A Novel Feature Extraction Method for the Condition Monitoring of Bearings - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Energies Année : 2021

A Novel Feature Extraction Method for the Condition Monitoring of Bearings

Résumé

This paper presents an innovative approach to the extraction of an indicator for the monitoring of bearing degradation. This approach is based on the principles of the empirical mode decomposition (EMD) and the Hilbert transform (HT). The proposed approach extracts the temporal components of oscillating vibration signals called intrinsic mode functions (IMFs). These components are classified locally from the highest frequencies to the lowest frequencies. By selecting the appropriate components, it is possible to construct a bank of self-adaptive and automatic filters. Combined with the HT, the EMD allows an estimate of the instantaneous frequency of each IMF. A health indicator called the Hilbert marginal spectrum density is then extracted in order to detect and diagnose the degradation of bearings. This approach was validated on two test benches with variable speeds and loads. The obtained results demonstrated the effectiveness of this approach for the monitoring of ball and roller bearings.

Dates et versions

hal-03682964 , version 1 (31-05-2022)

Identifiants

Citer

Abdenour Soualhi, Bilal El Yousfi, Hubert Razik, Tianzhen Wang. A Novel Feature Extraction Method for the Condition Monitoring of Bearings. Energies, 2021, 14 (8), pp.2322. ⟨10.3390/en14082322⟩. ⟨hal-03682964⟩
51 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More