Rolling bearing life prediction method based on similarity matching optimization theory

Abstract

The invention discloses a rolling bearing life prediction method based on a similarity matching optimization theory, and the method comprises the steps: firstly, simulating a bearing degradation signal through an exponential decay function and a double-exponential function model, and achieving the expansion of a sample dictionary set; and secondly, based on a Jensen-renyi divergence health index of a Gaussian mixture model, realizing the extraction of the degradation evolution trend of the vibration signal of the rolling bearing. And Gaussian function fitting is carried out on the bearing degradation data, so that noise can be effectively reduced. And measuring the similarity through a function space L2 norm, searching the dictionary set based on traversal to obtain the similarity and endowing a corresponding weight, and finally obtaining a residual service life prediction result of the rolling bearing. The effectiveness of the method is verified through simulation analysis of the full life cycle signal of the bearing. Experimental data analysis results also show that the method can effectively predict the remaining service life of the rolling bearing.

Description

technical field [0001] The invention relates to a method for predicting the life of a rolling bearing, in particular to a method for predicting the remaining life of a rolling bearing based on a parameter similarity matching theory, and belongs to the technical field of fault diagnosis. Background technique [0002] Rolling bearings are one of the most widely used and most critical basic components in major high-end equipment. Because of their failure, the equipment cannot work normally or even shut down, which will cause great economic losses and safety hazards. Therefore, real-time monitoring of bearing working status is a key link in fault and health management. Currently there are two aspects of fault and health management: fault diagnosis and remaining useful life (RUL) prediction. However, most fault diagnosis methods only make diagnostic conclusions when the fault has occurred, so the related research on prediction methods has received more attention. [0003] Life ...

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to provide a rolling bearing life prediction method based on similarity matching optimization theory to solve the above-mentioned technical problems in the traditional similarity method in bearing remaining life prediction

This method constructs a dictionary set according to the fault impact characteristics of rolling bearings, so that the simulation signal conforms to the actual degradation process, and solves the prediction error caused by the small sample data set

Images