Surface finish produced on machined surface plays an important role in production. The surface roughness has a vital influence on most important functional properties like wear resistance, fatigue strength, corrosion resistance and power losses due to friction. Poor surface roughness will lead to the rupture of oil films on the packs of micro irregularities which lead to a state approaching dry friction and results in decisive wear of rubbing surfaces therefore finishing process are employed in

more »

... machining the surface of many critical components to obtain a very high surface finish. Process variables surface roughness in milling depends on spindle speed, feed, number of flutes, and depth of cut and plan approach angle. Mainly surface finish depends on spindle rpm, feed rate and depth of cut) Keywords-surface roughness, fatigue strength ,corrosion, wear resistance I Introduction surface roughness has received serious attention for many years. it has been an important design feature and quality measure in many situations such as parts subjected to fatigue loads, precision fits and fasteners. the experiment was conducted to analyse surface roughness on 6081 aluminium alloy using various machining variables such as spindle speed, feed rate, depth of cut and number of flutes. this data was used to develop surface roughness prediction models: as a function of spindle speed, feed rate, depth of cut, number of flutes for this material. purpose of this study is to develop a technique to predict a surface roughness of part to be machined according to cutting parameters. this project focuses on developing a first-order, second-order and third-order regression equation for surface roughness in cnc milling process. in developing these, the most familiar milling parameters such as spindle speed, feed Rate, Depth Of Cut And Number Of Flutes are considered. Surface roughness of machined components corresponding to these conditions is the output of this technique. The trained regression equations were used in predicting surface roughness for cutting conditions and tested using test data. The above technique is applied for generating first, second and third order regression equations for calculating the surface roughness. The plots were drawn between experimental and predicted values of surface roughness for various regression techniques and percentage accuracy is calculated. Finally, comparison is made between surface roughness values of first-order, second-order and third-order regression models with experimental values. From graphs, it is observed that second order model gives accurate results of surface roughness. The experimental results show, regression technique can be successfully used for predicting surface roughness.