ONLINE WEAR ESTIMATION USING NEURAL NETWORKS

In this paper, a neural network based system for 'on-line' estimation of tool wear in turning operations is introduced. The system monitors the cutting force components and extracts the tool wear information fr om the changes occurring over the cutting process. A hierarchical stru cture using multilayered feedforward static and dynamic neural network s is used as a specialized subsystem, for each wear component to be mo nitored. These subsystems share information about the tool wear compon ents they are monitoring and their error in estimating the cutting for ce components is used to update the dynamic neural networks. The adapt ability property of neural networks ensures that changes in machining parameters can be accommodated. Simulation studies are undertaken usin g experimental data available from manufacturing literature. The resul ts are promising and show good estimation ability.