Fault Diagnosis Model Based on Fuzzy Support Vector Machine Combined with Weighted Fuzzy Clustering

(整期优先)网络出版时间:2013-03-13
/ 1
Afaultdiagnosismodelisproposedbasedonfuzzysupportvectormachine(FSVM)combinedwithfuzzyclustering(FC).Consideringtherelationshipbetweenthesamplepointandnon-selfclass,FCalgorithmisappliedtogeneratefuzzymemberships.Inthealgorithm,sampleweightsbasedonadistributiondensityfunctionofdatapointandgeneticalgorithm(GA)areintroducedtoenhancetheperformanceofFC.Thenamulti-classFSVMwithradialbasisfunctionkernelisestablishedaccordingtodirectedacyclicgraphalgorithm,thepenaltyfactorandkernelparameterofwhichareoptimizedbyGA.Finally,themodelisexecutedformulti-classfaultdiagnosisofrollingelementbearings.Theresultsshowthatthepresentedmodelachieveshighperformancesbothinidentifyingfaulttypesandfaultdegrees.TheperformancecomparisonsofthepresentedmodelwithSVManddistance-basedFSVMfornoisycasedemonstratethecapacityofdealingwithnoiseandgeneralization.