Bearing Fault Diagnosis Using Support Vector Classifier Based on Sine Cosine Algorithm

In order to ensure the normal operation of rotating machinery, it is necessary and important to carry out fault diagnosis of rolling bearings. This paper proposes a fault diagnosis algorithm for rolling bearings, which is based on singular value decomposition with traditional empirical mode decomposition, and support vector classifier with sine cosine algorithm. First, empirical mode decomposition is utilized to characterize the complexity of vibration signals. Furthermore, singular value decomposition is applied to extract the fault feature. Subsequently, support vector classifier with sine cosine algorithm is proposed for fault recognition under various conditions. The performance of the proposed method has been verified by its successful application in rolling bearings experiments. Compared with the existing methods, this approach can detect bearings faults effectively, and improve the classification efficiency.