Coke Rate Prediction Model Based on Genetic Algorithm Optimized Support Vector Machine

Abstract:

The accurate prediction model’s establishing of the blast furnace coke rate is important for optimizing the integrated production indicators of iron and steel enterprise. For the problem of accuracy of the model of coke rate, This paper established blast coke rate modeling with support vector machine algorithm, the model parameters of support vector machine was optimized by genetic algorithm, then a coke rate model based on support vector machine with the best parameters was built. Simulation results showed that: the forecasting model’s outcome, average absolute error and the mean relative error, was small which is based on genetic algorithm optimized SVM. coke rate model based on Genetic algorithm optimized support vector machine has high degree of accuracy and a certain practicality.

• Periodical: Applied Mechanics and Materials (Volume 740)
• Pages: 600-603
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.740.600
• Online since: March 2015
• Authors: You Jun Yue*, Yan Fei Hu, Hui Zhao, Hong Jun Wang
• Keywords: Coke Rate Forecasting Model, Genetic Algorithm (GA), Parameter Optimization, Support Vector Machines

References

[1] ZHOU J C, Zhang C. X, Ding Y, Qi Z, Shi D. M, Fan B. Ma Steel blast furnace iron making process energy consumption prediction model [J]. Journal of Iron and Steel Research, 2011, 02: 30-34.

[2] Guo T. Y, CHE Y. M, Sun P, Li L. C, SUN B. Blast furnace coke rate factors analysis based on partial least squares regression. [J]. Anshan Iron and Steel Technology, 2009, 05: 23-26.

[3] YANG T. J, GAO B, LU H. S, GONG Y. B, ZHAO L. G, GUO H.W. Blast furnace coke rate objective optimization model and result analysis [J]. Beijing University of Science and Technology Journal, 2001, 04: 305-307.

[4] Qin M. S, Zhang Y. T, Lu H. S, Zhang J.L. Comprehensive mathematical model of blast furnace ironmaking process [J]. Steel. 1990, 10: 9-14.

[5] Fan Z. G, Qiu G. B, JIA J. Y, BAI C.G. Blast furnace coke rate prediction method based on BP neural network [J]. Chongqing University (Natural Science), 2002, 06: 85-87+91.

[6] ZHOU Y, YU W. W, DONG X. J, ZHANG J.H. Prediction model based on cluster analysis and neural network of blast furnace coke rate [J]. Liaoning University of Science and Technology, 2010, 03: 245-247+257.

[7] HAN H. L, YAN X.L. Artificial neural networks and genetic algorithm in the blast furnace coke rate forecasting [J]. Hebei Institute of Technology Journal, 2006, 02: 23-27.

[8] WANG Y. H, ZHANG H, FENG C. H, ZHAO G, HE Z. P,. Blast furnace composite coke rate Parameter Optimization Research based on materials resources operational characteristics [J]. Metallurgical Automation, 2013, 01: 12-15.

[9] FAN G.Q. Blast furnace iron making foundation, Metallurgical Industry Press.

[10] LI L, NIU B. PSO Optimization algorithms, Metallurgical Industry Press.

[11] DENG N. Y, TIAN Y.J. New method in data mining - support vector machines, Science Press.

[12] DING H.F. Support vector machine regression and its application based on intelligent optimization algorithm. [D] Southwest Jiaotong University, (2011).