Prediction of milled surface characteristics of carbon fiber-reinforced polyetheretherketone using an optimized machine learning model by gazelle optimizer

Abstract

Motivated by the nonlinear behavior of composite materials under different machining operations, this work aims at developing an optimized artificial intelligence model to predict milled surface characteristics of carbon fiber-reinforced polyetheretherketone (CFRPEEK). The milling operations were carried out under high-speed dry-cutting conditions. The developed model was employed to predict fractal dimension and surface roughness as functions of cutting speed, cutting width, feed per tooth, and orientation of fibers. The model is composed of an adaptive network-based fuzzy inference system (ANFIS) optimized by a gazelle optimizer (GO). The performance of the model was compared with five other optimized ANFIS models. ANFIS-GO showed outperformance compared with other models to predict milled surface characteristics. The root-mean-square deviation and determination coefficient of predicted data by ANFIS-GO compared with experimental ones are 0.002 and 0.911 for fractal dimension and 0.129 and 0.998 for surface roughness, respectively.