FNN based online monitoring of flank wear during turning of EN-31 steel

This paper describes predictive machining approach with fuzzy neural network (FNN) modelling of the cutting tool flank wear in order to estimate the performance of CNMG 12 04 08 E-M 6630 insert during turning of EN-31 alloy steel. In the present work, a new approach for cutting tool wear detection with cutting conditions estimated wear through acoustic emission (AE) signal is presented. The measured tool wear and estimated tool wear by conditions monitoring and detected signals are compared and graphically analysed. Investigated results prove that the new method of FNN is reliable and appropriate to control and monitor the cutting tool wear.