PREDICTION AND ANALYSIS OF THE ROUGHNESS OF MILLED SURFACES BASED ON FUZZY LOGIC

The influence of the cutting conditions of machining process on the surface roughness has been the subject of several scientific works in order to optimize the milling process to get the best-finished surface machined by milling. During the last decades, many methods of artificial intelligence have been carried out to investigate the effect of milling conditions like the cutting speed, feed per tooth and depth of cut on surface integrity of machined surfaces by milling process. However, the progress on the use of Numerical Approaches to predict the surface integrity of machined surfaces like roughness, microhardness, residual stress and cutting temperature still lagging behind the other advances in the industry. The aim of this work is to use the fuzzy logic to predict the surface roughness of the milled surfaces and to study the effect of cutting parameters (cutting speed, feed per tooth and depth of cut) on the roughness of the surfaces machined by milling. a new model was created using fuzzy logic based on an experimental database. The database includes the variation of the surface roughness of machined surfaces of the Ti-6Al-4V by milling according to the cutting parameters (cutting speed, feed per tooth and depth of cut) on which the model was develop on MATLAB using fuzzy tool. The inputs of the fuzzy inference model were the three cutting parameters of milling: the cutting speed, feed per tooth and depth of cut, and the output of the fuzzy system was the roughness of the machined surfaces by milling of the Ti-6Al-4V. The predicted values of roughness obtained by the fuzzy model were compared to the experimental values and the result was very good, the average error rate was verry low that’s mean that the prediction model based on fuzzy logic works correctly and with high accuracy and can be used as a solution to predict the surface roughness before starting milling provided to respect a very specific range of parameters (defined by the universe of discourse) when using this model. The approach based on fuzzy logic can be used also to predict other phenomena of milling process like cutting temperature and microhardness.