Feature extraction of machine sound using wavelet... .pdf

Feature extraction of machine sound using wavelet... .pdf

ID:34818107

大小:247.98 KB

页数:6页

时间:2019-03-11

Feature extraction of machine sound using wavelet... .pdf_第1页
Feature extraction of machine sound using wavelet... .pdf_第2页
Feature extraction of machine sound using wavelet... .pdf_第3页
Feature extraction of machine sound using wavelet... .pdf_第4页
Feature extraction of machine sound using wavelet... .pdf_第5页
资源描述:

《Feature extraction of machine sound using wavelet... .pdf》由会员上传分享,免费在线阅读,更多相关内容在学术论文-天天文库

1、NDT&EInternational34(2001)25±30www.elsevier.com/locate/ndteintFeatureextractionofmachinesoundusingwaveletanditsapplicationinfaultdiagnosisJingLin*StateKeyLaboratoryofAcoustics,InstituteofAcoustics,ChineseAcademyofScience,Beijing100080,People'sRepublicofChinaReceived1December1999;re

2、ceivedinrevisedform13April2000;accepted17April2000AbstractMachinesoundalwayscarriesinformationabouttheworkingofthemachine.Butinmanycases,thesoundhasaverylowSNR.Toobtaincorrectinformation,thebackgroundnoisehastoberemovedorthesoundmustbepuri®ed.Ade-noisingmethodisgiveninthispaperandi

3、ssuccessfullyusedinfeaturesoundextraction.Wecaneasilydiagnoseamachineusingthepuri®edsound.Thisde-noisingmethodisbasedonthewavelettechniqueandusestheMorletwaveletasthemotherwavelet,becauseitstime±frequencyresolutioncanbeadjustedtoadapttothesignaltobeanalyzed.Themethodisusedforextrac

4、tingthesoundofsomevehicleengineswithdifferenttypesoffailure.Thefeaturesoundisextractedsuccessfully.q2001PublishedbyElsevierScienceLtd.Keywords:Faultdiagnosis;Wavelet;Featureextraction1.IntroductionThispaperisorganizedasfollows.InSection2,theproposedde-noisingmethodisusedforasimulat

5、edsignal,Machinesoundusuallyre¯ectstheworkingconditionofwhichshowsthepowerfulcapacityofthemethodforthemachine.Manyexperiencedoperatorscandiagnoseafeatureextraction.InSection3,theexperimentalsetupismachinejustbylisteningtoitssound.Butveryoften,theintroduced.InSection4,somesignalssam

6、pledfromaballfeaturesoundofthemachineisimmersedinheavynoisebearingandthereciprocatingcompressorareprocessedforandtheoperatorscanhardlymakeoutanychangesinthefeatureextractionusingthede-noisingmethod.InSection5,sound.Also,wecannot®ndanysymptomsinthewaveformtheconclusionsaregiven.andt

7、heFourierspectrumofthesoundatthistime.Thus,toobtaintheusefulinformationthatishiddeninthenoisysignalaneffectivemethodforfeatureextractionhastobe2.Waveletanditsapplicationforfeatureextractionused.Waveletanalysisisaneffectivetoolfornonstational2.1.Reviewofwavelettransformsignalprocess

8、ingandhasbeenusedinmanyres

当前文档最多预览五页,下载文档查看全文

此文档下载收益归作者所有

当前文档最多预览五页,下载文档查看全文
温馨提示:
1. 部分包含数学公式或PPT动画的文件,查看预览时可能会显示错乱或异常,文件下载后无此问题,请放心下载。
2. 本文档由用户上传,版权归属用户,天天文库负责整理代发布。如果您对本文档版权有争议请及时联系客服。
3. 下载前请仔细阅读文档内容,确认文档内容符合您的需求后进行下载,若出现内容与标题不符可向本站投诉处理。
4. 下载文档时可能由于网络波动等原因无法下载或下载错误,付费完成后未能成功下载的用户请联系客服处理。