Experimental Investigation of Cutting Parameters in Machining of Inconel-800 Super-Alloy Under Nanofluid MQL Using Integrated RSM and NSGA-II

Abstract

This study investigates the effect of cutting parameters on output responses in milling newly difficult-to-machine material. The nanofluid minimum quantity lubrication (MQL) - a fluid cutting approach that has allowed in modern industrial was utilized to improve the machinability of the difficult-to-machine material. A set of physical experiments were carried out using the Orthogonal Array experimental design method to generate 27 experiments with four input variables (cutting velocity, depth of cut, feed per tooth, and radius of the cutting tool). The output responses were collected, including surface roughness (Ra) and material removal rate (MRR). Three models (response surface methodology (RSM), radial basis function (RBF), and Kriging) were employed to render the relationship between the input and output responses to find out the most suitable model. Finally, the Non-dominated Sorting Genetic Algorithm II (NSGA-II) was used to solve the constrained optimization problems. The optimal surface roughness results showed that using the RSM model combination with the NSGA-II algorithm produced 40.8% enhancement compared to the non-optimal application.