Neural network approach of active ultrasonic signals for structural health monitoring analysis.pdf

Neural network approach of active ultrasonic signals for structural health monitoring analysis.pdf

ID:34114722

大小:289.94 KB

頁數:11頁

時間:2019-03-03

Neural network approach of active ultrasonic signals for structural health monitoring analysis.pdf_第1頁
Neural network approach of active ultrasonic signals for structural health monitoring analysis.pdf_第2頁
Neural network approach of active ultrasonic signals for structural health monitoring analysis.pdf_第3頁
Neural network approach of active ultrasonic signals for structural health monitoring analysis.pdf_第4頁
Neural network approach of active ultrasonic signals for structural health monitoring analysis.pdf_第5頁
資源描述:

《Neural network approach of active ultrasonic signals for structural health monitoring analysis.pdf》由會員上傳分享,免費在線閱讀,更多相關內容在學術論文-天天文庫

1、NeuralNetworkApproachofActiveUltrasonicSignalsforStructuralHealthMonitoringAnalysisZacharyKral,WalterHorn,andJamesSteckDept.ofAerospaceEngineering,WichitaStateUniversity,Wichita,KS67260ABSTRACTMaintenanceisanimportantissueforaerospacesystems,sincetheyareinservic

2、ebeyondtheirdesignedlifetime.Thisrequiresscheduledinspectionsanddamagerepairbeforefailure.Researchisinprogresstodevelopastructuralhealthmonitoringsystem(SHMS)toimprovethismaintenanceroutine.Ultrasonictesting,utilizingasystemofpiezoelectricactuatorsandsensors,isa

3、promisingconceptMeasuredwavesignalsarecomparedwithsignalsforpreviouslyscannedstates.Changestothesignalcouldbetheresultofdamagetothecomponent.Thispaperfocusesonanalyzingthedifferencesofstates,usingartificialneuralnetworks.Neuralnetworkanalysishasthepotentialofcre

4、atingaSHMSofgreaterabilityandprocessing.Experimentswereperformedonathin,flataluminumpanel.Ultrasonicactuatorsandsensorswereinstalledandabaselinescanwasperformedontheundamagedpanel.Simulateddamagewasintroducedinspecificareas,andscanswereconductedforseveraldamaged

5、states.Neuralnetworkswerecreatedtoassessthechangingconditionsofthepanel.Thesystemwaslatertestedonalapjointspecimentoconfirmtheabilitiesoftheneuralnetwork.Thisformofanalysisperformedwellatlocatingandquantifyingareasofchangewithinthestructure.Theneuralnetworkperfo

6、rmanceindicatedthatithasaroleintheSHMSofaerospacestructures.Keywords:Structuralhealthmonitoring,artificialneuralnetwork,ultrasonictesting,damagedetection,thin-walledstructures,piezoelectricmaterials1INTRODUCTIONStructuralhealthmonitoringofaerospacesystemsiscurre

7、ntlyamajortopicofresearch.Foraircraftandotheraerospacesystems,thetimeofusein-serviceisfargreaterthanthedesignedlifetimes.Thus,maintenancebecomesakeyissue.Currentmaintenancesystemsarecomposedofsimplenondestructiveinspection(NDI)techniques,wheretheaircraftorstruct

8、ureistakenoutofserviceafterapredeterminedamountofservicelife.Forthesemaintenanceinspectionssimplemethods,suchaseyeinspectioncointaptests,mightbeusedtosearchforstructu

當前文檔最多預覽五頁,下載文檔查看全文

此文檔下載收益歸作者所有

當前文檔最多預覽五頁,下載文檔查看全文
溫馨提示:
1. 部分包含數學公式或PPT動畫的文件,查看預覽時可能會顯示錯亂或異常,文件下載后無此問題,請放心下載。
2. 本文檔由用戶上傳,版權歸屬用戶,天天文庫負責整理代發(fā)布。如果您對本文檔版權有爭議請及時聯(lián)系客服。
3. 下載前請仔細閱讀文檔內容,確認文檔內容符合您的需求后進行下載,若出現(xiàn)內容與標題不符可向本站投訴處理。
4. 下載文檔時可能由于網絡波動等原因無法下載或下載錯誤,付費完成后未能成功下載的用戶請聯(lián)系客服處理。