A Bearing Fault Diagnosis Method Based on Multi-island Genetics and Variational Mode Decomposition

Abstract

The present invention provides a bearing fault diagnosis method based on multi-island genetics and variational mode decomposition, which comprises the following steps: collecting vibration signals of rolling bearings, and using the variational mode decomposition method optimized by multi-island genetic algorithm to analyze the vibration signals of rolling bearings Decompose to obtain the eigenmode components; calculate the sensitive parameter SP of each modal component, and select the two eigenmode components with the largest value of the sensitive parameter SP for reconstruction, and demodulate the reconstructed signal to obtain the envelope spectrum ; The minimum entropy convolution MOMEDA algorithm is used to enhance the signal of the envelope spectrum, and the enhanced envelope spectrum is obtained; according to the enhanced envelope spectrum, the frequency characteristics of the rolling bearing fault are identified, and the rolling bearing fault diagnosis is carried out. The invention can effectively separate the fault information of the bearing signal from the noise information, suppress the influence of the noise on the extraction accuracy of the rolling bearing fault feature, and greatly improve the extraction accuracy of the rolling bearing fault feature.

Description

technical field [0001] The invention relates to the technical field of rolling bearing detection, in particular to a bearing fault diagnosis method based on multi-island inheritance and variational modal decomposition. Background technique [0002] As one of the most commonly used and important components in rotating machinery, rolling bearings are directly related to the safe operation of equipment systems. In practical engineering applications, it is more expected to effectively check the early fault in the stage of failure, and to judge the damaged part of the bearing in the early stage of failure, so as to provide maintenance decision-making reference for on-site staff. In the early stage of failure, rolling bearings often have the characteristics of weak impact components and large noise interference from the surrounding environment. [0003] Therefore, there is a need for a method that can effectively identify different types of failures of equipment such as bearings ...

AI Technical Summary

Problems solved by technology

Rolling bearings in the early failure stage often have the characteristics of weak impact components and large noise interference in the surrounding environment, which makes it difficult to identify whether the bearing has an early failure on the one hand, and on the other hand increases the difficulty of early failure type diagnosis of the bearing

Images