Bearing residual life prediction method based on binary hybrid random process

Abstract

The invention discloses a bearing residual life prediction method based on a binary hybrid random process. The method comprises the following steps: S1, collecting a vibration signal and a temperaturesignal in a bearing degradation stage; S2, calculating the effective value of the vibration signal in the vertical direction and the average value of the temperature signal, and constructing two performance indexes representing the health state of the bearing; S3, checking and analyzing the two performance indexes, and judging which random process is suitable for describing the degradation process of the two performance indexes; and S4, selecting an appropriate Copula function by utilizing an AIC information criterion to analyze related characteristics between the two performance indexes, obtaining a joint probability density function of the residual life of the bearing, updating model parameters on line by utilizing a step-by-step maximum likelihood estimation method, and predicting theresidual life of the bearing. The method is high in prediction precision and wider in application range.

Description

technical field [0001] The invention belongs to the field of prediction of remaining life of bearings, in particular to a method for predicting remaining life of bearings based on binary mixed stochastic process. Background technique [0002] As a key component, bearings are widely used in major mechanical equipment such as handling machinery, automobiles, and generators. Usually, the working environment of the bearing is harsh, the working conditions are complex and changeable, and its working performance is easy to degrade with the increase of running time, which brings various safety hazards, such as cage damage, fracture and wear and other faults. Once the bearing breaks down, it will cause the entire mechanical equipment to be shut down for maintenance, resulting in economic losses, and serious accidents such as personal injury and death. Predicting the remaining life of a bearing can evaluate its current health status and predict its future working status in a timely ...

AI Technical Summary

Problems solved by technology

[0003] In order to improve the prediction accuracy of the remaining life prediction method of bearings and overcome the limitations of the current method of using multiple performance indicators to predict the remaining life of bearings

Images