Identifying optimal combination of wavelet packet bases for fault classification using Bayesian neural networks

Zhang, Sheng, Mathew, Joseph, Ma, Lin, & Sun, Yong (2004) Identifying optimal combination of wavelet packet bases for fault classification using Bayesian neural networks. In Vyas, N. S., Rao, J. S., Mathew, J., Ma, L., & Raghuram, V. (Eds.) VETOMAC-3 and ACSIM-2004, 6-9 December, New Delhi.


This paper presents an approach to automatically extract optimal feature combinations using Bayesian neural networks. Hyperparameters are used in Bayesian neural networks to reflect the significance of inputs to the underlying model. The relevant input variables can be determined by judging the magnitudes of these hyperparameters. This automatic relevance determination technique is applied on the signals’ wavelet packet transform to select an optimal feature combination for fault classification, with each feature element extracted from a wavelet packet basis. The proposed method integrates feature selection and pattern recognition, leading to a compact and automatic pattern identification procedure. A case study on rolling element bearing fault diagnosis showed that the selected features with reduced dimension derived accurate diagnosis results when compared with the original features, demonstrating that the proposed approach provides automatic fault classification.

Impact and interest:

Search Google Scholar™

Citation counts are sourced monthly from Scopus and Web of Science® citation databases.

These databases contain citations from different subsets of available publications and different time periods and thus the citation count from each is usually different. Some works are not in either database and no count is displayed. Scopus includes citations from articles published in 1996 onwards, and Web of Science® generally from 1980 onwards.

Citations counts from the Google Scholar™ indexing service can be viewed at the linked Google Scholar™ search.

ID Code: 5687
Item Type: Conference Paper
Refereed: Yes
Additional Information: For more information please contact the author:
Keywords: Fault diagnosis, wavelets, neural networks
Subjects: Australian and New Zealand Standard Research Classification > ENGINEERING (090000) > MECHANICAL ENGINEERING (091300) > Mechanical Engineering not elsewhere classified (091399)
Divisions: Past > QUT Faculties & Divisions > Faculty of Built Environment and Engineering
Copyright Owner: Copyright 2004 (please consult author)
Deposited On: 01 Dec 2006 00:00
Last Modified: 29 Feb 2012 13:05

Export: EndNote | Dublin Core | BibTeX

Repository Staff Only: item control page