On-line tool wear estimation in turning is essential for on-line cutting process optimization. In this work, cutting force measurement is used for a reliable on-line flank wear estimation and tool life monitoring. Models for flank wear will be obtained as a function of machining parameters and dynamic cutting forces. The coefficients for flank wear models are obtained by using the experimental results. Then the non-linear dynamic models obtained are calibrated with the actual conditions. These developed models will be used for the simulation of flank wear and using control variable such as cutting speed; the flank wear will be controlled. For model validation, the flank wear is estimated using a non-linear model. In the present work, an attempt has been made to control the flank wear during turning of on-line cutting process using the Neural network based on self-tuning of PID controller approaches. This approach treats the material as dynamic system and involves developing state space models from available material behavior model.

The evaluation of performance criteria can be compared for both approaches of PI controller and Neural network based on self-tuning of PID controller. Simulation studies are carried-out for the non-linear system using MATLAB software.