Application of Statistical and Soft Computing techniques for the Prediction of Grinding Performance

Thermal load in manufacturing processes is of special interest as it is closely connected with the surface integrity and life-cycle of the finished product. Especially in grinding, heat affected zones are created due to excessive heat dissipated within the workpiece during the process. In these zones, defects are created that undermine the quality of the workpiece and as grinding is a precision finishing operation, may render it unsuccessful. Grinding forces and temperatures are usually studied in relation to the heat affected zones. However, their experimental estimation or analytical evaluation may prove laborious and costly. Thus, simulation and modeling techniques are commonly employed for the prediction of these parameters and through them the performance evaluation of the process is performed. In this paper, statistical methods and soft computing techniques, namely regression models completed with analysis of variance, and artificial neural networks respectively, are presented for the estimation of grinding forces and temperature. A brief description of the models and a comparative study is performed, based on experimental results. Both modeling tools prove to be quite successful, predicting with high accuracy forces and temperatures.