Artificial Neural Network Applied to Acoustic Emission Based Surface Roughness Monitoring in Face Milling

This paper attempts to monitor the surface roughness caused by the increase of tool wear (flank wear), through the variations of acoustic emission in face milling operations under different cutting conditions and for one workpiece material. The analysis revealed that there is a good correlation between two important parameters of the acoustic emission signal namely ring down count and RMS voltage with the surface roughness parameter namely R_a. The results show that acoustic emission can be used as an effective signal for monitoring surface roughness in face milling and thereby can be useful for establishing the end of tool life in face milling operations. Artificial Neural Network (ANN) is a powerful tool that can be applied to many scientific and engineering problems. In this paper a simple feed forward ANN has been applied to predict surface roughness using acoustic emission parameters, flank wear and cutting conditions.