文档下载 文档下载导航
设为首页 | 加入收藏
搜索 请输入内容:  
 导航当前位置: 文档下载 > 所有分类 > 工程科技 > 机械/仪表 > Support vector machines-based fault diagnosis for turbo-pump rotor
侵权投诉

Support vector machines-based fault diagnosis for turbo-pump rotor

Support vector machines-based fault diagnosis for turbo-pump rotor

942

S.-F.Yuan,F.-L.Chu/MechanicalSystemsandSignalProcessing20(2006)939–952

recognitionstage,anewsamplexisinputtotheclassi erbetweenthemclassandthenclass:

()lX

mnmn

fmnðxÞ¼sgnlmn.iyiKðx;xiÞþb

i¼1

(5)

Iftheclassi ershowsthatxbelongstothemclass,thenaballotiscastforthemclass.AfterrecognisedbyallthesekðkÀ1Þ=2classi ers,xcanbejudgedtobelongtotheclassthathasthemostballots.

Somedisadvantagesofthisalgorithmare:(1)thenumberkðkÀ1Þ=2oftwo-classSVMclassi ersincreasesgreatlywiththeclassnumberk,calculationincreasesgreatlyaswell,andtherateoftrainingandrecognitionisveryslow;(2)whentwoormoreclasseshavethesameballots,itishardtojudgewhichclassthenewsamplexbelongsto;(3)thereisatleastaclasswhoseballotsarethemost,soanewsamplexthatdoesnotreallybelongtoanyofthesekclasseswouldbemisjudgedtobelongtothemandtheclassifyingerrorappears.

Theothersub-methodisthe‘onetorest’algorithm[1].Thisalgorithmtakesanyoneclassmofthesekclassesasacategory,takestherestkÀ1classesasanothercategory,constructsatwo-classSVMclassi erandnamesitSVMm.Inthisway,ktwo-classSVMclassi erscanbeconstructedinallforacaseofkclasses.TheclassifyingfunctionofSVMmis

()lX

mm

fmðxÞ¼sgnlm.(6)iyiKðx;xiÞþb

i¼1

Intherecognitionstage,thenewsamplexisinputtoallthesekclassi ers.Therearekoutputsinall.Thenewsamplexisjudgedtobelongtotheclasswhoseclassi erhasthelargestoutput.

Somedisadvantagesofthisalgorithmare:(1)allsampleshavetobetakenintothetrainingofallthesekclassi ers;intherecognitionstage,onlyafterallthesekclassi ershaverecognisedthenewsamplexcantheclassi cationresultbeobtained.Thereforethecalculationisverytime-consumingandtherateoftrainingandrecognitionisslowaswell;(2)thereisatleastatwo-classSVMclassi erwhoseoutputisthelargest,soanewsamplexthatdoesnotreallybelongtoanyofthesekclasseswouldbemisjudgedtobelongtothemandtheclassifyingerrorappears;(3)whentwoormoreclassi ershavethesameoutputs,itishardtojudgewhichclassthenewsamplexbelongsto.

3.Onetoothersmulti-classSVMalgorithm

Themulti-outputSVMalgorithmiscomplexandshortofpracticability;andthemethodsthatcombinesometwo-classSVMclassi ersformulti-classpatternrecognitionhaveyetanotherdisadvantage:rejectregion.

Adatasetof3classesisclassi edbythe‘onetoone’andthe‘onetorest’algorithmsrespectivelyasshowninFig.2.Rings,diamondsandtrianglesstandforthese3classesofsamplepointsrespectively,andthereallinesstandforoptimalseparatinghyper-planesofSVM.Itcanbeseenthatthereareshadowzonesinwhichthefaultsamplescannotbeclassi edtoanyclassesbytheoptimalseparatinghyper-planesofSVM;theseshadowzonesarerejectregions.

(a)

Support vector machines-based fault diagnosis for turbo-pump rotor

(b)

Fig.2.(a)Classi cationwithonetoonealgorithm.(b)Classi cationwithonetorestalgorithm.

上一页第4页

你可能喜欢

热门文档

相关文档

站点地图 | 文档上传 | 侵权投诉 | 手机版
本站所有资源均来自互联网,本站只负责收集和整理,均不承担任何法律责任,如有侵权等其它行为请联系我们.
文档下载 Copyright 2013 doc.guandang.net All Rights Reserved.  -  email