Survey of the methods for online broken bar induction motor fault detection
2010
Matic, D., Faculty of Technical Sciences, Novi Sad (Serbia) | Kulic, F., Faculty of Technical Sciences, Novi Sad (Serbia) | Bugarski, V., Faculty of Technical Sciences, Novi Sad (Serbia)
The paper deals with the survey of some know online methods for broken rotor bar (BB) detection within induction motors and provides an overview of the method for fault detection via the radial basis function (RBF) artificial neural network (ANN). The condition monitoring of electric machinery can significantly reduce tha cost of maintenance and the risk of unexpected failures by allowing the early detection of potentially catastrophic faults. The rotor faults account for 10% of overall induction motor faults. As classification features, the characteristic sidebands values extracted from line current spectrum are taken. Based on the chosen features, it is possible to classify induction motors in one of the two following groups: correct or BB fault in online working mode. If broken bar occurs, the proposed models give the estimation of the number of broken rotor bars. A motor must be connected to the mains for the direct online start at nominal load; there is no possibility for a multi-fault detection mode.
Afficher plus [+] Moins [-]Mots clés AGROVOC
Informations bibliographiques
Cette notice bibliographique a été fournie par Matica Srpska Library
Découvrez la collection de ce fournisseur de données dans AGRIS