Rolling bearing residual life prediction method

Abstract

The invention relates to a rolling bearing residual life prediction method, which predicts the life of a rolling bearing by using vibration signals of the rolling bearing through training a multi-scale convolutional neural network model, and comprises the following steps: carrying out an accelerated degradation experiment by using a plurality of unused bearings to obtain full-life vibration signals of the bearings; converting the service life of the bearing into a health index by using an inverse hyperbolic tangent function; establishing a multi-scale convolutional neural network model, and training the model by using the obtained data; measuring a vibration signal of the rolling bearing with the life to be predicted by using an acceleration sensor; inputting the obtained vibration signalinto a trained multi-scale convolutional neural network model to obtain a health index of the rolling bearing with the life to be predicted; and converting the obtained health index into the residuallife of the rolling bearing with the life to be predicted. The invention aims to provide a rolling bearing residual life prediction method which can efficiently and accurately predict the residual life of a rolling bearing under complex actual working conditions.

Description

technical field [0001] The invention belongs to the field of fault prediction and health management, and in particular relates to a method for predicting the remaining life of a rolling bearing. Background technique [0002] Bearings are widely used in modern machinery. According to the different friction properties of bearing components, bearings can be divided into rolling bearings and sliding bearings, of which rolling bearings are the most widely used. The main function of the rolling bearing is to support the shaft, and its working condition has a great influence on the safe and stable operation of the machine. Therefore, accurate and efficient prediction of the remaining life of the bearing is the basis for ensuring the continuous and good operation of the machine. [0003] The traditional calculation method of rolling bearing life has good accuracy only under the condition of external stable load, but in the actual mechanical operation, the load condition is changeabl...

AI Technical Summary

Problems solved by technology

[0003] The traditional calculation method of rolling bearing life has good accuracy only under the condition of external stable load, but in the actual mechanical operation, the load condition is changeable, the working condition of the bearing is very complicated, and the existing calculation method is difficult to accurately predict the bearing life. remaining life of

The existing methods for predicting the remaining life of rolling bearings are mostly based on the convolutional neural network model. When the amount of data is large, the number of network layers is too large, which will increase the difficulty of model training and lower training efficiency.

In addition, the existing bearing health index construction methods are mostly simple linear, which does not conform to the fault characteristics of the bearing, resulting in low prediction accuracy of the remaining life of the rolling bearing.

Images