Bearing residual life prediction method and system based on deep wavelet extreme learning machine

Abstract

The invention discloses a bearing residual life prediction method and system based on a deep wavelet extreme learning machine. The method comprises the following steps: detecting the fault occurrence time of a bearing through a time-varying 3 sigma criterion, dividing the operation state of the bearing into a health stage and a degradation stage, decomposing a vibration signal through a signal processing method, calculating the root-mean-square value of the signal under each scale, and carrying out the prediction of the residual life of the bearing. The characteristics are used as original characteristics for representing the bearing degeneration state; constructing a supervised learning model based on a deep wavelet extreme learning machine to obtain a DWELM-HI index; and describing the degradation trend of the DWELM-HI by adopting a linear model, estimating parameters of the linear model by using particle filtering, predicting the remaining service life of the bearing at the current moment according to the estimated parameters, and giving out RUL probability distribution. According to the method, data driving and model driving life methods are combined, so that on one hand, the prediction precision of the model driving method is prevented from being reduced due to degradation trend differences of different bearings; on the other hand, probability distribution of the bearing residual life is given, and important information is provided for predictive maintenance.

Description

technical field [0001] The invention belongs to the technical field of mechanical system state monitoring and health management, and in particular relates to a method and system for predicting the remaining life of a bearing based on a deep wavelet extreme learning machine. Background technique [0002] High-end bearings are key components of major equipment such as aero-engines, CNC machine tools, high-speed trains, wind turbines, and helicopters. Their healthy service is an important guarantee for the safety of the entire equipment. Due to the complex service environment and changing operating conditions of bearings, accidents occur frequently, and the cost of operation and maintenance remains high, which seriously affects the reliability and economy of equipment. Bearing condition monitoring and health management are urgent needs of wind power, rail transit, aerospace and other industries. [0003] Bearing condition monitoring and health management includes the following...

AI Technical Summary

Problems solved by technology

The traditional model-driven method uses statistical indicators to reflect the health status of bearings, which is easily affected by individual differences in bearings and operating conditions

However, the data-driven method is difficult to obtain the probability distribution that reflects the uncertainty of the remaining life prediction, and provides limited information for predictive maintenance.

Images