TY - JOUR
T1 - Fault diagnosis in spur gears based on genetic algorithm and random forest
AU - Cerrada, Mariela
AU - Zurita, Grover
AU - Cabrera, Diego
AU - Sánchez, René Vinicio
AU - Artés, Mariano
AU - Li, Chuan
N1 - Publisher Copyright:
© 2015 Elsevier Ltd. All rights reserved.
PY - 2016/3/1
Y1 - 2016/3/1
N2 - There are growing demands for condition-based monitoring of gearboxes, and therefore new methods to improve the reliability, effectiveness, accuracy of the gear fault detection ought to be evaluated. Feature selection is still an important aspect in machine learning-based diagnosis in order to reach good performance of the diagnostic models. On the other hand, random forest classifiers are suitable models in industrial environments where large data-samples are not usually available for training such diagnostic models. The main aim of this research is to build up a robust system for the multi-class fault diagnosis in spur gears, by selecting the best set of condition parameters on time, frequency and time-frequency domains, which are extracted from vibration signals. The diagnostic system is performed by using genetic algorithms and a classifier based on random forest, in a supervised environment. The original set of condition parameters is reduced around 66% regarding the initial size by using genetic algorithms, and still get an acceptable classification precision over 97%. The approach is tested on real vibration signals by considering several fault classes, one of them being an incipient fault, under different running conditions of load and velocity.
AB - There are growing demands for condition-based monitoring of gearboxes, and therefore new methods to improve the reliability, effectiveness, accuracy of the gear fault detection ought to be evaluated. Feature selection is still an important aspect in machine learning-based diagnosis in order to reach good performance of the diagnostic models. On the other hand, random forest classifiers are suitable models in industrial environments where large data-samples are not usually available for training such diagnostic models. The main aim of this research is to build up a robust system for the multi-class fault diagnosis in spur gears, by selecting the best set of condition parameters on time, frequency and time-frequency domains, which are extracted from vibration signals. The diagnostic system is performed by using genetic algorithms and a classifier based on random forest, in a supervised environment. The original set of condition parameters is reduced around 66% regarding the initial size by using genetic algorithms, and still get an acceptable classification precision over 97%. The approach is tested on real vibration signals by considering several fault classes, one of them being an incipient fault, under different running conditions of load and velocity.
KW - Fault diagnosis
KW - Feature selection
KW - Gearbox
KW - Genetic algorithms
KW - Random forest
KW - Wavelet packets
UR - http://www.scopus.com/inward/record.url?scp=84961051737&partnerID=8YFLogxK
U2 - 10.1016/j.ymssp.2015.08.030
DO - 10.1016/j.ymssp.2015.08.030
M3 - Article
AN - SCOPUS:84961051737
SN - 0888-3270
VL - 70-71
SP - 87
EP - 103
JO - Mechanical Systems and Signal Processing
JF - Mechanical Systems and Signal Processing
ER -