Optimal Cutting Parameters Selection of Multi-Pass Face Milling Using Evolutionary Algorithms

Abstract

Over decades, particular attention was devoted to the optimal selection of the cutting conditions associated with the material removal processes, particularly for the multi-pass face milling operations considered as a highly complex problem both theoretically and practically. The machining conditions in the milling operations consist commonly of cutting speed, depths of cut, and feed rate. Researches in this field are of huge interest due to their considerable importance for the Computer- Aided Process Planning (CAPP) on one hand and the large impact of those variables on the quality of machining products, the operational costs, and the machining efficiency on the other hand. In this paper, various evolutionary optimization techniques are proposed to minimize the unit production cost of multi-pass face milling operations while considering technological constraints. The proposed optimization tools are based initially on the Genetic Algorithm (GA) with two different selection strategies, namely stochastic and tournament selections.And secondly, on theHybrid SimulatedAnnealingGenetic Algorithm (SAGA). The integration target of the simulated annealing (SA) based local search strategy with the genetic search is to prevent accurately the trap of GAs in premature convergence. Parameters of these three optimization approaches are then calibrated using Taguchi design of experiment (DEO) L27 orthogonal arraymethod. Finally, different case studies are considered in order to adequately show the effectiveness of the proposed mechanisms. The comparison of the obtained results with the suggested literature approaches; show the effectiveness of the proposed SAGA for selecting optimal cutting parameters of the multi-pass face milling operation.