A method and apparatus for predicting wear and life of a sliding bearing

By combining finite element models and deep neural networks, a method for predicting the wear of sliding bearings was established. The neural network model was trained using simulation data, which enabled fast and accurate prediction of wear and lifespan, solving the problem of time-consuming and labor-intensive traditional methods.

CN116721725BActive Publication Date: 2026-07-21TSINGHUA UNIVERSITY
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
TSINGHUA UNIVERSITY
Filing Date
2023-06-21
Publication Date
2026-07-21

AI Technical Summary

Technical Problem

Existing methods for predicting wear of sliding bearings often use a single finite element model, which results in long time cycles and an inability to quickly adapt to different bearing models, making them time-consuming and labor-intensive.

Method used

A deep neural network model is trained based on the finite element wear simulation results. A finite element model of bearing wear is established by fitting a material wear rate model, and the deep neural network is trained using simulation data to predict wear amount and life.

Benefits of technology

It achieves efficient and accurate prediction of wear morphology and lifespan, avoiding the high cost and long cycle of physical experiments. It can output wear data online in real time, solving the problem of long calculation time of traditional finite element models.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN116721725B_ABST
    Figure CN116721725B_ABST
Patent Text Reader

Abstract

The application discloses a kind of sliding bearing wear prediction and life prediction method and device, the method, including based on material wear data fitting material wear rate model to establish bearing wear finite element model;To input condition is multilevel and combination to carry out revision to the parameter of bearing wear finite element model, and numerical simulation is carried out based on the revised bearing wear finite element model to obtain simulation wear data;Based on the input vector and output vector generated based on simulation wear data processing obtains offline data;Offline data is used to train deep neural network model to obtain trained deep neural network model, and the wear amount and life prediction of target sliding bearing are carried out using trained deep neural network model to obtain prediction result.The application solves the problem that traditional finite element model is long in calculation time, cannot be predicted in real time.
Need to check novelty before this filing date? Find Prior Art