Tool Wear Monitoring with Indirect Methods

The tool wear is significantly influenced by the cutting parameters like velocity, feed and depth of cut. Direct method of detecting the tool wear using tool makers microscope is not recommended in many situations. It has been observed that as tool wear begins for the same cutting parameters, the parameters like spindle power, cutting forces, surface roughness change abruptly. Hence the variations in these parameters indicate wear states qualitatively. In this paper some indirect methods of detecting tool wear status are proposed. A neural network model is developed to predict the spindle current and cutting forces for a given cutting parameters, so as to indicate levels of the tool wear. Also the tool wear can be indirectly estimated through finite element analysis, since the tool wear is influenced by stresses on the tool faces. Two-dimensional orthogonal cutting model is chosen with appropriate tool and work piece boundary conditions and material combinations. The deformations at the flank face are recorded for various values of tool chip contact lengths. The results are reported in the form of graphs and tables.