Mechanical equipment fault feature extraction method based on adaptive integrated multi-wavelets
A technology of fault characteristics and mechanical equipment, applied in computer parts, vibration measurement in solids, special data processing applications, etc. The effect of improving properties and reducing economic losses
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Publication Date
- 2018-02-16
- Estimated Expiration
- Not applicable · inactive patent
Smart Images

Figure 1 
Figure 2 
Figure 3
Abstract
Description
technical field
[0001] The invention relates to the technical field of equipment fault monitoring, in particular to a mechanical equipment fault feature extraction method based on self-adaptive integrated multi-wavelet. Background technique
[0002] Large-scale mechanical equipment has many components, and the signal transmission path is complex. The signal collected by the sensor is a comprehensive reflection of the response of each component. When its components fail early, the fault characteristics are very weak, and it is affected by the noise of the equipment itself, non-stationary The influence of operating status and interference in the signal acquisition process makes fault feature extraction a major difficulty. A series of new signal analysis theories and techniques have appeared for the processing of non-stationary signals, among which, the most widely used and active dynamic signal analysis method is the wavelet analysis theory and technique. Wavelet transform ha...
Examples
Embodiment Construction
[0037] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in combination with specific examples and with reference to the accompanying drawings.
[0038] Multiwavelet is a powerful tool for extracting weak features of mechanical faults. Its physical essence is to search for components that are most similar or most relevant to the "basis function" in the signal. However, different fault types and transmission paths make the fault characteristic waveforms not fixed. The fixed multi-wavelet basis function obviously cannot achieve the best match with the weak features of mechanical faults, which limits the ability of multi-wavelets in the application of mechanical fault feature extraction. Engineering practice shows that the fault waveforms of bearings and gears are basically unilateral attenuation waveforms. On the basis of in-depth research on the two-scale similarity tra...