Title: Neural network process modelling for turning of steel parts using conventional and wiper inserts

Authors: Tugrul Ozel, A. Esteves Correia, J. Paulo Davim

Addresses: Department of Industrial and Systems Engineering, Rutgers University, Piscataway, NJ 08854-8018, USA. ' Department of Mechanical Engineering and Industrial Management – DEMGI, School of Technology, Polytechnical Institute of Viseu, Campus de Repeses, 3504-510 Viseu, Portugal. ' Department of Mechanical Engineering, University of Aveiro, Campus Santiago, 3810–193 Aveiro, Portugal

Abstract: In this paper, the effects of insert design in turning of steel parts are presented. Surface finishing has been investigated in finish turning of AISI 1045 steel using conventional and wiper design inserts. Regression models and neural network models are developed for predicting surface roughness, mean force and cutting power. Experimental results indicate that lower surface roughness values are attainable with wiper tools. Neural network based predictions of surface roughness are carried out and compared with non-training experimental data. These results show that neural network models are suitable for predicting surface roughness patterns for a range of cutting conditions in turning.

Keywords: regression models; wiper inserts; neural networks; process modelling; steel turning; surface roughness; cutting force; insert design; surface finishing; finish turning; cutting power.

DOI: 10.1504/IJMPT.2009.025230

International Journal of Materials and Product Technology, 2009 Vol.35 No.1/2, pp.246 - 258

Published online: 16 May 2009 *

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