An intelligent bearing fault diagnosis based on hybrid signal processing and Henry gas solubility optimization

Bearing is regarded as one of the core elements in rotating machines and its fault diagnosis is essential for better reliability and availability of the rotating machines. This paper puts forward an intelligent vibration signal-based fault diagnosis approach for bearing faults identification at an early stage, irrespective of speed conditions. The proposed methodology comprises of a frequency shift-based hybrid signal processing technique that involves a combination of Hilbert Transform (HT) and Discrete Wavelet Transform (DWT) followed by sliding window-based feature extraction. Thereafter, a newly developed Henry Gas Solubility Optimization (HGSO) is implemented to select the relevant features. At last, the optimal attributes are used to train the Artificial Neural Network (ANN) model for the classification of the different bearing faults. To test the effectiveness of the speed independent model, experimental validation was done with constant and varying speed conditions. The results demonstrate that the proposed methodology has a tremendous potential to eliminate unplanned failures caused by bearing in rotating machinery.

Automated summary

This paper proposes an intelligent vibration signal-based fault diagnosis approach for early identification of bearing faults, regardless of speed conditions. The approach combines frequency shift-based hybrid signal processing technique, sliding window-based feature extraction, and Henry Gas Solubility Optimization algorithm for feature selection, followed by Artificial Neural Network model training for fault classification. Experimental validation under constant and varying speed conditions demonstrates the tremendous potential of this approach in eliminating unplanned failures caused by bearing in rotating machinery.