Experimental investigation on the performance of ceramics and CBN cutting materials during dry machining of cast iron: Modeling and optimization study using RSM, ANN, and GA

Abstract

This study focuses on the performance evaluation of CBN and ceramic tools in dry machining of gray cast iron EN GJL-350. The machining factors taken into account during turning are: cutting speed ( Vc), feed rate ( f), depth of cut ( ap), and cutting tool material (CBN, white ceramic, mixed ceramic, and silicon nitride). The first part of this investigation concerns the evaluation of the four cutting materials performance used in terms of tool wear evolutions, 2D and 3D surface roughness and cutting forces variation according to working parameters. The second part exposes the results according to L32 Taguchi design of experiment. Statistical treatment by ANOVA allowed to quantify the impact of the input factors on the performance parameters, namely the surface roughness ( Ra), the cutting force ( Fz), the cutting power ( Pc), and the specific cutting energy ( Ecs). The response surface methodology (RSM), and the artificial neural network (ANN) approach were adopted to develop mathematical models for predicting the different output parameters. The results of the two methods were compared and discussed. A multi-criteria optimization was performed using the desirability function (DF) approach. The genetic algorithm (GA) was also applied to find pareto fronts. The results found show that CBN is the most efficient material in terms of lower tool wear, surface roughness and cutting forces. The DF method allowed to find an optimal combination ( Vc = 660 m/min, f = 0.13 mm/rev, ap = 0.232 mm, and the CBN material) leading to a compromise between the minimization of ( Ra, Fz, Pc, and Ecs) and the maximization of (MRR). The Pareto fronts found by the (GA) method make it possible to propose a multitude of solutions according to the desired objectives.