Vibration signal characteristic value selection method and elevator health state evaluation or fault diagnosis method
A vibration signal and eigenvalue technology, which is applied in the field of vibration signal eigenvalue selection, elevator health status evaluation or fault diagnosis, can solve problems such as the recursive process is too long, affects, and affects the accuracy of the diagnosis model of mechanical equipment operation status
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0083] Such as figure 2 As shown, the vibration signal eigenvalue selection method includes the following steps:
[0084] 1. The operating state of mechanical equipment includes one normal state and m-1 abnormal states, where m is an integer greater than 1;
[0085] Perform preprocessing on the original vibration signal, so that there are n vibration signal data in each mechanical equipment operating state, and delete the redundant original vibration signal, where n is an integer greater than 1;
[0086] 2. Perform signal processing on each group of preprocessed vibration signal data, and extract b types of eigenvalues, b is an integer greater than 2; m×n groups of preprocessed vibration signal data are extracted to obtain m×n×b eigenvalues ;
[0087] 3. Constructing an eigenvalue matrix X and a mechanical equipment state label vector Y by the m×n×b eigenvalues;
[0088] The eigenvalue matrix X has m×n rows and b columns;
[0089] Mechanical equipment state label vector Y...
Embodiment 2
[0118] Based on the vibration signal eigenvalue selection method of Embodiment 1, in step 5, the comprehensive distance correlation coefficient of each time domain eigenvalue is by calculating the distance correlation between this kind of time domain eigenvalue and other p-1 kinds of time domain eigenvalues The sum of the coefficients, divided by p-1;
[0119] The comprehensive distance correlation coefficient of each frequency domain eigenvalue is calculated by calculating the sum of the distance correlation coefficients between this frequency domain eigenvalue and other q-1 frequency domain eigenvalues, and then dividing by q-1;
[0120] The comprehensive distance correlation coefficient of each time-frequency domain eigenvalue is calculated by calculating the sum of the distance correlation coefficients between this time-frequency domain eigenvalue and other r-1 time-frequency domain eigenvalues, and then dividing by r-1;
[0121]
[0122] SdCor(Ax) is the comprehensive ...
Embodiment 3
[0124] Based on the vibration signal eigenvalue selection method of Embodiment 1, in step 5, the time domain, frequency domain, and time-frequency domain eigenvalue correlation analysis are carried out, and the eigenvalues are subjected to a second rough screening, which is based on the calculated time domain, frequency Domain and time-frequency domain eigenvalue comprehensive distance correlation coefficient, according to the set ratio, delete some eigenvalues with larger comprehensive distance correlation coefficients in time domain, frequency domain and time-frequency domain, and get the second time after eigenvalue correlation analysis Time-domain eigenvalues, frequency-domain eigenvalues and frequency-domain eigenvalues after coarse screening.
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com