Factors like cutting force, cutting temperature, acoustic emission signals and vibration signals can be effectively used to predict tool wear. Even though each of these factors are used individually to predict tool wear, a more accurate prediction will be possible if all these factors are considered collectively since each of these factors predict tool wear in their own characteristic fashion. For example, temperature responds to flank wear and crater wear in a better way than to fracture type of tool failure, whereas cutting force has a better response to fracture type of tool failure. Hence a better prediction of tool wear consisting of different modes is possible by considering the response to these representative factors collectively.
In the present work, an attempt was made to use a combination of cutting force and cutting temperature along with cutting velocity and feed rate to predict the tool wear during hard turning of AISI 4340 Steel having a hardness of 46HRc using a multi coated hard metal insert with a sculptured rake face. A regression model was developed to fuse the cutting force and cutting temperature signals and to predict flank wear. Confirmatory experiments were conducted to validate the predictions of the regression model. The predictions matched well with the experimental results.
Keywords—. Tool wear, Sensor Fusion, Hard Turning