Modeling the Surface Roughness for Fine Turning of AISI304 Stainless Steel


Article Preview

High ductility, high strength, high work hardening rate and low thermal conductivity of stainless steels are the main factors that make their machinability difficult. In this study, determination of the optimum cutting condition has been aimed at when fine turning an AISI 304 austenitic stainless steel using ceramic cutting tools. The cutting speeds for the turning test were from 80 to 320 m / min, feed rates were from 0.04 to 0.10 mm / rev and the depth of cut was fixed at 0.1 mm. According to the test results, we can find that the values of surface roughness were decreased when the cutting speed was increasing, and decrease with the decrease of feed rate. But when the cutting speed was greater than 360 m / min, or the feed rate was smaller than 0.02 mm / rev,the surface roughness would be deteriorated because of the chatter phenomenon. In this paper, a polynomial network is adopted to construct a prediction model on surface roughness for fine turning of AISI304 austenitic stainless steel. The polynomial network is composed of a number of functional nodes. These functional nodes are self-organized to form an optimal network architecture by using a predicted square error (PSE) criterion. It is shown that the polynomial network can correctly correlate the input variables (cutting speed and feed rate) with the output variable (surface roughness). Based on the surface roughness prediction model constructed, the surface roughness of the workpiece can be predicted with reasonable accuracy if the turning conditions are given and it is also consistent with the experimental results very well.



Key Engineering Materials (Volumes 364-366)

Edited by:

Guo Fan JIN, Wing Bun LEE, Chi Fai CHEUNG and Suet TO




W. S. Lin, "Modeling the Surface Roughness for Fine Turning of AISI304 Stainless Steel", Key Engineering Materials, Vols. 364-366, pp. 644-648, 2008

Online since:

December 2007





[1] G. J. Montgomery, and K. C. Drake, Neurocomputing, Vol. 2(1991), p.97.

[2] A. G., Ivakhnenko, IEEE Transaction on System, Man and Cybenetics, 1(4)(1971), p.364.

[3] A. R. Barron, Predicted Square Error: A Criterion for Automatic Model Selection, SelfOrganizing Methods in Modeling: GMDH Type Algorithms, ed. by Farlow, S. J., (Marcel-Dekker, New York, 1983).

[4] R. L. Barron, A. N. Mucciardi, F. J. Cook, J. N. Craig, and A. R. Barron, Adaptive Learning Networks: Development and Application in the United States of Algorithms Related to GMDH, Self-Organizing Methods in Modeling: GMDH Type Algorithms, ed. by Farlow, S. J., (Marcel- Dekker, New York, 1984).

[5] S., Vajpayee, Wear, Vol. 70(1981), p.165.

[6] T., Sata, et al, Annals of CIRP, Vol. 34/1/(1985).