Bearing Fault Diagnosis Based on Optimized Deep Hybrid Kernel Extreme Learning Machine

Bearings are important components in mechanical equipment. Fault diagnosis of bearings is of great significance. High accuracy and strong adaptability are necessary for a bearing fault diagnosis method. In this paper, a fault diagnosis method based on an optimized deep hybrid kernel extreme learning machine is proposed. This method adds the idea of deep learning to the traditional machine learning method, and has the characteristics of simple implementation and strong feature extraction ability. In addition, the sparrow search optimization algorithm is used to optimize the parameters of the diagnostic model, so that the model can achieve the best effectiveness. Experiments show that our proposed method can achieve satisfying performance on the same working condition, different working conditions and imbalanced datasets.