Article(id=1205158522716664025, tenantId=1146029695717560320, journalId=1189987059142926344, issueId=1205158521005384666, articleNumber=null, orderNo=null, doi=10.19457/j.1001-2095.dqcd25144, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=research-article, receivedDate=1684944000000, receivedDateStr=2023-05-25, revisedDate=1686499200000, revisedDateStr=2023-06-12, acceptedDate=null, acceptedDateStr=null, onlineDate=1765261782577, onlineDateStr=2025-12-09, pubDate=1724083200000, pubDateStr=2024-08-20, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1765261782577, onlineIssueDateStr=2025-12-09, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1765261782577, creator=13701087609, updateTime=1765261782577, updator=13701087609, issue=Issue{id=1205158521005384666, tenantId=1146029695717560320, journalId=1189987059142926344, year='2024', volume='54', issue='8', pageStart='3', pageEnd='96', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1765261782170, creator=13701087609, updateTime=1765261980641, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1205159353524400961, tenantId=1146029695717560320, journalId=1189987059142926344, issueId=1205158521005384666, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1205159353524400962, tenantId=1146029695717560320, journalId=1189987059142926344, issueId=1205158521005384666, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=90, endPage=96, ext={EN=ArticleExt(id=1205158522955739358, articleId=1205158522716664025, tenantId=1146029695717560320, journalId=1189987059142926344, language=EN, title=Research on Small Sample Machine Learning Method for Acoustic Quality Detection of Micro Motors, columnId=null, journalTitle=Electric Drive, columnName=null, runingTitle=null, highlight=null, articleAbstract=

In order to solve the problems of high subjective misjudgment rate and low efficiency in manual hand touch and auscultation methods for acoustic quality detection of micro motors,while taking into account the accuracy of detection results and the fast construction of detection models,a small sample machine learning detection method was proposed. Based on the physical model of micro motor transmission chain,multi-dimensional acoustic fault features were extracted,particle swarm optimization was used to optimize the core parameters of support vector machine,a small sample learning method,so as to improve the accuracy of model discrimination.The experimental results show that this method can effectively distinguish abnormal vibration and sound of micro motors,with an accuracy rate of over 95%.

, 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=Zhidan TIAN, Xiang YU, Haibo WAN), CN=ArticleExt(id=1205158526344737068, articleId=1205158522716664025, tenantId=1146029695717560320, journalId=1189987059142926344, language=CN, title=微型电机声学质量检测小样本机器学习方法研究, columnId=1190325456588079763, journalTitle=电气传动, columnName=可靠性与诊断, runingTitle=null, highlight=null, articleAbstract=

为了解决微型电机声学质量检测人工手摸及听诊方法存在的主观误判率高、效率低下等问题,同时兼顾检测结果准确率和检测模型构建的快速性,提出了一种小样本机器学习检测方法,其根据微型电机传动链物理模型进行多维声学故障特征提取,在此基础上,采用粒子群优化算法对支持向量机这种小样本学习方法的核心参数进行优化,从而提高模型判别的准确率。试验结果表明,该方法能够有效判别微型电机异常振动和声音,准确率达到95%以上。

, correspAuthors=null, authorNote=null, correspAuthorsNote=
俞翔(1978—),男,博士,教授,硕士生导师,主要研究方向为振动与噪声控制,Email:
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=SIJ3iKnt1aLt79Mb80eQww==, magXml=Tr20I0kfbWtUtPDtg0istg==, pdfUrl=null, pdf=ponQXhlJZ3WPBfOHcG/DHQ==, pdfFileSize=3113728, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=l79GnDQMfhPiz+xqKqOOVw==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=nwXf8RIJFZU0d7EvRaHevA==, mapNumber=null, authorCompany=null, fund=null, authors=

田芝丹(1998—),女,硕士研究生,主要研究方向为振动与噪声控制、故障诊断,Email:

, authorsList=田芝丹, 俞翔, 万海波)}, authors=[Author(id=1205172815587680353, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205158522716664025, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=M21385503@nue.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1205172815696732266, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205158522716664025, authorId=1205172815587680353, language=EN, stringName=Zhidan TIAN, firstName=Zhidan, middleName=null, lastName=TIAN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=College of Naval Architecture and Ocean,Naval University of Engineering,Wuhan 430033,Hubei,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1205172815809978481, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205158522716664025, authorId=1205172815587680353, language=CN, stringName=田芝丹, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=海军工程大学 舰船与海洋学院,湖北 武汉 430033, bio={"content":"

田芝丹(1998—),女,硕士研究生,主要研究方向为振动与噪声控制、故障诊断,Email:

"}, bioImg=null, bioContent=

田芝丹(1998—),女,硕士研究生,主要研究方向为振动与噪声控制、故障诊断,Email:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1205172815491211352, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205158522716664025, xref=null, ext=[AuthorCompanyExt(id=1205172815495405657, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205158522716664025, companyId=1205172815491211352, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=College of Naval Architecture and Ocean,Naval University of Engineering,Wuhan 430033,Hubei,China), AuthorCompanyExt(id=1205172815503794267, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205158522716664025, companyId=1205172815491211352, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=海军工程大学 舰船与海洋学院,湖北 武汉 430033)])]), Author(id=1205172815931613301, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205158522716664025, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=yuxiang898@sina.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1205172816019693693, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205158522716664025, authorId=1205172815931613301, language=EN, stringName=Xiang YU, firstName=Xiang, middleName=null, lastName=YU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=College of Naval Architecture and Ocean,Naval University of Engineering,Wuhan 430033,Hubei,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1205172816153911429, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205158522716664025, authorId=1205172815931613301, language=CN, stringName=俞翔, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=海军工程大学 舰船与海洋学院,湖北 武汉 430033, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1205172815491211352, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205158522716664025, xref=null, ext=[AuthorCompanyExt(id=1205172815495405657, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205158522716664025, companyId=1205172815491211352, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=College of Naval Architecture and Ocean,Naval University of Engineering,Wuhan 430033,Hubei,China), AuthorCompanyExt(id=1205172815503794267, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205158522716664025, companyId=1205172815491211352, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=海军工程大学 舰船与海洋学院,湖北 武汉 430033)])]), Author(id=1205172816229408906, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205158522716664025, 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=1205172816367820949, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205158522716664025, authorId=1205172816229408906, language=EN, stringName=Haibo WAN, firstName=Haibo, middleName=null, lastName=WAN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=College of Naval Architecture and Ocean,Naval University of Engineering,Wuhan 430033,Hubei,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1205172816497844382, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205158522716664025, authorId=1205172816229408906, language=CN, stringName=万海波, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=海军工程大学 舰船与海洋学院,湖北 武汉 430033, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1205172815491211352, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205158522716664025, xref=null, ext=[AuthorCompanyExt(id=1205172815495405657, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205158522716664025, companyId=1205172815491211352, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=College of Naval Architecture and Ocean,Naval University of Engineering,Wuhan 430033,Hubei,China), AuthorCompanyExt(id=1205172815503794267, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205158522716664025, companyId=1205172815491211352, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=海军工程大学 舰船与海洋学院,湖北 武汉 430033)])])], keywords=[Keyword(id=1205172817798078636, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205158522716664025, language=EN, orderNo=1, keyword=micro motor), Keyword(id=1205172817894547632, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205158522716664025, language=EN, orderNo=2, keyword=quality inspection), Keyword(id=1205172818058125494, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205158522716664025, language=EN, orderNo=3, keyword=physical model), Keyword(id=1205172818154594488, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205158522716664025, language=EN, orderNo=4, keyword=particle swarm optimization(PSO)), Keyword(id=1205172818234286268, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205158522716664025, language=EN, orderNo=5, keyword=support vector machine(SVM)), Keyword(id=1205172818355921090, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205158522716664025, language=CN, orderNo=1, keyword=微型电机), Keyword(id=1205172818502721741, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205158522716664025, language=CN, orderNo=2, keyword=质量检测), Keyword(id=1205172818678882520, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205158522716664025, language=CN, orderNo=3, keyword=物理模型), Keyword(id=1205172818766962912, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205158522716664025, language=CN, orderNo=4, keyword=粒子群优化), Keyword(id=1205172818834071781, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205158522716664025, language=CN, orderNo=5, keyword=支持向量机)], refs=[Reference(id=1205172823040958824, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205158522716664025, doi=null, pmid=null, pmcid=null, year=2023, volume=14, issue=4, pageStart=154, pageEnd=155, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=宋昱晓, 王雨璐, 于宏博, journalName=黑龙江科学, refType=null, unstructuredReference=宋昱晓, 王雨璐, 于宏博, 等. 一种图像识别车辆定位系统摄像头的设计[J]. 黑龙江科学, 2023, 14(4):154-155,158., articleTitle=一种图像识别车辆定位系统摄像头的设计, refAbstract=null), Reference(id=1205172823145816428, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205158522716664025, doi=null, pmid=null, pmcid=null, year=2023, volume=14, issue=4, pageStart=154, pageEnd=155, url=null, language=null, rfNumber=[1], rfOrder=1, authorNames=SONG Yuxiao, WANG Yuliu, YU Hongbo, journalName=Heilongjiang Science, refType=null, unstructuredReference=SONG Yuxiao, WANG Yuliu, YU Hongbo, et al. Design of a camera for image recognition vehicle positioning system[J]. Heilongjiang Science, 2023, 14(4):154-155,158., articleTitle=Design of a camera for image recognition vehicle positioning system, refAbstract=null), Reference(id=1205172823250674031, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205158522716664025, doi=null, pmid=null, pmcid=null, year=2023, volume=52, issue=3, pageStart=80, pageEnd=84, url=null, language=null, rfNumber=[2], rfOrder=2, authorNames=纪永, journalName=工业加热, refType=null, unstructuredReference=纪永. 基于机器视觉的加热炉内异常情况图像识别方法研究[J]. 工业加热, 2023, 52(3):80-84., articleTitle=基于机器视觉的加热炉内异常情况图像识别方法研究, refAbstract=null), Reference(id=1205172823384891761, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205158522716664025, doi=null, pmid=null, pmcid=null, year=2023, volume=52, issue=3, pageStart=80, pageEnd=84, url=null, language=null, rfNumber=[2], rfOrder=3, authorNames=JI Yong, journalName=Industrial Heating, refType=null, unstructuredReference=JI Yong. Study on image recognition of abnormal in heating furnace based on machine vision[J]. Industrial Heating, 2023, 52(3):80-84., articleTitle=Study on image recognition of abnormal in heating furnace based on machine vision, refAbstract=null), Reference(id=1205172823460389233, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205158522716664025, doi=null, pmid=null, pmcid=null, year=2024, volume=null, issue=2, pageStart=87, pageEnd=95, url=null, language=null, rfNumber=[3], rfOrder=4, authorNames=范传刚, 李玉豪, 王峥阳, journalName=土木工程学报, refType=null, unstructuredReference=范传刚, 李玉豪, 王峥阳, 等. 基于图像识别技术的工业建筑火灾风险远程评估方法及应用研究[J]. 土木工程学报, 2024(2):87-95., articleTitle=基于图像识别技术的工业建筑火灾风险远程评估方法及应用研究, refAbstract=null), Reference(id=1205172823523303798, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205158522716664025, doi=null, pmid=null, pmcid=null, year=2024, volume=null, issue=2, pageStart=87, pageEnd=95, url=null, language=null, rfNumber=[3], rfOrder=5, authorNames=FAN Chuangang, LI Yuhao, WANG Zhengyang, journalName=China Civil Engineering Journal, refType=null, unstructuredReference=FAN Chuangang, LI Yuhao, WANG Zhengyang, et al. Study on remote fire risk assessment method for industrial buildings based on image recognition technology[J]. China Civil Engineering Journal, 2024(2):87-95., articleTitle=Study on remote fire risk assessment method for industrial buildings based on image recognition technology, refAbstract=null), Reference(id=1205172823594606970, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205158522716664025, doi=null, pmid=null, pmcid=null, year=2020, volume=19, issue=null, pageStart=100625, pageEnd=null, url=null, language=null, rfNumber=[4], rfOrder=6, authorNames=LI P, ZHAO W, journalName=Case Studies in Thermal Engineering, refType=null, unstructuredReference=LI P, ZHAO W. Image fire detection algorithms based on convolutional neural networks[J]. Case Studies in Thermal Engineering, 2020, 19:100625., articleTitle=Image fire detection algorithms based on convolutional neural networks, refAbstract=null), Reference(id=1205172823691075965, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205158522716664025, doi=null, pmid=null, pmcid=null, year=1999, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[5], rfOrder=7, authorNames=BRACKLEY M, POLLOCK C, journalName=IEEE Transactions on Industry Applications, refType=null, unstructuredReference=BRACKLEY M, POLLOCK C. Analysis and reduction of acoustic noise from a brushless DC drive[J]. IEEE Transactions on Industry Applications, 1999., articleTitle=Analysis and reduction of acoustic noise from a brushless DC drive, refAbstract=null), Reference(id=1205172823787544962, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205158522716664025, doi=null, pmid=null, pmcid=null, year=2000, volume=36, issue=5, pageStart=1467, pageEnd=1480, url=null, language=null, rfNumber=[6], rfOrder=8, authorNames=FINLEY W R, HODOWANEC M M, HOLTER W G, journalName=IEEE Transactions on Industry Applications, refType=null, unstructuredReference=FINLEY W R, HODOWANEC M M, HOLTER W G. An analyti-cal approach to solving motor vibration problems[J]. IEEE Transactions on Industry Applications, 2000, 36(5):1467-1480., articleTitle=An analyti-cal approach to solving motor vibration problems, refAbstract=null), Reference(id=1205172823879819655, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205158522716664025, doi=null, pmid=null, pmcid=null, year=2018, volume=null, issue=10, pageStart=7460419, pageEnd=null, url=null, language=null, rfNumber=[7], rfOrder=9, authorNames=GLOWACZ A, GLOWACZ W, journalName=Shock and Vibration, refType=null, unstructuredReference=GLOWACZ A, GLOWACZ W. Vibration-based fault diagnosis of commutator motor[J]. Shock and Vibration, 2018(10):7460419., articleTitle=Vibration-based fault diagnosis of commutator motor, refAbstract=null), Reference(id=1205172823955317130, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205158522716664025, doi=null, pmid=null, pmcid=null, year=2021, volume=41, issue=3, pageStart=311, pageEnd=319, url=null, language=null, rfNumber=[8], rfOrder=10, authorNames=JUNIOR R F R, AREIAS I, GOMES G F, journalName=Sensor Review, refType=null, unstructuredReference=JUNIOR R F R, AREIAS I, GOMES G F. Fault detection and diagnosis using vibration signal analysis in frequency domain for electric motors considering different real fault types[J]. Sensor Review, 2021, 41(3):311-319., articleTitle=Fault detection and diagnosis using vibration signal analysis in frequency domain for electric motors considering different real fault types, refAbstract=null), Reference(id=1205172824035008908, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205158522716664025, doi=null, pmid=null, pmcid=null, year=2007, volume=1, issue=11, pageStart=632, pageEnd=635, url=null, language=null, rfNumber=[9], rfOrder=11, authorNames=KITAMOTO T, journalName=International Journal of Mechanical and Mechatronics Engineering, refType=null, unstructuredReference=KITAMOTO T. A method for quality inspection of motors by detecting abnormal sound[J]. International Journal of Mechanical and Mechatronics Engineering, 2007, 1(11):632-635., articleTitle=A method for quality inspection of motors by detecting abnormal sound, refAbstract=null), Reference(id=1205172824123089297, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205158522716664025, doi=null, pmid=null, pmcid=null, year=2014, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[10], rfOrder=12, authorNames=刘力源, journalName=基于机器学习方法的电机异音检测研究, refType=null, unstructuredReference=刘力源. 基于机器学习方法的电机异音检测研究[D]. 广州: 五邑大学, 2014., articleTitle=null, refAbstract=null), Reference(id=1205172824190198165, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205158522716664025, doi=null, pmid=null, pmcid=null, year=2014, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[10], rfOrder=13, authorNames=LIU Liyuan, journalName=Research on motor abnormal sound detection based on machine learning methods, refType=null, unstructuredReference=LIU Liyuan. Research on motor abnormal sound detection based on machine learning methods[D]. Guangzhou: Wuyi University, 2014., articleTitle=null, refAbstract=null), Reference(id=1205172824282472857, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205158522716664025, doi=null, pmid=null, pmcid=null, year=2017, volume=36, issue=5, pageStart=102, pageEnd=107, url=null, language=null, rfNumber=[11], rfOrder=14, authorNames=刘思思, 谭建平, 易子馗, journalName=振动与冲击, refType=null, unstructuredReference=刘思思, 谭建平, 易子馗. 基于MFCC和SVM的车窗电机异常噪声辨识方法研究[J]. 振动与冲击, 2017, 36(5):102-107., articleTitle=基于MFCC和SVM的车窗电机异常噪声辨识方法研究, refAbstract=null), Reference(id=1205172824366358941, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205158522716664025, doi=null, pmid=null, pmcid=null, year=2017, volume=36, issue=5, pageStart=102, pageEnd=107, url=null, language=null, rfNumber=[11], rfOrder=15, authorNames=LIU Sisi, TAN Jianping, YI Zikui, journalName=Journal of Vibration and Shock, refType=null, unstructuredReference=LIU Sisi, TAN Jianping, YI Zikui. A window motor abnormal noise identification method based on MFCC and SVM[J]. Journal of Vibration and Shock, 2017, 36(5):102-107., articleTitle=A window motor abnormal noise identification method based on MFCC and SVM, refAbstract=null), Reference(id=1205172824420884897, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205158522716664025, doi=null, pmid=null, pmcid=null, year=2004, volume=23, issue=4, pageStart=51, pageEnd=53, url=null, language=null, rfNumber=[12], rfOrder=16, authorNames=蒋伟康, 严莉, journalName=振动与冲击, refType=null, unstructuredReference=蒋伟康, 严莉. 基于神经网络的电机噪声性能在线检测技术研究[J]. 振动与冲击, 2004, 23(4):51-53,57., articleTitle=基于神经网络的电机噪声性能在线检测技术研究, refAbstract=null), Reference(id=1205172824487993765, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205158522716664025, doi=null, pmid=null, pmcid=null, year=2004, volume=23, issue=4, pageStart=51, pageEnd=53, url=null, language=null, rfNumber=[12], rfOrder=17, authorNames=JIANG Weikang, YAN Li, journalName=Journal of Vibration and Shock, refType=null, unstructuredReference=JIANG Weikang, YAN Li. Research on online detection technology for motor noise performance based on neural networks[J]. Journal of Vibration and Shock, 2004, 23(4):51-53,57., articleTitle=Research on online detection technology for motor noise performance based on neural networks, refAbstract=null), Reference(id=1205172824563491241, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205158522716664025, doi=null, pmid=null, pmcid=null, year=2020, volume=48, issue=23, pageStart=190, pageEnd=195, url=null, language=null, rfNumber=[13], rfOrder=18, authorNames=蔡文伟, 黄键, 李伟光, journalName=机床与液压, refType=null, unstructuredReference=蔡文伟, 黄键, 李伟光, 等. 基于声音信号的微型电机故障诊断方法研究[J]. 机床与液压, 2020, 48(23):190-195., articleTitle=基于声音信号的微型电机故障诊断方法研究, refAbstract=null), Reference(id=1205172824651571629, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205158522716664025, doi=null, pmid=null, pmcid=null, year=2020, volume=48, issue=23, pageStart=190, pageEnd=195, url=null, language=null, rfNumber=[13], rfOrder=19, authorNames=CAI Wenwei, HUANG Jian, LI Weiguang, journalName=Machine Tools and Hydraulics, refType=null, unstructuredReference=CAI Wenwei, HUANG Jian, LI Weiguang, et al Research on fault diagnosis method for micro motors based on sound signals[J]. Machine Tools and Hydraulics, 2020, 48(23):190-195., articleTitle=et al Research on fault diagnosis method for micro motors based on sound signals, refAbstract=null), Reference(id=1205172824714486192, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205158522716664025, doi=null, pmid=null, pmcid=null, year=2024, volume=61, issue=4, pageStart=161, pageEnd=168, url=null, language=null, rfNumber=[14], rfOrder=20, authorNames=张雅晖, 杨凯, 杨帆, journalName=电测与仪表, refType=null, unstructuredReference=张雅晖, 杨凯, 杨帆. 基于小波包能量分析和信号融合的异步电机转子故障诊断[J]. 电测与仪表, 2024, 61(4):161-168., articleTitle=基于小波包能量分析和信号融合的异步电机转子故障诊断, refAbstract=null), Reference(id=1205172824794177971, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205158522716664025, doi=null, pmid=null, pmcid=null, year=2024, volume=61, issue=4, pageStart=161, pageEnd=168, url=null, language=null, rfNumber=[14], rfOrder=21, authorNames=ZHANG Yahui, YANG Kai, YANG Fan, journalName=Electrical Measurement and Instrumentation, refType=null, unstructuredReference=ZHANG Yahui, YANG Kai, YANG Fan. Asynchronous motor rotor fault diagnosis based on wavelet packet power analysis and signal fusion[J]. Electrical Measurement and Instrumentation, 2024, 61(4):161-168., articleTitle=Asynchronous motor rotor fault diagnosis based on wavelet packet power analysis and signal fusion, refAbstract=null), Reference(id=1205172824869675446, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205158522716664025, doi=null, pmid=null, pmcid=null, year=2019, volume=36, issue=6, pageStart=915, pageEnd=922, url=null, language=null, rfNumber=[15], rfOrder=22, authorNames=徐可, 陈宗海, 张陈斌, journalName=控制理论与应用, refType=null, unstructuredReference=徐可, 陈宗海, 张陈斌, 等. 基于经验模态分解和支持向量机的滚动轴承故障诊断[J]. 控制理论与应用, 2019, 36(6):915-922., articleTitle=基于经验模态分解和支持向量机的滚动轴承故障诊断, refAbstract=null), Reference(id=1205172824949367225, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205158522716664025, doi=null, pmid=null, pmcid=null, year=2019, volume=36, issue=6, pageStart=915, pageEnd=922, url=null, language=null, rfNumber=[15], rfOrder=23, authorNames=XU Ke, CHEN Zonghai, ZHANG Chenbin, journalName=Control Theory and Applications, refType=null, unstructuredReference=XU Ke, CHEN Zonghai, ZHANG Chenbin, et al. Rolling bearing fault diagnosis based on empirical mode decomposition and support vector machine[J]. Control Theory and Applications, 2019, 36(6):915-922., articleTitle=Rolling bearing fault diagnosis based on empirical mode decomposition and support vector machine, refAbstract=null), Reference(id=1205172825075196349, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205158522716664025, doi=null, pmid=null, pmcid=null, year=2016, volume=32, issue=17, pageStart=69, pageEnd=76, url=null, language=null, rfNumber=[16], rfOrder=24, authorNames=林福, 左曙光, 吴旭东, journalName=农业工程学报, refType=null, unstructuredReference=林福, 左曙光, 吴旭东, 等. 基于阶次分析的永磁同步电机噪声源识别[J]. 农业工程学报, 2016, 32(17):69-76., articleTitle=基于阶次分析的永磁同步电机噪声源识别, refAbstract=null), Reference(id=1205172825196831170, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205158522716664025, doi=null, pmid=null, pmcid=null, year=2016, volume=32, issue=17, pageStart=69, pageEnd=76, url=null, language=null, rfNumber=[16], rfOrder=25, authorNames=LIN Fu, ZUO Shuguang, WU Xudong, journalName=Transactions of the Chinese Society of Agricultural Engineering, refType=null, unstructuredReference=LIN Fu, ZUO Shuguang, WU Xudong, et al. Noise source recongnition of permanent magnet synchronous motor based on order analysis[J]. Transactions of the Chinese Society of Agricultural Engineering, 2016, 32(17):69-76., articleTitle=Noise source recongnition of permanent magnet synchronous motor based on order analysis, refAbstract=null), Reference(id=1205172825289105862, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205158522716664025, doi=null, pmid=null, pmcid=null, year=2023, volume=36, issue=1, pageStart=53, pageEnd=55, url=null, language=null, rfNumber=[17], rfOrder=26, authorNames=张能文, 姜天尚, 杨凯铭, journalName=工业控制计算机, refType=null, unstructuredReference=张能文, 姜天尚, 杨凯铭, 等. 基于EMD-Hilbert和主成分降维的电机故障信号特征提取[J]. 工业控制计算机, 2023, 36(1):53-55., articleTitle=基于EMD-Hilbert和主成分降维的电机故障信号特征提取, refAbstract=null), Reference(id=1205172825364603338, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205158522716664025, doi=null, pmid=null, pmcid=null, year=2023, volume=36, issue=1, pageStart=53, pageEnd=55, url=null, language=null, rfNumber=[17], rfOrder=27, authorNames=ZHANG Nengwen, JIANG Tianshang, YANG Kaiming, journalName=Industrial Control Computer, refType=null, unstructuredReference=ZHANG Nengwen, JIANG Tianshang, YANG Kaiming, et al. Feature extraction of motor fault signals based on EMD Hilbert and principal component dimensionality reduction[J]. Industrial Control Computer, 2023, 36(1):53-55., articleTitle=Feature extraction of motor fault signals based on EMD Hilbert and principal component dimensionality reduction, refAbstract=null), Reference(id=1205172825435906508, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205158522716664025, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[18], rfOrder=28, authorNames=陆怡, journalName=混合动力汽车车内声品质评价预测与控制研究, refType=null, unstructuredReference=陆怡. 混合动力汽车车内声品质评价预测与控制研究[D]. 镇江: 江苏大学, 2020., articleTitle=null, refAbstract=null), Reference(id=1205172825503015374, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205158522716664025, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[18], rfOrder=29, authorNames=LU Yi, journalName=Research on evaluation,prediction and control of interior sound quality in hybrid electric vehicles, refType=null, unstructuredReference=LU Yi. Research on evaluation,prediction and control of interior sound quality in hybrid electric vehicles[D]. Zhenjiang: Jiangsu University, 2020., articleTitle=null, refAbstract=null), Reference(id=1205172826690003409, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205158522716664025, doi=null, pmid=null, pmcid=null, year=2022, volume=42, issue=3, pageStart=474, pageEnd=482, url=null, language=null, rfNumber=[19], rfOrder=30, authorNames=胡少梁, 李宏坤, 王朝阁, journalName=振动、测试与诊断, refType=null, unstructuredReference=胡少梁, 李宏坤, 王朝阁, 等. 基于MEWT-ASCS的行星齿轮箱微弱故障特征提取[J]. 振动、测试与诊断, 2022, 42(3):474-482., articleTitle=基于MEWT-ASCS的行星齿轮箱微弱故障特征提取, refAbstract=null), Reference(id=1205172826773889492, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205158522716664025, doi=null, pmid=null, pmcid=null, year=2022, volume=42, issue=3, pageStart=474, pageEnd=482, url=null, language=null, rfNumber=[19], rfOrder=31, authorNames=HU Shaoliang, LI Hongkun, WANG Chaoge, journalName=Journal of Vibration,Measurement & Diagnosis, refType=null, unstructuredReference=HU Shaoliang, LI Hongkun, WANG Chaoge, et al. Weak fault diagnosis method of planetary gearbox based on modified empirical wavelet transform and adaptive sparse coding shrink algorithm[J]. Journal of Vibration,Measurement & Diagnosis, 2022, 42(3):474-482., articleTitle=Weak fault diagnosis method of planetary gearbox based on modified empirical wavelet transform and adaptive sparse coding shrink algorithm, refAbstract=null), Reference(id=1205172826840998358, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205158522716664025, doi=null, pmid=null, pmcid=null, year=2007, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[20], rfOrder=32, authorNames=彭璐, journalName=支持向量机分类算法研究与应用, refType=null, unstructuredReference=彭璐. 支持向量机分类算法研究与应用[D]. 长沙: 湖南大学, 2007., articleTitle=null, refAbstract=null), Reference(id=1205172826929078746, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205158522716664025, doi=null, pmid=null, pmcid=null, year=2007, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[20], rfOrder=33, authorNames=PENG Lu, journalName=Research and application of support vector machine classification algorithms, refType=null, unstructuredReference=PENG Lu. Research and application of support vector machine classification algorithms[D]. Changsha: Hunan University, 2007., articleTitle=null, refAbstract=null), Reference(id=1205172827021353436, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205158522716664025, doi=null, pmid=null, pmcid=null, year=2014, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[21], rfOrder=34, authorNames=徐晓明, journalName=SVM参数寻优及其在分类中的应用, refType=null, unstructuredReference=徐晓明. SVM参数寻优及其在分类中的应用[D]. 大连: 大连海事大学, 2014., articleTitle=null, refAbstract=null), Reference(id=1205172827142988255, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205158522716664025, doi=null, pmid=null, pmcid=null, year=2014, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[21], rfOrder=35, authorNames=XU Xiaoming, journalName=SVM parameter optimization and its application in classification, refType=null, unstructuredReference=XU Xiaoming. SVM parameter optimization and its application in classification[D]. Dalian: Dalian Maritime University, 2014., articleTitle=null, refAbstract=null), Reference(id=1205172827239457246, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205158522716664025, doi=null, pmid=null, pmcid=null, year=2017, volume=25, issue=3, pageStart=48, pageEnd=50, url=null, language=null, rfNumber=[22], rfOrder=36, authorNames=孙瑶琴, journalName=计算机测量与控制, refType=null, unstructuredReference=孙瑶琴. 改进粒子群算法优化支持向量机在故障诊断中的应用研究[J]. 计算机测量与控制, 2017, 25(3):48-50,54., articleTitle=改进粒子群算法优化支持向量机在故障诊断中的应用研究, refAbstract=null), Reference(id=1205172827331731936, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205158522716664025, doi=null, pmid=null, pmcid=null, year=2017, volume=25, issue=3, pageStart=48, pageEnd=50, url=null, language=null, rfNumber=[22], rfOrder=37, authorNames=SUN Yaoqin, journalName=Computer Measurement & Control, refType=null, unstructuredReference=SUN Yaoqin. Application of improved particle swarm optimization support vector machine in fault diagnosis[J]. Computer Measurement & Control, 2017, 25(3):48-50,54., articleTitle=Application of improved particle swarm optimization support vector machine in fault diagnosis, refAbstract=null), Reference(id=1205172827428200930, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205158522716664025, doi=null, pmid=null, pmcid=null, year=2011, volume=32, issue=11, pageStart=276, pageEnd=278, url=null, language=null, rfNumber=[23], rfOrder=38, authorNames=蔡振宇, 史乔波, journalName=煤矿机械, refType=null, unstructuredReference=蔡振宇, 史乔波. 基于PSO-SVM模型的旋转机械故障诊断研究[J]. 煤矿机械, 2011, 32(11):276-278., articleTitle=基于PSO-SVM模型的旋转机械故障诊断研究, refAbstract=null), Reference(id=1205172827486921187, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205158522716664025, doi=null, pmid=null, pmcid=null, year=2011, volume=32, issue=11, pageStart=276, pageEnd=278, url=null, language=null, rfNumber=[23], rfOrder=39, authorNames=CAI Zhenyu, SHI Qiaobo, journalName=Coal Mining Machinery, refType=null, unstructuredReference=CAI Zhenyu, SHI Qiaobo. Fault diagnosis of rotating machinery based on PSO-SVM model[J]. Coal Mining Machinery, 2011, 32(11):276-278., articleTitle=Fault diagnosis of rotating machinery based on PSO-SVM model, refAbstract=null)], funds=[Fund(id=1205172822801883488, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205158522716664025, awardId=2022CFB405, language=CN, fundingSource=湖北省自然科学基金(2022CFB405), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1205172815491211352, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205158522716664025, xref=null, ext=[AuthorCompanyExt(id=1205172815495405657, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205158522716664025, companyId=1205172815491211352, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=College of Naval Architecture and Ocean,Naval University of Engineering,Wuhan 430033,Hubei,China), AuthorCompanyExt(id=1205172815503794267, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205158522716664025, companyId=1205172815491211352, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=海军工程大学 舰船与海洋学院,湖北 武汉 430033)])], figs=[ArticleFig(id=1205172819060564207, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205158522716664025, language=EN, label=Fig.1, caption=Schematic diagram of micro motor, figureFileSmall=PO7KjiL/eU7bNajt/GGdiw==, figureFileBig=9N0vtUGza0JK70Spbw1HDA==, tableContent=null), ArticleFig(id=1205172819173810425, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205158522716664025, language=CN, label=图1, caption=微型电机示意简图, figureFileSmall=PO7KjiL/eU7bNajt/GGdiw==, figureFileBig=9N0vtUGza0JK70Spbw1HDA==, tableContent=null), ArticleFig(id=1205172819287056638, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205158522716664025, language=EN, label=Fig.2, caption=Speed of micro motor during forward and reverse transients, figureFileSmall=Jc4n9sjb16fXLRsgXsAjUg==, figureFileBig=lHFGD1+/ZybzxLi0JGepow==, tableContent=null), ArticleFig(id=1205172819366748417, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205158522716664025, language=CN, label=图2, caption=微型电机正、反转瞬时转速, figureFileSmall=Jc4n9sjb16fXLRsgXsAjUg==, figureFileBig=lHFGD1+/ZybzxLi0JGepow==, tableContent=null), ArticleFig(id=1205172819467411719, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205158522716664025, language=EN, label=Fig.3, caption=Vibration order spectrum of micro motor, figureFileSmall=7vyxZknDSz+PjxPCND4DPQ==, figureFileBig=OXDliGoVZyfmDydN4FmeXA==, tableContent=null), ArticleFig(id=1205172819563880715, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205158522716664025, language=CN, label=图3, caption=微型电机振动阶次谱, figureFileSmall=7vyxZknDSz+PjxPCND4DPQ==, figureFileBig=OXDliGoVZyfmDydN4FmeXA==, tableContent=null), ArticleFig(id=1205172819660349711, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205158522716664025, language=EN, label=Fig.4, caption=Instantaneous speed envelope spectrum of micro motors, figureFileSmall=VEGt8wIGjUnQeuj+7BypVA==, figureFileBig=ERs0G2awGFKiHM8joPBnmQ==, tableContent=null), ArticleFig(id=1205172819777790228, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205158522716664025, language=CN, label=图4, caption=微型电机瞬时转速包络谱, figureFileSmall=VEGt8wIGjUnQeuj+7BypVA==, figureFileBig=ERs0G2awGFKiHM8joPBnmQ==, tableContent=null), ArticleFig(id=1205172819853287705, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205158522716664025, language=EN, label=Fig.5, caption=Acceleration envelope spectrum of micro motor vibration, figureFileSmall=NgPV+IXoJrW3w5/wtGre0w==, figureFileBig=rhfhM6nQj3SZKrAwya2t2w==, tableContent=null), ArticleFig(id=1205172819979116834, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205158522716664025, language=CN, label=图5, caption=微型电机振动加速度包络谱, figureFileSmall=NgPV+IXoJrW3w5/wtGre0w==, figureFileBig=rhfhM6nQj3SZKrAwya2t2w==, tableContent=null), ArticleFig(id=1205172820117528870, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205158522716664025, language=EN, label=Fig.6, caption=Roughness time history of micro motors, figureFileSmall=j1gEE3PJB9RmrxRyLKDbjg==, figureFileBig=0+6cD75zGtEq7v3SRmyJ8A==, tableContent=null), ArticleFig(id=1205172820193026347, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205158522716664025, language=CN, label=图6, caption=微型电机粗糙度时间历程, figureFileSmall=j1gEE3PJB9RmrxRyLKDbjg==, figureFileBig=0+6cD75zGtEq7v3SRmyJ8A==, tableContent=null), ArticleFig(id=1205172820281106735, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205158522716664025, language=EN, label=Fig.7, caption=Comparison of damage waveforms of micro motor gears, figureFileSmall=MifR82z3nnJKBuHSCtdoUQ==, figureFileBig=B+2QHo+y9ZGtzgzxlZGo/Q==, tableContent=null), ArticleFig(id=1205172820381770035, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205158522716664025, language=CN, label=图7, caption=微型电机齿轮损伤波形对比, figureFileSmall=MifR82z3nnJKBuHSCtdoUQ==, figureFileBig=B+2QHo+y9ZGtzgzxlZGo/Q==, tableContent=null), ArticleFig(id=1205172820536959291, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205158522716664025, language=EN, label=Fig.8, caption=Abnormal vibration and noise characteristics engineering of micro motors, figureFileSmall=3NMVczaHcTDRdLGjN5HZdA==, figureFileBig=kA4alr4KdY+5LeLeHRPvVQ==, tableContent=null), ArticleFig(id=1205172820687954242, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205158522716664025, language=CN, label=图8, caption=微型电机异常振动噪声特征工程, figureFileSmall=3NMVczaHcTDRdLGjN5HZdA==, figureFileBig=kA4alr4KdY+5LeLeHRPvVQ==, tableContent=null), ArticleFig(id=1205172820847337799, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205158522716664025, language=EN, label=Fig.9, caption=Training process of small sample machine learning model based on PSO-SVM, figureFileSmall=Jit70nSbmmKddHtpI6EM1w==, figureFileBig=3ks7XShlA9zlVepFwXY0Wg==, tableContent=null), ArticleFig(id=1205172820935418187, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205158522716664025, language=CN, label=图9, caption=基于PSO-SVM 的小样本机器学习模型训练流程, figureFileSmall=Jit70nSbmmKddHtpI6EM1w==, figureFileBig=3ks7XShlA9zlVepFwXY0Wg==, tableContent=null), ArticleFig(id=1205172821023498574, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205158522716664025, language=EN, label=Fig.10, caption=Micro motor vibration test bench, figureFileSmall=6wWkp71V3kYfPnfFQmnauw==, figureFileBig=G8BMf1kURfmooBIT03EUJQ==, tableContent=null), ArticleFig(id=1205172822189515089, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205158522716664025, language=CN, label=图10, caption=微型电机振动测试台, figureFileSmall=6wWkp71V3kYfPnfFQmnauw==, figureFileBig=G8BMf1kURfmooBIT03EUJQ==, tableContent=null), ArticleFig(id=1205172822277595477, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205158522716664025, language=EN, label=Tab.1, caption=

Sample statistics of microprocessor motor acoustic data

, figureFileSmall=null, figureFileBig=null, tableContent=
故障类型 样本数量/个 标签
正常情况 600 0
振动偏大 40 1
电机异音 40 2
蜗杆异音 80 3
齿轮损伤 30 4
合计 790
), ArticleFig(id=1205172822361481558, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205158522716664025, language=CN, label=表1, caption=

微机电机声学数据样本统计

, figureFileSmall=null, figureFileBig=null, tableContent=
故障类型 样本数量/个 标签
正常情况 600 0
振动偏大 40 1
电机异音 40 2
蜗杆异音 80 3
齿轮损伤 30 4
合计 790
), ArticleFig(id=1205172822466339162, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205158522716664025, language=EN, label=Tab.2, caption=

Comparison of SVM method accuracy

, figureFileSmall=null, figureFileBig=null, tableContent=
故障类型 检测模型
SVM(σ =0.5,C=2)
检测模型
SVM(σ =0.5,C=4)
检测模型
PSO-SVM(σ =0.7,C=4.8)
正确数/总数 准确率/% 正确数/总数 准确率/% 正确数/总数 准确率/%
正常 165/180 91.7 169/180 93.9 173/180 96.1
振动偏大 10/12 83.3 10/12 83.3 11/12 91.7
电机异音 9/12 75.0 10/12 83.3 11/12 91.7
蜗杆异音 19/24 79.2 21/24 87.5 22/24 91.7
齿轮损伤 8/9 88.9 8/9 88.9 9/9 100
总计 211/237 89.0 218/237 92.0 226/237 95.4
), ArticleFig(id=1205172822567002460, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205158522716664025, language=CN, label=表2, caption=

SVM方法准确率对比

, figureFileSmall=null, figureFileBig=null, tableContent=
故障类型 检测模型
SVM(σ =0.5,C=2)
检测模型
SVM(σ =0.5,C=4)
检测模型
PSO-SVM(σ =0.7,C=4.8)
正确数/总数 准确率/% 正确数/总数 准确率/% 正确数/总数 准确率/%
正常 165/180 91.7 169/180 93.9 173/180 96.1
振动偏大 10/12 83.3 10/12 83.3 11/12 91.7
电机异音 9/12 75.0 10/12 83.3 11/12 91.7
蜗杆异音 19/24 79.2 21/24 87.5 22/24 91.7
齿轮损伤 8/9 88.9 8/9 88.9 9/9 100
总计 211/237 89.0 218/237 92.0 226/237 95.4
)], attaches=null, journal=Journal(id=1149695973913305096, delFlag=0, nameCn=电气传动, nameEn=Electric Drive, nameHistory1=null, nameHistory2=null, issn=1001-2095, eissn=null, cn=12-1067/TP, 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=MX9kQyxauhRIcWSHz1lsfg==, journalPrice=null, startedYear=null, abbrevIsoEn=null, journalRemark=null, publicationField=null, createdTime=1752038480501, updatedTime=1761735785885, createdBy=18614031015, updatedBy=13701087609, firstLetterCn=E, firstLetterEn=E, subjectCode=Engineering, subjectName=Engineering, subjectCodeEn=Engineering, subjectNameEn=null, picCn=MX9kQyxauhRIcWSHz1lsfg==, picEn=R8RQJTk995s1dk9HSLANAQ==, jcr=null, cjcr=null, exts=[JournalExt(id=1190369420775096487, language=CN, name=电气传动, 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=1761735785907, updatedTime=1761735785907, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=https://tg.au365.cn/Login/index.html, submissionEditorUrl=https://tg.au365.cn/Login/index/cate/3.html, submissionReviewUrl=https://tg.au365.cn/Login/index/cate/2.html, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1190369420829622440, language=EN, name=Electric Drive, 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=1761735785920, updatedTime=1761735785920, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=https://tg.au365.cn/Login/index.html, submissionEditorUrl=https://tg.au365.cn/Login/index/cate/3.html, submissionReviewUrl=https://tg.au365.cn/Login/index/cate/2.html, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1189987059142926344, websiteList=[Website(id=1189988338468713189, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1189987059142926344, 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/dqcd/CN, language=CN, createTime=1761644928805, createBy=18614031015, updateTime=1761644944247, updateBy=18614031015, name=电气传动-中文, tplId=1146099689490845704, title=电气传动, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1190236467705254391, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189988338468713189, code=articleTextType, value=kx, createTime=1761704087425, updateTime=1761704087425, creator=18614031015, updator=18614031015), WebsiteProps(id=1190236467671699956, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189988338468713189, code=banner, value=null, createTime=1761704087417, updateTime=1761704087417, creator=18614031015, updator=18614031015), WebsiteProps(id=1190236467763974650, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189988338468713189, code=grayFlag, value=0, createTime=1761704087439, updateTime=1761704087439, creator=18614031015, updator=18614031015), WebsiteProps(id=1190236467663311347, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189988338468713189, code=logo, value=https://castjournals.cast.org.cn/joweb/dqcd/CN/file/pic?fileId=C+51VGe7It8gHMdS0MAlXg==, createTime=1761704087415, updateTime=1761704087415, creator=18614031015, updator=18614031015), WebsiteProps(id=1190236467784946172, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189988338468713189, code=minRunFlag, value=0, createTime=1761704087444, updateTime=1761704087444, creator=18614031015, updator=18614031015), WebsiteProps(id=1190236467692671478, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189988338468713189, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/dqcd/CN/file/pic, createTime=1761704087422, updateTime=1761704087422, creator=18614031015, updator=18614031015), WebsiteProps(id=1190236467776557563, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189988338468713189, code=silenceFlag, value=0, createTime=1761704087442, updateTime=1761704087442, creator=18614031015, updator=18614031015), WebsiteProps(id=1190236467680088565, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189988338468713189, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1761704087419, updateTime=1761704087419, creator=18614031015, updator=18614031015), WebsiteProps(id=1190236467713643000, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189988338468713189, code=themeColor, value=null, createTime=1761704087427, updateTime=1761704087427, creator=18614031015, updator=18614031015), WebsiteProps(id=1190236467726225913, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189988338468713189, code=themeStyle, value=null, createTime=1761704087430, updateTime=1761704087430, creator=18614031015, updator=18614031015)]), Website(id=1189988338527433447, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1189987059142926344, 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/dqcd/EN, language=EN, createTime=1761644928819, createBy=18614031015, updateTime=1761644963810, updateBy=18614031015, name=电气传动-英文, tplId=1146101810881728533, title=Electric Drive, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1190236496637563393, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189988338527433447, code=articleTextType, value=kx, createTime=1761704094323, updateTime=1761704094323, creator=18614031015, updator=18614031015), WebsiteProps(id=1190236496612397566, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189988338527433447, code=banner, value=null, createTime=1761704094317, updateTime=1761704094317, creator=18614031015, updator=18614031015), WebsiteProps(id=1190236496666923524, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189988338527433447, code=grayFlag, value=0, createTime=1761704094330, updateTime=1761704094330, creator=18614031015, updator=18614031015), WebsiteProps(id=1190236496604008957, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189988338527433447, code=logo, value=https://castjournals.cast.org.cn/joweb/dqcd/EN/file/pic?fileId=C+51VGe7It8gHMdS0MAlXg==, createTime=1761704094315, updateTime=1761704094315, creator=18614031015, updator=18614031015), WebsiteProps(id=1190236496683700742, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189988338527433447, code=minRunFlag, value=0, createTime=1761704094334, updateTime=1761704094334, creator=18614031015, updator=18614031015), WebsiteProps(id=1190236496629174784, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189988338527433447, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/dqcd/EN/file/pic, createTime=1761704094321, updateTime=1761704094321, creator=18614031015, updator=18614031015), WebsiteProps(id=1190236496675312133, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189988338527433447, code=silenceFlag, value=0, createTime=1761704094332, updateTime=1761704094332, creator=18614031015, updator=18614031015), WebsiteProps(id=1190236496620786175, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189988338527433447, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_en_623/, createTime=1761704094319, updateTime=1761704094319, creator=18614031015, updator=18614031015), WebsiteProps(id=1190236496650146306, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189988338527433447, code=themeColor, value=null, createTime=1761704094326, updateTime=1761704094326, creator=18614031015, updator=18614031015), WebsiteProps(id=1190236496658534915, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189988338527433447, code=themeStyle, value=null, createTime=1761704094328, updateTime=1761704094328, creator=18614031015, updator=18614031015)])], journalTitle=电气传动, weixinUrl=null, journalUrl=https://www.au365.cn/, iacademicId=null, status=1, seqNo=null, journalTitleEn=Electric Drive, journalPhotoCn=MX9kQyxauhRIcWSHz1lsfg==, journalPhotoEn=R8RQJTk995s1dk9HSLANAQ==, journalFirstLetter=E, 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/dqcd/CN/10.19457/j.1001-2095.dqcd25144, detailUrlEn=https://castjournals.cast.org.cn/joweb/dqcd/EN/10.19457/j.1001-2095.dqcd25144, pdfUrlCn=https://castjournals.cast.org.cn/joweb/dqcd/CN/PDF/10.19457/j.1001-2095.dqcd25144, pdfUrlEn=https://castjournals.cast.org.cn/joweb/dqcd/EN/PDF/10.19457/j.1001-2095.dqcd25144, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
微型电机声学质量检测小样本机器学习方法研究
收藏切换
PDF下载
田芝丹 , 俞翔 , 万海波
电气传动 | 可靠性与诊断 2024,54(8): 90-96
收起
收藏切换
电气传动 | 可靠性与诊断 2024, 54(8): 90-96
微型电机声学质量检测小样本机器学习方法研究
全屏
田芝丹 , 俞翔 , 万海波
作者信息
  • 海军工程大学 舰船与海洋学院,湖北 武汉 430033
  • 田芝丹(1998—),女,硕士研究生,主要研究方向为振动与噪声控制、故障诊断,Email:

通讯作者:

俞翔(1978—),男,博士,教授,硕士生导师,主要研究方向为振动与噪声控制,Email:
Research on Small Sample Machine Learning Method for Acoustic Quality Detection of Micro Motors
Zhidan TIAN , Xiang YU , Haibo WAN
Affiliations
  • College of Naval Architecture and Ocean,Naval University of Engineering,Wuhan 430033,Hubei,China
出版时间: 2024-08-20 doi: 10.19457/j.1001-2095.dqcd25144
文章导航
收藏切换

为了解决微型电机声学质量检测人工手摸及听诊方法存在的主观误判率高、效率低下等问题,同时兼顾检测结果准确率和检测模型构建的快速性,提出了一种小样本机器学习检测方法,其根据微型电机传动链物理模型进行多维声学故障特征提取,在此基础上,采用粒子群优化算法对支持向量机这种小样本学习方法的核心参数进行优化,从而提高模型判别的准确率。试验结果表明,该方法能够有效判别微型电机异常振动和声音,准确率达到95%以上。

微型电机  /  质量检测  /  物理模型  /  粒子群优化  /  支持向量机

In order to solve the problems of high subjective misjudgment rate and low efficiency in manual hand touch and auscultation methods for acoustic quality detection of micro motors,while taking into account the accuracy of detection results and the fast construction of detection models,a small sample machine learning detection method was proposed. Based on the physical model of micro motor transmission chain,multi-dimensional acoustic fault features were extracted,particle swarm optimization was used to optimize the core parameters of support vector machine,a small sample learning method,so as to improve the accuracy of model discrimination.The experimental results show that this method can effectively distinguish abnormal vibration and sound of micro motors,with an accuracy rate of over 95%.

micro motor  /  quality inspection  /  physical model  /  particle swarm optimization(PSO)  /  support vector machine(SVM)
田芝丹, 俞翔, 万海波. 微型电机声学质量检测小样本机器学习方法研究. 电气传动, 2024 , 54 (8) : 90 -96 . DOI: 10.19457/j.1001-2095.dqcd25144
Zhidan TIAN, Xiang YU, Haibo WAN. Research on Small Sample Machine Learning Method for Acoustic Quality Detection of Micro Motors[J]. Electric Drive, 2024 , 54 (8) : 90 -96 . DOI: 10.19457/j.1001-2095.dqcd25144
微型电机是一种广泛应用于汽车、白色家电、电动工具以及精密设备等行业的动力元件,其运行过程中不可避免地产生振动和噪声,一旦出现异常振动和声音,则表明微型电机出现了质量缺陷。目前企业均通过人工手摸及听诊的方法在生产线上对微型电机进行声学质量检测。但是上述检测方式主观误判率较高,且效率低下,不利于企业产品质量检测与把控。
基于大数据的图像识别技术已经成功构建了机器的“眼睛”[1-4],可以准确实现产品外观缺陷检测,为微型电机声学质量检测提供了思路。国内外不少学者也开展了类似的研究[5-8],Tadatsugu Kitamoto[9]通过获取微型电机声音信号,结合语音识别技术,分别选用K-means和Nearest Neighbor method方法对电机异音进行了分类识别;刘力源等[10]在采集电机声音信号基础上,分别在时域、频域及小波域提取了特征,进而通过SVM方法进行了电机异音识别;刘思思等[11]以车窗电机噪声为输入,以优化的梅尔频率倒谱系数为特征值,以SVM为噪声辨识模型,构建了电机异常噪声辨别方法;蒋伟康等[12]通过测量电机振动,从中提取加速度均方值、振动能量的波动度、分频段振动能量、频谱中50个最大峰值等特征指标用于电机振动特性检测,并建立了BP网络模型,用于异常识别;蔡文伟等[13]提出了基于声音信号的微型电机故障诊断方法,运用小波阈值降噪的方法对声音信号中的周期性冲击成分进行增强并滤除环境噪声,采用希尔伯特变换得到信号的包络线和包络谱并根据其峰值对应的频率进行判断,实现了对微型电机故障的诊断;张雅晖等[14]采用定子电流信号和振动信号的频谱特征融合作为转子断条以及气隙偏心故障的诊断依据,对信号进行小波包分解,获得能量分布并与正常电机信号进行比较,进而对能量异常的信号频段进行小波包节点重构,最后通过快速傅里叶变换识别故障特征频率,诊断电机转子故障是否发生;徐可等[15]提出了一种利用延拓对EMD的端点效应进行改进,然后基于改进的EMD和PSO-SVM设计了滚动轴承故障诊断的方法。尽管如此,围绕微型电机振动噪声异常识别,上述研究还存在以下工作需要完善:一是并未结合微型电机传动链信息和故障类型进行多维特征提取,不利于提高机器学习检测准确率;二是并未结合下线检测过程中不良品较少的小样本情况进行机器模型训练,不利于提高检测模型部署效率;三是上述研究中所用到的机器学习智能算法目前大多都应用在某一类传统的机械故障诊断方面,如齿轮故障、轴承故障等,未应用在整体的机械设备故障诊断中。
针对上述问题,结合微型电机声学质量检测实际需求,本文分析了微型电机的传动链和振动噪声异常故障类型,通过采集微型电机运行过程中振动信号,建立振动与异音深度关联的多维特征提取方法,在此基础上选用SVM这种小样本机器学习方法,并通过粒子群优化算法对其径向基函数和核函数进行优化,从而构建一种准确、合理且能够快速部署的微型电机整体声学质量检测小样本机器学习方法。
微型电机由电机本体和两级减速机构组成,具体如图1所示。其中电机本体为有刷直流电机,由定子和转子组成,定子的结构简单,主要包括定子壳、电刷、主磁极和机座等,定子用来引导主磁场的产生,同时给电机提供机械支撑;转子结构包括转子轴、硅钢片绕组、换向器和轴承等部件,其中电机绕组数量为10;在磁场旋转的过程中,转子将电能转化为机械能,然后对外输出转矩。
考虑到电机输出转速较高,为了满足工作场景要求,微型电机集成了两级减速机构,一级减速机构选用蜗轮蜗杆机构,蜗杆头数为1,传动比为62;二级减速机构选用行星齿轮机构,小齿轮齿数为10,大齿轮齿数为33。因此,整个两级减速机构的传动比为204.6。
由于不可预测的零部件加工误差及质量缺陷,微型电机在运行过程中不可避免地会产生异常振动和噪声,其故障类型主要包括:1)电机振动偏大。主要指微型电机长时间处于持续性的高振动状态;2)电机异音。指电机运行过程中声音起伏波动、音色差异、音调差异及正反转声音异常等,主要由于电机内部绕组、磁路及气隙不均匀、不稳定产生;3)蜗杆异音。主要由于蜗杆表面不平顺或毛刺,引起明显的振声粗糙感;4)齿轮损伤。主要由于二级减速齿轮存在个别齿损伤引起周期性敲击声。
微型电机存在异常振动噪声等声学缺陷,若同步采集振动噪声信号,则为了屏蔽外界噪声干扰,需要在生产线上增加静音箱,势必影响检测节拍。考虑到噪声本质上是通过本体振动产生,因此,可在微型电机表面仅测量三轴振动加速度信号,在特征提取过程中,可结合微型电机传动结构,建立异常振动与噪声的映射关系,从而构建覆盖微型电机声学质量检测的多维特征工程。
为了衡量振动偏大程度,不仅要从宏观上计算总的振动加速度级,还要从微观上计算电机电枢绕组频率、换向器频率以及换向器谐波频率下的幅值。考虑到电机转速的波动情况,需要利用振动加速度信号间接计算其瞬时转速信号,进而开展阶次分析[16],获取电机本体振动阶次谱特征,由于即将下线的微型电机大多数都是合格的,即转速波动不大较平稳,我们就用基本的可变时长离散傅里叶变换来实现阶次分析,时间块长度如下:
Δ T = 60 n O r
式中: Δ T为截取的时间块长度;n为转速; O r为阶次分辨率。
在转速与振动噪声关联的阶次分析中,振动噪声会随着转速变化,由式(1)可知转速越高,采样的时间越短,就能更好地获取转速变化特征,进而实现阶次分析。
图2为微型电机振动间接计算获得的瞬时转速信号,可发现其正、反转转速均存在一定波动及偏差。图3为微型电机振动阶次谱,可以发现电机本体在电枢频率、换向器频率及谐波处振动较为明显,可以作为特征值有效表征电机振动状态。
当电机内部绕组、磁路及气息不均匀、不稳定产生时,其实际转速可能在额定转速上下波动,由于旋转机械的固有特性,其振动频率同样会存在对应波动,当频率偏差大于2 Hz左右时,声音中的音调会有明显不同;同时其振动幅值同样会出现波动,进而出现声音忽大忽小的现象。上述现象分别对应电机异音中的音色差异和声音起伏波动,为了准确通过振动信号进行故障表征,可通过振动加速度信号间接获取瞬时转速信号,在此基础上分别计算瞬时转速信号和振动加速度信号的包络谱,通过对电机包络信号进行频谱分析,可以有效地提取电机在运转过程中产生的故障信息[17]。具体如图4图5所示,并对其进行低通滤波后计算有效值即可获取其特征值。
值得说明的是,为了衡量电机转速偏低带来的声音异常,需要计算其瞬时转速的平均值作为特征值。
对于电机正反转声音异常,可利用电枢频率、换向器基频及谐波阶次谱差值大小作为特征值进行衡量,通过数据统计分析表明,当上述特征频率处幅值差值大于6 dB时,人耳便可以明显感知异常。
由于蜗杆头数为1,因此当蜗杆滑道出现损伤时,一级蜗轮蜗杆减速机构每转1圈就会与蜗轮出现1次敲击声,所以蜗杆出现损伤时,这种敲击频率与电枢频率相同,换向器两侧边频带谐波增多,就会使声音比较粗糙。粗糙度是评价声音是否具有嘈杂、粗犷、冲击感等特性的心理声学客观参量,其主要受到调制频率和调制深度影响。当调制频率在20 Hz以下变化时,人耳可以主观感受到时域上声信号幅值的波动。但是当调制频率在20~300 Hz间变化时,人耳就很难再主观感受到声信号的波动,所以我们可以通过计算粗糙度参数来识别蜗杆损伤。使用Hilbert变换对电机噪音进行包络解调发现电机噪声的调制频率在70 Hz附近,采用Zwicker模型[18]对测试声音样本粗糙度R进行计算:
R = 0.011 f 0 f m o d f 0 2 + f m o d 2 0 B a r k Δ L E ( z ) d z
其中
Δ L E ( z ) = 20 l o g ( N ' m a x N ' m i n )
式中:fmod为调制频率;f0为调制基频,取值70 Hz; z为特征频率带; Δ L E ( z )为激励级的变化量; N m a x ' N m i n '分别为参考特征响度的极大值、极小值。
图6为微型电机粗糙度时间历程,通过对比可以发现该特征可有效表征蜗杆损伤故障。
与常见的齿轮故障不同,微型电机内部二级齿轮减速机构均注塑生产,可能存在个别齿形存在偏差,从而导致周期性脱啮[19],出现周期性“敲击信号”。根据传动链信息可知,一级减速机构蜗轮每转1圈,会出现1次敲击,敲击间隔是电机旋转周期的1/62。该敲击信号十分微弱,冲击信号会整个淹没在振动加速度信号里面,但是敲击会引起结构共振。通过寻找敲击作用下的共振频带,即可以获取敲击声音的载波信息,进而计其波峰因子即可。图7即为齿轮损伤情况下信号波形对比,可知在原始信号中并未出现明显冲击,但是通过共振解调后即可发现明显的周期性冲击,表明齿轮损伤故障特征提取的有效性。
综上,通过采集微型电机运行过程中振动信号,建立振动与异音深度关联的多维特征,合计共28维度,具体如图8所示,可有效涵盖电机振动偏大、电机异音、蜗杆异音以及齿轮损伤等故障类型。
支持向量机(support vector machine,SVM)是一种在统计学习理论基础上发展起来的小样本机器学习方法,其有着坚实的数学和理论基础,小样本情况下能够得到现有信息的最优解,且具有很强的学习和泛化能力,在解决小样本的学习问题中表现出了许多的独特优势[20]。同时,SVM通过引入一些具有特殊性质的核函数,将实际问题通过非线性变换转换到高维特征空间,在高维空间中构造线性决策函数来实现原有空间中的非线性决策函数,使得求解SVM的过程只和训练样本的数目有关,与样本维数无关,即算法复杂度与样本维数无关,从而巧妙而有效地解决了传统学习机器不好解决的高维问题[21]
假设可分的数据集 ( x i ,   y i ) ,   i = 1 ,   2 ,   ,   l ,   x i R d , y i [ - 1,1 ),假定yi为分类标签,d为输入向量的维数,求解该超平面问题可以转化为以下优化问题:
m i n ( 1 2 | | ω | | 2 + C i = 1 l ξ i )
y i [ ( ω * x i ) + b ] 1 - ξ i         i = 1,2 , , l
式中: ω为超平面法向量; b为常数项; ξ i为松弛因子;C为惩罚因子。
定义SVM的分类函数如下:
f ( x ) = s g n { i = 1 l α i y i K ( x i , x ) + b }
式中: α i为拉格朗日算子; K ( x i , x )为核函数,用于将输入数据转化到高维特征空间。
最常用的核函数径向基函数(radical basis function,RBF)为
K ( x i , x ) = e x p ( - | | x i - x | | 2 σ 2 )
为了取得较好的故障检测效果,如何选取最优的SVM模型参数至关重要。粒子群优化(particle swarm optimization,PSO)算法是一种基于种群的全局并行优化方法,具有收敛速度快且易于实现等优点。本文通过PSO算法对SVM的惩罚因子C及径向基函数半径 σ进行寻优。
PSO的思想来源于动物种群的集群行为[22]。假设在n维空间中搜索,由m个粒子组成一个种群,其中第i个粒子位置表示为 x k i = ( x 1 i , x 2 i , , x n i ),假定每一个粒子的位置都有可能是一个潜在解,将 x k i代入到目标函数fx)中可得到适应度 f k i,适应度用来衡量该解的优劣。假定第i个粒子飞行速度为 V k i = ( v 1 i , v 2 i , , v n i ),到第i个粒子时的最优解为 P k i = ( p 1 i , p 2 i , , p n i ),整个粒子群中搜索的最优解[23] P k g = ( p 1 g , p 2 g , , p n g )
在PSO算法进行优化的过程中,先初始化搜索位置 x i 0和速度 v i 0,计算出每个粒子的适应度,得到当前粒子群的最优解。然后按照速度更新粒子群,按照设定的迭代次数,不断更新最优解,对粒子速度和位置的更新迭代公式为
V k + 1 i = w k V k i + c 1 ϑ 1 ( P k i - x k i ) + c 2 ϑ 2 ( P k g - x k i )
x k + 1 i = x k i + V k + 1 i
式中: w k为惯性因子, w k>0; c 1 c 2为学习因子; ϑ 1 ϑ 2为随机数, ϑ 1 ϑ 2 [ 0,1 ] V k i为第k次迭代粒子的速度矢量; P k ik次迭代后粒子i的最优解; x k i为第k次迭代后粒子i的位置; P k gk次迭代后粒子群的最优解。
因此,本文采用基于PSO-SVM 的小样本机器学习模型训练,来实现微型电机声学质量机器学习检测,具体流程如图9所示。
为了对上述方法进行验证,设计了如图10所示的微型电机半自动振动测试台,从而对微型电机进行标准化振动测试,确保声学数据样本的一致性。测试过程中,选用三轴振动加速度通过磁力吸附安装在微型电机本体下表面,传感器灵敏度100 mV/g,采样频率40 kHz,信号采集过程中电机正转3 s,反转3 s。本文考虑了4种典型的微型电机声学质量缺陷,如表1所列,包含正常情况、振动偏大、电机异音、蜗杆损伤以及齿轮损伤等,累计样本为790个。根据前述特征提取方法,每个微型电机声学样本可以构建为1×28维特征向量。
将每种故障类型微型电机声学数据样本按照训练样本与测试样本7∶3比例进行试验分析。在利用PSO优化SVM模型时,优化选择RBF核函数半径 σ及惩罚因子C。选取种群粒子数为56,最大迭代次数300,惯性权值 w k=1,学习因子 c 1= c 2=2,将适应度函数定义为SVM分类的准确率。为了证明PSO-SVM方法的优越性,通过设定不同RBF核函数半径 σ及惩罚因子C计算SVM方法准确率进行对比分析,具体如表2所示。
通过对比发现,经过粒子群优化算法对核函数半径 σ及惩罚因子C进行优化处理后,PSO-SVM模型的检测准确率较常规SVM明显增加,基本上能够满足微型电机声学质量检测要求。考虑到目前测试样本较少,若进一步补充微型电机声学样本,其准确率可进一步提升。
针对微型电机声学质量检测人工手摸及听诊方法存在的主观误判率高、效率低下等问题,开展了微型电机声学质量检测小样本机器学习方法理论研究与试验验证,主要技术创新如下:
1)通过微型电机振动加速度测量,结合其传动链及故障模型,建立了振动与异音深度关联的多维特征提取方法,可有效涵盖电机振动偏大、电机异音、蜗杆异音以及齿轮损伤等故障类型。
2)采用了PSO-SVM机器学习模型训练方法,通过粒子群算法对SVM参数进行优化选取,确保在小规模微特电机振动样本情况下能够准确、合理地完成机器学习模型训练,且能够快速部署应用。
下一步打算用其他更新颖、快速准确的算法及更多的样本以识别故障电机,从而降低微型电机生产成本并提高生产效率。
  • 湖北省自然科学基金(2022CFB405)
参考文献 引证文献
排序方式:
[1]
宋昱晓, 王雨璐, 于宏博, 等. 一种图像识别车辆定位系统摄像头的设计[J]. 黑龙江科学, 2023, 14(4):154-155,158.
SONG Yuxiao, WANG Yuliu, YU Hongbo, et al. Design of a camera for image recognition vehicle positioning system[J]. Heilongjiang Science, 2023, 14(4):154-155,158.
[2]
纪永. 基于机器视觉的加热炉内异常情况图像识别方法研究[J]. 工业加热, 2023, 52(3):80-84.
JI Yong. Study on image recognition of abnormal in heating furnace based on machine vision[J]. Industrial Heating, 2023, 52(3):80-84.
[3]
范传刚, 李玉豪, 王峥阳, 等. 基于图像识别技术的工业建筑火灾风险远程评估方法及应用研究[J]. 土木工程学报, 2024(2):87-95.
FAN Chuangang, LI Yuhao, WANG Zhengyang, et al. Study on remote fire risk assessment method for industrial buildings based on image recognition technology[J]. China Civil Engineering Journal, 2024(2):87-95.
[4]
LI P, ZHAO W. Image fire detection algorithms based on convolutional neural networks[J]. Case Studies in Thermal Engineering, 2020, 19:100625.
[5]
BRACKLEY M, POLLOCK C. Analysis and reduction of acoustic noise from a brushless DC drive[J]. IEEE Transactions on Industry Applications, 1999.
[6]
FINLEY W R, HODOWANEC M M, HOLTER W G. An analyti-cal approach to solving motor vibration problems[J]. IEEE Transactions on Industry Applications, 2000, 36(5):1467-1480.
[7]
GLOWACZ A, GLOWACZ W. Vibration-based fault diagnosis of commutator motor[J]. Shock and Vibration, 2018(10):7460419.
[8]
JUNIOR R F R, AREIAS I, GOMES G F. Fault detection and diagnosis using vibration signal analysis in frequency domain for electric motors considering different real fault types[J]. Sensor Review, 2021, 41(3):311-319.
[9]
KITAMOTO T. A method for quality inspection of motors by detecting abnormal sound[J]. International Journal of Mechanical and Mechatronics Engineering, 2007, 1(11):632-635.
[10]
刘力源. 基于机器学习方法的电机异音检测研究[D]. 广州: 五邑大学, 2014.
LIU Liyuan. Research on motor abnormal sound detection based on machine learning methods[D]. Guangzhou: Wuyi University, 2014.
[11]
刘思思, 谭建平, 易子馗. 基于MFCC和SVM的车窗电机异常噪声辨识方法研究[J]. 振动与冲击, 2017, 36(5):102-107.
LIU Sisi, TAN Jianping, YI Zikui. A window motor abnormal noise identification method based on MFCC and SVM[J]. Journal of Vibration and Shock, 2017, 36(5):102-107.
[12]
蒋伟康, 严莉. 基于神经网络的电机噪声性能在线检测技术研究[J]. 振动与冲击, 2004, 23(4):51-53,57.
JIANG Weikang, YAN Li. Research on online detection technology for motor noise performance based on neural networks[J]. Journal of Vibration and Shock, 2004, 23(4):51-53,57.
[13]
蔡文伟, 黄键, 李伟光, 等. 基于声音信号的微型电机故障诊断方法研究[J]. 机床与液压, 2020, 48(23):190-195.
CAI Wenwei, HUANG Jian, LI Weiguang, et al Research on fault diagnosis method for micro motors based on sound signals[J]. Machine Tools and Hydraulics, 2020, 48(23):190-195.
[14]
张雅晖, 杨凯, 杨帆. 基于小波包能量分析和信号融合的异步电机转子故障诊断[J]. 电测与仪表, 2024, 61(4):161-168.
ZHANG Yahui, YANG Kai, YANG Fan. Asynchronous motor rotor fault diagnosis based on wavelet packet power analysis and signal fusion[J]. Electrical Measurement and Instrumentation, 2024, 61(4):161-168.
[15]
徐可, 陈宗海, 张陈斌, 等. 基于经验模态分解和支持向量机的滚动轴承故障诊断[J]. 控制理论与应用, 2019, 36(6):915-922.
XU Ke, CHEN Zonghai, ZHANG Chenbin, et al. Rolling bearing fault diagnosis based on empirical mode decomposition and support vector machine[J]. Control Theory and Applications, 2019, 36(6):915-922.
[16]
林福, 左曙光, 吴旭东, 等. 基于阶次分析的永磁同步电机噪声源识别[J]. 农业工程学报, 2016, 32(17):69-76.
LIN Fu, ZUO Shuguang, WU Xudong, et al. Noise source recongnition of permanent magnet synchronous motor based on order analysis[J]. Transactions of the Chinese Society of Agricultural Engineering, 2016, 32(17):69-76.
[17]
张能文, 姜天尚, 杨凯铭, 等. 基于EMD-Hilbert和主成分降维的电机故障信号特征提取[J]. 工业控制计算机, 2023, 36(1):53-55.
ZHANG Nengwen, JIANG Tianshang, YANG Kaiming, et al. Feature extraction of motor fault signals based on EMD Hilbert and principal component dimensionality reduction[J]. Industrial Control Computer, 2023, 36(1):53-55.
[18]
陆怡. 混合动力汽车车内声品质评价预测与控制研究[D]. 镇江: 江苏大学, 2020.
LU Yi. Research on evaluation,prediction and control of interior sound quality in hybrid electric vehicles[D]. Zhenjiang: Jiangsu University, 2020.
[19]
胡少梁, 李宏坤, 王朝阁, 等. 基于MEWT-ASCS的行星齿轮箱微弱故障特征提取[J]. 振动、测试与诊断, 2022, 42(3):474-482.
HU Shaoliang, LI Hongkun, WANG Chaoge, et al. Weak fault diagnosis method of planetary gearbox based on modified empirical wavelet transform and adaptive sparse coding shrink algorithm[J]. Journal of Vibration,Measurement & Diagnosis, 2022, 42(3):474-482.
[20]
彭璐. 支持向量机分类算法研究与应用[D]. 长沙: 湖南大学, 2007.
PENG Lu. Research and application of support vector machine classification algorithms[D]. Changsha: Hunan University, 2007.
[21]
徐晓明. SVM参数寻优及其在分类中的应用[D]. 大连: 大连海事大学, 2014.
XU Xiaoming. SVM parameter optimization and its application in classification[D]. Dalian: Dalian Maritime University, 2014.
[22]
孙瑶琴. 改进粒子群算法优化支持向量机在故障诊断中的应用研究[J]. 计算机测量与控制, 2017, 25(3):48-50,54.
SUN Yaoqin. Application of improved particle swarm optimization support vector machine in fault diagnosis[J]. Computer Measurement & Control, 2017, 25(3):48-50,54.
[23]
蔡振宇, 史乔波. 基于PSO-SVM模型的旋转机械故障诊断研究[J]. 煤矿机械, 2011, 32(11):276-278.
CAI Zhenyu, SHI Qiaobo. Fault diagnosis of rotating machinery based on PSO-SVM model[J]. Coal Mining Machinery, 2011, 32(11):276-278.
2024年第54卷第8期
PDF下载
174
77
引用本文
BibTeX
文章信息
doi: 10.19457/j.1001-2095.dqcd25144
  • 接收时间:2023-05-25
  • 首发时间:2025-12-09
  • 出版时间:2024-08-20
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2023-05-25
  • 修回日期:2023-06-12
基金
湖北省自然科学基金(2022CFB405)
作者信息
    海军工程大学 舰船与海洋学院,湖北 武汉 430033

通讯作者:

俞翔(1978—),男,博士,教授,硕士生导师,主要研究方向为振动与噪声控制,Email:
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/dqcd/CN/10.19457/j.1001-2095.dqcd25144
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