Railway wagon bearing fault diagnosis method based on improved sparrow search algorithm optimizing variational mode...

Area of Science:

• Railway engineering
• Mechanical fault diagnosis
• Computational intelligence

Background:

• Precise bearing condition monitoring is crucial for safe train operation.
• Traditional maintenance methods for railway wagon bearings lack real-time precision and efficiency.
• A need exists for advanced, data-driven approaches to mechanical equipment diagnostics.

Purpose of the Study:

• To enhance the sparrow search algorithm (SSA) with logistic chaos mapping and levy flight strategy.
• To optimize variational mode decomposition (VMD) parameters for improved bearing fault diagnosis.
• To develop a robust fault diagnostic methodology for railway wagon bearings.

Main Methods:

• Incorporation of logistic chaos mapping and levy flight into the SSA.
• Optimization of VMD parameters using average dispersion entropy of intrinsic mode components as the fitness function.
• Integration of the optimized VMD with a multi-level convolutional neural network (CNN) for fault diagnosis.

Main Results:

• The enhanced SSA demonstrated improved spatial search capabilities and reduced modal aliasing.
• The multi-level CNN achieved higher diagnostic accuracy and faster convergence speeds compared to traditional models (LeNet-5, AlexNet).
• Experimental validation on public datasets and a dedicated platform confirmed the methodology's effectiveness.

Conclusions:

• The proposed method offers a highly accurate and efficient solution for railway wagon bearing fault diagnosis.
• This approach aligns with the requirements of the "smart" era for intelligent mechanical equipment monitoring.
• The research provides a valuable tool for enhancing the safety and reliability of railway transport.