) and a high-dimensional feature mapping classifier based on the Kolmogorov-Arnold network (KAN) were constructed. This approach analyzes molten pool dynamic characteristics through a multi-scale time domain feature fusion mechanism. By precisely mapping high-dimensional features using high-dimensional manifolds, the method achieves enhanced characterization of weak fluctuation features in AE signals and high-precision quality discrimination. Experimental results demonstrate that developed monitoring system effectively captures the dynamic behavior of the molten pool, and the proposed method achieves a quality discrimination accuracy exceeding 97%.

laser powder bed fusion  /  process monitoring  /  acoustic emission  /  quality evaluation  /  deep learning
张兴武, 唐甲锋, 谭鲲鹏, 赵志斌, 陈雪峰, 李应红. 基于声发射信号的激光粉末床熔融在线监测与内部质量智能判别方法. 振动工程学报, 2025 , 38 (6) : 1134 -1144 . DOI: 10.16385/j.cnki.issn.1004-4523.2025.06.002
Xingwu ZHANG, Jiafeng TANG, Kunpeng TAN, Zhibin ZHAO, Xuefeng CHEN, Yinghong Li. Online monitoring and intelligent internal quality discrimination method for laser powder bed fusion based on acoustic emission signals[J]. Journal of Vibration Engineering, 2025 , 38 (6) : 1134 -1144 . DOI: 10.16385/j.cnki.issn.1004-4523.2025.06.002
激光粉末床熔融(laser powder bed fusion, LPBF)作为金属增材制造领域颇有前景的前沿技术,已在航空航天、生物医疗、电子消费品等关键领域展现出显著优势[1-2]。其基本原理为高能量激光按照设定轨迹连续扫描和熔化金属粉末,逐层制备复杂金属零部件[3]。然而,该工艺涉及热-流-固多物理场动态强耦合作用,致使制造过程面临质量稳定一致性挑战[4-5]。例如,在打印过程中,高能激光熔化粉末形成的熔池受到多种复杂力(马兰戈尼力、表面张力等)的联合作用,失稳波动易导致内部缺陷(未熔融缺陷、匙孔孔隙缺陷等)[6-7]。研究表明,LPBF工艺的成形质量问题和熔池的失稳状态密切相关,如何实现熔池状态的精准监控成为突破该技术产业化瓶颈的关键。
利用各种先进的传感技术原位监测LPBF制造过程,通过分析熔池状态过程传感数据来判别成形质量,调整打印策略或工艺参数(比如激光功率、扫描速度等)是解决LPBF成形质量稳定一致性问题的关键[8]。近年来,LPBF原位监测的传感技术主要包括高速相机、红外热像仪、光电探测器等。其中,利用高速相机在线监测熔池的形貌、飞溅等特征,进而判别熔池状态是较为常见的方法。YEUNG等[9]将高速相机以旁轴方式(与激光光路非同轴)安装在LPBF设备上以监测熔池形貌变化,根据形貌的不稳定变化调整激光功率,以此提升成形质量;KWON等[10]同轴安装(与激光光路同轴)高速相机以监测不同激光功率下的熔池图像,研究激光功率与熔池形貌以及零件内部缺陷间的关系。光电探测器凭借其成本低的优势被用于监测LPBF过程中的熔池辐射。例如,SAMAEI等[11]开发了一套双波长同轴光电探测器系统,用于监测打印过程中的逐层熔池辐射强度,进而判别熔池状态。此外,红外热像仪也被用于监测熔池的温度场变化,进而探索熔池状态。YANG等[12]利用红外热像仪监测熔池温度场,并结合仿真数据判别内部缺陷。尽管上述传感技术在LPBF原位过程监测中取得了成功,但是部署成本与复杂的安装过程使得这些技术尚未得到大规模应用。
得益于低成本、高灵敏度、易部署等诸多优点,声发射(acoustic emission, AE)传感技术近年来逐渐被应用于LPBF过程原位监测[13-14]。从原理上讲,LPBF过程高能激光束与金属粉末相互作用会引起熔池波动(如粉末熔融、汽化、飞溅等),导致局部能量瞬间释放,激发周围气体的振动,形成宽频域的声波信号,其声学特征与熔池动力学行为存在强相关性[15]。利用AE传感器捕获熔池的声波信号,通过分析熔池状态与信号间的关联关系可以进一步判别成形质量。目前,一些研究已经探索了基于AE传感器的熔池监测技术。例如,PANDIYAN等[16]通过监测熔池的声信号来判别熔池的3种状态(未熔融、匙孔和传导模式)。HAMIDI NASAB等[17]进一步结合同步高能X射线成像技术,从缺陷机理上探索了AE信号与熔池状态间的关系。然而,由于缺乏合理的信号同步采样和安装设置,目前基于AE传感器的熔池监测系统尚未在商用打印机上实现集成。此外,由于在LPBF过程中监测到的声信号成分复杂,包括熔池演化发出的声波、设备元器件运行产生的声音以及风场与材料或设备交互产生的声信号。因此,如何从采集到的AE信号中提取出代表熔池状态的特征是一个尚未完全解决的难题。
近年来,基于数据驱动的深度学习(deep learning, DL)方法在工业领域取得了巨大的成功[18-21],同时在LPBF过程监测与质量判别领域也正快速发展[22-24]。利用原位监测数据训练神经网络,通过其强大的建模能力探索LPBF过程数据与成形件内部质量间的关联关系,进而可以准确判别打印零件的内部质量。为此,大量的工作利用打印过程中采集的AE监测数据开展基于DL的LPBF内部质量智能判别研究。DRISSI-DAOUDI等[25]利用卷积神经网络对LPBF熔池的状态进行判别,以此评估成形件内部缺陷;WANG等[26]采用一种基于深度神经网络的去噪方法来识别和消除AE信号中的噪声,并判别熔化道的质量。尽管目前基于DL的方法能够从AE信号中提取相关特征以实现内部质量判别,但其在辨别熔池微弱波动导致细微内部缺陷变化的质量判别状态下仍然存在不足。
针对上述问题,本研究提出基于自适应傅里叶神经算子[27](adaptive Fourier neural operator, AFNO)的质量判别方法。首先,前端利用深度残差网络从时域AE信号中提取具有熔池动态敏感性的潜在特征,继而在模型中嵌入AFNO将特征映射至频域空间,通过可学习的权重矩阵对熔池AE信号频段特征进行动态强化,最后引入Kolmogorov-Arnold网络(KAN)作为分类器,实现高维特征空间的有效映射,显著提升微弱波动信号与内部缺陷(匙孔、未熔融和正常)的关联建模能力。同时,研制了一套具有逐层触发功能的AE在线监测系统,以实现LPBF全工艺周期声信号监测,为建立熔池动力学与声学特征的物理关联提供试验基础。
快速傅里叶变换(fast Fourier transform, FFT)是基于傅里叶分析理论的将时域信号分解为频域谐波分量的数学工具。其核心是将任意周期或非周期信号分解为不同频率的正弦或余弦波的线性组合。FFT是离散傅里叶变换(discrete Fourier transform, DFT)的高效数值算法,利用优化计算过程将复杂度从O(N2)降至O(NlgN),其中,ON分别表示复杂度和信号长度。同理,逆快速傅里叶变换(inverse fast Fourier transform, IFFT)基于离散傅里叶逆变换(inverse discrete Fourier transform, IDFT),可将频域信号恢复成时域信号。DFT和IDFT的数学定义分别为:
X[g]=n=0N1x[n]ei2πgn/Ng=0,1,,N1
x[n]=1Ng=0N1X[g]ei2πgn/Ng=0,1,,N1
式中,n为信号时域采样点索引,对应t=nTs,其中Ts为采样间隔(s);g表示频域谱线索引,对应fg=gNFs,其中Fs=1/Ts为采样率(Hz);X[g]为复数频谱,表示信号在频率fg处的幅值与相位。
为了提升DFT和IDFT的计算效率,FFT和IFFT利用分治法和旋转因子的对称性,将复杂的高维运算分解为低维子问题的递归组合。(1)分解:将长度为N的序列按照奇偶索引拆分成两个子序列xeven[m]=x[2m]xodd[m]=x[2m+1]m为序列长度索引),递归计算子序列的DFT(Xeven[]Xodd[])及IDFT(xeven[]xodd[]);(2)组合:利用旋转因子WNg=ei2πgn/N(FFT)或WNg=ei2πg/N(IFFT)的对称性合并结果。基于上述思想,FFT和IFFT公式分别定义如下:
X[g]=Xeven[g]+WNgXodd[g]
x[n]=1N(xeven[g]+WNgxodd[g])
KAN[28]是基于Kolmogorov-Arnold表示理论的神经网络架构,其核心思想为:对于有界域上的多元连续函数,可以表示为有限数量一元函数和加法运算的符合函数。换句话说,高维非线性函数可以分解为多个单变量函数的组合。数学定义为:对于任何连续多元函数f(x1,x2,,xn),可表示如下:
f(x1,x2,,xn)=q=12n+1Φq(p=1nϕq,p(xp))
式中,Φ()ϕ()为单变量函数;pq分别表示输入变量的索引和函数Φ层级的索引。从原理上讲,KAN可以通过单变量函数的非线性变换与线性组合精确地逼近任意高维连续函数。
为了解决传统深度网络中因网络层数增加导致的梯度消失与模型退化问题,HE等[29]提出了残差神经网络(residual network, ResNet)。其核心思想为网络学习输入与输出间的残差映射而非完整的非线性变换。基本假设为:深层网络的理想映射H(y)可以分解为恒定映射与残差函数的叠加,用公式表示如下:
H(y)=F(y)+y
式中,y为输入的特征;F(y)=H(y)y为待学习的残差函数,表示目标映射与恒等映射的差异。从物理上讲,当残差F(y)0时,网络退化为恒等映射H(y)=y,避免了深层网络的退化问题。而利用链式法则推导残差块的梯度可表示为:
Hy=F(y)y+I
式中,I为单位矩阵。当F(y)y0时,残差块梯度为1,能够有效地缓解梯度消失问题。
本节介绍LPBF内部质量智能判别方法的整体框架。具体的质量判别方法如图1所示,表述如下:
(1)利用搭建的LPBF增材制造过程监测系统采集打印过程中的AE信号。
(2)将采集的数据按照时间维度做划分,每隔Ts为一个数据,并根据后处理的金相结果为数据做标签。然后将数据集划分出训练集、验证集和测试集。
(3)搭建基于AFNO的质量判别模型,并进行模型参数初始化,利用训练集数据训练网络,并利用验证集调整训练参数。
(4)利用交叉熵损失和反向传播算法优化网络,以更新模型的权重和偏置,直至模型收敛,若不收敛,则返回步骤(3)继续训练。
(5)将AE信号的测试集数据输入训练好的模型中,进行成形件内部质量判别。也可将训练好的模型部署到硬件设备上,在监测系统运行中进行质量在线判别。
(6)根据判别结果,对打印的工艺参数进行离线或在线调整,以提高成形质量。
为了高效地从复杂LPBF过程AE数据中提取出熔池状态相关的特征,本研究以经典的深度残差网络作为特征提取器。但深度残差网络最初提出的目的是为了解决复杂的图像识别问题,其内部的卷积等操作主要针对二维图像。为此,本研究首先将ResNet中的二维卷积核和卷积改为适合一维声信号的卷积。
除此之外,本研究发现使用一维ResNet架构在辨别熔池微弱波动导致细微内部缺陷变化的情况下仍存在漏检或误检的现象。为此,通过分析AE数据和LPBF工艺特点,发现在LPBF过程中存在多种声信号源,熔池波动发出的声波信号往往被淹没在其他的信号中。针对熔池AE数据的微弱特征,传统信号处理方法存在固定频段适应性不足、时频分析分辨率受限、去噪过程保真度有限等问题。而一维ResNet中卷积操作的平移不变形与LPBF声信号的非平稳瞬态特性存在冲突,导致微弱瞬态特征在多层卷积后发生波形弥散。此外,时域信号中的卷积操作由于缺乏频域物理先验的嵌入机制,在强背景噪声下容易发生细节丢失。
因此,本研究提出基于AFNO的质量判别模型。该模型由ResNet架构和AFNO模块级联组成,其中AFNO首先利用快速傅里叶变换(fast Fourier transform, FFT)将一维卷积操作提取的时域特征转为频域特征,在频域中对LPBF熔池多频带特征进行自适应特征加权,然后利用软阈值缩放操作对熔池波动相关频域特征进行增强,最后利用IFFT(inverse FFT)将其转换为时域特征进行下一步的特征提取。此外,为了进一步提升熔池微弱波动的AE信号与孔隙缺陷的关联建模能力,具有自适应激活函数和稀疏结构的KAN被用作判别网络的分类器。AFNO主要基于傅里叶神经算子[30](Fourier neural operator, FNO),接下来介绍FNO模块和AFNO模块的原理,如下所示:
(1)FNO模块:图2为FNO模块的原理示意图。其原理为:对于输入时域特征x(t)B×N×DBND分别表示批量大小、 数据长度和数据维度),首先经过FFT(F())映射为频域特征,然后利用可学习的权重矩阵M增强熔池频带特征(利用Hadamard积⊙加权频域特征),最后使用IFFT(F1())将频域特征恢复成时域特征xr(t),并使用残差结构聚合输入时序特征得到增强后的特征xo(t)。上述原理使用公式表示如下:
Z(w)=F(x(t))
Zr(w)=M(w)Z(w)
xr(t)=F1{Zr(w)}
xo(t)=x(t)+xr(t)
(2)AFNO模块:基于FNO方法,AFNO方法在频域中利用分块矩阵和软阈值化对熔池波动频域特征进行稀疏化学习,实现高效的非局部算子建模。如图3所示,即首先将权重矩阵MD×DD为输入特征维度)分割为大小为D/K×D/K的块对角矩阵,然后在权重矩阵块Mk间使用权重共享策略(多层感知机(multi-layer perceptron,MLP)),使其自适应地更新参数,最后使用软阈值化操作对频域特征进行稀疏化学习,保留主导特征。其原理使用公式表示如下:
z~kr=Mkzkk=1,,K
z~kr=MLP(zk)=W2σ(W1zk)+b
z~kr=Sλ(z~kr)=sgn(z~kr)max{|z~kr|λ,0}
式中,k为权重矩阵块索引;zk为AFNO模块输入特征;W1W2为两层MLP的权重;σ为激活函数;b为偏置;Sλ()表示软阈值化操作;λ为一个可调节稀疏度的参数;sgn()表示符号函数。当z~kr>0时,输出为z~kr,否则输出为0。
本文利用AFNO在AE信号的频域中进行特征映射,以提升熔池波动相关特征的自适应增强。具体而言,熔池声发射信号本质上是非平稳时变信号,其频域能量分布随激光-粉末交互过程剧烈波动。传统的卷积操作因全局基函数限制,难以捕获时频变特征。而AFNO利用可学习的分块权重矩阵在频域中对熔池波动特征进行稀疏化学习,实现高效的非局部算子建模。此外,AFNO在频域中通过权重矩阵对不同频带的熔池波动特征进行自适应加权和软阈值稀疏化,结合神经网络的强大特征提取能力,提升模型对熔池波动特征的感知能力。最后,为了实现上述AFNO的高效建模能力,本研究利用网格搜索技术确定AFNO模块的分块参数K=8,稀疏度参数λ=0.01。此外,AFNO模块使用级联的方式和ResNet18_1d的残差块结合,根据ResNet18_1d的网络结构确定AFNO模块的输入特征维度为D{64,128,256,512}
(3)KAN分类器:为了提升质量判别模型的分类性能,本研究也使用一层KAN作为网络的分类器。从结构机理分析,KAN采用可学习的激活函数矩阵代替传统MLP中固定结构的全连接层,这使得其能够将结合AFNO的特征提取器输出的高维熔池状态特征更加有效地映射到低维的样本类别空间中,显著提升熔池微弱波动信号与缺陷的关联关系建模。此外,从模块消融试验结果上看,KAN分类器在数据集D上能够获得0.43%的精度提升(+KAN相比于ResNet18-1d),这表明在微弱熔池波动工况下,KAN能够更好地建模分类边界,以获取更好的质量判别精度。
图4展示了基于AFNO的质量判别模型的训练与推断过程。当模型训练阶段,输入熔池AE信号后,使用交叉熵损失函数(cross entropy, CE)优化整个模型的参数。在推断阶段,使用训练好的模型判别成形件内部缺陷,根据判别的结果优化或调整打印的工艺参数。此外,训练好的模型也可以被部署在边缘端设备上,根据当前层成形件的质量判别结果去调整下一层的工艺参数(激光功率或扫描速度),形成监测-评估-调控为一体的智能监控系统,实现LPBF在线质量判别与调控,提升质量稳定一致性。
模型训练的超参数均使用网格搜索技术确定。具体如下:批量大小(batch size)和训练轮次(epoch)分别设置为64和100。使用AdamW优化器和学习率(learning rate)为0.0005去优化提出的质量判别模型。模型训练的平台如下:Linux OS系统;CPU为Intel(R) Xeon(R) Platinum 8167M@2.00 GHz;显卡为两块内存为24 GB的NVIDIA GeForce RTX 3090。
考虑到采集到的数据存在非均衡问题,为了验证本文提出方法的有效性,本文使用以下4种分类任务中常用的评估指标:精度(accuracy)、准确率(precision)、召回率(recall)和F1分数(F1-score)。所有指标的值越高,代表本文所提方法的效果越好。
为了监测LPBF过程中的声信号,通过分析AE信号判别成形件的质量。本研究自主搭建了基于AE传感器的LPBF在线监测系统,如图5所示。该系统硬件系统主要由声发射传感器(PXR04A)、光电触发器(EE-SPY402A-1)、数据采集卡(ART USB5763)、声信号放大器(PXPA3,40 dB)以及上位机组成。如图6所示,传感器安装在商用打印机易加三维EP-M250设备上,安装位置为基板上方,通过转接头将传感器信号线连接到藏室外。
图5所示,为了监测层间-层内每个成形件的成形质量,该系统同时采集3种信号,包括光电触发器的数字信号、激光器的控制信号和AE传感器的声信号。当系统运行时,通过安装在刮刀上方的光电触发器启动当前层的数据采集,即当每一层刮刀铺粉完成后触发器运行,系统开始采集当前层的AE数据,当前层打印完成后开始下一层铺粉时停止采集,以此循环往复,采集打印件制造全周期的AE信号。此外,同步采集当前层中每个成形件对应的激光功率控制信号,然后通过使用阈值分割的方式将每个成形件的AE信号分割开来。声信号放大器用于放大LPBF过程中熔池的微弱声信号,同时抑制其他噪声信号。
监测系统软件使用NI LabVIEW编程语言在上位机中运行,在监测的同时自动保存对应层的过程数据。此外,考虑到信号采样的完整性,本系统以100 kHz的采样频率同步采集上述3种信号。
本次试验采用商用打印机EP-M250,配备连续单模红外光纤激光器,额定功率为500 W,激光波长为1064 nm,光斑直径为70 μm。振镜系统为SCANLAB公司的hurrySCAN 20,最大扫描速度为2 m/s。试验中打印机舱室内部通入惰性气体氩气作为保护气,氧含量不超过0.03%。
试验金属粉末材料为Ti6-Al-4V粉末,呈近似球状,直径为15~54 μm。使用激光衍射技术测量粉末的统计粒度分布指数为D10=16.58μmD50 = 33.36μmD90 = 54.09μm。此外,粉末的流动性为31.1s/50g
本次试验中,成形件的工艺参数主要基于激光体积能量密度(volumetric energy density, VED)进行设计[31]。其表示成形过程中单位体积的激光功率,广泛应用于LPBF工艺参数设计中。VED使用公式表示如下:
VED=Pvha
式中,Pvha分别表示激光功率、扫描速度、扫描熔化道间距和粉层厚度。
在LPBF试验中,激光功率P和扫描速度v对成形质量影响最为显著。如图7所示,为了探索不同工艺参数组合对成形质量的影响,该试验通过改变激光功率和扫描速度(激光功率范围:170~420 W,扫描速度:850~1850 mm/s)得到36组工艺参数组合试验件。此外,本次试验的扫描熔化道间距h和粉层厚度a分别设置为0.12和0.06 mm。为了便于记录,本次试验对36个试验件进行编号,“1-1”和“6-6”分别对应最低的激光功率-扫描速度和最高的激光功率-扫描速度。
本次试验结束后,对打印件进行一系列后处理操作以评估质量分析。首先,使用线切割装置(FP600S)将成形件与打印基板分离;然后利用环氧树脂对成形件进行冷镶嵌处理,以便进行金相试验;最后,对每个成形试件进行磨金相操作,使用金相显微镜查看其内部质量。如图8所示,展示了3种LPBF成形件质量,包括未熔融缺陷、质量良好、匙孔孔隙缺陷。从原理上讲,未熔融缺陷由激光能量不足或扫描速度过快导致,金属粉末未完全熔化而形成孔隙;匙孔孔隙缺陷则因激光能量过高引发熔池剧烈汽化,蒸汽反冲压力使熔池塌陷并捕获气泡所致。两类缺陷分别表征了激光-物质相互作用中热输运失衡的两种极端状态:前者为熔融不充分的热力学相变阻滞,后者为熔体剧烈汽化的流体动力学失稳。
本研究构建的LPBF熔池监测系统同步采集AE信号、激光功率控制信号和光电触发器信号,用于区分打印过程层间和层内每个成形件的熔池AE数据。如图9所示,由于激光功率控制信号和AE信号为同步采集,通过设置阈值得到每个成形样本的起始上升沿和结束下降沿索引,以此分割得到每个成形件的AE信号。此外,进一步使用5000个点(Ts=0.05s)的间隔划分36个成形试件对应的38层AE数据,最终得到88716个AE数据样本。
为了验证本研究所提出的质量判别方法在典型缺陷判别、临界状态与微弱波动分辨率下的有效性。AE数据集构建4个数据集:首先,选择工艺参数组1-6(未熔融缺陷)、5-3(正常)和6-1(匙孔孔隙缺陷)构建基准数据集A,该数据集覆盖熔池动态的极端状态(未熔融、正常和匙孔状态),验证方法在典型工况下的基础质量判别能力;其次,针对熔池波动临界状态下的质量判别工况,在匙孔孔隙缺陷区(6-1、6-2和5-2)以及未熔融缺陷区(2-4、2-5和3-4)分别构建数据集B和C,考察方法在缺陷临界区域的有效性;进一步以正常区最优工艺参数组合5-3(370 W, 1250 mm/s)为中心,在其领域(±50 W,±200 mm/s)选取9组参数构建数据集D,验证方法在熔池微弱波动情况下的质量判别能力。上述4种数据集均使用8∶1∶1比例划分训练集、验证集和测试集,样本数量具体情况如表1所示。
为了验证本研究所提方法在基准数据集A上的质量判别能力,本节在数据集A上进行了试验验证。试验中,考虑到AE数据的低维度特点和其较为简单的数据特征,选择原始的ResNet18网络将其二维卷积修改为适合AE数据的一维卷积后记为ResNet18-1d,并将其作为基准模型。表2展示了所提方法在基准数据集A上的试验结果,其中,Acc、Pre、Rec和F1分别表示精度、准确率、召回率和F1分数。
表2中可以看出,基准数据集中3种工艺参数组合对应的AE数据特征辨识度很高,基准模型ResNet18-1d取得了99%以上的精度,这表明在极端的熔池波动情况下,对应的AE数据和成形件的质量高度相关。此外,本文所提方法在各项指标上均获得了100%的性能,这说明所提方法能够更加精准建模AE数据和成形件质量间的关联关系。图10展示了两种方法的试验结果,ResNet18-1d模型由于无法提取频域特征,出现了误判。而本方法通过在频域空间中自适应增强熔池状态相关特征的表征权重,有效抑制了其他声信号对质量判别的干扰,并最终获得了最优的效果。
本节分析所提方法在临界熔池波动情况下的熔池相关特征提取能力和质量判别能力。试验中,依然选择ResNet18-1d作为基准模型。
图10中可以看出,在数据集B和C中,由于工艺参数边界位于匙孔孔隙缺陷和未熔融缺陷区域,临界工艺参数熔池波动较为剧烈,对应的AE数据特征较为明显,ResNet18-1d方法也取得了超过98%的精度。而本文所提方法在数据集B和C中的所有评估指标均取得了1%和0.4%左右的提升。具体而言,在频率空间中增强熔池相关特征,并利用强大的KAN将高维特征映射到类别空间中,这有利于边界区域AE信号的特征提取与质量判别。此外,从图11中可以看出,所提方法对跨类别样本(如未熔融-正常临界样本)具有近乎完美的区分能力,但对同类样本中由工艺参数微扰引起的特征偏移仍存在误判率,这源于同类样本的AE信号在时频域具有高度相似性。
本节验证所提方法在微弱熔池波动状况下的质量判别能力。所提方法的Acc为97.60%,Pre为97.56%,Rec为97.50%,F1分数为97.51%,相比于基准模型ResNet18-1d,所有指标均提升超过1%。此外,图12展示了所提方法在数据集D上的试验结果的混淆矩阵。从试验结果中可以看出,尽管在工艺参数处于质量正常区域,但熔池依然存在微弱波动。事实上,这符合LPBF工艺本身的特点,当激光与粉末交互时,在反冲压力的作用下,熔池呈现钥匙孔状,而当匙孔壁上的粉末继续吸收能量后,导致液态熔池所受的马兰戈尼力、表面张力等失稳,引起熔池振荡,容易产生气孔等缺陷。而当熔池微弱波动时,尽管也会产生缺陷,但与正常工艺参数的差异较小,这进一步导致过程数据差异较小。然而,从结果中可以看出,本研究所提方法通过在频域中自适应增强熔池状态相关特征,并使用KAN高效建模高维空间与类别空间的关联关系,最终取得了97%以上的质量判别性能。
本节验证文中提出的几种网络模块在质量判别任务中的有效性。基于ResNet18-1d网络,逐个添加相关模块,在数据集B、C和D上进行消融试验。
表3展示了消融试验的结果。从结果中可以看出,在数据集B、C和D上,本文方法均取得了最优的结果。此外,可以看出KAN分类器和AFNO模块对质量辨识均发挥着作用。在数据集B和C上,上述两个模块和基准模型ResNet18-1d的组合效果稍逊于基准模型。一方面可能是由于数据集B和C的设定为熔池波动边界区域,数据分布不均衡导致辨别模型未能充分学习到每种类别的可辨别特征,引起误报。另一方面,尽管KAN分类器利用其自适应激活函数的功能将高维特征映射到样本类别空间中,但由于前端模块输出的高维特征中大量熔池状态无关特征,引起映射效果较差。而仅使用AFNO模块尽管可以在频域空间中增强熔池相关特征,但网络后端的特征到类别空间中映射能力不足,导致效果较差。总而言之,试验结果表明,KAN分类器与AFNO模块协同作用有效提升了质量判别性能,在数据集D上达到最优表现,但两者在数据分布不均衡的数据集B和C上因特征映射能力不足而导致性能波动,验证了模块设计的有效性。
表3中也展示了不同基线模型的质量判别结果。从结果中可以看出,ResNet18-1d模型能够取得令人满意的结果,而表达力更好和参数量更大的ResNet34-1d、ResNet50-1d反而取得了与ResNet18-1d相同或稍逊的结果。其原因主要由于熔池声发射信号为简单的信号,使用ResNet18-1d模型已经能够提取出熔池状态相关特征,表达能力更好会导致模型出现过拟合现象,降低精度。因此,本文使用ResNet18-1d作为基线模型。
LPBF在线监测与质量评估是保证其质量稳定一致性的关键。本研究针对传统监测技术存在的挑战,自主搭建一套基于声发射传感器的LPBF熔池监测系统,实现制造过程全周期的成形质量监测。此外,针对打印过程中熔池微弱波动导致特征提取困难的问题,提出了基于AFNO的质量智能判别方法。通过大量试验对该系统和方法的有效性进行了验证,获得的主要结论如下:
(1)搭建的基于声发射传感器的熔池监测系统能够全周期地逐层监测多种成形件的声信号,通过探索过程数据与质量的映射关系,原位在线监测成形件的质量,具有较大的工程应用价值。
(2)基于搭建的监测系统构建了较大规模的LPBF熔池状态AE数据集,样本数量超过8万。
(3)本文提出的基于AFNO的质量判别方法能够在临界参数空间内熔池波动、微弱熔池波动状况下均获得超过97%的精度,展示了良好的LPBF质量判别性能。
  • 国防基础科研计划资助项目(JCKY2023110C044)
参考文献 引证文献
排序方式:
[1]
KHORASANI A, GIBSON I, VEETIL J K, et al.A review of technological improvements in laser-based powder bed fusion of metal printers[J]. The International Journal of Advanced Manufacturing Technology, 2020, 108(1): 191-209.
[2]
SINGH D D, MAHENDER T, REDDY A R. Powder bed fusion process: a brief review[J]. Materials Today: Proceedings, 2021, 46: 350-355.
[3]
NARASIMHARAJU S R, ZENG W H, SEE T L, et al.A comprehensive review on laser powder bed fusion of steels: processing, microstructure, defects and control methods, mechanical properties, current challenges and future trends[J]. Journal of Manufacturing Processes, 2022, 75: 375-414.
[4]
SINGH R, GUPTA A, TRIPATHI O, et al.Powder bed fusion process in additive manufacturing: an overview[J]. Materials Today: Proceedings,2020,26: 3058-3070.
[5]
CHOWDHURY S, YADAIAH N, PRAKASH C, et al.Laser powder bed fusion: a state-of-the-art review of the technology, materials, properties & defects, and numerical modelling[J]. Journal of Materials Research and Technology, 2022, 20: 2109-2172.
[6]
ZHAO C, PARAB N D, LI X X, et al.Critical instability at moving keyhole tip generates porosity in laser melting[J]. Science, 2020, 370(6520): 1080-1086.
[7]
BITHARAS I, PARAB N, ZHAO C, et al.The interplay between vapour, liquid, and solid phases in laser powder bed fusion[J]. Nature Communications, 2022, 13(1): 2959.
[8]
MCCANN R, OBEIDI M A, HUGHES C, et al.In-situ sensing, process monitoring and machine control in Laser Powder Bed Fusion: a review[J]. Additive Manufacturing, 2021, 45: 102058.
[9]
YEUNG H, YANG Z, YAN L. A meltpool prediction based scan strategy for powder bed fusion additive manufacturing[J]. Additive Manufacturing, 2020, 35: 101383.
[10]
KWON O, KIM H G, HAM M J, et al.A deep neural network for classification of melt-pool images in metal additive manufacturing[J]. Journal of Intelligent Manufacturing, 2020, 31(2): 375-386.
[11]
SAMAEI A, PORTER C, KOZJEK D, et al.Understanding coaxial photodiode-based multispectral pyrometer measurements at the overhang regions in laser powder bed fusion for part qualification[J]. Additive Manufacturing, 2024, 93: 104398.
[12]
YANG W M, QIU Y B, LIU W W, et al.Defect prediction in laser powder bed fusion with the combination of simulated melt pool images and thermal images[J]. Journal of Manufacturing Processes, 2023, 106: 214-222.
[13]
SELEZNEV M, GUSTMANN T, FRIEBEL J M, et al.In situ detection of cracks during laser powder bed fusion using acoustic emission monitoring[J]. Additive Manufacturing Letters, 2022, 3: 100099.
[14]
KONONENKO D Y, NIKONOVA V, SELEZNEV M, et al.An in situ crack detection approach in additive manufacturing based on acoustic emission and machine learning[J]. Additive Manufacturing Letters,2023,5: 100130.
[15]
DE FORMANOIR C, NASAB M H, SCHLENGER L, et al.Healing of keyhole porosity by means of defocused laser beam remelting: operando observation by X-ray imaging and acoustic emission-based detection[J]. Additive Manufacturing, 2024, 79: 103880.
[16]
PANDIYAN V, WRÓBEL R, RICHTER R A, et al.Monitoring of Laser Powder Bed Fusion process by bridging dissimilar process maps using deep learning-based domain adaptation on acoustic emissions[J]. Additive Manufacturing, 2024, 80: 103974.
[17]
HAMIDI NASAB M, MASINELLI G, DE FORMANOIR C, et al.Harmonizing sound and light: X-ray imaging unveils acoustic signatures of stochastic inter-regime instabilities during laser melting[J]. Nature Communications, 2023, 14(1): 8008.
[18]
张亚军,潘东辉, 张先杰,等.多尺度图池化特征融合的集成智能故障诊断方法[J]. 振动工程学报, 2024, 37(12):2148-2157.
ZHANG Yajun, PAN Donghui, ZHANG Xianjie, et al.Ensemble intelligent fault diagnosis method based on multi-scale graph pooling feature fusion[J]. Journal of Vibration Engineering, 2024, 37(12): 2148-2157.
[19]
郭盼盼,张文斌, 崔奔,等.基于增强深度卷积神经网络的滚动轴承多工况故障诊断方法[J]. 振动工程学报, 2025, 38(1):96-108.
GUO Panpan, ZHANG Wenbin, CUI Ben, et al.Multi-condition fault diagnosis method of rolling bearing based on enhanced deep convolutional neural network[J]. Journal of Vibration Engineering, 2025, 38(1): 96-108.
[20]
TANG J F, ZHAO Z B, GUO Y J, et al.Privacy-preserving federated transfer learning for defect identification from highly imbalanced image data in additive manufacturing[J]. Robotics and Computer-Integrated Manufacturing, 2024, 89: 102779.
[21]
TAN K P, TANG J F, ZHAO Z B, et al.Efficient and lightweight layer-wise in-situ defect detection in laser powder bed fusion via knowledge distillation and structural re-parameterization[J]. Expert Systems with Applications, 2024, 255: 124628.
[22]
LI J C, HU J X, ZHOU Q, et al.Transfer learning-based quality monitoring of laser powder bed fusion across materials[J]. Expert Systems with Applications, 2024, 252: 124150.
[23]
ZHAO Z B, LIU W L, REN J X, et al.Uncertainty-driven trustworthy defect detection for high-resolution powder bed images in selective laser melting[J]. Journal of Manufacturing Systems, 2024, 72: 59-73.
[24]
KOZJEK D, PORTER C, CARTER F M, et al.Data-driven prediction of inter-layer process condition variations in laser powder bed fusion[J]. Additive Manufacturing, 2024, 88: 104230.
[25]
DRISSI-DAOUDI R, MASINELLI G, DE FORMANOIR C, et al.Acoustic emission for the prediction of processing regimes in Laser Powder Bed Fusion, and the generation of processing maps[J]. Additive Manufacturing, 2023, 67: 103484.
[26]
WANG H J, ZHANG S F, LI B. Machine learning-assisted acoustic emission monitoring for track formability prediction of laser powder bed fusion[J]. Materials Today Communications, 2024, 38: 108522.
[27]
GUIBAS J, MARDANI M, LI Z Y, et al.Adaptive fourier neural operators: efficient token mixers for transformers[EB/OL]. (2021-11-24)[2025-03-31]. https://arXiv.org/abs/2111.13587v2.
[28]
LIU Z, WANG Y, VAIDYA S, et al.Kan: Kolmogorov-arnold networks[EB/OL]. (2024-04-30)[2025-03-31]. https://arXiv.org/abs/2404.19756.
[29]
HE K M, ZHANG X Y, REN S Q, et al.Deep residual learning for image recognition[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 2016: 770-778.
[30]
LI Z Y, KOVACHKI N, AZIZZADENESHELI K, et al.Fourier neural operator for parametric partial differential equations[EB/OL]. (2020-10-18)[2025-03-31]. https://arXiv.org/abs/2010.08895v3.
[31]
BUHAIRI M A, FOUDZI F M, JAMHARI F I, et al.Review on volumetric energy density: influence on morphology and mechanical properties of Ti6Al4V manufactured via laser powder bed fusion[J]. Progress in Additive Manufacturing, 2023, 8(2): 265-283.
2025年第38卷第6期
PDF下载
86
39
引用本文
BibTeX
文章信息
doi: 10.16385/j.cnki.issn.1004-4523.2025.06.002
  • 接收时间:2025-03-31
  • 首发时间:2026-02-12
  • 出版时间:2025-06-10
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2025-03-31
  • 修回日期:2025-05-10
基金
国防基础科研计划资助项目(JCKY2023110C044)
作者信息
    1.西安交通大学航空动力系统与等离子体技术全国重点实验室,陕西 西安 710049
    2.西安交通大学机械工程学院,陕西 西安 710049
    3.空军工程大学航空动力系统与等离子体技术全国重点实验室,陕西 西安 710038

通讯作者:

赵志斌(1993—),男,博士,副教授。E-mail:
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/zdgcxb/CN/10.16385/j.cnki.issn.1004-4523.2025.06.002
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