engleski

INVESTIGATION OF DRILLING PROCESS USING REGRESSION ANALYSIS AND NEURAL NETWORK

The focus of this paper is to develop a reliable model to predict the depth of drilling, by standard drilling, where the conditions of machinability still stay satisfactory. In this sense, this paper is concerned with the influence of spindle speed and feedrate on increasing thrust force and torque in drilling process. Two modeling methodologies, namely regression analysis and artificial neural network, have been applied to experimentally determined data by means of the design of experiments. The results obtained by the models have been compared. The best prediction of depth of drilling shows neural network model with average relative prediction error of 6, 16%.

drilling; thrust force and torque; regression analysis; neural network.

nije evidentirano