Bearing life prediction method based on multi-stage Wiener process

Abstract

The invention discloses a bearing life prediction method based on the multi-stage Wiener process. Firstly, the vibration signal during the operation of the bearing is collected and the degradation characteristic index is extracted; then, according to the state change of the bearing during service, the degradation process is divided based on the Wiener process. The normal stage, the slow degradation stage and the accelerated degradation stage are used to establish a multi-stage stochastic degradation model; at the same time, the degradation state and model parameters are estimated and updated by using the Kalman filter and the expectation maximization algorithm; finally, a sliding window identification method is constructed to judge the bearing For the degradation stage, the remaining life expression corresponding to each stage is derived and the remaining life is predicted. This method can effectively judge the degradation stage of the bearing, and then predict the remaining life under the corresponding stage, and has a good application effect.

Description

technical field [0001] The invention belongs to the field of remaining life prediction and relates to a bearing life prediction method based on a multi-stage Wiener process. Background technique [0002] Bearings are one of the key components for the normal operation of mechanical equipment, and are widely used in various large and small equipment. Due to the influence of the internal and external environment, the bearing will fail with the increase of service time, and its degradation or failure will directly affect the performance and reliability of the equipment. By accurately predicting the performance changes of bearings and estimating the remaining life, we can formulate reasonable maintenance strategies and organize production in a targeted manner, which can greatly reduce the losses caused by bearing failure and improve the operational reliability of mechanical equipment. [0003] In the patent specification CN111414703A, a method for predicting the remaining life o...

AI Technical Summary

Problems solved by technology

[0005] In order to overcome the problem of low prediction accuracy of the staged life prediction model, the purpose of the present invention is to provide a bearing life prediction method based on the multi-stage Wiener process. Considering that the bearing degradation has the characteristics of multiple stages and the uncertainty of the degradation, By virtue of the mathematical advantages of the Wiener process to construct a life prediction model, accurate remaining life prediction results can be obtained

Images