Development of a cutting tool condition monitoring system for high speed turning operation by vibration and strain analysis

Cutting tool wear is a critical phenomenon which influences the quality of the machined part. In this paper, an attempt has been made to create artificial flank wear using the electrical discharge machining (EDM) process to emulate the actual or real flank wear. The tests were conducted using coated carbide inserts, with and without wear on EN-8 steel, and the acquired data were used to develop artificial neural networks model. Empirical models have been developed using analysis of variance (ANOVA). In order to analyze the response of the system, experiments were carried out for various cutting speeds, depths of cut and feed rates. To increase the confidence limit and reliability of the experimental data, full factorial experimental design (135 experiments) has been carried out. Vibration and strain data during the cutting process are recorded using two accelerometers and one strain gauge bridge. Power spectral analysis was carried out to test the level of significance through regression analysis. Experimental results were analyzed with respect to various depths of cut, feed rates and cutting speeds.