A rolling bearing life prediction method based on multi-source domain adaptation

CN114091349BActive Publication Date: 2024-11-08SOUTHEAST UNIV
View PDF 0 Cites -1 Cited by

Patent Information

Application Number
CN202111447955.8
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-11-30
Publication Date
2024-11-08
Estimated Expiration
2041-11-30

Smart Images

  • Figure CN114091349B_ABST
    Figure CN114091349B_ABST
Patent Text Reader

Abstract

The present invention relates to a rolling bearing life prediction method based on multi-source domain adaptation, comprising the following steps: collecting full-life and multi-channel vibration signals of rolling bearings under various working conditions, constructing a multi-source domain bearing full-life data set; extracting time-frequency domain features from multi-channel vibration signals that have been pre-processed for noise reduction; determining hyperparameters to construct a multi-source domain adaptive network, and using multi-source domain and target domain training data sets to train the network to achieve regression error minimization and multi-source domain adaptation; collecting test data and importing the trained multi-source domain adaptive network to obtain remaining life prediction. The model used in the multi-working condition rolling bearing life prediction method of the present invention has the advantages of strong generalization ability, strong robustness, high accuracy, etc.
Need to check novelty before this filing date? Find Prior Art