A study on rolling bearing fault diagnosis using RIME-VMD

Area of Science:

• Engineering
• Mechanical Engineering
• Signal Processing

Background:

• Variational Mode Decomposition (VMD) faces challenges in feature extraction for rolling bearing fault diagnosis.
• Accurate fault identification is crucial for predictive maintenance and operational safety.

Purpose of the Study:

• To propose an optimized feature extraction method for rolling bearing fault diagnosis using the RIME algorithm with VMD.
• To enhance the efficiency and robustness of fault detection and identification.

Main Methods:

• The RIME algorithm optimizes VMD parameters (decomposition components, penalty factors).
• Intrinsic Mode Functions (IMFs) are decomposed, and kurtosis is used for component selection.
• Reconstruction and sample entropy calculation are performed for fault feature extraction.
• Support Vector Machine (SVM) is used for fault classification.

Main Results:

• RIME-VMD demonstrated shorter search times and higher search efficiency compared to WOA-VMD.
• The method achieved faster identification of decomposition parameters under various fault conditions.
• Enhanced robustness in fault signal detection and rapid, efficient rolling bearing fault identification were observed.

Conclusions:

• The proposed RIME-VMD method offers a significant improvement in rolling bearing fault diagnosis.
• This approach provides a valuable reference for future research in fault diagnosis techniques.
• Optimized VMD using RIME enhances the speed and accuracy of fault identification.