Fan bearing fault diagnosis method and storage medium thereof

Abstract

The application provides a fan bearing fault diagnosis method and a storage medium thereof, and comprises the following steps: constructing a time domain vibration signal of a fan rolling bearing into a hypergraph signal; optimizing the hypergraph signal by using generalized dynamic graph learning; extracting a feature index set representing different states of the bearing through a dynamic hypergraph signal; applying a clustering algorithm to evaluate and classify the feature index set to achieve the purpose of feature extraction and classification of different fault bearings, so as to realize the diagnosis of the fan bearing fault; realizing the recognition and prediction of the fan bearing state, thereby providing theoretical and data support for the maintenance and repair strategy of the fan bearing, solving the technical problem that the similarity matrix constructed by the general graph is difficult to reflect the complex relationship between samples, solving the technical problem that the traditional fault feature extraction method is not accurate, efficiently extracting the fault impact signal and accurately diagnosing the fan bearing fault, and improving the reliability of the graph signal data structure.

Images