×
The submission system is temporarily under maintenance. Please send your manuscripts to
Go to Editorial ManagerBearing fault diagnosis is essential for the maintenance, durability, and reliability of rotating machines. It can minimize economic losses by removing unplanned downtime in the industry due to the failure of rotary machines. In bearing fault detection, developing fault features extraction techniques that can successfully applicable for various fault severity and different operating conditions is still a critical issue. In the current work, the feature extraction technique is a combination between pre-processing algorithms and envelope analysis method. In the pre- processing stage, the autoregressive (AR) model is used to filter the original signal and remove the deterministic vibration sources, as well as maintain the signal representing the condition of the bearing without contaminating noises. Then, the most suitable frequency band is selected based on the spectral kurtosis (SK) analysis. This band contains the signature frequencies of the roller bearing. After that, envelope analysis is employed for detecting faults at different severity. Finally, the features represented the peaks at fundamental fault frequencies are automatically selected from the envelope spectrum. By analyzing all diagnoses results, it is found that the presented method effectively extracts the features at calculated resonance bearing frequencies and proves the significance of the enhancements in a pre-filtering stage in the overall detection performance. Also, it can benefit from these features in the fault classification fields at different speeds because it is independent of speed variation.
Diagnosing faults in rotary machines is critical, as early fault detection is a precise and essential task in minimizing operational risks and economic losses. Bearings are vital components in rotary machines and are subject to gradual degradation due to continuous operation. Failure to detect early damage can lead to problem escalation, resulting in severe damage and increased costs. In this study, two types of signals from rotary machines are analyzed: acoustic emission (AE) signals and vibration signals. These signals are utilized as input features for a deep learning neural network based on images, where the features are extracted using the Kurtogram, a powerful fourth-order spectral analysis tool that generalizes spectral kurtosis (SK) for a given signal. The results demonstrate that the accuracy of diagnosing the machine’s operational condition whether healthy or faulty ranges from 99.2% to 100%, while the accuracy of fault classification reaches 96.6%. These findings highlight the high efficiency of this methodology in fault detection and classification, establishing it as one of the most important techniques for diagnosing faults in rotary machines.