An application of the adaptive neuro-fuzzy inference system for prediction of surface roughness in turning

Surface roughness is an important parameter in manufacturing engineering. This paper proposes a method using an Adaptive Neuro-Fuzzy Inference System (ANFIS) to establish the relation between cutting parameters and surface roughness in turning, and consequently to predict surface roughness of the work piece using input cutting parameters, namely cutting speed, feed rate and depth of cut. Three different Membership Functions (MF) (i.e., triangular, trapezoidal and bell-shaped) were adopted during the training process of ANFIS in order to compare the prediction accuracy of surface roughness. The comparison indicates that the bell-shaped MF in ANFIS achieves slightly higher prediction accuracy than other MF.