Fault Classification in Cylinders Using Multilayer Perceptrons, Support Vector Machines and Guassian Mixture Models

Simple item page
dc.creatorMarwala, Tshilidzi
dc.creatorMahola, Unathi
dc.creatorChakraverty, Snehashish
dc.date2007-05-02
dc.date.accessioned2026-07-07T07:59:05Z
dc.date.available2026-07-07T07:59:05Z
dc.descriptionGaussian mixture models (GMM) and support vector machines (SVM) are introduced to classify faults in a population of cylindrical shells. The proposed procedures are tested on a population of 20 cylindrical shells and their performance is compared to the procedure, which uses multi-layer perceptrons (MLP). The modal properties extracted from vibration data are used to train the GMM, SVM and MLP. It is observed that the GMM produces 98%, SVM produces 94% classification accuracy while the MLP produces 88% classification rates.
dc.description10 pages, 2 figures, 4 tables
dc.identifierhttps://arxiv.org/abs/0705.0197
dc.identifierhttp://arxiv.org/abs/0705.0197
dc.identifierComputer Assisted Mechanics and Engineering Sciences, Vol. 14, No. 2, 2007.
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/128237
dc.subjectArtificial Intelligence
dc.titleFault Classification in Cylinders Using Multilayer Perceptrons, Support Vector Machines and Guassian Mixture Models
dc.typetext

Files

Collections

arXiv