Thermal load in manufacturing processes is of special interest\nas it is closely connected with the surface integrity and life-cycle\nof the finished product. Especially in grinding, heat affected\nzones are created due to excessive heat dissipated within the\nworkpiece during the process. In these zones, defects are created\nthat undermine the quality of the workpiece and as grinding\nis a precision finishing operation, may render it unsuccessful.\nGrinding forces and temperatures are usually studied in\nrelation to the heat affected zones. However, their experimental\nestimation or analytical evaluation may prove laborious and\ncostly. Thus, simulation and modeling techniques are commonly\nemployed for the prediction of these parameters and through\nthem the performance evaluation of the process is performed.\nIn this paper, statistical methods and soft computing techniques,\nnamely regression models completed with analysis of variance,\nand artificial neural networks respectively, are presented for\nthe estimation of grinding forces and temperature. A brief\ndescription of the models and a comparative study is performed,\nbased on experimental results. Both modeling tools prove to\nbe quite successful, predicting with high accuracy forces and\ntemperatures.
Loading....