Manufacturing Technology Today

R. Viswanathan ¹, S. Ramesh ²

Affiliations
1 Dept of Mech Engg, Paavai Engineering College, Namakkal, IN
2 Annai Mathammal Sheela Engineering College, Namakkal, IN

Abstract

Magnesium alloy is one of the lightest materials currently finding wide applications in the production of aircraft engines, airframes, helicopter components, light trucks, automotive parts and computers parts due to its attractive properties. The difficulty in machining mg alloys with regular cutting tools like high speed steel (HSS), carbide tools requires new cutting tools to be tried. The surface finish is a key quality characteristic in dry turning of magnesium pieces and is often affected by multiple factors within the machining process. In this attempt Mg AZ91D alloy is machined with polycrystalline diamond (PCD) coated cutting tool and the effects of input parameters like cutting speed, feed and depth of cut were studied to evaluate the surface roughness obtained. The input parameters were optimized using Taguchi techniques. It was found that the parameter having greatest influence on the surface roughness was feed rate followed by depth of cut and cutting speed.

Keywords

Magnesium Alloy, Machining, Optimization, Taguchi Technique and Surface Roughness.

Full Text

     

S. Ramesh ¹, M. Pradeep Kumar ², L. Karunamoorthy ², K. S. Vijay Sekar ²

Affiliations
1 Dept. of Mechanical & Prod. Engg., Sathyabama University, Chennai, IN
2 Dept. of Mechanical Engg., Anna University, Chennai, IN

Abstract

Titanium and its alloys are attractive materials due to their unique high strength to weight ratio and their exceptional corrosion resistance. This paper combines the predictive machining approach with neural network modeling of cutting parameters. Experimental work has been performed in orthogonal cutting of Ti-6Al-4V using Plain Carbide tool. At the selected cutting conditions the forces have been measured. The experimental data were utilized to train the developed simulation environment based on back propagation neural network modeling. The cutting speed, feed, depth of cut have been considered as the input parameters and cutting force, feed force as output parameters to develop the model. The trained neural network was used in predicting the cutting parameters. Predictive ANN models were found to be capable of better predictions of forces about 93 to 97% accuracy within the range that they had been trained.

Full Text