A multi-source domain approximation fault diagnosis method combining real data and mechanism data for fluctuating speed working conditions

By integrating mechanistic models with real data into a multi-source domain approximation fault diagnosis method, the problems of recognition rate and robustness in fault diagnosis under bearing speed fluctuations are solved, and high-precision bearing fault identification is achieved.

CN120257056BActive Publication Date: 2026-06-23CHINA UNIV OF MINING & TECH
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
CHINA UNIV OF MINING & TECH
Filing Date
2025-04-01
Publication Date
2026-06-23

AI Technical Summary

Technical Problem

Traditional fault diagnosis models that rely on training in a single data domain show a decrease in recognition rate and insufficient robustness under bearing speed fluctuation conditions, making it difficult to effectively diagnose bearing faults.

Method used

A multi-source domain approximation fault diagnosis method based on Vision-Transformer is adopted. By fusing bearing mechanism model data with real data of large-fluctuation speed conditions, a dynamic multi-source domain migration strategy is designed. Distance metric is used to iteratively approximate the differences between domains, and the label space is aligned by combining minimum class confusion loss for feature extraction and classification.

Benefits of technology

It significantly improves the accuracy of cross-domain fault diagnosis, enhances the identification rate and robustness of bearing faults, and enables effective diagnosis of bearing faults under speed fluctuations.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN120257056B_ABST
    Figure CN120257056B_ABST
Patent Text Reader

Abstract

A multi-source domain approximation fault diagnosis method for fluctuating speed operation conditions combines real data and mechanism data, mainly by fusing bearing mechanism model data and real data under large fluctuating speed operation conditions, designing a dynamic multi-source domain migration strategy, using distance measurement distance iterative approximation of the maximum difference between domains, and combining minimum class confusion loss to realize label space alignment. The method solves the feature drift caused by speed fluctuation and the problem of insufficient labeled data, significantly improves the cross-domain fault diagnosis accuracy, improves the recognition rate and robustness of bearing fault, and realizes effective diagnosis of bearing fault under fluctuating speed.
Need to check novelty before this filing date? Find Prior Art