Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
10368836 | Mechanical Systems and Signal Processing | 2005 | 14 Pages |
Abstract
The wavelet packet transform decomposes a signal into a set of bases for time-frequency analysis. This decomposition creates an opportunity for implementing distributed data mining where features are extracted from different wavelet packet bases and served as feature vectors for applications. This paper presents a novel approach for integrated machine fault diagnosis based on localised wavelet packet bases of vibration signals. The best basis is firstly determined according to its classification capability. Data mining is then applied to extract features and local decisions are drawn using Bayesian inference. A final conclusion is reached using a weighted average method in data fusion. A case study on rolling element bearing diagnosis shows that this approach can greatly improve the accuracy of diagnosis.
Related Topics
Physical Sciences and Engineering
Computer Science
Signal Processing
Authors
S. Zhang, J. Mathew, L. Ma, Y. Sun,