Prediction of Oxygen Consumption of BF in Iron & Steel Factories Based on Least Squares Support Vector Machine

Abstract:

In this paper, we presented a prediction model of oxygen consumption of blast furnace (BF) based on least squares support vector machine (LSSVM) with the production data of an iron and steel factory. This method utilizes data pre-processing and parameters optimization to improve the fitting precision and operation speed of the model. By comparing the prediction results using different models with actual production data, we found out that the modified regression model of LSSVM is more suitable to predict the trend of oxygen consumption than others. The prediction accuracy is satisfactory and is helpful for oxygen system dispatch and production practice.

• Periodical: Advanced Materials Research (Volumes 634-638)
• Pages: 3143-3148
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.634-638.3143
• Online since: January 2013
• Authors: Pei Lin Wu, Jian Jun Wang, Hong Juan Li, Hua Wang
• Keywords: LSSVM, Oxygen System, Parameter Optimization, Pre-Processing, Support Vector Machine (SVM)

References

[1] Z. Liu: Energy for Metallurgical Industry Vol. 6-11 (1998), p.17 (In Chinese).

[2] G.L. Tong, L. Wang, Y.P. Zhang: Iron and Steel Vol. 53-56 (2003), p.38 (In Chinese).

[3] Y.K. Mo: Research about the Decision Support System of Iron and Steel Enterprise Optimum Oxygen Supply: Master's dissertation (Huazhong University of Science and Technology, Hubei, China, 2004) (In Chinese).

[4] F.Y. Lu: Technical Gas Supply and Demand and Optimize Allocation in Iron and Steel Enterprise: Master's dissertation (Automation Research and Design Institute of Metallurgical Industry, Beijing, China, 2010) (In Chinese).

[5] Y.Z. Hu, Y.P. Zhang, S. Hu: Pretest the Oxygen Dosage for Iron and Steel Industry By MATLAB Neural Network Model, Metallurgical cycle economic development BBS 2008, Beijing, Metal World Vol. 242, 247 (2011), p.9 (In Chinese).

[6] X.F. Yang, T.K. Chen: Computer Science Vol. 23-26 (1994), p.21 (In Chinese).

[7] C.L. Wang, H. Zhou, Z.H. Zhou: Proceedings of the CSEE: Vol. 72-76 (2005), p.25 (In Chinese).

[8] VAPNIK V N. The Nature of Statistical Learning Theory (Springer-Verlag, New York 1995).

[9] Z.B. Ma, Research on Classification System Based on Support Vector Machine: Master's dissertation (Wuhan University of Technology, Hubei, China, 2006) (In Chinese).

[10] Faruto and liyang: LIBSVM-faruto Ultimate Version a toolbox with implements for support vector machines based on libsvm, 2011 Software available at http: /www. matlabsky. com.

[11] C.C. Chang and C.J. Lin, LIBSVM: a library for support vector machines, 2001. Software available at http: /www. csie. ntu. edu. tw/~cjlin/libsvm.