Bearing fault identification of three-phase induction motors bases on two current sensor strategy
- 201 Downloads
Three-phase induction motors are the most commonly used devices for electromechanical energy conversion. This study proposes an alternative approach for identifying bearing faults in induction motors, using two current sensors and a pattern classifier, based on artificial neural networks. To validate the methodology, results are given from experiments carried out on a test bench where the motors operate with different types of bearing faults, under varying conditions of load torque and voltage unbalance. This paper also provides the comparative performance of neural network and random forest classifiers. This study also presents an analysis of the current signals in the time domain, applied to different neural structures.
KeywordsThree-phase induction motor Bearing faults Artificial neural network
This study was funded by the contributions of CNPq (Process #552269/2011-5), Araucária Foundation and CAPES (CP 13/2014), CAPES-DS and Federal Technological University of Paraná for their financial support toward the development of this research.
Compliance with ethical standards
Conflict of interest
The authors declare that they have no conflict of interest.
This article does not contain any studies with human participants or animals performed by any of the authors.
- Bollen M (2000) Understanding power quality problems: voltage sags and interruptions. IEEE—TP 139-0. WileyGoogle Scholar
- Garcia-Ramirez A, Morales-Hernandez L, Osornio-Rios R, Garcia-Perez A, Romero-Troncoso R et al (2014a) Thermographic technique as a complement for mcsa in induction motor fault detection. In: International conference on electrical machines (ICEM), pp 1940–1945Google Scholar
- Godoy W, da Silva I, Goedtel A, Palácios R, Gongora W et al (2014) Neural approach for bearing fault classification in induction motors by using motor current and voltage. In: 2014 International joint conference on neural networks (IJCNN), pp 2087–2092Google Scholar
- Hollander M, Wolfe DA (1999) Nonparametric statistical methods. Wiley series in probability and statistics. Wiley, New York. http://opac.inria.fr/record=b1095753, a Wiley-Interscience publication
- Leite V, Borges da Silva J, Cintra Veloso G, Borges da Silva L, Lambert-Torres G, Bonaldi E, Lacerda De, de Oliveira L (2015) Detection of localized bearing faults in induction machines by spectral kurtosis and envelope analysis of stator current. IEEE Trans Ind Electron 62(3):1855–1865CrossRefGoogle Scholar
- Palácios RHC, Silva IN, Goedtel A, Godoy WF, Oleskovicz M (2014) A robust neural method to estimate torque in three-phase induction motor. J Control Autom Electr Syst 25(4):493–502Google Scholar
- Vakharia V, Gupta V, Kankar P (2015) A comparison of feature ranking techniques for fault diagnosis of ball bearing. Soft Comput 20(4):1601–1619Google Scholar