Design of adaptive neuro-fuzzy inference system for predicting surface roughness in turning operation

This paper proposes an Adaptive Neuro-Fuzzy Inference System (ANFIS) for predicting the surface roughness in turning operation for set of given cutting parameters, namely cutting speed, feed rate and depth of cut. Two different membership functions, triangular and bell shaped, were adopted during the training process of ANFIS in order to compare the prediction accuracy of surface roughness by the two membership functions. The comparison of ANFIS values with experimental data indicates that the adoption of both triangular and bell shaped membership functions in proposed system achieved satisfactory accuracy. The bell-shaped membership function in ANFIS achieves slightly higher prediction accuracy than triangular membership function.