Research on Vibration Fault Diagnosis Technology of Steam Turbine Unit in Power Plant Based on Wavelet Theory

Abstract

Aiming at the frequency spectrum characteristics of the vibration of steam turbine generator sets, a fault diagnosis method of steam turbine rotor vibration based on wavelet packet transform is proposed, which can better reflect the spectral components and energy contained in vibration signals than general wavelet transform. Experimental analysis shows that the fault feature extraction method based on wavelet packet analysis and signal energy decomposition can obtain the fault status of steam turbine rotor vibration; according to the frequency spectrum characteristics of different faults, different faults can be identified, so as to perform steam turbine rotor vibration fault diagnosis. This method is more effective than the fault feature extraction method based on Fourier transform and is suitable for mechanical fault diagnosis.