Surface roughness prediction in machining using computational intelligence

A study is presented to model surface roughness in turning using Genetic Programming (GP). The machining parameters, namely, the spindle speed, feed rate, depth of cut and the workpiece tool vibration amplitudes in three orthogonal directions have been used as inputs to model the workpiece surface roughness. The input parameters and the corresponding functional relationship are automatically selected using GP and maximising the modelling accuracy. The effects of different GP parameters on the prediction accuracy and training time are studied. The results of the GP-based approach are compared with other Computational Intelligence (CI) techniques like Artificial Neural Networks (ANN).