Title :
Classification of induction machine faults by K-nearest neighbor
Author :
Bouguerne, Abla ; Lebaroud, Abdesselam ; Medoued, Ammar ; Boukadoum, Ahcene
Author_Institution :
Electr. Eng. Dept., Univ. Mentouri Constantine, Constantine, Algeria
Abstract :
New diagnosis method of induction motor faults based on classification of the current waveforms is presented in this paper. This method is composed of two sequential processes: a feature extraction and a rule decision. The diagnosis is realized the detection of different faults - bearing fault, stator fault and rotor fault. K-nearest neighbor (K-NN) is used as decision criterion. The flexibility of this method allows an accurate classification independent from the level of load. This method is validated on a 5.5-kW induction motor test bench.
Keywords :
asynchronous machines; decision theory; fault diagnosis; K-nearest neighbor; bearing fault; current waveform classification; decision criterion; fault detection; fault diagnosis method; feature extraction; induction machine faults classification; induction motor faults; power 5.5 kW; rotor fault; rule decision; sequential processes; stator fault; Euclidean distance; Feature extraction; Gravity; Kernel; Stators; Support vector machine classification; Vectors;
Conference_Titel :
Electrical and Electronics Engineering (ELECO), 2011 7th International Conference on
Conference_Location :
Bursa
Print_ISBN :
978-1-4673-0160-2
