Sensor Monitoring of Machining based on Audible Sound Detection and Analysis

Machining process monitoring is a critical requirement in the implementation of any automated operation of the shop floor. This is especially crucial for Flexible Manufacturing Systems (FMS) and Computer Integrated Manufacturing Systems (CIMS) where most of the operations are performed in an unattended way. Numerous research activities have been carried out on this topic by making use of different sensing techniques such as those based on the measurement of cutting force and cutting torque, motor current and effective power, acoustic emission, vibrations, and audible sound energy. In this work, particular attention is given to audible sound energy with the scope of characterising the sound signals from milling processes as a first approach towards the development of a sensor monitoring system based on audible sound sensors. Different processing conditions were considered by varying spindle rotation speed, feed rate and depth of cut. The classification of audible sound signal features for process monitoring was carried out by graphical analysis and parallel distributed data processing using a supervised neural network approach.