GMPSO-VMD Algorithm and Its Application to Rolling Bearing Fault Feature Extraction.

Area of Science:

• Mechanical Engineering
• Signal Processing
• Fault Diagnosis

Background:

• Rolling bearing faults present challenges due to non-stationary, nonlinear vibration signals.
• Weak fault signatures are difficult to extract using traditional methods.

Purpose of the Study:

• To develop an advanced algorithm for accurate rolling bearing fault feature extraction.
• To improve the detection of early-stage bearing failures.

Main Methods:

• Proposed a Genetic Mutation Particle Swarm Optimization Variational Mode Decomposition (GMPSO-VMD) algorithm.
• Utilized minimum envelope entropy as the objective function for optimizing VMD parameters.
• Applied GMPSO-VMD to decompose bearing vibration signals and extract fault features via envelope spectrum analysis.

Main Results:

• Accurately extracted feature frequencies for four distinct rolling bearing fault states.
• Demonstrated the effectiveness of GMPSO-VMD in analyzing simulation and real-world fault signals.
• GMPSO-VMD outperformed Fixed Parameter VMD (FP-VMD), CEEMDAN, and EMD algorithms.

Conclusions:

• GMPSO-VMD offers a robust and effective solution for rolling bearing fault diagnosis.
• The algorithm successfully addresses the challenges of weak and complex fault signals.
• This method enhances the reliability of condition monitoring for rotating machinery.