基于奇异值分解的轴承故障识别方法
By considering the characteristic frequencies and signal characteristics of typical components of the equipment in singular value decomposition, and selecting effective row vectors and singular values, the uncertainty problem in the construction of the Hankel matrix is solved, and the accurate extraction and identification of bearing fault characteristic frequencies are realized.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- SHENYANG AEROSPACE UNIVERSITY
- Filing Date
- 2025-12-31
- Publication Date
- 2026-07-17
AI Technical Summary
Existing singular value decomposition methods lack consideration for bearing characteristics when constructing the Hankel matrix, leading to uncertainty in fault identification results and loss of weak fault information, as well as poor signal denoising performance.
The number of columns in the Hankel matrix is determined based on the minimum characteristic frequencies of typical components of the equipment. Effective row vectors are selected using the periodicity, cyclic stationarity, and complexity indices of the signal, and effective singular values are determined for signal reconstruction, thereby enhancing the extraction of fault characteristic frequencies.
It achieves effective noise reduction of signals and accurate extraction of fault characteristic frequencies, thereby improving the accuracy of bearing fault identification and real-time monitoring capabilities.
Smart Images
Figure CN121958963B_ABST