Neural Network Processing of Audible Sound Signal Parameters for Sensor Monitoring of Tool Conditions

The increase of productivity in manufacturing processes largely relies on the successful introduction of flexible automation in machining processes. Such success, in turn, is largely based on the availability of data on the operating conditions, provided by reliable sensing devices. In the present work, experimental verifications of the possibilities of utilizing audible sound based sensing methods for in-process identification of tool conditions are presented for band sawing processes carried out on aluminium alloy and low carbon steel plates