Rolling Bearing Fault Diagnosis Based on Support Vector Machine Optimized by Improved Grey Wolf Algorithm.

Area of Science:

• Mechanical Engineering
• Artificial Intelligence
• Signal Processing

Background:

• Rolling bearing fault diagnosis is crucial for machinery health.
• Existing Support Vector Machine (SVM) methods suffer from low accuracy and efficiency.
• Optimization algorithms are needed to improve SVM performance in fault diagnosis.

Purpose of the Study:

• To propose an Improved Grey Wolf Optimizer (IGWO) algorithm for optimizing Support Vector Machine (SVM) parameters.
• To enhance the accuracy and efficiency of rolling bearing fault diagnosis.
• To introduce novel strategies for nonlinear contraction factor and dynamic weight updates.

Main Methods:

• Developed an Improved Grey Wolf Optimizer (IGWO) integrating deep learning and swarm intelligence.
• Implemented a nonlinear contraction factor update strategy for balanced search capabilities.
• Utilized a dynamic weight update strategy for adaptive position updates.
• Validated the IGWO-SVM model using Case Western Reserve University dataset and a custom mechanical transmission bearing test platform.

Main Results:

• The IGWO-SVM model achieved a diagnosis accuracy of 98.75% on the Case Western Reserve University dataset.
• Comparative analysis showed IGWO-SVM outperformed PSO-SVM and GWO-SVM in fault diagnosis accuracy and convergence.
• The proposed model demonstrated superior performance on a full-life-cycle mechanical transmission bearing test platform.

Conclusions:

• The IGWO-SVM model significantly improves rolling bearing fault diagnosis accuracy and efficiency.
• The nonlinear contraction factor and dynamic weight update strategies enhance optimization convergence.
• This approach offers a robust solution for intelligent fault diagnosis in mechanical systems.