Bearing residual life prediction method based on ternary Wiener process

Abstract

The invention discloses a method for predicting the residual life of a bearing based on a ternary Wiener process. The method comprises the following steps: S1, collecting two vibration signals in mutually vertical directions and a temperature signal in a bearing degradation stage; s2, calculating the effective values of the vibration signals in the two directions and the average value of the temperature signals, and constructing three performance indexes representing the health state of the bearing; S3, checking and analyzing the three performance indexes, and judging whether the degradation process of the three performance indexes can be described by using a Wiener process or not; s4, decomposing the joint probability density function of the three performance indexes into three binary Copula functions by utilizing a Vine Copula function, and processing the three binary Copula functions, a Copula function is selected through an AIC information criterion to describe related characteristics among all performance indexes, a joint probability density function of the residual life of the bearing is obtained, model parameters are updated on line through a step-by-step maximum likelihoodestimation method, and the residual life of the bearing is predicted. The method is high in prediction precision and requires less training data.

Description

technical field [0001] The invention belongs to the field of bearing remaining life prediction, in particular to a bearing remaining life prediction method based on a three-dimensional Wiener process. Background technique [0002] As a key component, bearings are widely used in major equipment such as wind turbines, automobiles, and cranes. Due to the harsh working environment and complex and changeable working conditions, the working performance of the bearing gradually degrades with the increase of the cumulative working time, leading to various failures, such as corrosion and wear, fracture and pressure damage, etc. Once the bearing breaks down, it will cause the entire mechanical equipment to be shut down for maintenance, resulting in economic losses, or it will lead to safety accidents and personal casualties. Therefore, it is necessary to carry out health status monitoring, fault diagnosis and remaining life prediction of equipment bearings to ensure reliable and stab...

AI Technical Summary

Problems solved by technology

[0003] In order to overcome the problem of low prediction accuracy of existing bearing remaining life prediction methods, the present invention provides a bearing remaining life prediction method based on a three-dimensional Wiener process with high prediction accuracy and less training data required

Images