Please use this identifier to cite or link to this item: http://repositorio.ufla.br/jspui/handle/1/42430
metadata.artigo.dc.title: Higher-Order Statistics and support vector machines applied to fault detection in a cantilever beam
metadata.artigo.dc.creator: Borges, Fernando Elias de Melo
Pinto, Andrey Willian Marques
Pereira, Daniel Augusto
Barbosa, Bruno Henrique Groenner
Magalhães, Ricardo Rodrigues
Ferreira, Danton Diego
Barbosa, Tássio Spuri
metadata.artigo.dc.subject: Vibration analysis
Structural health monitoring
One-Class learning
Análise de vibração
Monitoramento de integridade estrutural
Detecção de falhas
Máquina de vetores de suporte
Função discriminante de Fisher
metadata.artigo.dc.publisher: Universidade Federal de Lavras
metadata.artigo.dc.date.issued: 2020
metadata.artigo.dc.identifier.citation: BORGES, F. E. de M. et al. Higher-Order Statistics and support vector machines applied to fault detection in a cantilever beam. Theoretical and Applied Engineering, Lavras, v. 4, n. 1, p. 1-8, 2020..
metadata.artigo.dc.description.abstract: In this paper, it is proposed a method to detect structural faults or damages using Higher-Order Statistics (HOS). For this, vibration signals were taken from cantilever beams. Such vibrations were generated by a DC motor with varying rotation, generating vibrations at various frequencies. Vibration signals and engine speed control were performed by an Arduino board. After the signal acquisition, parameters are extracted by means of second-, third- and fourthorder cumulants and then the most relevant ones were selected by the Fisher’s Discriminant Ratio (FDR). To fault detection, a Support Vector Machine (SVM) classifier has been designed in its One-Class version, where only oneclass knowledge is required. The results showed a good ability to represent vibration signals via HOS along with a large reduction in dimensionality given using FDR and a good generalization by means of the SVM classifier. Failure detection results showed 100% success rates.
metadata.artigo.dc.identifier.uri: http://www.taaeufla.deg.ufla.br/index.php/TAAE/article/view/30
http://repositorio.ufla.br/jspui/handle/1/42430
metadata.artigo.dc.language: en
Appears in Collections:DAT - Artigos publicados em periódicos
DEG - Artigos publicados em periódicos

Files in This Item:
There are no files associated with this item.


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.