Online Quality Prediction of Strip Hot-Dip Galvanizing Based on Support Vector Regression

Fei He; Zhi Guo Liang; Min Li; Jin Wu Xu

doi:10.4028/www.scientific.net/AMR.145.153

Paper Titles

Analysis on Influence of Dynamic Setting AGC Model Parameters on the Stability of Control System
p.128

The Calculation of Initial Velocity Field in Tension Reducing Deformation Zone of Steel Pipe
p.134

Research on Energy Equation of Lubrication Model on Large-Scale Journal Bearing System
p.139

Key Equipment and Innovative Technology for Tempering of Super Thin Strip
p.145

Online Quality Prediction of Strip Hot-Dip Galvanizing Based on Support Vector Regression
p.153

Analysis of the Mill Roller Bearing Using Mixed Fast Multipole Boundary Element Method
p.159

Optimization of Rolling Schedule in Tandem Cold Mill Based on QPSO Algorithm
p.165

The Development of Short Stress Path Experimental Asymmetric Multifunctional Rolling Mill
p.171

Analysis on Diffusion Parameters of Rolling Mill Bearing Alloy-Interface
p.177

HomeAdvanced Materials ResearchAdvanced Materials Research Vol. 145Online Quality Prediction of Strip Hot-Dip...

Online Quality Prediction of Strip Hot-Dip Galvanizing Based on Support Vector Regression

Abstract:

In order to predict product quality and optimize production process, the product quality model needs to be built. According to the fact that the common methods always cost long training time and can not realize real-time update, an online product quality model based on the online support vector regression is here proposed. The real field data of zinc coating weights from strip hot-dip galvanizing are used for validation. The results show that the models based on the online support vector regression have a higher prediction precision and shorter training time than traditional support vector regression, which is convenient to complete the real-time update. The zinc coating weights forecasting model based on the online support vector regression for multi-group data has an average of the relative prediction error of 4.35%, thus for the model will be used as an analysis tools for the quality control.

You might also be interested in these eBooks

Advances in Rolling Equipment and Technologies

View Preview

Info:

Periodical:

Advanced Materials Research (Volume 145)

Pages:

153-158

DOI:

https://doi.org/10.4028/www.scientific.net/AMR.145.153

Citation:

Cite this paper

Online since:

October 2010

Authors:

Fei He, Zhi Guo Liang, Min Li, Jin Wu Xu

Keywords:

Hot-Dip Galvanizing, Online Support Vector Regression, Quality Prediction, Zinc Coating Weight

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] L. H. Chiang, E. L. Russell and R. D. Braatz: Fault Detection and Diagnosis in Industrial Systems (Springer, NewYork 2001).

Google Scholar

[2] F. Jia, E. B. Martin and A. J. Morris: International Journal of Systems Science, Vol. 31 (2000) No. 11, p.1473.

Google Scholar

[3] V Vapnik: The Nature of Statistical Learning Theory (Springer, NewYork 1999).

Google Scholar

[4] J. S. Ma, J Theiler and S Perkins: Neural Computation, Vol. 15 (2003) No. 11, p.2683.

Google Scholar

[5] M. Martin: On-line Support Vector Machines for Function Approximation (Technical Report LSI-02-11-R, Software Department, Universitat Politecnica de Catalunya, Spain 2002).

Google Scholar

[6] F. Parrella: Online Support Vector Regression (MS. University of Genoa, Italy 2007), p.34.

Google Scholar

[7] V. Cherkassky and Y. Q. Ma: Neural Networks, Vol. 17 (2004) No. 1, p.113.

Google Scholar

[8] L. Zhu: Steel Materials Heat Coating Zinc (In Chinese) (Beijing Chemical Industry Press, China 2006). actual value prediction value sample number zinc coating weights / g·m －2.

Google Scholar