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.
Index Terms—Surface roughness, linear regression, genetic algorithm.
Mohd Fadzil Faisae Ab. Rashid is with the Faculty of Mechanical Engineering, Universiti Malaysia Pahang, 26600 Pekan, Pahang, Malaysia (e-mail: ffaisae@ump.edu.my).
[PDF]
Cite: Mohd Fadzil Faisae Ab. Rashid, "An Improved Mathematical Model to Predict Surface Roughness Using Hybrid Method," International Journal of Materials, Mechanics and Manufacturing vol. 3, no. 1, pp. 36-39, 2015.
![[Click]](http://www.ijmmm.org/img/ijmmm_v7n2_inspec%28IET%29_indexscreenshot.jpg){kind=link}