Prediction of cutting force in end milling of glass fiber reinforced polymer (GFRP) composites using adaptive neuro fuzzy inference system (ANFIS)

Abstract

The anisotropic and heterogeneous properties of glass fiber-reinforced plastic (GFRP) composites lead to a challenging machining process. The end milling process of these materials generates excessive cutting force that leads to several undesirable damages such as high surface roughness and delamination. Therefore, it is necessary to model the cutting force during the end milling process of GFRP composites materials to obtain an accurate prediction of cutting force. End milling process parameters, i.e., depth of cut (Aa), feeding speed (Vf), and spindle speed (n) are used as an input parameter and each has three levels. Hence, a randomized full factorial 3 × 3 × 3 is applied as the design of experiments. On the other hand, the cutting force (Fc) was used as an output parameter. In this study, an adaptive network-based fuzzy inference system (ANFIS) method is applied to model the cutting force during the end milling process of GFRP composites.