For Libraries For Publication Open Access Downloads About Us Contact Us
Paper Titles
Research on Network Manufacturing Resources Optimization Deployment
p.485
A Direct Approach for Loop Subdivision Surface Offset Approximation
p.495
An Overview of STL Model Offset
p.499
Calling Method of Process Sheet in Interactive Round-Hole Broach CAPP System
p.503
An Online Prediction Model for BFG Output in Steel Industry
p.507
Discussion on Equipment Acquisition System Modeling
p.513
Finite Element Analysis of Deformation of the Multipoint Flexible Clamped Thin-Wall Component during Machining
p.519
The Research of Machining Process Design Based on Manufacturing Resources in MBD Mode
p.523
Application of Proteus Simulation for the Stepper Motor Control in Experimental Teaching
p.528

An Online Prediction Model for BFG Output in Steel Industry

Article Preview

Abstract:

The output prediction of blast furnace gas (BFG), influenced by many complex production factors, is a very important and difficult problem concerning the byproduct gas balance in steel industry. A new online least squares support vector machine (LSSVM) prediction model is proposed in this paper, in which the training data is filtered by an improved empirical mode decomposition threshold filtering (IEMDTF). The model is solved and optimized by an online learning algorithm and an online bayesian parameters optimization, respectively. The experimental results using practical BFG output data from BaoSteel Co. Ltd., China show the proposed model is effective and enable to offer reasonable gas balance scheduling for operators.

You might also be interested in these eBooks
Automatic Manufacturing Systems II View Preview

Info:

Periodical:

Advanced Materials Research (Volumes 542-543)

Pages:

507-512

DOI:

https://doi.org/10.4028/www.scientific.net/AMR.542-543.507

Citation:

Cite this paper

Online since:

June 2012

Authors:

Xiaoping Zhang, Jun Zhao

Keywords:

Bayesian Parameters Optimization, Blast Furnace Gas Output Prediction, Empirical Mode Decomposition Threshold Filtering, Least Squares Support Vector Machines (Ls-SVM)

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

© 2012 Trans Tech Publications Ltd. All Rights Reserved

Share:

Citation:

References

[1] J. A. K. Suykens: Neural network world Vol.10(2000), p.29

Google Scholar

[2] Marcelo Espinoza, J. A. K. Suykens and Bart De Moor:Computational Management Science Vol.3(2006 ), p.113

Google Scholar

[3] B.Jiang, H. Q. Wang and Y. W. Fu: Nature Science Process Vol.17(2007), p.415

Google Scholar

[4] X. L.Wang, W. H. Zhang and H. Z. Wang:Control and Decision Vol.23(2008), p.357 (in Chinese)

Google Scholar

[5] J. A. K. Suykens, J. De Brabanter, L.Lukas and et al.: Neurocomputing Vol.48(2002), p.85

Google Scholar

[6] P.Flandrin, G.Rilling and P. Goncalves: IEEE Signal Processing Letters Vol.11(2004), p.112

Google Scholar

[7] Z.Wu, N. E. Huang: Proceedings of the Royal Society A Vol.23(2004), p.1597

Google Scholar

[8] L. J.Li, H. Y. Su, and J. Chu:Acta automatic sinica Vol.33(2007), p.1182

Google Scholar

[9] G. C. Cawley and N. L. C.Talbot: Neural Networks Vol.17(2004), p.1467

Google Scholar

[10] Tony Van Gestel, J. A. K. Suykens and et al.:IEEE transactions on neural networks Vol.12(2001), p.809

Google Scholar

[11] M. V.Chi, P. K.Wong and Y. P. Li:Engineering Applications of Artificial Intelligence Vol.19(2006), p.277

Google Scholar

© 2025 Trans Tech Publications Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies. For open access content, terms of the Creative Commons licensing CC-BY are applied.
Scientific.Net is a registered trademark of Trans Tech Publications Ltd.