Abstract
In this paper, a novel method of diesel engine pattern recognition is introduced. Hilbert spectrum (HS) and information entropy are combined to form the Hilbert spectrum entropy (HSE) which is able to give an accurate entropy estimation for Hilbert spectrum. It is more convenient and visual to pattern recognition and fault diagnosis. Experimental data of piston and cylinder liner wear rates obtained from a production diesel engine is used to evaluate the newly developed method. A good conclusion has been reached. Hilbert spectrum entropy is a more advanced method, owing to its numerical outputs, for pattern recognition and fault diagnosis of diesel engines.
Original language | English |
---|---|
Pages (from-to) | 43-48 |
Number of pages | 6 |
Journal | Proceedings- Institute of Marine Engineering Science and Technology Part A Journal of Marine Engineering and Technology |
Volume | A6 |
Publication status | Published - 2005 |
Keywords
- pattern recognition
- hilbert spectrum calculation