Discrimination of D2 steel roughness after hard milling

¹ Laboratory of Mechanics, Materials and Processes (LMMP), National High School of Engineering of Tunis (ENSIT) - University of Tunis. 5, Avenue Taha Hussein - Montfleury - 1008 Tunis, Tunisia
² Department of Mathematics and Industrial Engineering, Polytechnique Montreal, Montreal, QC H3T 1J4, Canada

^* Corresponding author: This email address is being protected from spambots. You need JavaScript enabled to view it.

Abstract

This article discusses the discrimination of machined surfaces following the milling of 62 HRC hardened AISI D2 steel, a material used in the industrial sector due to its considerable harnesses and resistance to wear. The main aim of this research is to determine the most appropriate surface roughness parameter, be it Ra evaluated on two orientations (Ra (0) and Ra (90)) or Sa (arithmetic surface roughness), in order to effectively distinguish between surfaces that appear visually similar. To this end, a series of milling experiments were carried out by varying several machining parameters, including cutting speed, feed rate and tool trajectory angle. Following machining, the surfaces produced were analyzed using precise roughness measurements. The experimental data were then studied using a machine-learning classification technique, with the aim of assessing the ability of each roughness parameter to differentiate the various surfaces created. The most decisive indicator of clustering is the Ra (0) parameter, as shown by the results.