A study of surface roughness in drilling using mathematical analysis and neural networks

Drilling is one of the most common and fundamental machining processes. It is most frequently performed in material removal and is used as a preliminary step for many operations, such as reaming, tapping and boring. Because of their importance in nearly all production operations, twist drills have been the subject of numerous investigations. The aim of this study is to identify suitable parameters for the prediction of surface roughness. Back propagation neural networks are used for the detection of surface roughness. Drill diameter, cutting speed, feed and machining time are given as inputs to the neural network structure and surface roughness was estimated. Drilling experiments with 12 mm drills are performed at three cutting speeds and feeds. The number of neurons are selected from 1,2,3, ..., 20. The learning rate was selected as 0.01, and no smoothing factor was used. The best structure of neural network was selected based on a criteria including the minimum of sum of squares with the actual value of surface roughness. For mathematical analysis, an inverse coefficient matrix method was used for calculating the estimated values of surface roughness. Comparative analysis was performed between actual values and estimated values obtained by mathematical analysis and neural network structures.