A method, apparatus, computer component, and computer program product for monitoring the health status of rotating machinery.

CN122133002APending Publication Date: 2026-06-02EAST CHINA UNIV OF SCI & TECH +1

Patent Information

Authority / Receiving Office: CN · China
Patent Type: Applications(China)
Current Assignee / Owner: EAST CHINA UNIV OF SCI & TECH
Filing Date: 2026-04-30
Publication Date: 2026-06-02

AI Technical Summary

Technical Problem

Existing technologies suffer from information redundancy and contradiction in multi-channel signal monitoring, resulting in low accuracy in the construction of health indicators and difficulty in effectively integrating multi-source heterogeneous information, which affects the accuracy and reliability of equipment health status monitoring.

Method used

A graph fusion model and graph Fourier transform are used to extract the graph frequency domain features of multi-channel vibration signals. The signal coherence between adjacent channels is used as the fusion weight, and the importance weight of the frequency domain features is calculated by the random forest method. The health status is classified by combining the 3σ principle and the Mann-Kendall trend test.

Benefits of technology

It enables efficient extraction of core feature information from multi-channel signals, constructs a health index that is sensitive to and robust to equipment degradation trends, and improves the accuracy and stability of health status monitoring of rotating machinery.

✦ Generated by Eureka AI based on patent content.

Smart Images

Figure CN122133002A_ABST

Patent Text Reader

Abstract

This application discloses a method, device, computer component, and computer program product for monitoring the health status of rotating machinery, relating to the field of machinery condition monitoring and fault diagnosis. The method includes acquiring multi-channel vibration signals; constructing a graph fusion model and extracting multi-channel graph frequency domain feature matrices through graph Fourier transform; obtaining a channel fusion spectrum by weighting the coherence of adjacent channel signals as a fusion feature; calculating the importance weight of each frequency domain feature using a random forest method, and weighted fusion to obtain a health index; and classifying the health status based on this index, combined with the 3σ principle and the Mann-Kendall trend test. This application effectively solves the problems of redundancy and contradiction in multi-channel signal information through graph modeling and feature fusion, constructs a health index sensitive to equipment degradation, and achieves accurate status classification by combining statistical tests, significantly improving the accuracy and reliability of monitoring.

Need to check novelty before this filing date? Find Prior Art