Feature extraction of vibration signals based on wavelet packet transform

A method is proposed for the analysis of vibration signals from components of rotating machines, based on the wavelet packet transformation (WPT) and the underlying physical concepts of modulation mechanism. The method provides a finer analysis and better time-frequency localization capabilities than any other analysis methods. Both details and approximations are split into finer components and result in better-localized frequency ranges corresponding to each node of a wavelet packet tree. On the purpose of feature extraction, a hard threshold is given and the energy of the coefficients above the threshold is used, as a criterion for the selection of the best vector. The feature extraction of a vibration signal is accomplished by computing the reconstruction signal and its spectrum. When applied to a rolling bear vibration signal feature extraction, the proposed method is effective.