Cargando…

An SVM-Based Solution for Fault Detection in Wind Turbines

Research into fault diagnosis in machines with a wide range of variable loads and speeds, such as wind turbines, is of great industrial interest. Analysis of the power signals emitted by wind turbines for the diagnosis of mechanical faults in their mechanical transmission chain is insufficient. A su...

Descripción completa

Detalles Bibliográficos
Autores principales: Santos, Pedro, Villa, Luisa F., Reñones, Aníbal, Bustillo, Andres, Maudes, Jesús
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2015
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4435112/
https://www.ncbi.nlm.nih.gov/pubmed/25760051
http://dx.doi.org/10.3390/s150305627
_version_ 1782371853017284608
author Santos, Pedro
Villa, Luisa F.
Reñones, Aníbal
Bustillo, Andres
Maudes, Jesús
author_facet Santos, Pedro
Villa, Luisa F.
Reñones, Aníbal
Bustillo, Andres
Maudes, Jesús
author_sort Santos, Pedro
collection PubMed
description Research into fault diagnosis in machines with a wide range of variable loads and speeds, such as wind turbines, is of great industrial interest. Analysis of the power signals emitted by wind turbines for the diagnosis of mechanical faults in their mechanical transmission chain is insufficient. A successful diagnosis requires the inclusion of accelerometers to evaluate vibrations. This work presents a multi-sensory system for fault diagnosis in wind turbines, combined with a data-mining solution for the classification of the operational state of the turbine. The selected sensors are accelerometers, in which vibration signals are processed using angular resampling techniques and electrical, torque and speed measurements. Support vector machines (SVMs) are selected for the classification task, including two traditional and two promising new kernels. This multi-sensory system has been validated on a test-bed that simulates the real conditions of wind turbines with two fault typologies: misalignment and imbalance. Comparison of SVM performance with the results of artificial neural networks (ANNs) shows that linear kernel SVM outperforms other kernels and ANNs in terms of accuracy, training and tuning times. The suitability and superior performance of linear SVM is also experimentally analyzed, to conclude that this data acquisition technique generates linearly separable datasets.
format Online
Article
Text
id pubmed-4435112
institution National Center for Biotechnology Information
language English
publishDate 2015
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-44351122015-05-19 An SVM-Based Solution for Fault Detection in Wind Turbines Santos, Pedro Villa, Luisa F. Reñones, Aníbal Bustillo, Andres Maudes, Jesús Sensors (Basel) Article Research into fault diagnosis in machines with a wide range of variable loads and speeds, such as wind turbines, is of great industrial interest. Analysis of the power signals emitted by wind turbines for the diagnosis of mechanical faults in their mechanical transmission chain is insufficient. A successful diagnosis requires the inclusion of accelerometers to evaluate vibrations. This work presents a multi-sensory system for fault diagnosis in wind turbines, combined with a data-mining solution for the classification of the operational state of the turbine. The selected sensors are accelerometers, in which vibration signals are processed using angular resampling techniques and electrical, torque and speed measurements. Support vector machines (SVMs) are selected for the classification task, including two traditional and two promising new kernels. This multi-sensory system has been validated on a test-bed that simulates the real conditions of wind turbines with two fault typologies: misalignment and imbalance. Comparison of SVM performance with the results of artificial neural networks (ANNs) shows that linear kernel SVM outperforms other kernels and ANNs in terms of accuracy, training and tuning times. The suitability and superior performance of linear SVM is also experimentally analyzed, to conclude that this data acquisition technique generates linearly separable datasets. MDPI 2015-03-09 /pmc/articles/PMC4435112/ /pubmed/25760051 http://dx.doi.org/10.3390/s150305627 Text en © 2015 by the authors; licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution license (http://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Santos, Pedro
Villa, Luisa F.
Reñones, Aníbal
Bustillo, Andres
Maudes, Jesús
An SVM-Based Solution for Fault Detection in Wind Turbines
title An SVM-Based Solution for Fault Detection in Wind Turbines
title_full An SVM-Based Solution for Fault Detection in Wind Turbines
title_fullStr An SVM-Based Solution for Fault Detection in Wind Turbines
title_full_unstemmed An SVM-Based Solution for Fault Detection in Wind Turbines
title_short An SVM-Based Solution for Fault Detection in Wind Turbines
title_sort svm-based solution for fault detection in wind turbines
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4435112/
https://www.ncbi.nlm.nih.gov/pubmed/25760051
http://dx.doi.org/10.3390/s150305627
work_keys_str_mv AT santospedro ansvmbasedsolutionforfaultdetectioninwindturbines
AT villaluisaf ansvmbasedsolutionforfaultdetectioninwindturbines
AT renonesanibal ansvmbasedsolutionforfaultdetectioninwindturbines
AT bustilloandres ansvmbasedsolutionforfaultdetectioninwindturbines
AT maudesjesus ansvmbasedsolutionforfaultdetectioninwindturbines
AT santospedro svmbasedsolutionforfaultdetectioninwindturbines
AT villaluisaf svmbasedsolutionforfaultdetectioninwindturbines
AT renonesanibal svmbasedsolutionforfaultdetectioninwindturbines
AT bustilloandres svmbasedsolutionforfaultdetectioninwindturbines
AT maudesjesus svmbasedsolutionforfaultdetectioninwindturbines