28-08-2014, 11:24 AM
End milling
End.doc (Size: 24.5 KB / Downloads: 67)
ABSTRACT
End milling process being an important machining process widely used in aerospace industry and elsewhere for the machining of dies and molds. The optimization of this process is particularly more important to save cost and time. Experimental optimization consisting of suitable selection of machining parameters for End Milling process relies heavily on the operator’s technologies and experience because of their numerous and diverse range. Machining parameters provided by the machine tool builder cannot meet operator’s requirements. Since for an arbitrary desired machining time for a particular job, they do not provide the optimal conditions. Therefore there is a need to develop a methodology to optimize the process parameters in End Milling process.
The present work involves the estimation of optimal values of the process variables like, speed, feed and depth of cut are studied as metal removal rate (MRR) and tool wear resistance as the output .An Artificial Neural Network (ANN) was developed and predicted of the relationship between input& output parameters during .Work piece AISI 52100 steel of size 200mm*300mm*25mm with hardness 50 HRC. The input parameters of the ANN model are the cutting parameters: speed, feed rate and depth of cut. The output parameters of the model are two measured during the machining trials namely, Metal removal rate (MRR) and tool wear resistance. The model consists of a two layered feed forward back propagation neural network.
The thesis discusses the Optimization of surface roughness in milling using Artificial Neural Network (ANN). Response Surface Methodology (RSM) and Neural Network implemented to model the end milling process that are using coated carbide TiN as the cutting tool and aluminium 6061 as material due to predict the resulting of surface roughness. The parameters of the variables are feed, cutting speed and depth of cut while the output is surface roughness. The model is validated through a comparison of the experimental values with their predicted counterparts. A good agreement is found where RSM approaches show 83.64% accuracy which reliable to be use in Ra prediction and state the feed parameter is the most significant parameter followed by depth of cut and cutting speed influence the surface roughness. ANN technique shows 96.68% of accuracy which is feasible and applicable in the prediction value of Ra.