Genetic Modeling for Enhancing Machining Performance of High-Volume Fraction 45% SiCp/Al Particle Reinforcement Metal Matrix Composite

Abstract

Metal matrix composites (MMCs) have gained great recognition in recent decades in a wide range of applications, including aerospace, automobiles, engine cylinders, and other sectors. MMCs possess excellent properties including being light in weight, high corrosion resistance, stiffness, and strength. However, they are categorized as difficult-to-cut materials where machining of these materials remains a challenging task. To improve the machining process quality and to avoid unnecessary experiments in a cost-effective manner, this article aims to develop an artificial intelligence model, using the genetic programming (GP) method to predict the cutting force, surface roughness, and tool life during the machining process of SiCp/Al at different cutting parameters including cutting speed, feed rate, and depth of cut. The developed genetic programming-based prediction model is designed and developed using MATLAB software. Meanwhile, the GP parameters including mean square error, root means square error, normalized mean square error, mean error, variation of error, correlation coefficient, and R-square are used for the validating of the proposed model. The GP model results are compared with our previous response surface methodology (RSM) model results that were employed to estimate the machining characteristics of the SiC particle-reinforced metal matrix composites (45% SiCp) with different cutting parameters. The GP results prove the higher efficiency with the prediction of the cutting force, surface roughness, and tool life, 43.07%, 37.82%, and 115.64%, respectively, compared with the previous RSM method.