Rolling bearing fault diagnosis method based on SE-ResNeXt and Informer hybrid network model

By combining SE-ResNeXt and Informer network models, the problem of poor feature extraction and classification effects of traditional fault diagnosis methods under complex operating conditions is solved, and high-precision and robust rolling bearing fault diagnosis is achieved, which significantly improves the accuracy of fault pattern recognition.

CN119740011AActive Publication Date: 2025-04-01HEBEI BAISHA TOBACCO
5 Cites 9 Cited by

Patent Information

Application Number
CN202510227526.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-02-27
Publication Date
2025-04-01
Estimated Expiration
2045-02-27

AI Technical Summary

Technical Problem

Traditional rolling bearing fault diagnosis methods are difficult to cope with complex working conditions and non-stationary signals, feature extraction and classification effects are limited, and deep learning models have shortcomings in local feature extraction and global dependency modeling.

Method used

The rolling bearing fault diagnosis method based on the hybrid network model of SE-ResNeXt and Informer is adopted. Time series data is processed through the SE-ResNeXt network structure, multi-branch features are fused, and the global timing dependency is captured by combining the sparse attention mechanism of Informer.

Benefits of technology

It significantly improves the accuracy and robustness of rolling bearing fault category prediction, can effectively extract spatial and timing characteristics in vibration signals, reduce calculation complexity, improve the accuracy of fault diagnosis, and avoid overfitting.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention discloses a rolling bearing fault diagnosis method based on an SE-ResNeXt and Informer hybrid network model, and relates to the field of industrial process control, spatial features of time series data are extracted through a plurality of convolution modules in the SE-ResNeXt, an SE module is added for adaptively adjusting the response intensity of each channel, and a fault diagnosis result is obtained. The design of a residual network is combined, so that the feature extraction process is more efficient, and fault diagnosis analysis is performed through an Informer model. In the training process of the model, cross entropy is adopted as a loss function, and optimization is carried out through an Adam optimizer, so that the prediction accuracy and stability are improved. Experimental results show that the method shows excellent fault diagnosis capability on a public data set CWRU, has good robustness and prediction precision, is significantly superior to a traditional deep learning model, and provides a new thought for state monitoring and fault prediction under complex working conditions.
Need to check novelty before this filing date? Find Prior Art