Predictive Modeling of Surface Roughness and Feed Force in Al-50wt% Si Alloy Milling Based on Response Surface Method and Various Optimal Algorithms

Al-50wt% Si alloy is considered as a difficult-to-machine material and is lack of precision machining research. In this paper, the response surface methodology (RSM), artificial neural network (ANN) and genetic algorithm (GA) are coupled to determine the optimum cutting conditions leading to the minimum surface roughness R-a and feed force F-t in Al-50wt% Si alloy precision milling. The purpose is to address the problem of machining parameters optimization in precision milling high Si-Al alloy. The R-a and F-t were considered as two process responses and cutting speed (v(c)), feed per tooth (f(z)), radial cutting depth (a(e)) and axial cutting depth (a(p)) were the process parameters. Using the rotatable orthogonal central composite design, 31 experiments were conducted. Based on RSM and analysis of variance (ANOVA), the influence of milling parameters on R-a and F-t was studied. The ANN was also employed for developing R-a and F-t predictive models, and its predictive capability was more accurate compared with RSM. Parameter optimizations were performed for minimizing R-a and F-t in single-objective and multi-objective cases using GA. In multi-objective optimization, the entropy weight method (EWM) was also implemented. Finally, the optimal parameter combination for precision milling Al-50wt% Si alloy was obtained as v(c) = 105 m/min, f(z) = 0.013 mm/z, a(e) = 3.909 mm and a(p) = 0.14 mm. The prediction errors were found as 3.27% and 4.65% for R-a and F-t, respectively. The results showed the effectiveness of the predictive model and the optimization method.