Optimization of cutting parameters to minimize surface roughness by integrating Artificial Neural Network and Imperialist Competitive Algorithm

The surface roughness is a widely used index of surface quality which depends entirely on the input parameters and cutting conditions. This paper presents an approach for determining the optimum cutting speed, feed rate, radial depth of cut and milling type leading to minimum surface roughness in milling process of AISI 420 stainless steel by integrating Arti9icial Neural Network (ANN) and Imperialist Competitive Algorithm (ICA). The combination of these two methods to optimize the cutting process is provided for the 9irst time in this article. 54 different cases were tested and surface roughness was measured in each experiment. The predicted results using ANN indicated good agreement between the predicted values and the experimental values. ICA was used to determine the optimal machining parameters leading to minimum surface roughness. The obtained results proved that the ANN-ICA approach is capable of predicting the optimum machining parameters to minimum surface roughness in milling process.