Surface Roughness Prediction in Turning Operation of Aluminum Alloy 6061using Artificial Neural Network (Ann)
Osamah Fadhil Abdulateef*
AlKhwarizmi College of Engineering, Automated Manufacturing Engineering Department, University of Baghdad, Baghdad, Iraq.
This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Surface quality receives great attention in turning achievement as a good quality turned surface greatly enhances the mechanical and chemical properties of the products. Consequently, the required surface finish is typically prescribed, and the correct cutting parameters are chosen to achieve the superior quality needed. In this work, an experimental investigation and predictive model utilizing the MATLAB with neural network (NN) back-propagation learning algorithms were conducted for studying the effect of feed rate, cutting depth, and cutting speed on surface roughness during dry turning of 6061 aluminum alloy. The experimental design was followed up with a complete factorial design of experiments corresponding to 27 runs. The contribution from mentioned three parameter’s to surface roughness is determined using a sensitivity analysis. During the study, the feed rate is found to be the most important parameter influencing surface roughness (70.3%), followed by cutting speed with a percentage contribution (19.9%). Further, it was also noticed that due to thermal softening effect, surface roughness decreases as cutting speed increases and surface roughness increases as feed rate increases as a result of friction between the cutting tool and the manufacturing material. Comparing the experimental data with the finding from artificial neural network (ANN) reveals that there is no substantial variance and that algorithm has been used with confidence.