Abstract
This article discusses a system of recognition of acoustic signals of
loaded synchronous motor. This software can recognize various types of
incipient failures by means of analysis of the acoustic signals. Proposed
approach uses the acoustic signals generated by loaded synchronous motor.
A plan of study of the acoustic signals of loaded synchronous motor is
proposed. Studies include following states: healthy loaded synchronous
motor, loaded synchronous motor with shorted stator coil, loaded
synchronous motor with shorted stator coil and broken coil, loaded
synchronous motor with shorted stator coil and two broken coils. The
methods such as FFT, method of selection of amplitudes of frequencies
(MSAF-5), Linear Support Vector Machine were used to identify specific
state of the motor. The proposed approach can keep high recognition rate
and reduce the maintenance cost of synchronous motors.
Go to article