Mechanical Fault Diagnosis Method Based on mpga Parametric Resonance Sparse Decomposition

Abstract

The invention discloses a mechanical fault diagnosis method based on MPGA parameterized resonance sparse decomposition, which is used to improve the accuracy of mechanical bearing fault feature extraction and fault type identification. The present invention constructs the wavelet basis function library according to the characteristics of the bearing fault vibration signal, integrates the optimization algorithm into the resonance sparse decomposition method, and adaptively obtains the parameters that best match the fault vibration signal through the optimization algorithm in the resonance sparse decomposition, and utilizes the obtained The resonance sparse decomposition of the vibration signal is carried out according to the parameters, and then the obtained low resonance components are subjected to envelope analysis, so as to realize the accurate extraction of bearing fault features. The invention is suitable for fault diagnosis of rolling bearings.

Description

technical field [0001] The invention relates to the field of mechanical fault diagnosis, in particular to a mechanical fault diagnosis method based on MPGA parameterized resonance sparse decomposition. Background technique [0002] Mechanical equipment mainly realizes power transmission through the transmission mechanism, and rolling bearings, as an important part of the transmission mechanism, play a vital role in the operation of the equipment. Therefore, effective fault diagnosis and monitoring of rolling bearings are crucial to ensuring the safe operation of mechanical equipment has far-reaching significance. However, in the early stage of rolling bearing failure, the fault features are relatively weak and are easily covered by the normal vibration and noise of other components. Therefore, the extraction of bearing fault feature information has become a difficult task. [0003] Resonance sparse decomposition is based on the resonance properties of the vibration signal, ...

AI Technical Summary

Problems solved by technology

[0004] At present, the determination of the quality factor in the resonance sparse decomposition is mainly determined by manual determination or by using a conventional genetic algorithm. The accuracy of the extraction of mechanical fault characteristics determined by such a determined quality factor is poor, and it is increasingly difficult to meet today's production requirements.

Images