Research on Bearing Fault Diagnosis of Submersible Pump Motor Based on LMD and SVDD

Abstract

The motor is a key component of the submersible pump. The health of the motor would greatly affect the safety and efficiency of the submersible pump. The bearing fault is one of the most common faults in motors. Therefore, detection and diagnosis of bearing faults are essential in the condition monitoring of pumps. In this paper, the local average decomposition (LMD) method is used to analyze the bearing vibration signals of submersible pump motor and extract feature vectors. A fault diagnostic model is established by the support vector data description (SVDD) to determine whether the submersible pump motor is faulty. The developed model exhibits practical significance in condition monitoring of submersible pump motor bearings.