Fault Feature Extraction Based on Improved EEMD and Hilbert Transform
Ensemble Empirical Mode Decomposition (EEMD) can overcome the mode mixing problem in Empirical Mode Decomposition (EMD) effectively. The Hilbert-Huang transform still exists end effect in applications, in order to improve the end effect, this paper put forward a method of fault feature extraction based on improved EEMD and Hilbert transform which combines support vector regression (SVR) machine with mirror extension to continue the signal. The analysis on simulation experiments results show that the method can restrain the end effect effectively, get a more accurate instantaneous frequency and instantaneous amplitude.
P. G. Hou et al., "Fault Feature Extraction Based on Improved EEMD and Hilbert Transform", Advanced Materials Research, Vols. 314-316, pp. 1126-1130, 2011