Title: Modelling of surface roughness in CNC face milling of alloy stellite 6

Authors: Saeed Zare Chavoshi

Addresses: Department of Design, Manufacture and Engineering Management, University of Strathclyde, Glasgow, G1 1XJ, UK

Abstract: In this study, soft computing techniques including multilayer perceptron (MLP), generalised feed forward (GFF), modular neural network (MNN) and co-active neuro-fuzzy inference system (CANFIS) are presented for the prediction of surface roughness during CNC face milling of alloy stellite 6. Prediction model based on regression analysis (RA) is also presented for comparison. Input variables consist of cutting speed, feed rate and depth of cut while output variable is surface roughness. The trained models using experimental data are tested using the set of validation data. Modelling results presented using machining data demonstrate that the CANFIS is reasonably more accurate. For determining the effects of machining parameters on surface roughness, statistical analysis using main effect and interaction plots are performed.

Keywords: face milling; stellite 6; surface roughness; soft computing; regression analysis; modelling; surface quality; CNC milling; multilayer perceptron; MLP; neural networks; neuro-fuzzy inference system; fuzzy logic; cutting speed; feed rate; depth of cut.

DOI: 10.1504/IJCMSSE.2013.059121

International Journal of Computational Materials Science and Surface Engineering, 2013 Vol.5 No.4, pp.304 - 321

Received: 13 Nov 2012
Accepted: 11 Jun 2013

Published online: 21 Jun 2014 *

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