Fault diagnosis of rolling element bearings based on complexity measure and ν support vector machine
The acoustic emission (AE) signal is an effective means to depict a fault in rolling element bearings. However, the effective feature is hard to extract in the incipient fault stage because the periodic impulse characteristic is not obvious. In this paper, two kinds of complexity measure – Lempel-Ziv complexity and Tsallis entropy – are presented to depict the non-linear characteristic of the acoustic emission signal. In comparison with some traditional indicators, such as skewness, crest factor and kurtosis, these two indicators are more sensitive to the variation of the incipient fault status. Moreover, to further realise accurate multi-fault classification, a ν support vector machine is presented. The main characteristic of this classifier is that the model parameter is optimised automatically according to the training samples. Therefore, a good balance between the accuracy and the margin can be realised, which makes it easy to use in real industrial applications. The classification of three kinds of incipient bearing fault shows that the combination of the complexity measure and the ν support vector machine can achieve satisfactory results in the case of a small sample size. This method casts new light on the early fault diagnosis of rolling element bearings.
No Reference information available - sign in for access.
No Citation information available - sign in for access.
No Supplementary Data.
No Article Media
Document Type: Research Article
Publication date: March 1, 2013
More about this publication?
- Official Journal of The British Institute of Non-Destructive Testing - includes original research and devlopment papers, technical and scientific reviews and case studies in the fields of NDT and CM.
- Information for Authors
- Submit a Paper
- Subscribe to this Title
- Information for Advertisers
- Terms & Conditions
- Ingenta Connect is not responsible for the content or availability of external websites