In metal cutting processes, the condition of a cutting tool as it come
s into contact with the workpiece greatly affects the quality of the m
achined part and hence the technical aspects and economics of the manu
facturing process. On-line monitoring and assessment of the state of a
cutting tool is therefore considered to be a significant factor in th
e cost-effectiveness of the whole process. Multiple sensors are used i
n this work to provide complementary information about the process and
this helps to improve the confidence factor of the resulting diagnost
ics. The use of multiple sensors, however, entails integration and fus
ion of the sensory information to elicit the essential features from t
he data by removing the redundancy present. Artificial neural networks
, which mimic the functional behaviour of the biological neural networ
k system, are used to integrate and fuse information from the multiple
-sensor source. The problem of on-line tool wear monitoring in turning
operations is approached by applying a three-layered, error-back-prop
agation-based network for fusion of three machinery performance-indict
ing features. A demonstrator system has been developed from this resea
rch and is capable of classifying previously unseen data into five dis
crete levels (three levels of flank wear and two levels of chipping).