欢迎来到天天文库
浏览记录
ID:34818107
大小:247.98 KB
页数:6页
时间:2019-03-11
《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
此文档下载收益归作者所有