Variable parameter information fusing method for variation modal decomposition

Abstract

The invention relates to a variable parameter information fusing method for variation modal decomposition. The variable parameter information fusing method comprises the following steps: setting a decomposition modal number K=1, setting a bandwidth balance parameter a, carrying out VMD (Variable Modal Decomposition) processing on an analysis signal so as to obtain an IMF component, and subtractingthe IMF component from an original signal so as to obtain rest components; by taking the rest components as an analysis signal, repeating the steps for n times so as to obtain n IMF components and nrest components; according to a provided optimization index method, selecting components with the most fault information from 2n components, that is, a fault modal component; changing the value of a,repeating the steps for N times, thereby obtaining N fault modal components with different bandwidths. By adopting the variable parameter information fusing method for variation modal decomposition, information fusion is carried out on multi-dimensional fault modal components obtained through VMD processing of variable parameters through manifold learning, and fault transient-state components withhigh signal to noise ratios are obtained.

Description

technical field [0001] The invention relates to fault diagnosis of rotating machinery, in particular to a variable parameter information fusion method of variational mode decomposition. Background technique [0002] Rotating mechanical equipment is developing towards large-scale, precision and automation, which puts forward stricter requirements for the manufacture, installation and daily maintenance of each component in the entire equipment system. A slight damage or vibration of any component Misalignment may affect the normal operation of the entire system and even cause major accidents. Rolling bearings play a key role in rotating machinery, and their health status will affect the working status of the entire mechanical system, so the monitoring and diagnosis of rolling bearings is of great significance. When a bearing component fails, it will generate a periodic transient impulse response. Faults at different locations will show different fault characteristic periods. ...

AI Technical Summary

Problems solved by technology

[0007] Based on this, it is necessary to address the above technical problems and provide a variable parameter information fusion method based on variational mode decomposition. This method aims at the problem of difficult elimination of in-band noise and low computational efficiency in the VMD method based on parameter optimization. The learning method performs information fusion of multiple IMFs containing fault information under different parameters, and extracts the internal manifold structure of fault transient components, so that there is no need to search for optimal parameters, improve operating efficiency, and eliminate in-band noise, which can effectively detect The transient characteristic components in the outgoing signal

Images