Community Research and Development Information Service - CORDIS

Abstract

The optimisation of on-line grinding wheel control is difficult, due to the complexity of the interaction between workpiece and grinding wheel. The aim of this work is to determine an event type from the emission acoustics produced during machining in real time. A Kohonen map is used to group samples of work into four classes without knowing the exact machining techniques employed. The results show that it is possible to classify the event types, but a relationship between a type and its acoustic power has not yet been established.

Additional information

Authors: BRANCI S, Ecole Nationale Supérieure des Techniques et des Mines d'Alès (FR)
Bibliographic Reference: Paper presented: 10th International Conference on Systems Engineering, Coventry (GB), September 8, 1994
Availability: Available from (1) as Paper EN 38653 ORA
Record Number: 199411330 / Last updated on: 1994-12-06
Category: PUBLICATION
Original language: en
Available languages: en