基于小波分析與神經(jīng)網(wǎng)絡(luò)的軸承故障診斷研究.pdf

1、天津大學(xué)碩士學(xué)位論文基于小波分析與神經(jīng)網(wǎng)絡(luò)的軸承故障診斷研究姓名：張維新申請(qǐng)學(xué)位級(jí)別：碩士專(zhuān)業(yè)：機(jī)械制造及其自動(dòng)化指導(dǎo)教師：王國(guó)鋒20080601ABSTRACT、Ⅳimnledevelopmentofcomplexit)raIldautomatic1eVelofthemacllineequipmem，mac№eequipmentsfaultdia印osisismoreandmoreimportantBesides，itisiInpor

2、tanttochooseappropriatemethodforf孤ltdiagnosisforprccisionofresult011meresearchofintelligencediagnosistecllIlolo鼢mewaVeletaIlalysis姍dtlleneurmnetworktechnologyismehotspot，alsoistheresearchedgeCon幽i11ationofWaveletanalysis

3、aIldn㈣lne觚orkisalsoan印pealingtopicThewaVeletanalysistheoD，waSstudiediIlthisp印er0111t11ebasisofthecharacteristicthatwaveletpacketcoulddecomposethesignalstodifl研ent舭quencyse舯emsiIlaccordancewitha11ytiInenequencyresolutiomt

4、hememodforfeaturesex仃actionbasedonenergyofwaveletpacketa11ds硫【ulationanalyzillgcollf嘞edthatthenlethodisaccumteande丘ectiveThemodelingp血cipleand缸ainingalgori恤ofBPneuralne庀work，RBFn(IuralnetworkandFuz糾AI汀networkwereSummariz

5、edAiIl血gatmeshortageofBPalgoritllIn，theLevenbe唱一Maulquardt叩tiIIlizationalgoritllIIlwas鋤：roducedWaVelet觚alysispossesseseXcellentcharacteristicoftime一丘equencylocalizationandissuitableforanalyzingt11e血e—Varyingor饑msiemsigna

6、lsHoweV％neuralne研orkissuccess血li11reco印iziIlgnon—lineaursystemandclassi匆illgpattemNeuralnet、)l，orkintelligencediagIlosticnlodelhasbeeIlestablishedwiththeaboVep血ciple，鋤dithasbeenusedinrollingbea而唱’sfailurediagnosisAccordi

7、ngtotheVibrationsigllalfeaturesof骶quencydomiIl，eIl唧eigenVectorwase如blishedbymea璐ofwaVeletpacketThenreco鰣tionoffaultpattemofroll她bea血gwaspreselltedusiIlgneuralne謝orkTheexpemlemalresultshowsmattllesyst鋤cannotoIdydetectnlef

8、jallltofbe撕ngbutalsocanrecogllizef撕ltpattemcorrectlyWhentheBPne啪1networkusingmeLeveIlbe唱一Marqu卸dtopt砌zationalgoritllIIl，theconVe瑪encerateisquickandhast11e11i曲accuracyrateoffaihedia田∞sis，butstillhadmedisadv趾tage，forexampl

9、e，conVergenceisu11Stable111eradialbasis缸lctionneuralnet、VorkhasadvaIltagesovertlleBPnet、ⅣorkmodeliIltheaspectsofne似orkconfiguration，net、)l，orkperfonnanceaIldthene帆orkfaulttoleLantperfo肌aIlceetcBasedont11ewaveletaIlalysis

10、andthemdialbasismnctionne似。叱thefaultpanemrecogIlitionmethodismuchmoreefrectivelyandaccurately，wKchshouldbebetter叩pliediIlmefaundia印osisofmechaIlicalequipmentsTheFuzzyARTnetworkmodeltladquickandstableidentificationabilit)