Bearing Fault Diagnosis Based on Multiscale Sample Entropy and Improved Support Vector Machine

Abstract:
Bearings are widely used in port equipment, and their vibration signals are nonlinear and non-stationary, which makes it difficult to extract fault features and low accuracy of fault diagnosis. To solve the above problems, this paper proposes a bearing fault diagnosis method based on multi-scale sample entropy and improved support vector machine (SVM). Firstly, the multi-scale sample entropy is used to extract the fault characteristics and form the feature vector set. Then, the feature vector set is divided into test set training set, and the SVM is optimized by grey wolf algorithm to obtain the penalty coefficient and kernel parameter. Finally, the improved SVM is used as the pattern recognition algorithm for fault pattern recognition. The experimental results show that the proposed method can effectively carry out fault diagnosis, and the recognition accuracy rate reaches 97.14 %, which is better than the comparison method and is suitable for bearing fault diagnosis.