Face milling by round insert is currently one of the most common processes for roughing, semi-finishing, and finishing machining operations. Proper estimation and analysis of the round insert cutting forces play an important role in the process optimization. This paper presents a new method for identifying specific cutting force coefficients (SCFCs) for full immersion face milling with round inserts. At the first step, an inverse method is proposed to solve the mechanistic force model equations by non-dominated sorting genetic algorithm II (NSGA-II) which is one of the powerful multiobjective optimization methods. In addition, the artificial neural network (ANN) models are developed to predict the SCFCs in non-experimented conditions. Mean absolute percentage error values for the proposed ANN are between 1.7 and 10.1 % for training and testing which are satisfactory. In order to evaluate the efficiency of NSGA-II and ANN models, extensive experimental cutting force results are compared with those obtained with the proposed algorithm. The good accordance in the entire time of cutting edge engagement shows the validity of the developed methodology. Moreover, the interactions of cutting parameters, i.e., cutting speed, feed per tooth, and depth of cut (DOC) on variations of tangential and radial shearing coefficients (ktc, krc) of specific cutting force are thoroughly investigated. The results show that in addition to cutting conditions, the cutting edge geometry of round insert has a significant influence on ktc and krc variations.

Keywords