Identification of machining processes using a Kohonen self organizing map
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.
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
Original language: en
Available languages: en