The paper considers methodologies for rotating machinery diagnostics based on the application of clustering techniques, i.e. on the automatic classification of data into groups. Different algorithms of clustering have been used on data taken from an experimental model of rotor in different anomalous operation conditions (rubbing, cracked shaft, bearing defect) and in healthy conditions. A vibrational diagnostics has been performed based on data of traditional techniques (e.g. the values of particular harmonics of the signal, of the energy of the spectrum in different frequency bands) and on some chaos quantifiers [1]. The paper reports also an example of rotating machinery automatic diagnostics through expert systems.
Experiences on innovative trends in the field of rotating machinery condition monitoring and diagnostics
LUCIFREDI, ALERAMO;SILVESTRI, PAOLO
2004-01-01
Abstract
The paper considers methodologies for rotating machinery diagnostics based on the application of clustering techniques, i.e. on the automatic classification of data into groups. Different algorithms of clustering have been used on data taken from an experimental model of rotor in different anomalous operation conditions (rubbing, cracked shaft, bearing defect) and in healthy conditions. A vibrational diagnostics has been performed based on data of traditional techniques (e.g. the values of particular harmonics of the signal, of the energy of the spectrum in different frequency bands) and on some chaos quantifiers [1]. The paper reports also an example of rotating machinery automatic diagnostics through expert systems.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
