Swarm intelligence integrated approach for experimental investigation in milling of multiwall carbon nanotube/polymer nanocomposites

Abstract

In manufacturing industries, the selection of machine parameters is a very complicated task in a time-bound manner. The process parameters play a primary role in confirming the quality, low cost of manufacturing, high productivity, and provide the source for sustainable machining. This paper explores the milling behavior of MWCNT/epoxy nanocomposites to attain the parametric conditions having lower surface roughness ( Ra ) and higher materials removal rate ( MRR ). Milling is considered as an indispensable process employed to acquire highly accurate and precise slots. Particle swarm optimization (PSO) is very trendy among the nature-stimulated metaheuristic method used for the optimization of varying constraints. This article uses the non-dominated PSO algorithm to optimize the milling parameters, namely, MWCNT weight% ( Wt .), spindle speed ( N ) , feed rate ( F ) , and depth of cut ( D ) . The first setting confirmatory test demonstrates the value of Ra and MRR that are found as 1 . 62 µ m and 5.69 mm 3 /min, respectively and for the second set, the obtained values of Ra and MRR are 3.74 µ m and 22.83 mm 3 /min respectively. The Pareto set allows the manufacturer to determine the optimal setting depending on their application need. The outcomes of the proposed algorithm offer new criteria to control the milling parameters for high efficiency.