Application of Elman Neural Network with HP Filter in the Trend Supply of Self-Provided Power Plant Forecasting in the Iron and Steel Industry

Abstract:

Aiming at the power plant energy consumption and gas balance influenced serious with the affluent gas fluctuate frequently of byproduct gas system in an iron and steel industry, which is very difficult to be modeled using the mechanism modeling, a forecast trend sequence of the gas supply HP-ENN model was established based on the characteristics of self-provided power plant energy utilization and the properties of HP filter, Elman neural network. The prediction results using practical production data show that using the proposed HP-Elman method that sample A 48, 60 points trend forecast average relative error are 0.37%, 0.47% and sample B 48, 60 points trend forecast average relative error are 0.82%, 1.03%,which can effectively for the trend forecast of self-provided power plant gas supply with a reliable prediction capacity.

• Periodical: Advanced Materials Research (Volumes 712-715)
• Pages: 3211-3214
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.712-715.3211
• Online since: June 2013
• Authors: Hong Juan Li, Jian Jun Wang, Hua Wang, Hua Meng
• Keywords: Elman Neural Network (ENN), HP Filter, Trend Sequence

References

[1] Zhang qi, Study on Reasonable Utilization and Optimizing Distribution of Gases Fuel in Iron and Steel Complex [D]. Shen yang：Northeastern University，2008. In Chinese

[2] LIU Ying, SHI Fei fei, ZHAO Jun, etc. Study on Prediction Method for Generation and Consumption of Blast Furnace Gas Based on Improved Echo State Network [J] Journal of System Simulation. 2011,23(10),2184-2189. In Chinese

[3] ZHANG Xiao ping, ZHAO Jun, WANG Wei. Multi-output least squares support-vector-machine for level prediction in Linz Donaniz gas holder [J]. Control Theory & Applications. 2010,27(11), 1463-1470. In Chinese

[4] TANG Zhen xing. Generation-consumption prediction method of cove oven gas in steel industry and its application [D]. Dalian：Dalian University of Teehnology，2009. In Chinese

[5] ZHANG Xiao ping, ZHAO Jun, WANG Wei, etc. COG holder level prediction model based on least square support vector machine and its application [J]. Control and Decision.2010,25(8), 1178-1188. In Chinese

[6] Chu Y H, Kim J H, Moon S J, etc. Control of gasholder level by trend prediction based on time-series analysis and process heuristics[C]. The 7th Int Symposium on Advanced Control of Chemical Processes. Hong Kong, 2004.

[7] Iwao Higashi. Energy balance of steel mills and utilization of byproduct gases[J]. Trans of the Iron and Steel Institute of Japan, 1982, 22(1): 57-65

DOI: 10.2355/isijinternational1966.22.57

[8] MING De ting . LI Juan ． YIN Yi xin，Research of gas optimal scheduling model in iron and steel enterprise [J]. Computer Engineering and Design，2008，29(6)：1575-1578.

[9] N.H. Packard，J．PCrutchfietd， J.D. Farmer, et a1. Geometry from a time series．Phys．Rev. Lett，1980，45(9)：712-716.

[10] ETakens．Deterrning strange attractors in turbulence．Lecture notes in Math，1981，898: 361-38l.

[11] Hodrick R.J., and Prescott, E.C., Postwar U.S. Business Cycles：an Empirical Investigation[J]. Journal of Money, Credit and Banking, 1997,29,pp.1-1.

DOI: 10.2307/2953682

[12] J.L. Elman, E.A. Bates, M.H. Johnson, A. Karmiloff-Smith, D. Parisi, K. Plunkett, Rethink Innateness, MIT Press, Cambridge, MA, 1996.

DOI: 10.7551/mitpress/5929.001.0001

[13] Elman J (1990). Finding structure in time. Cognitive Science 14: 179–211.

[14] X. Z. Gao and S. J. Ovaska. Genetic Algorithm Training of Elman Neural Network in Motor Fault Detection. Neural Comput & Applic (2002)11:37–44.

DOI: 10.1007/s005210200014

[15] Li Xiang，Chen Guanrong，Chen Zengqian et al. Chaotifying linear Elman networks[J]. IEEE Transactions on Neural Networks 2002，13(5)：1193-1199.

DOI: 10.1109/tnn.2002.1031950

[16] Cheng Y L，Huang J C，Yang W C. Modeling word perception using the Elman network[J]. Neurocomputing，2008，71(16/17/18)：3150-3157.

DOI: 10.1016/j.neucom.2008.04.030

[17] Gao X Z. Gao X M. Ovaska S J. Trajectory control based on a modified Elman neural network[C]. Orlando Florida，USA：IEEE International Conference on SMC，1997. 1995, 6(5)：1212-1228.

DOI: 10.1109/icsmc.1997.635310