Optimizing Milling Parameters for Al7075/ nano SiC/TiC Hybrid Metal Matrix Composites using Taguchi Analysis and ANN Prediction

Abstract

This research deals with the optimization of milling parameters for Al7075/nano SiC/TiC hybrid metal matrix composites by Taguchi approach an Artificial Neural Network. Experimental trials conducted in accordance with Taguchi L9 orthogonal array design conveyed that the optimum combination to minimize surface roughness is with a cutting speed of 100 m/min, feed 0.1 mm/tooth, and depth of cut as 1 mm. The results revealed that the surface roughness was significantly decreased under the optimal conditions and the values were in the range of 0.85 μm. Further, an ANN model was developed to predict the surface roughness based on the inputs. It is found that it showed excellent prediction, and the overall accuracy was 99.48% after 195 epochs. Therefore, system validation using experimental results showed that the ANN can be relied upon to forecast the surface roughness values. Thus, the combination of the experimental validation and ANN modeling studies provided valuable information for the optimization of machining parameters, which helped manufacturers to improve the surface quality and performance of the product in Al7075/nano SiC/TiC hybrid metal matrix composites .

Keywords

• milling parameters
• taguchi analysis
• artificial neural network
• surface roughness
• metal matrix composites