International Scientific Journals
of Scientific Technical Union of Mechanical Engineering "Industry 4.0"

This paper presents an experimental study related to the optimization of cutting parameters in roughing turning of AISI 1045 steel under flooded conditions. The aim is to find a suitable combination of cutting parameters (cutting speed, depth of cut and feed rate) that minimize specific cutting energy and maximize material removal rate. The machining experiments were performed based on the Taguchi L27 full-factorial orthogonal array and response surface methodology (RSM) has been used to obtain the regression model for the specific cutting energy and material removal rate. Analysis of variance (ANOVA) was used to find out the significance of each cutting parameter. Finally, the developed models were interfaced with an artificial bee colony (ABC) to determine the optimal set of cutting parameters.

Modelling and prediction of cutting forces in metal cutting is very important, due to their significant impacts on quality of machined surface, tool wear, self-excited vibrations, etc. However, accurate modelling of the cutting forces in high pressure jet assisted machining is not a simply task due to complex relations between many highly interlinked variables of cutting process influencing these forces. The objective of this study is to utilize two artificial intelligence methods, namely particle swarm optimization (PSO) and simulated annealing (SA), for prediction of the cutting forces components in high pressure jet assisted turning of carbon steel Ck45E. A study of effect of various process parameters including feed, cutting speed and depth of cut on the cutting forces was carried out. The results obtained from the PSO and SA based models were compared with experimental results for their performance. The analysis reveals that developed models are able to make accurate prediction of cutting forces by utilizing small sized training and testing datasets.