Mechanical part fault diagnosis method based on SVD and VMD

Abstract

The invention relates to a mechanical part fault diagnosis method based on SVD and VMD. The method comprises the following steps: acquiring a vibration signal of a mechanical part; comparing the mechanical part with a fault-free mechanical part, and judging whether abnormity exists or not; performing singular value decomposition on the vibration signal, and calculating a difference value of adjacent singular values of a singular value sequence to obtain a difference spectrum; analyzing the differential spectrum, determining a reconstruction order, and reconstructing the vibration signal of the mechanical part; decomposing the reconstructed signal into modal components, and determining the optimal number of the modal components; carrying out variational mode decomposition on the vibration signal of the mechanical part subjected to original fault diagnosis; selecting a modal component with a relatively large weighted kurtosis index value for signal synthesis; generating an envelope spectrum by using the synthesized signal; and judging the fault type of the mechanical part according to the envelope spectrum. The problem that the decomposition parameters of the variational mode decomposition method are difficult to determine is solved, the correlation between the modal components and the original signal is considered in the process of determining the optimal modal component number through variational mode decomposition of the reconstructed signal, and the determined decomposition parameters are better.

Description

technical field [0001] The invention belongs to the field of mechanical fault diagnosis, in particular to a fault diagnosis method for mechanical parts based on SVD and VMD. Background technique [0002] Once key mechanical equipment fails, it will bring huge economic losses and even casualties. Major accidents caused by mechanical equipment failures have occurred frequently at home and abroad. It is of great significance for the safe operation of equipment and the avoidance of economic losses and catastrophic accidents to find fault symptoms and take measures in time during the operation of equipment. [0003] One of the difficulties in mechanical fault diagnosis is to extract useful fault feature information from complex monitoring signals, which has attracted extensive attention in industry and academia in recent years. Variational mode decomposition (VMD) is a signal adaptive decomposition method proposed by UCLA scholars Dragomiretskiy and Zosso in 2014. As an improved...

AI Technical Summary

Problems solved by technology

However, VMD decomposition parameters such as the number of modal components and frequency bandwidth control parameters of modal components have a significant impact on its decomposition results

At present, in the field of mechanical failure, the VMD decomposition parameters are specified in advance in most studies, and it is difficult to obtain satisfactory analysis results.

Although a few scholars have proposed to use the envelope entropy as a fitness function to optimize the VMD decomposition parameters, the adopted envelope entropy only considers the characteristics of the decomposed modal components, and does not consider the correlation between the modal components and the original signal, which is easy to cause missing information problem

Images