<abstract xmlns="http://www.w3.org/1999/xhtml">

The study of fault feature extraction and early warning of rolling bearing vibration signal of generator sets is beneficial for the timely diagnosis of bearing faults, thus improving the service life of generators. In this paper, a combined EEMD-GRU-MC prediction method is adopted to predict the model based on GRU through the data decomposition of EEMD, and the predicted model residuals are corrected using MC. The analysis and diagnosis of the algorithmic model are used to determine the fault characteristics of the generator’s vibration signals for diagnosis, and the analysis and diagnosis of the characteristics are verified using experiments with publicly available data sets from the Bearing Data Center at the Paderborn University School of Mechanical Engineering in Paderborn, Germany. Diagnosis can be performed with an accuracy of 99.6% under condition load <italic>K</italic>0 and 99.9% close to 100% under condition load <italic>K</italic>3 . The accuracy is the highest at this point, while the diagnostic accuracy at conditional load <italic>K</italic>1 is only 99.8%, the lowest at this point. However, the accuracy under condition load <italic>K</italic>2 is also 99.5%. Therefore, the diagnostic accuracy with EEMD-GRU-MC is around 99%. In this study, the EEMD-GRU-MC model can be used to extract the fault characteristics and early warning of the rolling bearing vibration signal of generator sets.
</abstract>

The study of fault feature extraction and early warning of rolling bearing vibration signal of generator sets is beneficial for the timely diagnosis of bearing faults, thus improving the service life of generators. In this paper, a combined EEMD-GRU-MC prediction method is adopted to predict the model based on GRU through the data decomposition of EEMD, and the predicted model residuals are corrected using MC. The analysis and diagnosis of the algorithmic model are used to determine the fault characteristics of the generator’s vibration signals for diagnosis, and the analysis and diagnosis of the characteristics are verified using experiments with publicly available data sets from the Bearing Data Center at the Paderborn University School of Mechanical Engineering in Paderborn, Germany. Diagnosis can be performed with an accuracy of 99.6% under condition load K0 and 99.9% close to 100% under condition load K3 . The accuracy is the highest at this point, while the diagnostic accuracy at conditional load K1 is only 99.8%, the lowest at this point. However, the accuracy under condition load K2 is also 99.5%. Therefore, the diagnostic accuracy with EEMD-GRU-MC is around 99%. In this study, the EEMD-GRU-MC model can be used to extract the fault characteristics and early warning of the rolling bearing vibration signal of generator sets.

Research on fault feature extraction and early warning of rolling bearing vibration signal of generator set

Zhejiang University of Water Resources and Electric Power

Applied Mathematics and Nonlinear Sciences

This work is licensed under the Creative Commons Attribution 4.0 International License.

The study of fault feature extraction and early warning of rolling bearing vibration signal of generator sets is beneficial for the timely diagnosis of bearing...

Research on fault feature extraction and early warning of rolling bearing vibration signal of generator set

Pubblicato online: 02 ott 2023

Pagine: -

Ricevuto: 20 dic 2022

Accettato: 12 apr 2023

DOI: https://doi.org/10.2478/amns.2023.2.00435

Parole chiave
Generator, Rolling bearing, EEMD-GRU-MC, Paderborn experiment, Fault characterization

© 2023 Yan Ma et al., published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Research on fault feature extraction and early warning of rolling bearing vibration signal of generator set

Pubblicato online: 02 ott 2023

Pagine: -

Ricevuto: 20 dic 2022

Accettato: 12 apr 2023

DOI: https://doi.org/10.2478/amns.2023.2.00435

Parole chiaveGenerator, Rolling bearing, EEMD-GRU-MC, Paderborn experiment, Fault characterization

© 2023 Yan Ma et al., published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Parole chiave
Generator, Rolling bearing, EEMD-GRU-MC, Paderborn experiment, Fault characterization