Amplitude envelope analysis for feature extraction of power plant blower bearing failure

Bearing vibrations of a power plant blower have random characteristics with stark noise, which make it difficult for fault feature extraction both by using vibration effective data of monitoring system and vibration analysis function of a portable measuring instrument. Made use of the vibration signals which were measured from a normal blower and a fault one, the vibration characteristics of fault impeller rotor support bearing were analyzed and studied. From time domain, frequency domain and cepstrum domain, the vibration signal characteristics were analyzed and compared between normal and fault units. Then narrowband envelope analysis had been made. The difference of envelope spectrum for vibration signals between normal and fault units was revealed. The results show that narrowband envelope analysis can effectively identify the bearing fault state.