Optimization and prediction of surface quality and cutting forces in the milling of aluminum alloys using ANFIS and interval type 2 neuro fuzzy network coupled with population-based meta-heuristic learning methods

Milling is among the most commonly used, flexible, and complex machining methods; and adequate selection of process parameters, modeling, and optimization of milling is challenging. Due to complex morphology of cutting process, edge and surface defects and elevated cutting forces and temperature are the main observations if non-adequate cutting parameters are selected. Therefore, modeling surface roughness and cutting forces in the milling process are of prime importance. Due to the ability of neuro-fuzzy networks to maintain appropriate modeling with investigation of uncertainties and the capacity of meta-heuristic approaches to set the coefficients of these networks precisely, in the present study, the coupled models of adaptive neuro-fuzzy inference system (ANFIS-type fuzzy neural networks) and interval type 2 fuzzy neural networks with evolutionary learning algorithms including particle swarm optimization (PSO) and genetic algorithm (GA) were used to predict the mean values of directional cutting forces as well as average surface roughness (Ra) in milling aluminum alloys (AA6061, AA2024, AA7075) under various cutting conditions and insert coatings. The main innovation of the present study refers to implementation of IT2FNN- PSO method in the machining operations. No similar research in this regards was found in the literature. According to the results, it was found that the proposed methods led to excellent and precise modeling results with high correlation rates with experimental outputs. The use of IT2FNN-PSO led to better performance as compared to observations made in other two ANFIS-based models aforementioned.