Abstract

In recent years remaining useful life of rolling bearings is paid much more attention. In this paper, the remaining useful life prediction based on fault diagnosis is proposed. Based on the real-time fault diagnosis results of the bearing, the remaining life is predicted and a set of bearing life expectancy prediction system is established by obtaining the vibration signal. In order to solve the problem that the whole life fault data is difficult to obtain, make full use of the bearing information contained in unlabeled data and take into account the advantages of each algorithm, the remaining useful life prediction of bearing is studied based on a semi supervised co-training method. The effectiveness and prediction accuracy of this method are demonstrated by a case study.

Keywords

Bearing Remaining useful life prediction Fault diagnosis Semi supervised co-training 

Notes

Acknowledgements

This work is also partly supported by State Key Lab of Rail Traffic Control & Safety (Contract No. RCS2016ZT006). This work is also partly supported by National Key R&D Program of China (Contract No. 2017YFB1201201).

References

  1. 1.
    Jianwei Y (2015) Fault diagnosis of railway bearing based on FIR-wavelet packet and LVQ neural network. Open Autom Control Syst J 7:303–313CrossRefGoogle Scholar
  2. 2.
    Oppenheimer CH, Loparo KA (2002) Physically based diagnosis and prognosis of cracked rotor shafts. In Aerosense international society for optics and photonicsGoogle Scholar
  3. 3.
    Zio E, Maio FD (2010) A data-driven fuzzy approach for predicting the remaining useful life in dynamic failure scenarios of a nuclear system. Reliab Eng Syst Safety 95(1):49–57CrossRefGoogle Scholar
  4. 4.
    Hu C (2015) A co-training-based approach for prediction of remaining useful life utilizing both fault and suspension data. Mech Syst Signal Process 62–63:75–90CrossRefGoogle Scholar
  5. 5.
    Zhou Z (2013) Disagreement-based semi-supervised learning. Acta Automatica Sinica 39(11)Google Scholar
  6. 6.
    Sikorska JZ, Hodkiewicz M, Ma L (2011) Prognostic modelling options for remaining useful life estimation by industry. Mech Syst Signal Process 25:1803–1836CrossRefGoogle Scholar
  7. 7.
    Chen Yuhao (2010) Review of neural network BP algorithm. Comput Knowl Technol 6(36):10364–10365Google Scholar
  8. 8.
    Dvaid M, Alexnader F (2004) Active set support vector regression. IEEE Trans Neural Netw 15(2)Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2018

Authors and Affiliations

  1. 1.State Key Laboratory of Rail Traffic Control and SafetyBeijing Jiaotong UniversityBeijingChina

Personalised recommendations