Title :
Unsupervised Neural-Network-Based Algorithm for an On-Line Diagnosis of Three-Phase Induction Motor Stator Fault
Author :
Martins, J.F. ; Pires, V.F. ; Pires, A.J.
Author_Institution :
Escola Superior Tecnologia de Setubal, Instituto Politecnico de Setubal
Abstract :
In this paper, an automatic algorithm based an unsupervised neural network for an on-line diagnostics of three-phase induction motor stator fault is presented. This algorithm uses the alfa-beta stator currents as input variables. Then, a fully automatic unsupervised method is applied in which a Hebbian-based unsupervised neural network is used to extract the principal components of the stator current data. These main directions are used to decide where the fault occurs and a relationship between the current components is calculated to verify the severity of the fault. One of the characteristics of this method, given its unsupervised nature, is that it does not need a prior identification of the system. The proposed methodology has been experimentally tested on a 1kW induction motor. The obtained experimental results show the effectiveness of the proposed method
Keywords :
Hebbian learning; electric machine analysis computing; fault diagnosis; induction motors; machine testing; neural nets; principal component analysis; unsupervised learning; 1 kW; Hebbian learning; alfa-beta stator currents; fault diagnosis; on-line diagnosis; principal component method; three-phase induction motor stator fault; unsupervised learning; unsupervised neural-network-based algorithm; Condition monitoring; Fault detection; Fault diagnosis; Frequency; Induction motors; Industrial training; Neural networks; Stator windings; Temperature sensors; Vibrations; Fault diagnosis; Hebbian learning; induction motors; neural networks; unsupervised learning;
Journal_Title :
Industrial Electronics, IEEE Transactions on
DOI :
10.1109/TIE.2006.888790
