Railway fastener loosening state detection method and device and computer equipment

By combining singular value decomposition and short-time Fourier transform, vibration signals of railway fasteners are obtained, abnormal vibration periods are determined, and time-frequency analysis is performed. This solves the problem of low sensitivity in fastener loosening detection in existing technologies and achieves detection with higher sensitivity and accuracy.

CN122306390APending Publication Date: 2026-06-30SHUOHUANG RAILWAY DEV
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
SHUOHUANG RAILWAY DEV
Filing Date
2026-04-02
Publication Date
2026-06-30

AI Technical Summary

Technical Problem

In existing technologies, single spectrum analysis methods are not sensitive enough to changes in dynamic response signals caused by loosening of railway fasteners, resulting in low sensitivity in fastener loosening detection.

Method used

A method combining singular value decomposition and short-time Fourier transform is used to obtain the vibration signal of railway fasteners. The natural frequency and first damping ratio are obtained through singular value decomposition, and the time-frequency relationship is obtained through short-time Fourier transform. The abnormal vibration period is determined by combining time-frequency analysis, and the fastener is judged to be loose by comparing the instantaneous frequency and damping ratio within the abnormal vibration period.

Benefits of technology

It improves the sensitivity and accuracy of fastener loosening detection, breaks through the limitations of single analysis methods, and can more accurately reflect the actual vibration state of fasteners.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122306390A_ABST
    Figure CN122306390A_ABST
Patent Text Reader

Abstract

This application relates to a method, apparatus, and computer equipment for detecting the loose state of railway fasteners. It combines singular value decomposition and short-time Fourier transform to extract modal reference parameters and locate abnormal time periods. Furthermore, it performs refined time-frequency analysis on abnormal time periods to obtain dynamic characteristic parameters. The determination is completed by comparing the reference parameters and dynamic parameters. This method overcomes the limitations of a single analysis method, has higher sensitivity to signal changes caused by fastener loosening, improves the sensitivity of fastener loosening detection, and makes the detection results more consistent with the actual vibration state of the fastener, thereby improving the detection accuracy.
Need to check novelty before this filing date? Find Prior Art