Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | 박준홍 | - |
dc.contributor.author | 곽윤상 | - |
dc.date.accessioned | 2024-03-01T07:32:04Z | - |
dc.date.available | 2024-03-01T07:32:04Z | - |
dc.date.issued | 2018.8 | - |
dc.identifier.uri | http://hanyang.dcollection.net/common/orgView/200000433269 | en_US |
dc.identifier.uri | https://repository.hanyang.ac.kr/handle/20.500.11754/188208 | - |
dc.description.abstract | Anovelmethodforthelocalizationtoidentifyacousticsourceswasproposedbyutilizingtimereversalfordispersivewavesanddeepneuralnetworksbasedonthewaveprediction.Thestructuralvibrationsincomplexstructureswithmulti-linkedpathswerepredictedusingthewaveapproachafterconsideringdispersivepropagationcharacteristics.Inordertoconsiderlinkedconditionsbetweenmultiplepaths,thevibrationsinthecomplexstructureswereanalyzedaswavescoupledbothintransverseandtorsionaldirections.Thecouplingeffectsondispersivevibrationswasverifiedbysimplebeammodels.Thenumericalprocedurefortimereversalwasproposedtoidentifytheimpactlocationinthecomplexstructureshavingarbitrarypaths.Theproposedmethodwasappliedforexperimentsinanactualvehiclestructure.Thelocationsoftherattlesourceswereidentifiedfromthefocusedpointofflexuralvibrationsanalyzedbytheproposednumericaltimereversalprocedure.Giventhecoupledwaveapproach,theproposedmethodwasappliedforlocalizationofdispersivesignalsinarbitrarycomplexstructures. Thedeepconvolutionalneuralnetworks(DCNNs)wereproposedthroughthefeatureconstructionforthelocalizationandthesimulativelearningtechnique.Thefeaturesfordetectingthelocationofsourceswereextractedbyperformingacross-cepstralanalysisandimage-mappingprocess.Groupsofcomplexcross-cepstrumswerecalculatedbyusingwavesmeasuredbythreecloselyspacedtransducers.Theproposedfeatureconstructionallowstoclassifyingthesourcelocationsregardlessofspectraldensityofthesources.Eachgroupwastransformedintored,green,andblue(RGB)channelsbypixelmapping.Theimagepatternswereinfluencedbythesourcelocation.AsimulativelearningtechniquewasproposedinthisstudyandpresentedtotraintheDCNNwithoutrepetitiveexperiments.InordertogeneratethelearningdatafortheDCNN,thepropagatedwaveswerepredictedforvarioussourcelocationsandconditions.Themethodwasverifiedbyperformingexperimentsinananechoicroom.ThemappedimagesofthemeasuredacousticwaveswereclassifiedbyusingtheDCNNtodetectthelocationoftheacousticsources.Thesourceswereaccuratelydeterminedbyusingonlysmallmicrophonesirrespectiveofthetypeofacousticsourceandwithreducedeffectsfromthebackgroundnoise. TheproposedDCNNforlocalizationofthesourcesonthecomplexstructureswaspresented.TheDCNNforthecomplexstructureswasachievedthroughthecoupledwavepredictionandfeatureconstructionfortheflexuralwaves.ThefeaturesfortheDCNNwerecomprisedbyutilizingmeasuredvibrations.Themodifiedcepstralanalysisusingenvelopsofthespectrumswaspresentedinordertoextractthefeaturesforthesourcelocations.ThedatafortrainingoftheDCNNweregeneratedbychangingconditionsofsourcesandstructuresinthecoupledwaveprediction.Thefourchangedconditionswerecorrespondedtolocationandspectraldensityofsources,thicknessandwidthofstructures.Thenetworksweretrainedbythegenerateddata,andthesourcelocationswereidentifiedfor150classes.Theproposednetworkswereverifiedbythevibrationmeasurementsontheactualvehicle.Thelocationsofsourcesinthecomplexstructurewerepredictedthroughthenetworkswithonlysimplecomputationalcosts.Thedeepneuralnetworkwiththesimulativelearningtechniqueandthefeatureconstructionsprovidestheoptimalperformanceforlocalizationofsourcesonthecomplexstructuresevenundersparsedatafortraining.Giventhewaveapproachforthestructures,theproposedmethodmakesitpossibletoeasilyadoptvariouscomplexsystems. | - |
dc.publisher | 한양대학교 | - |
dc.title | AcousticSourceLocalizationviaPredictingPropagatedWavesonComplexSystemsusingTimeReversalandDeepNeuralNetworks | - |
dc.type | Theses | - |
dc.contributor.googleauthor | YunsangKwak | - |
dc.contributor.alternativeauthor | 곽윤상 | - |
dc.sector.campus | S | - |
dc.sector.daehak | 대학원 | - |
dc.sector.department | 융합기계공학과 | - |
dc.description.degree | Doctor | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.