Properties on Bearing Fault Diagnosis of Water Injection Motor

Abstract

Water injection motor in western Daqing Oilfield is the key equipment of water injection to the oil field. Due to the great pressure of water injection to the oil field, the water injection motor is often overloaded and runs at high speed, so that the rolling bearing of the motor is worn, deformed and other faults. In order to detect the small faults that are not easy to detect in the early stage of the motor bearing, this paper proposes a method combining variational mode decomposition (VMD) and fast spectral kurtosis. The optimal number of modes is determined by correlation and energy ratio. The fast spectral kurtosis operation is carried out on the modes with large kurtosis. The fault signal is enveloped and decomposed by the optimal filter parameters. The experimental results show that the algorithm can successfully identify the rolling bearing fault of water injection motor and determine the fault location.