Dynamic Bayesian wavelet transform : New methodology for extraction of repetitive transients

Research output: Journal Publications and ReviewsRGC 21 - Publication in refereed journalpeer-review

51 Scopus Citations
View graph of relations


  • Dong Wang
  • Kwok-Leung Tsui


Original languageEnglish
Pages (from-to)137-144
Journal / PublicationMechanical Systems and Signal Processing
Online published24 Nov 2016
Publication statusPublished - 1 May 2017


Thanks to some recent research works, dynamic Bayesian wavelet transform as new methodology for extraction of repetitive transients is proposed in this short communication to reveal fault signatures hidden in rotating machine. The main idea of the dynamic Bayesian wavelet transform is to iteratively estimate posterior parameters of wavelet transform via artificial observations and dynamic Bayesian inference. First, a prior wavelet parameter distribution can be established by one of many fast detection algorithms, such as the fast kurtogram, the improved kurtogram, the enhanced kurtogram, the sparsogram, the infogram, continuous wavelet transform, discrete wavelet transform, wavelet packets, multiwavelets, empirical wavelet transform, empirical mode decomposition, local mean decomposition, etc. Second, artificial observations can be constructed based on one of many metrics, such as kurtosis, the sparsity measurement, entropy, approximate entropy, the smoothness index, a synthesized criterion, etc., which are able to quantify repetitive transients. Finally, given artificial observations, the prior wavelet parameter distribution can be posteriorly updated over iterations by using dynamic Bayesian inference. More importantly, the proposed new methodology can be extended to establish the optimal parameters required by many other signal processing methods for extraction of repetitive transients.

Research Area(s)

  • Bayesian inference, Dynamic Bayesian wavelet transform, Repetitive transients, Wavelet parameter distribution