A Predictive Model of Hot Rolling Flow Stress by Multivariate Adaptive Regression Spline

Wan Huan Yu; Chang Gui Yao; Xiang De Yi

doi:10.4028/www.scientific.net/MSF.898.1148

Paper Titles

Welding Performance of Several New Rare Earth Tungsten Electrodes
p.1117

Abnormal Grain Growth on the Surface of Cold-Rolled AA1235 Aluminum Plate during the Annealing Process
p.1123

The Optimal Selection of Extrusion Parameters of As-Cast TC27 Titanium Alloy Based on Processing-Map
p.1134

Microstructure Evolution of Hot-Extruded Cu-15Ni-8Sn Alloy with Different Extrusion Ratios
p.1140

A Predictive Model of Hot Rolling Flow Stress by Multivariate Adaptive Regression Spline
p.1148

Effect of Solution Treatment on Microstructure and Mechanical Properties of Hot-Extruded Cu-15Ni-8Sn Alloy
p.1156

Numerical Simulation on Filling Optimization of Copper Rotor for High Efficient Electric Motors in Die Casting Process
p.1163

Filling of Microarray Fabricated by Micro Powder Injection Molding
p.1171

Finite Element Simulation of Chain-Die Forming U Profiles with Variable Cross-Section
p.1177

HomeMaterials Science ForumMaterials Science Forum Vol. 898A Predictive Model of Hot Rolling Flow Stress by...

A Predictive Model of Hot Rolling Flow Stress by Multivariate Adaptive Regression Spline

Abstract:

A new modeling method called multivariate adaptive regression spline (MARS) was firstly employed to predict the hot rolling flow stress and explain the relationship among flow stress and various parameters such as major chemical compositions, rolling temperature, rolling speed, compression ratio, thickness, roll radius, furthermore, analyze the importance of the predictor variables. The results showed that the error of training and testing was less than 2%, and rolling temperature, rolling speed, and strip thickness had much contribution to flow stress. Moreover, the impact of various factors on the flow stress can be validated by real production data, which proved the reliability of MARS model to predict the flow stress and guide the practical production.

You might also be interested in these eBooks

View Preview

Info:

Periodical:

Materials Science Forum (Volume 898)

Pages:

1148-1155

DOI:

https://doi.org/10.4028/www.scientific.net/MSF.898.1148

Citation:

Cite this paper

Online since:

June 2017

Authors:

Wan Huan Yu, Chang Gui Yao, Xiang De Yi

Keywords:

Flow Stress, Hot Rolling, MARS, Multivariate Adaptive Regression Spline, Predictive Model

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] J. H. Friedman, J. The Annals of Statistics 19(1) (1991) 1-67.

Google Scholar

[2] J. H. Friedman, Fast MARS, Department of Statistics and Stanford Linear Accelerator Center, Stanford University, (1993).

Google Scholar

[3] Z. Chu, Y. Z. Wu, L. P. Chen et al, J. Journal of System Simulation 24(8) (2012) 1561-1566.

Google Scholar

[4] Q. F. Meng, Y. Y. Du, H. F. Qu, J. Journal of Finance and Economics 26(25) (2011) 65-76.

Google Scholar

[5] L. C. Briand, B. Freimut, F. Vollei, J. Journal of Systems and Software 7(6) (2004) 80-82.

Google Scholar

[6] X. M. Zhang, Z. T. Nan, J. C. Wu, J. Journal of Glaciology and Geocryology 5 (2011) 1088-1097.

Google Scholar

[7] J. S. Liao, J. S. Hong, Proceedings of Conference on Environmental Pollution and Public Health, Wuhan, 2011, 335-33.

Google Scholar

[8] H. L. Wang, J. P. Xiang, G. Ge, J. Ocean Technology 25(3) (2006) 7-9.

Google Scholar

[9] A. Mukhopadhyay. A. Iqbal, J. Journal of Applied Statistics 36(1) (2009) 793-812.

Google Scholar

[10] J. H. Friedman, C. B. Roosen, J. Statistical Methods in Medical Research 4(3)(1995) 197-217.

Google Scholar

[11] Y. L. Kang, The rolling engineering, Metallurgical Industry Press, Beijing, (2004).

Google Scholar