Rolling Bearing Fault Diagnosis Method Based on DBO-VMD-TCN

In response to the complex working environment of rolling bearings and the issue of low fault identification due to noise interference in vibration signals, a rolling bearing fault diagnosis method based on DBO-VMD-TCN is proposed. Firstly, the parameters of VMD are optimized using DBO to decompose into k Intrinsic Mode Functions (IMFs). Secondly, the IMFs that contain rich fault information are selected through evaluation indicators, and nine features including mean, variance, peak value, kurtosis, effective value, peak factor, impulse factor, waveform factor, and margin factor are calculated. Finally, the TCN model processes these attributes for training and forecasting, culminating in a precise fault diagnosis rate. Employing vibration signals from the Case Western Reserve University's rolling bearings, the method's effectiveness is confirmed. It adeptly captures fault-related traits and accurately pinpoints the bearings' fault status. The results underscore the method's high diagnostic precision and its substantial potential for practical implementation.