PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Decoding aggregated profiles using dynamic calibration of machine vibration data
Vladimir N. Kulikov and Wicher P. Bergsma
(2004) Technical Report. EURANDOM, the Netherlands.

Abstract

We investigate the feasibility of using vibration measurements for online monitoring of photocopying machines. Salient features in the measurements, such as the maximum vibration induced by the stapler, are extracted from experimental data. For the purpose of on-line monitoring of machines and for estimating the remaining life time of components, a method is proposed for calibrating these features with internal machine settings. It is shown that calibration can be done with a very high success rate, opening up the possibility for online detection of machine malfunction by monitoring the vibrations it produces during operation.

EPrint Type:Monograph (Technical Report)
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Learning/Statistics & Optimisation
ID Code:793
Deposited By:Vladimir Koulikov
Deposited On:30 December 2004