Surface roughness prediction in end milling using multiple regression and adaptive neuro-fuzzy inference system

Faculty of Engineering

Assiut University

Surface roughness prediction in end milling using multiple regression and adaptive neuro-fuzzy inference system

Research Authors
I. M. Soltan , M. E. H. Eltaib , R. M. El-Zahry
Mechanical Engineering Department, Faculty of Engineering, Assiut University, Assiut,
Research Member
Mohamed El_sayyed Hosni Tayeb
Research Year
2006
Research Journal
Fourth Assiut University Int. Conf. on Mech. Eng. Advanced Tech.
614
For Indus. Prod., December 12-14 (2006)
Research Publisher
ASSIUT UNIVERSITY-FACULTY OF ENGINEERING
Research Vol
DECEMBER-2006
Research Rank
3
Research_Pages
614-620
Research Abstract

ABSTRACT–
Multiple regression and adaptive neuro-fuzzy in
ference system (ANFIS) were used to
predict the surface roughness in the end milling process.
Spindle speed, feed rate
and depth of cut were
used as predictor variables. Generalized bell me
mberships function (gbellmf) was adopted during the
training process of ANFIS in this study. The pr
edicted surface roughness using multiple regression and
ANFIS were compared with measured data, the ac
hieved accuracy were 91.9% and 94% respectively.
These results indicate that the tr
aining of ANFIS with the gbellmf is
accurate than multiple regression in
the prediction of surface roughness.