A rotor bearing system fault diagnosis method based on FSASCA-VMD and GraphSAGE-SA

Abstract

Abstract In complex environments, signals from rotor bearing systems can easily be drowned out by strong noise, leading to low fault diagnosis accuracy. In order to reduce noise and improve diagnostic accuracy, this paper proposes a rotor bearing system fault diagnosis method based on FSASCA-VMD (Future Search Algorithm based on Sine Cosine Algorithm-Variational Mode Decomposition) and GraphSAGE-SA (Graph SAmple and aggreGatE-Self Attention). First, the FSASCA optimization algorithm is used to determine two parameters in VMD. The best combination found is then input into VMD to decompose the original signal. Then, filter the IMF (Intrinsic Mode Function) components with high correlation to the original signal using cumulative percentage kurtosis. Reconstruct the filtered IMF components to complete signal denoising. Finally, this paper utilizes graph theory and time series correlation to uncover the hidden relationships within the data. Utilizing the Euclidean distance as the edge weight between nodes, a graph model is established based on the topological structure of the PathGraph, and a GraphSAGE-SA fault diagnosis framework is constructed. Utilizing a self-attention mechanism to aggregate nodes enhances the weight allocation of important information. The experimental results indicate that the method proposed in this paper can effectively remove most of the noise in the signal while preserving a significant amount of useful information. In rotor bearing system fault diagnosis, the diagnostic accuracies of this method for simulated and laboratory signals are 98.33% and 98.56%, respectively, surpassing those of other methods.