Title: A systematic approach of surface texture prediction during high-speed CNC turning of ARNE^® (AISI O1) alloyed steel using response surface analysis and artificial neural networks

Authors: Nikolaos A. Fountas; Aleksandar Vencl; Angelos M. Koutsomichalis; Nikolaos M. Vaxevanidis

Addresses: Laboratory of Manufacturing Processes and Machine Tools (LMProMaT), Department of Mechanical Engineering, School of Pedagogical and Technological Education (ASPETE), ASPETE Campus, 151 22 Amarousion, Greece ' Faculty of Mechanical Engineering, University of Belgrade, Kraljice Marije 16, 11120 Belgrade 35, Serbia ' Hellenic Air-Force Academy, Faculty of Aerospace Studies, Dekelia Air Force Base, GR 19005, Greece ' Laboratory of Manufacturing Processes and Machine Tools (LMProMaT), Department of Mechanical Engineering, School of Pedagogical and Technological Education (ASPETE), ASPETE Campus, 151 22 Amarousion, Greece

Abstract: The present research reports on the application of the artificial neural networks (ANNs) for the modelling of processed surface texture parameters in turning of a high-strength, high alloyed steel. The variable input parameters of the ANN consisted of cutting speed Vc (m/min), feed rate f (mm/rev), and depth of cut, a (mm) whereas the output parameters that utilised were the average surface roughness Ra and maximum height of the measured profile, Rt. A full factorial experimental design (FF-DOE) was selected for generating the experimental data. The achieved outcomes indicated that, despite the complexity of the process and parameter interactions, the suggested ANN could be efficiently used to forecast the surface texture parameters during the hard turning process, thus confirming the production process planning.

Keywords: design of experiments; response surface analysis; artificial neural networks; ANNs; high-speed CNC turning; surface roughness.

DOI: 10.1504/IJEDPO.2024.140473

International Journal of Experimental Design and Process Optimisation, 2024 Vol.7 No.2, pp.153 - 171

Received: 02 Oct 2023
Accepted: 30 Jan 2024
Published online: 19 Aug 2024 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article