Supply and Demand Forecasting of Blast Furnace Gas Based on Artificial Neural Network in Iron and Steel Works

Abstract:

Abstract.Blast Furnace Gas (BFG) system of an iron and steel works was considered. The relationship of gas amount and factors about BFG generation and consumption was analyzed by grey correlationand the BP neural network prediction model of blast furnace gaswas established based on artificial neural network for forecasting thesupply and demandof BFGinthe iron and steel-making processes.The scientific forecasting of BFG generation and consumption in each process was discussed undernormal production and accidental maintenance condition. The results show that established forecasting model is high precision, small errors, and can solve effectively actual production of BFG prediction problem and decreasing BFG flare, providing theoretical basis for establishing reasonable plans in the iron and steel works.

• Periodical: Advanced Materials Research (Volumes 443-444)
• Pages: 183-188
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.443-444.183
• Online since: January 2012
• Authors: Qi Zhang, Yan Liang Gu, Wei Ti, Jiu Ju Cai
• Keywords: Blast Furnace Gas, BP Neural Network (BPNN), Demand Forecasting, Iron Work, Saving Energy, Steel Works, Supply Forecasting

References

[1] ZHANG Qi, CAI Jiu-ju, WANG Jian-jun, et al. Recovery and Utilization of By-product Gases in Iron and Steel Works[J]. Iron and Steel, 2009, 43(12): 95-99. (in Chinese).

[2] Eglen S J , HillAG. Usingneural networks [J]. GEC Review, 1992, 7(3)：27-36.

[3] Udo meissner, Hermann Wibbeler. A least square principle for the a posteriori computation of finite element approximation errors [J]. Computer Methods in Applied Mechanics and Engineering, 1991, 85(1): 89-108.

DOI: 10.1016/0045-7825(91)90124-o

[4] S. GonzalesChavez , J. XibertaBernat. Forecastingofenergyproduction and consumption inAsturias (northern Spain) [J]. Energy, 24 (1999) 183–198.

[5] LI Wen-bin, JI Yang. Dynamic Models for Gas Output and Consumption in Iron and Steel Company[J]. Metallurgical Industry Automation, 2008, 32(3): 28-33. (in Chinese).

[6] BIAN He-ying, LI Hong-wei. Predictive Control of Gas Recovery System Based on Neural Network[J]. Industry and Automation, 2009, (8): 69-71. (in Chinese).

[7] QIU Dong, CHEN Shuang, TONG Cai-xia, et al. Blast Furnace Gas Balance and Comprehensive Optimization in Iron and Steel Enterprises[J]. Computer Technology and Development, 2009, 19(3): 196-199. (in Chinese).

[8] Miyahara, H., Yamamoto, S., Sugioka, S., etal. A new control system at Keihin coke plant[C]. NKK Technical Report, Japan: NKK, 1995: 1-6.

[9] DONG Chang-hong. Matlab Neural Network and Application[M]. Beijing: National Defence Industrial Press, 2005, 68-71. (in Chinese).