JACIII Vol.27 No.2 pp. 304-313
doi: 10.20965/jaciii.2023.p0304

Research Paper:

A Data-Driven Prediction Model of Blast Furnace Gas Generation Based on Spectrum Decomposition

Lili Feng*,** ORCID Icon, Jun Peng***,† ORCID Icon, and Zhaojun Huang**

*School of Automation, Central South University
Democracy Building, Yuelu District, Changsha, Hunan 410083, China

**Hunan Valin Lianyuan Steel Co., Ltd.
1005 Gangui North Road, Louxing District, Loudi, Hunan 417009, China

***School of Computer Science and Engineering, Central South University
Computer Building, Yuelu District, Changsha, Hunan 410083, China

Corresponding author

April 25, 2022
December 28, 2022
March 20, 2023
blast furnace iron-making, prediction model, support vector regression, Elman neural network, spectrum decomposition

Blast furnace gas (BFG) is an important secondary energy in the iron and steel industries, and its efficient and reasonable utilization is the key to improving the economic efficiency of enterprises and the level of energy conservation and emission reduction. Aiming at the problems of difficult accurate modeling on the generation process and difficult prediction of real-time flow, this paper proposes a generation prediction model based on spectrum decomposition. Firstly, the major chemical reactions, production process, and data characteristics of blast furnace are analyzed, and the input variables for the prediction model are reasonably selected based on the correlation analysis results. Then, according to the spectrum characteristics, the BFG data is decomposed into low-frequency and medium-frequency parts by two finite impulse response filters. Next, for the low- and middle-frequency components of data, a low-frequency component prediction model based on the support vector regression, and a middle-frequency component prediction model based on the Elman neural network (ENN) are designed respectively. Finally, we decompose the spectrum of the actual industrial production data and find that the spectrum of the decomposed data basically meets the expected target, which verifies the effectiveness of the finite impulse response filters. In addition, we compare the prediction effect of the designed combined model with other models, such as the support vector regression, the back-propagation neural network, and the ENN. The final experimental results show the correctness, effectiveness, and superiority of the combined model and the spectral decomposition method proposed in this paper.

Combining two models to predict the BFG generation

Combining two models to predict the BFG generation

Cite this article as:
L. Feng, J. Peng, and Z. Huang, “A Data-Driven Prediction Model of Blast Furnace Gas Generation Based on Spectrum Decomposition,” J. Adv. Comput. Intell. Intell. Inform., Vol.27 No.2, pp. 304-313, 2023.
Data files:
  1. [1] C. Sheng et al., “Prediction for noisy nonlinear time series by echo state network based on dual estimation,” Neurocomputing, Vol.82, pp. 186-195, 2012.
  2. [2] J. Zhao et al., “A two-stage online prediction method for a blast furnace gas system and its application,” IEEE Trans. on Control Systems Technology, Vol.19, No.3, pp. 507-520, 2011.
  3. [3] F. S. V. Gomes, J. L. F. Salles, and L. A. Wasem, “A new prediction model for liquid level in blast furnaces based on time series analysis,” 2011 9th IEEE Int. Conf. on Control and Automation (ICCA), pp. 772-777, 2011.
  4. [4] Z. Lv et al., “Use of a quantile regression based echo state network ensemble for construction of prediction Intervals of gas flow in a blast furnace,” Control Engineering Practice, Vol.46, pp. 94-104, 2016.
  5. [5] W. Sun, Z. Wang, and Q. Wang, “Hybrid event-, mechanism- and data-driven prediction of blast furnace gas generation,” Energy, Vol.199, Article No.117497, 2020.
  6. [6] X. Sun, Z. Wang, and J. Hu, “Prediction interval construction for byproduct gas flow forecasting using optimized twin extreme learning machine,” Mathematical Problems in Engineering, Vol.2017, Article No.5120704, 2017.
  7. [7] X. Zhang et al., “An optimal method for prediction and adjustment on byproduct gas holder in steel industry,” Expert Systems with Applications, Vol.38, No.4, pp. 4588-4599, 2011.
  8. [8] J. Zhao et al., “Online parameter optimization-based prediction for converter gas system by parallel strategies,” IEEE Trans. on Control Systems Technology, Vol.20, No.3, pp. 835-845, 2011.
  9. [9] L. Yang et al., “The prediction for output of blast furnace gas based on genetic algorithm and LSSVM,” 2014 9th IEEE Conf. on Industrial Electronics and Applications, pp. 1493-1498, 2014.
  10. [10] Z. Han et al., “Real time prediction for converter gas tank levels based on multi-output least square support vector regressor,” Control Engineering Practice, Vol.20, No.12, pp. 1400-1409, 2012.
  11. [11] Y. Zhu et al., “Prediction of blast furnace gas output based on GA-Elman neural network,” 2021 33rd Chinese Control and Decision Conf. (CCDC), pp. 1337-1342, 2021.
  12. [12] H. J. Li et al., “Application of Elman neural network with HP filter in the trend supply of self-provided power plant forecasting in the iron and steel industry,” Advanced Materials Research, Vols.712-715, pp. 3211-3214, 2013.
  13. [13] Q. Zhang et al., “Supply and demand forecasting of blast furnace gas based on artificial neural network in iron and steel works,” Advanced Materials Research, Vols.443-444, pp. 183-188, 2012.
  14. [14] T. Miyano et al., “Predicting chaotic sequences in a blast furnace by a generalized radial basis function network,” Electronics and Communications in Japan (Part III: Fundamental Electronic Science), Vol.79, No.7, pp. 1-10, 1996.
  15. [15] Z. M. Lv, Z. Wang, and Z. Y. Wang, “Short-term forecast of blast furnace gas production amount based on grey RBF neural network,” Applied Mechanics and Materials, Vols.713-715, pp. 1907-1913, 2015.
  16. [16] Z. Lu, N. Zhang, and Z. Wang, “Improved wavelet neural network to predict blast furnace gas production in iron and steel enterprises,” Proc. of the 2017 Int. Conf. on Computer Graphics and Digital Image Processing (CGDIP’17), pp. 1-5, 2017.
  17. [17] P. Zahradnik and M. Vlcek, “Perfect decomposition narrow-band FIR filter banks,” IEEE Trans. on Circuits and Systems II: Express Briefs, Vol.59, No.11, pp. 805-809, 2012.
  18. [18] D. Zhang, M. Wu, and L. Chen, “A prediction model based on SVR for untwist angle in drilling process,” 2018 37th Chinese Control Conf. (CCC), pp. 10259-10262, 2018.
  19. [19] S. M. Zainorzuli et al., “Comparative study of Elman neural network (ENN) and neural network autoregressive with exogenous input (NARX) for flood forecasting,” 2019 IEEE 9th Symp. on Computer Applications & Industrial Electronics (ISCAIE), pp. 11-15, 2019.

*This site is desgined based on HTML5 and CSS3 for modern browsers, e.g. Chrome, Firefox, Safari, Edge, Opera.

Last updated on Jul. 12, 2024