Bearing Localized Fault Detection Based on Hilbert-Huang Transformation

The Hilbert-Huang transform and its marginal spectrum are applied to bearing fault diagnosis of ball bearing. The principle of Empirical mode decomposition (EMD), Hilbert-Huang transformation (HHT) and marginal spectrum is introduced. Firstly, the vibration signals of bearing fault are separated into several intrinsic mode functions (IMFs) using EMD method. Secondly, the marginal spectrum of each IMF is calculated. In the end, according to the marginal spectrum, the localized fault in a ball bearing can be detected and faults patterns can be identified. The experimental results show that the proposed method can provide not only an increase in the spectral resolution but also reliability for the faults diagnosis of ball bearing.