Bearing fault diagnosis and residual life prediction method based on Johnson transformation and particle filter algorithm

Abstract

Provided is a bearing fault diagnosis and residual life prediction method based on Johnson transformation and a particle filter algorithm. The method comprises the followings steps of: 1) acquiring a bearing full-life-cycle vibration signal; 2) computing K-S distance by using the vibration signal, and constructing an index reflecting a bearing health state based on the K-S distance; 3) performing Johnson transformation on non-Gaussian distribution health index data in healthy operation based on the constructed index in order to transform the health index data into Gaussian distribution data, and determining an associated abnormal threshold range by using the attribute of the Gaussian distribution; and 4) performing fitting analysis on health index data in a loss cycle, constructing a state space model representing the bearing degeneration process, updating model parameters by using currently observed health index data and the particle filter algorithm, and predicting the residual life of the bearing. The method diagnoses early bearing fault so as to accurately derive the performance degeneration data of the bearing in the loss cycle, and is fast in computation speed and high in residual life prediction precision.

Description

Technical field [0001] The invention belongs to the field of bearing fault diagnosis and prediction, and in particular relates to a bearing fault diagnosis and remaining life prediction method based on Johnson transform and particle filter algorithm. Background technique [0002] Bearings are indispensable parts of rotating machinery. They are widely used in electric power, petrochemical, metallurgy, machinery, aerospace and some military industry sectors. They are used to ensure the accuracy, performance, and performance of important equipment such as precision machine tools, high-speed railways, and wind turbines. The core component of life and reliability, but it is also one of the most prone to failure of these equipment. According to statistics, most failures of rotating machinery are caused by bearing failures. The failure of the bearing can reduce or lose certain functions of the equipment, and cause serious or even catastrophic consequences. Therefore, bearing condition...

AI Technical Summary

Problems solved by technology

[0003] In order to overcome the shortcomings of the existing nonlinear Bayesian filter algorithm in solving bearing fault prediction, the remaining life prediction accuracy is low, and the fault prediction method based on the Kalman filter framework is not suitable for the remaining life prediction of non-Gaussian distribution samples. The invention provides a bearing fault diagnosis and remaining life prediction method based on Johnson transform and particle filter algorithm with high prediction accuracy, short time consumption, and suitable for non-Gaussian distribution samples

Images