Induction motor condition monitoring using infrared thermography imaging and ensemble learning techniques

In this paper, a novel noncontact and nonintrusive framework experimental method is used for the monitoring and the diagnosis of a three phase’s induction motor faults based on an infrared thermography technique (IRT). The basic structure of this work begins with this applying IRT to obtain a thermo...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Amine Mahami, Chemseddine Rahmoune, Toufik Bettahar, Djamel Benazzouz
Formato: article
Lenguaje:EN
Publicado: SAGE Publishing 2021
Materias:
Acceso en línea:https://doaj.org/article/33f9873071a04a9f94bfecec7fb594a7
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:33f9873071a04a9f94bfecec7fb594a7
record_format dspace
spelling oai:doaj.org-article:33f9873071a04a9f94bfecec7fb594a72021-12-02T03:33:59ZInduction motor condition monitoring using infrared thermography imaging and ensemble learning techniques1687-814010.1177/16878140211060956https://doaj.org/article/33f9873071a04a9f94bfecec7fb594a72021-11-01T00:00:00Zhttps://doi.org/10.1177/16878140211060956https://doaj.org/toc/1687-8140In this paper, a novel noncontact and nonintrusive framework experimental method is used for the monitoring and the diagnosis of a three phase’s induction motor faults based on an infrared thermography technique (IRT). The basic structure of this work begins with this applying IRT to obtain a thermograph of the considered machine. Then, bag-of-visual-word (BoVW) is used to extract the fault features with Speeded-Up Robust Features (SURF) detector and descriptor from the IRT images. Finally, various faults patterns in the induction motor are automatically identified using an ensemble learning called Extremely Randomized Tree (ERT). The proposed method effectiveness is evaluated based on the experimental IRT images, and the diagnosis results show its capacity and that it can be considered as a powerful diagnostic tool with a high classification accuracy and stability compared to other previously used methods.Amine MahamiChemseddine RahmouneToufik BettaharDjamel BenazzouzSAGE PublishingarticleMechanical engineering and machineryTJ1-1570ENAdvances in Mechanical Engineering, Vol 13 (2021)
institution DOAJ
collection DOAJ
language EN
topic Mechanical engineering and machinery
TJ1-1570
spellingShingle Mechanical engineering and machinery
TJ1-1570
Amine Mahami
Chemseddine Rahmoune
Toufik Bettahar
Djamel Benazzouz
Induction motor condition monitoring using infrared thermography imaging and ensemble learning techniques
description In this paper, a novel noncontact and nonintrusive framework experimental method is used for the monitoring and the diagnosis of a three phase’s induction motor faults based on an infrared thermography technique (IRT). The basic structure of this work begins with this applying IRT to obtain a thermograph of the considered machine. Then, bag-of-visual-word (BoVW) is used to extract the fault features with Speeded-Up Robust Features (SURF) detector and descriptor from the IRT images. Finally, various faults patterns in the induction motor are automatically identified using an ensemble learning called Extremely Randomized Tree (ERT). The proposed method effectiveness is evaluated based on the experimental IRT images, and the diagnosis results show its capacity and that it can be considered as a powerful diagnostic tool with a high classification accuracy and stability compared to other previously used methods.
format article
author Amine Mahami
Chemseddine Rahmoune
Toufik Bettahar
Djamel Benazzouz
author_facet Amine Mahami
Chemseddine Rahmoune
Toufik Bettahar
Djamel Benazzouz
author_sort Amine Mahami
title Induction motor condition monitoring using infrared thermography imaging and ensemble learning techniques
title_short Induction motor condition monitoring using infrared thermography imaging and ensemble learning techniques
title_full Induction motor condition monitoring using infrared thermography imaging and ensemble learning techniques
title_fullStr Induction motor condition monitoring using infrared thermography imaging and ensemble learning techniques
title_full_unstemmed Induction motor condition monitoring using infrared thermography imaging and ensemble learning techniques
title_sort induction motor condition monitoring using infrared thermography imaging and ensemble learning techniques
publisher SAGE Publishing
publishDate 2021
url https://doaj.org/article/33f9873071a04a9f94bfecec7fb594a7
work_keys_str_mv AT aminemahami inductionmotorconditionmonitoringusinginfraredthermographyimagingandensemblelearningtechniques
AT chemseddinerahmoune inductionmotorconditionmonitoringusinginfraredthermographyimagingandensemblelearningtechniques
AT toufikbettahar inductionmotorconditionmonitoringusinginfraredthermographyimagingandensemblelearningtechniques
AT djamelbenazzouz inductionmotorconditionmonitoringusinginfraredthermographyimagingandensemblelearningtechniques
_version_ 1718401721958400000