Title: Experimental evaluation of surface roughness for end milling of Al 6063: response surface and neural network model
Authors: P.S. Sivasakthivel; V. Vel Murugan; R. Sudhakaran
School of Mechanical Engineering, SASTRA University, Thanjavur 613 401, Tamil Nadu, India.
Sree Sakthi Engineering College, Coimbatore 641 104, Tamil Nadu, India.
Department of Mechanical Engineering, Kumaraguru College of Technology, Coimbatore 641 049, Tamil Nadu, India
Abstract: This paper presents a study on the effect of process parameter on surface roughness in end milling process. Response surface methodology was employed to create a model to predict surface roughness in terms of machining parameters such as helix angle of cutting tool, spindle speed, feed rate, axial and radial depth of cut. The experiments were conducted on Al 6063 by HSS end mill cutter and surface roughness value was measured using Surftest SJ201. The adequacy of the model was verified using analysis of variance. The direct and interaction effect of the machining parameter with surface roughness were analysed. Neural network model was developed to predict surface roughness. Error percentages of both predicted response of response surface and neural model are found to be less than 5%. [Received 16 April 2010; Revised 30 September 2010; Accepted 30 December 2010]
Keywords: response surface methodology; RSM; neural networks; analysis of variance; surface roughness; mathematical modelling; end milling; ANOVA; surface quality; aluminium.
Int. J. of Manufacturing Research, 2012 Vol.7, No.1, pp.9 - 25
Available online: 01 Feb 2012