Abstract
This article introduces a novel pattern recognition and fault diagnosis method for diesel engines. The method is developed from engine vibration signal analysis in combination with wavelet and Kullback-Leibler distance (KLD) approaches. The new approach is termed wavelet Kullback-Leibler distance (WKLD). Experimental data relating to piston and cylinder liner wear obtained from a production diesel engine are used to evaluate the newly developed method. A good agreement between the experimental data and the WKLD estimation is found. The results of this article suggest that WKLD is an advancement on the methods which have been currently developed for pattern recognition and fault diagnosis of diesel engines.
Original language | English |
---|---|
Pages (from-to) | 879-887 |
Number of pages | 8 |
Journal | Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science |
Volume | 219 |
Issue number | 9 |
DOIs | |
Publication status | Published - 2005 |
Keywords
- wavelet
- fault diagnosis
- Kullback-Leibler distance
- pattern recognition
- diesel engines
- vibration