Optimization of surface roughness and cutting force during AA7039/Al2O3 metal matrix composites milling using neural networks and Taguchi method

• AA7039 based metal matrix composites reinforced with 10 wt.% Al2O3 were fabricated.
• The effects of cutting parameters in face milling AA7039/MMCs were investigated.
• Surface roughness values were significantly improved in milling of MMCs.
• Cutting forces were not affected significantly in milling 10 wt.% Al2O3 composites.
• ANNs was able to use for the prediction of surface roughness and cutting force.

In the present study, AA7039/Al2O3 metal matrix composites were produced by powder metallurgy and the effect of milling parameters on surface roughness and cutting force using an uncoated carbide insert were investigated. The milling tests were performed based on the Taguchi design of experiment method using L18 21 × 32 with a mixed orthogonal array. The effects of the cutting parameters on surface roughness and cutting force were determined by using analysis of variance (ANOVA). The analysis results showed that material structure was the most effective factor on surface roughness and feed rate was the dominant factor affecting cutting force. Surface roughness values were significantly improved by between 196% and 312% in milling Al2O3 particle-reinforced aluminum alloy composite compared to AA7039 aluminum. Artificial neural networks (ANN) and regression analysis were used to predict surface roughness and cutting force. ANN was able to predict the surface roughness and cutting force with a mean squared error equal to 2.25% and 6.66% respectively.