An Improved Mathematical Model to Predict Surface Roughness Using Hybrid Method

M. F. F., Ab Rashid (2015) An Improved Mathematical Model to Predict Surface Roughness Using Hybrid Method. International Journal of Materials, Mechanics and Manufacturing, 3 (1). pp. 36-39. ISSN 1793-8198. (Published)

	PDF 162-S103_Improved_Math_Model.pdf - Published Version Restricted to Repository staff only Download (1MB) | Request a copy
	PDF fkm-2014-fadzil-An_Improved_Mathematical.pdf Restricted to Repository staff only Download (403kB) | Request a copy

Abstract

Surface roughness is one of the most important requirements in machining process. In order to obtain needed surface roughness, the proper setting of cutting parameters is crucial before the process take place. Therefore, an accurate mathematical model to predict surface roughness is totally needed. This research presents a hybrid method which combine conventional multiple regression analysis and genetic algorithm to improve the accuracy of mathematical model to predict surface roughness. In experiment, three independent variables: spindle speed, feed rate and depth of cut were manipulated in collecting data. Full factorials cut were performed using FANUC CNC Milling α-Τ14ιE. The results show that the proposed hybrid method capable to improve accuracy of model with 23% and 28% of reduction in error.

Item Type:	Article
Additional Information:	This paper presented at 3rd International Conference on Manufacturing and Industrial Engineering, Bali, 22-23 March 2014
Uncontrolled Keywords:	Surface roughness; Linear regression; Genetic algorithm
Subjects:	T Technology > TS Manufactures
Faculty/Division:	Faculty of Mechanical Engineering
Depositing User:	Dr. Mohd Fadzil Faisae Ab. Rashid
Date Deposited:	26 Sep 2014 03:13
Last Modified:	03 Mar 2015 09:32
URI:	http://umpir.ump.edu.my/id/eprint/6693
Download Statistic:	View Download Statistics

Available Versions of this Item

• An Improved Mathematical Model to Predict Surface Roughness Using Hybrid Method. (deposited 26 Sep 2014 03:13) [Currently Displayed]

Actions (login required)

View Item