Rolling Bearing Fault Diagnosis Method Based on SSA-ELM

In the motor and its control system fault diagnosis, the rolling bearings' fault diagnosis is particularly important. In its fault diagnosis, the main method is to classify and recognize faults by the classification of each fault type feature vector. In this paper, the sparrow search algorithm is proposed to optimize the machine learning method of extreme learning machine to classify and diagnose the rolling bearing faults of motor. Firstly, the sparrow search algorithm was used to promote the function of the extreme learning machine, and the SSA-ELM was used to accurately classify and diagnose the rolling bearing faults of the motor. Experimental results show that compared with the original ELM, the SSA-ELM can realize the classification and diagnosis of rolling bearing faults more quickly, which proves the time-based stability of the proposed model.