This paper presents a technique for fault diagnosis of synchronous motor. This technique used acoustic signals generated by synchronous motor. An analysis was carried out for three conditions of synchronous motor: faultless motor, motor with shorted stator coils, motor with one broken coil in stator circuit. Studies were carried out for methods of data processing: Haar Wavelet Transform and Nearest Mean classifier with Manhattan distance. Patterns creation process was carried out for 30 training samples of acoustic signals. Identification process used 72 test samples. The results of recognition were presented and discussed in the paper. The proposed approach based on computational methods is effective in detecting faults occurring in synchronous motor.
FAULT DIAGNOSTICS OF SYNCHRONOUS MOTOR BASED ON ANALYSIS OF ACOUSTIC SIGNALS WITH THE USE OF HAAR WAVELET TRANSFORM AND NEAREST MEAN CLASSIFIER
Eleonora Carletti;
2017
Abstract
This paper presents a technique for fault diagnosis of synchronous motor. This technique used acoustic signals generated by synchronous motor. An analysis was carried out for three conditions of synchronous motor: faultless motor, motor with shorted stator coils, motor with one broken coil in stator circuit. Studies were carried out for methods of data processing: Haar Wavelet Transform and Nearest Mean classifier with Manhattan distance. Patterns creation process was carried out for 30 training samples of acoustic signals. Identification process used 72 test samples. The results of recognition were presented and discussed in the paper. The proposed approach based on computational methods is effective in detecting faults occurring in synchronous motor.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
