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

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

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

943

Wepresentanewmulti-classSVMalgorithmhere.Itiscalled‘onetoothers’algorithm.Foradatasetofkclasses:

ðxi;yiÞ;

i¼1;...;l;

xi2Rd;

yi2f1;2;...;kg,

(7)

wherelissamplenumber,disdimensionofsamplevector,kisclassnumber.First,wehaveacaseofkclasses,takeatop-priorityclassfromthesekclassesasacategory,taketherest(kÀ1)classesasanothercategory,constructatwo-classSVMclassi erandnameitSVM1;Next,thistop-priorityclassisexcluded,andthenwehaveacaseofkÀ1classes,takeatop-priorityclassfromthosekÀ1classesasacategory,andtaketherestðkÀ1ÞÀ1classesasanothercategory,andconstructasecondtwo-classSVMclassi erandnameitSVM2,andsoonandsoforthtillthelasttwo-classSVMclassi erisconstructedandnamedSVMkÀ1.Inthisway,kÀ1two-classSVMclassi erscanbeconstructedinallforacaseofkclasses.Inthefaultdiagnosis,themostcommonorthemostdangerousfaultcanbegiventoppriority.The‘onetoothers’multi-classSVMclassi erisabinarytreecomposedofseveraltwo-classSVMclassi ersorganisedbyfaultpriorityasshownisFig.3.Foradatasetof3classes,theclassi cationresultwiththe‘onetoothers’SVMalgorithmisshownasFig.4.Itcanbeseenthattherearenoshadowzonesorrejectregions.Furthermore,itneedsonlykÀ1two-classSVMclassi ersforacaseofkclasses,whilethe‘onetoone’algorithmneedskðkÀ1Þ=2two-classclassi ersandthe‘onetorest’algorithmneedsk.Obviouslylesstwo-classclassi ershelpexpeditetherateoftrainingandrecognition.

The‘onetoothers’SVMalgorithmalsoreducestherepeatedtrainingamountgreatly.

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

Fig.3.Frameworkofthe‘onetoothers’SVMalgorithm.

Fig.4.Classi cationwith‘onetoothers’SVMalgorithm.

上一页第5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