Method for predicting residual service life of rolling bearing based on linear reliability index

Abstract

The invention provides a method for accurately predicting the residual service life of a rolling bearing based on a linear reliability index, which aims to improve the prediction precision of a modeland comprises the following implementation steps of: obtaining a training sample set and a test sample set; establishing a plurality of stacked auto-encoder models, training the plurality of stacked auto-encoder models in sequence by taking the training sample set and the test sample set as inputs respectively, and extracting performance degradation features; setting threshold screening features based on clustering, monotonicity and correlation pair evaluation performance degradation features; training original optimal features are selected based on monotonicity, a linear reliability index curve is established, feature translation and feature interpolation are performed, and a training mapping feature set and a test mapping feature set are constructed respectively; and training the mappingfeature set as an input training reliability evaluation model, inputting the test mapping feature set into the trained reliability evaluation model to obtain test reliability, and predicting the residual service life of the to-be-predicted bearing based on a particle filtering algorithm.

Description

technical field [0001] The invention belongs to the technical field of reliability evaluation of rolling bearings, and relates to a method for predicting the remaining life of a rolling bearing, in particular to a method for evaluating the reliability of a rolling bearing based on a linear reliability index, which can be used for predicting the remaining life of the rolling bearing. Background technique [0002] During normal operation of rotating machinery, performance degradation is unavoidable, and it is an accumulated process with the increase of operating time. As a key component of rotating machinery, the performance of rolling bearing directly affects the operation and production safety of mechanical equipment. Under the influence of factors such as working conditions, vibration, temperature, etc., rolling bearings will experience performance degradation, and this degradation behavior may lead to the failure or collapse of the entire mechanical system. To prevent the...

AI Technical Summary

Problems solved by technology

However, although this method combines multiple features to construct a virtual health indicator, the correlation between the health indicator and the real remaining service life is low, and the performance of representing the real remaining service life is weak, which affects the prediction accuracy of the remaining life.

Images