RT info:eu-repo/semantics/article
T1 An SVM-based solution for fault detection in wind turbines
A1 Santos González, Pedro
A1 Villa, Luisa F.
A1 Reñones, Anibal
A1 Bustillo Iglesias, Andrés
A1 Maudes Raedo, Jesús M.
K1 fault diagnosis
K1 neural networks
K1 support vector machines
K1 wind turbines
K1 Informática
K1 Computer science
AB 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.
PB MDPI
SN 1424-8220
YR 2015
FD 2015-03
LK http://hdl.handle.net/10259/4264
UL http://hdl.handle.net/10259/4264
LA eng
NO Projects, CENIT-2008-1028, TIN2011-24046,IPT-2011-1265-020000 and DPI2009-06124-E/DPI of the Spanish Ministry of Economy andCompetitiveness
DS Repositorio Institucional de la Universidad de Burgos
RD 26-abr-2024