Optimization Research of the Comprehensive Coke Rate of Blast Furnace Based on the Operational Characteristic of Auxiliary Materials

Abstract:

With the in-depth study on the blast furnace iron-making process and the operational characteristic of auxiliary materials in iron-making process, the comprehensive coke rate’s main influencing factors based on the operation characteristics of auxiliary materials were found. Then, a BP neural network model was used to simulate the mathematic mapping relationship between comprehensive coke rate and main influencing factors. Based on the established BP neural network model, through setting the comprehensive coke rate lowest as the goal and using the actual production data of a iron &steel company’s 6# blast furnace ,a genetic algorithm method is adopted to find the best optimal combination among the main influencing factors. The results show that after optimization calculation the comprehensive coke rate could be reduced about 35.85kg. A new perspective and a scientific method are proposed to realize the target of energy conservation and emission reduction in ironmaking process in this paper.

• Periodical: Applied Mechanics and Materials (Volumes 260-261)
• Pages: 3-9
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.260-261.3
• Online since: December 2012
• Authors: Hua Zhang, Zhao Hui Feng, Yan Hong Wang
• Keywords: Auxiliary Materials, Bp Neural Network Model, Comprehensive Coke Rate, Genetic Algorithm (GA)

References

[1] CHU Man-sheng. Steel Metallurgical Raw Material and Fuel and Auxiliary Materials [M]. Beijing: Metallurgical Industry Press, (2010).

[2] ZHANG Shou-rong, YIN Han. Current Situation and Existing Problems 0f Blast Furnace Ironmaking in China [J]. Iron and Stee1, 2007, 42(9): 1-8.

[3] YANG Tianjun, GAO Bin. Optimization Aimed at the Lowest Coke Consumption by Model and Analysis of the Application[J]. Journal of University of Science and Technology Beijing, 2001, 23(4): 305-307.

[4] HAO Xiao-jing, DU Gang. Mathematical optimization Model for Blast Furnace operation [J]. Journal of Materials and Metallurgy, 2002, 1(2): 120-123.

[5] ZHA Feng-wei, LIU Qi . Optimization of Pulverized Coal Injection for the Blast Furnace Based on NeuraI Network and Genetic Algorithm [J]. Control Theory and Applications, 2006, 25(10): 11-13.

[6] WANG Jin-liang, LU Hong. Control optimization of copper flash smelting process based on genetic algorithms [J]. The Chinese Journal of Nonferrous Metals, 2007, 17(1): 156-159.

[7] M. Bayat, M.R. Rahimpour. Genetic algorithm strategy (GA) for optimization of a novel dual-stage slurry bubble column membrane configuration for Fischer–Tropsch synthesis in gas to liquid (GTL) technology [J]. Journal of Natural Gas Science and Engineering, 2011, 3 (4) 555-570.

DOI: 10.1016/j.jngse.2011.06.004

[8] F. Musharavati, A.S.M. Hamouda. Modified genetic algorithms for manufacturing process planning in multiple parts manufacturing lines [J]. Expert Systems with Applications, 2011, 38 (9) 10770-10779.

DOI: 10.1016/j.eswa.2011.01.129

[9] L.E. Agustı´n-Blas, S. Salcedo-Sanz. A new grouping genetic algorithm for clustering problems [J]. JExpert Systems with Applications, 2012, 39 (10) 9695-9703.

DOI: 10.1016/j.eswa.2012.02.149

[10] ZHOU Yang, YU Wen-wu . A prediction model for blast furnace coke ratio with clustering analysis and neural network [J]. Journal of University of Science and Technology Liaoning, 2010, 33(3): 245-247.