ANN and QRCCD Prediction of Surface Roughness Under Biodegradable Nano-lubricant

Sustainable manufacturing of machine parts lies in predicting and optimizing the machining parameters for the machining operations. The optimized parameters will produce sustainable products with reduced corrosion and fatigue problems because the roughness of the surface of the product will lead to the failure of the component or part during the production process. This investigation focuses on the prediction and optimization of the experimental data of surface roughness of AA8112 alloys obtained during the end-milling process with a biodegradable nano-lubricant. The study employed vegetable oil as the base cutting fluid (copra oil) and MWCNTs nanoparticles as an additive. This study prediction analysis was carried out with an artificial neural network (ANN) and quadratic rotatable central composite design (QRCCD). The results show that the ANN and QRCCD predicted the experimental data with 95.50% and 99.50%, respectively. Both prediction analyses’ error percentages are 5.5% from the ANN and 0.5% from the QRCCD. The QRCCD optimized parameters for the minimum surface roughness are spindle speed of 3366 rpm, 101 mm/min feed rate, 1 mm depth of cut, 20 mm length-of-cut, and 39.6° helix angle. These parameters achieved the minimum surface roughness of 1.16 μm, which is closely related to the optimized value from the experimental data. Therefore, the study in this chapter will recommend manufacturers employ the optimized machining parameters for product production.