Effect of cutting parameters on tool life during end milling of AISI 4340 under MQL condition

Purpose The purpose of this paper is to study the cutting performance of high-speed regime end milling of AISI 4340 by investigating the tool life and wear mechanism of steel using the minimum quantity lubrication (MQL) technique to deliver the cutting fluid. Design/methodology/approach The experiments were designed using Taguchi L9 orthogonal array with the parameters chosen: cutting speed (between 300 and 400 m/min), feed rate (between 0.15 and 0.3 mm/tooth), axial depth of cut (between 0.5 and 0.7 mm) and radial depth of cut (between 0.3 and 0.7 mm). Toolmaker microscope, optical microscope and Hitachi SU3500 Variable Pressure Scanning Electron Microscope used to measure tool wear progression and wear mechanism. Findings Cutting speed 65.36%, radial depth of cut 24.06% and feed rate 6.28% are the cutting parameters that contribute the most to the rate of tool life. The study of the tool wear mechanism revealed that the oxide layer was observed during lower and high cutting speeds. The former provides a cushion of the protective layer while later reduce the surface hardness of the coated tool Originality/value A high-speed regime is usually carried out in dry conditions which can shorten the tool life and accelerate the tool wear. Thus, this research is important as it investigates how the use of MQL and cutting parameters can prolong the usage of tool life and at the same time to achieve a sustainable manufacturing process.

Prediction and Analysis of the Surface Roughness in CNC End Milling Using Neural Networks

In the metal cutting process of machine tools, the quality of the surface roughness of the product is very important to improve the friction performance, corrosion resistance, and aesthetics of the product. Therefore, low surface roughness is ideal for mechanical cutting. If the surface roughness of the product can be predicted, not only the quality of the product can be improved but also the processing cost can be reduced. In this study a back propagation neural network (BPNN) was proposed to predict the surface roughness of the processed workpiece. ANOVA was used to analyze the influence of milling parameters, such as spindle speed, feed rate, cutting depth, and milling distance. The experimental results show that the root mean square error (RMSE) obtained by using the back propagation neural network is 0.008, which is much smaller than the 0.021 obtained by the traditional linear regression method.