Single Spectrum End Point Predict of BOF with SVM

SVM ( Support Vector Machine ) is a new method in the artificial neural network ( ANN ). In the steel making, how to use computer to predict the end point of BOF accuracy is a great problem. A lot of method and theory have been claimed, but most of the results is not satisfied. Now the hot topic in the BOF end point predicting is to use optical way the predict the end point in the BOF. And we found that there exist some regular in the characteristic curve of the flame from the mouse of pudding. And we can use SVM to predict end point of the BOF, just single spectrum intensity should be required as the input parameter. Moreover, its compatibility for the input space is better than the BP network.

• Ling-fei Xu
• Qi Zhao
• Yan-ru Chen
• Mu-chun Zhou
• Meng Zhang
• Shi-xue Xu

• SVM
• predict
• BOF
• single spectrum intensity.

[1] Feng Jie, Zhang Hongwen, BOF steelmaking(M). Beijing: Metallurgical
Industry Press, 2006. 332-338.
[2] Sharan A., Light sensors for BOF carbon control in low cabon heats(C).
Steelmaking Conference Proceedings, 1998, 81: 337-345.
[3] Hong-yuan Wen, Qi Zhao, Yan-ru Chen, Mu-chun Zhou, Meng Zhang,
Ling-fei Xu., IBasic-Oxygen-Furnane Endpoint Forecating Model Based
on Radiation and Modified Neural Network(J). ACTA Opitca sinica.
2008, 28(11): 2131-2135.
[4] Hong-yuan Wen, Qi Zhao, Yan-ru Chen, Mu-chun Zhou, Meng Zhang,
Ling-fei Xu., TConerter End-point Prediction Model Using Spectum
Image Analysis and Improved Neural Network Algorithm(J). Optica
Applicata, 2008, 38(4): 693-704.
[5] C. Cortes, V.Vapnik. Support vecter networks(J). Machine Learning,
1995(20): 273-297.
[6] Nello Cristianini, John Shawe-Taylor, An Introduction to Support Vector
Machines(M), London: Cambridge University Press, 2006: 54-59.
[7] Wang Weiwei. Time Series Prediction Based on SVM and GA(J). The
Eighth International Conference on Electronic Measurement and
Instruments,2007,2:307-310.
[8] Weiping Wang, Chengxian Guan, Zhongqing Chen. HF-NQO-100 model
oxygen concentration cell(J). Proc. SPIE 4077, 304-308 (2000).