Vibration Signal Noise-Reduction Method of Slewing Bearings Based on the Hybrid Reinforcement Chameleon Swarm...

Area of Science:

• Mechanical Engineering
• Signal Processing
• Artificial Intelligence

Background:

• Slewing bearing vibration analysis is crucial for fault detection.
• Existing noise reduction methods often struggle with complex signal interference.
• Effective signal denoising is vital for accurate machinery diagnostics.

Purpose of the Study:

• To develop an advanced noise-reduction model for slewing bearing vibration signals.
• To improve the accuracy and efficiency of fault detection in slewing bearings.
• To introduce a novel optimization algorithm for signal processing applications.

Main Methods:

• Developed Hybrid Reinforcement Chameleon Swarm Algorithm (HRCSA) by integrating Chaotic Reverse Learning, Whale Optimization Algorithm, and Cauchy mutation.
• Optimized Variational Mode Decomposition (VMD) using HRCSA to extract Intrinsic Mode Functions (IMFs).
• Applied Wavelet Threshold (WT) denoising to noisy IMFs and reconstructed the signal.

Main Results:

• HRCSA demonstrated superior convergence speed and precision compared to PSO, WOA, and GWO.
• HRCSA-VMD-WT achieved a minimum 74.9% increase in Signal-to-Noise Ratio (SNR).
• HRCSA-VMD-WT resulted in at least a 41.2% reduction in Root Mean Square Error (RMSE).

Conclusions:

• The HRCSA-VMD-WT model offers significant noise reduction for slewing bearing vibration signals.
• This approach enhances fault detection accuracy and diagnostic efficiency.
• The study provides a reliable and effective solution for slewing bearing maintenance.