Neural Processing Letters

, Volume 50, Issue 2, pp 1191–1213 | Cite as

A Soft Sensing Scheme of Gas Utilization Ratio Prediction for Blast Furnace Via Improved Extreme Learning Machine

  • Yanjiao Li
  • Sen ZhangEmail author
  • Yixin Yin
  • Jie Zhang
  • Wendong Xiao


Gas utilization ratio (GUR) is an important indicator reflecting the operating state and energy consumption of blast furnace (BF). Skilled operators usually refer to changing trends of GUR to guide the next step of production. For these reasons, this paper establishes a soft sensing scheme based on an improved extreme learning machine (ELM) to predict GUR. In order to enhance the modeling capability of ELM for industrial data, an improved ELM, named GR-ELM, is proposed based on grey relational analysis (GRA) and residual modification mechanism. In GR-ELM, considering the different effective information contained in each input attribute for modeling, the input attribute optimization is proposed combining with GRA and entropy weight method. Then, because the modeling capability of ELM is limited and the data collected from industrial process are usually contaminated, the residual modification mechanism is implemented to improve the reliability of the model. In addition, considering the influence of time delay in BF ironmaking process, generalized correlation coefficient method based on mutual information is used for time delay analysis to eliminate the influence. The real data collected from a BF are applied and validated the performance and effectiveness of the proposed soft sensing scheme. The experimental results show that the proposed soft sensing scheme is available and can achieve better performance than some state-of-the-art algorithms. The soft sensing scheme can provide effective decision support and guidance for further optimization operation.


Blast furnace Gas utilization ratio Extreme learning machine Grey relational analysis Residual modification mechanism Time delay analysis 



This work has been supported by the National Natural Science Foundation of China (NSFC Grants Nos. 61333002 and 61673056), Beijing Natural Science Foundation (No. 4182039) and Beijing Key Subject Construction Projects (No. XK100080573).

Compliance with Ethical Standards

Conflict of interest

All authors declare that they have no conflict of interest.

Ethical Approval

This article does not contain any studies with human participants performed by any of the authors.


  1. 1.
    Zeng JS, Gao CH, Su HY (2010) Data-driven predictive control for blast furnace ironmaking process. Comput Chem Eng 34:1854–1862CrossRefGoogle Scholar
  2. 2.
    Liu DX, Li XL, Zhou X (2010) Application of fuzzy pattern recognition in burden surface identification. In: International conference on intelligent control and information processing, 2010, pp 292–296Google Scholar
  3. 3.
    Yang K, Choi S, Chung J, Yagi JI (2010) Numerical modeling of reaction and flow characteristics in a blast furnace with consideration of layered burden. ISIJ Int 50(7):972–980CrossRefGoogle Scholar
  4. 4.
    Liu ZJ, Zhang JL, Yang TJ (2015) Low carbon operation of super-large blast furnace in China. ISIJ Int 55(6):1146–1156CrossRefGoogle Scholar
  5. 5.
    Xiao DF, An JQ, Wu M, He Y (2016) Research on carbon-monoxide utilization ratio in blast furnace based on kolmogorov entropy. J Adv Comput Intell Intell Inf 20(2):310–316CrossRefGoogle Scholar
  6. 6.
    Helle H, Helle M, Saxen H (2011) Nonlinear optimization of steel production using traditional and novel blast furnace operation strategies. Chem Eng Sci 66(24):6470–6481CrossRefGoogle Scholar
  7. 7.
    Na SR (2010) Calculation and analysis of iron-making. Metallurgical Industry Press, BeijingGoogle Scholar
  8. 8.
    Wei HY (2013) The analysis and practice of gas utilization for blast furnace. Efficiency of iron-making raw material and the practical seminar on new technology and new equipment, pp 87–90Google Scholar
  9. 9.
    Xiao DF, An JQ, He Y, Wu M (2017) The chaotic characteristic of the carbon-monoxide utilization ration in the blast furnace. ISA Trans 68:109–115CrossRefGoogle Scholar
  10. 10.
    Huang GB, Zhu QY, Siew CK (2006) Extreme learning machine: theory and applications. Neurocomputing 70:489–501CrossRefGoogle Scholar
  11. 11.
    Huang GB, Zhou HM, Ding XJ, Zhang R (2012) Extreme learning machine for regression and multiclass classification. IEEE Trans Syst Man Cybern B Cybern 42(2):513–529CrossRefGoogle Scholar
  12. 12.
    Huang GB (2014) An insight into extreme learning machine: random neurons, random features and kernels. Cogn Comput 6:376–390CrossRefGoogle Scholar
  13. 13.
    Li YJ, Zhang S, Yin YX, Xiao WD, Zhang J (2017) A novel online sequential extreme learning machine for gas utilization ratio prediction in blast furnaces. Sensors 17(8):1847–1870CrossRefGoogle Scholar
  14. 14.
    Symone GS, Rui A (2016) An adaptive ensemble of on-line extreme learning machines with variable forgetting factor for dynamic system prediction. Neurocomputing 171:693–707CrossRefGoogle Scholar
  15. 15.
    Xiao WD, Zhang J, Li YJ, Zhang S, Yang WD (2017) Class-specific cost regulation extreme learning machine for imbalanced classification. Neurcomputing 261:70–82CrossRefGoogle Scholar
  16. 16.
    Han M, Zhang RQ, Xu ML (2017) Multivariate chaotic time series prediction based on ELM-PLSR and hybrid variable selection algorithm. Neural process lett 46:705–717CrossRefGoogle Scholar
  17. 17.
    Ma ZC, Dai Q (2016) Selected an stacking ELMs for time series prediction. Neural process lett 44:831–856CrossRefGoogle Scholar
  18. 18.
    Zou H, Lu XX, Jiang H, Xie LH (2015) A fast and precise indoor localization algorithm based on an online sequential extreme learning machine. Sensors 15:1804–1824CrossRefGoogle Scholar
  19. 19.
    Zhang J, Xiao WD, Zhang S, Huang SD (2017) Device-free localization via an extreme learning machine with parameterized geometrical feature extraction. Sensors 17(4):879–899CrossRefGoogle Scholar
  20. 20.
    Zhang J, Sun J, Wang HL, Xiao WD, Tan L (2017) Large-scale WiFi indoor localization via extreme learning machine. In: Proceedings of the 36th Chinese control conference, 2017, pp 4115–4120Google Scholar
  21. 21.
    Cao JW, Zhao YF, Lai XP, Ong MEH, Yin C, Koh ZX, Liu N (2015) Landmark recognition with sparse representation classification and extreme learning machine. J Frankl Inst 352:4528–4545CrossRefMathSciNetzbMATHGoogle Scholar
  22. 22.
    Zhou HM, Huang GB, Lin ZP, Wang H, Soh YC (2015) Stacked extreme learning machine. IEEE Trans Cybern 45(9):2013–2025CrossRefGoogle Scholar
  23. 23.
    Cao JW, Lin ZP, Huang GB (2012) Self-adaptive evolutionary extreme learning machine. Neural Process Lett 36:285–305CrossRefGoogle Scholar
  24. 24.
    Huang GB, Song S, Gupta JN (2014) Semi-supervised and unsupervised extreme learning machines. IEEE Trans Cybern 78(3):2405–2417CrossRefGoogle Scholar
  25. 25.
    Han M, Liu XX (2014) An extreme learning machine algorithm based on mutual information variable selection. Control Decis 29(9):1576–1580zbMATHGoogle Scholar
  26. 26.
    Wong SY, Yap KS, Yap HJ (2015) A truly online learning algorithm using hybrid fuzzy ARTMAP and online extreme learning machine for pattern classification. Neural Process let 42:585–602CrossRefGoogle Scholar
  27. 27.
    Miche Y, Sorjamaa A, Bas P, Simula O, Jutten C, Lendasse A (2011) OP-ELM: optimally pruned extreme learning machine. IEEE Trans Neural Netw 21(1):158–162CrossRefGoogle Scholar
  28. 28.
    Feng GR, Huang GB, Lin QP, Gay R (2009) Error minimized extreme learning machine with growth of hidden nodes and incremental learning. IEEE Trans Neural Netw 20(8):1352–1357CrossRefGoogle Scholar
  29. 29.
    Zhai JH, Shao QY, Wang XZ (2015) Architecture selection of ELM networks based on sensitivity of hidden nodes. Neural process lett 44:471–489CrossRefGoogle Scholar
  30. 30.
    Kuo Y, Yang T, Huang GW (2008) The use of grey relational analysis in solving multiple attribute decision-making problems. Comput Ind Eng 55(1):80–93CrossRefGoogle Scholar
  31. 31.
    Song QB, Shepperd M (2011) Predicting software project effort: a grey relational analysis based method. Expert Syst Appl 38:7302–7316CrossRefGoogle Scholar
  32. 32.
    Lin CT, Chang CW, Chen CB (2006) The worst ill-conditioned silion wafer slicing machine detected by using grey relational analysis. Int J Adv Manuf Technol 31:388–395CrossRefGoogle Scholar
  33. 33.
    Chen WH (2005) Distribution system restoration using the hybrid fuzzy-grey method. IEEE Trans Power Syst 20(1):199–205CrossRefGoogle Scholar
  34. 34.
    Jiang BC, Tasi SL, Wang CC (2002) Machine vision-based gray relational theory applied to IC marking inspection. IEEE Trans Semicond Manuf 15(4):531–539CrossRefGoogle Scholar
  35. 35.
    Cortes C, Vapnik V (1995) Support vector networks. Mach Learn 20(3):273–297zbMATHGoogle Scholar
  36. 36.
    Abaszade M, Effati S (2017) Stochastic support vector machine for classifying and regression of random variables. Neural Process Lett. CrossRefzbMATHGoogle Scholar
  37. 37.
    Ho TK (1995) Random decision forests. In: Proceedings of the 3rd international conference on document analysis and recognition, pp 278–282Google Scholar
  38. 38.
    Cheng YP (2017) Backpropagation for fully connected cascade networks. Neural Process Lett 46:293–311CrossRefGoogle Scholar
  39. 39.
    Li J, Cheng JH, Shi JY, Huang F (2012) Brief introduction of back propagation (BP) neural network algorithm and its improvement. In: Advances in computer science and information engineering, pp 553–558Google Scholar
  40. 40.
    Shi J, Ding ZH, Lee WJ, Yang YP, Liu YQ, Zhang MM (2014) Hybrid forecasting model for very-short term wind power forecasting based on grey relational analysis and wind speed distribution features. IEEE Trans Smart Grid 5(1):521–526CrossRefGoogle Scholar
  41. 41.
    Qi YG, Wen FS, Wang K, Li L, Singh SN (2010) A fuzzy comprehensive evaluation and entropy weight decision-making based method for power network structure assessment. Int J Eng Sci Technol 2(5):92–99CrossRefGoogle Scholar
  42. 42.
    Peng HC, Long FH, Ding C (2005) Feature selection based on mutual information: criteria of max-dependency, max-relevance, and min-redundancy. IEEE Trans Pattern Anal 27(8):1226–1238CrossRefGoogle Scholar
  43. 43.
    Jian L, Gao CH (2013) Binary coding SVMs for the multiclass problem of blast furnace system. IEEE Trans Ind Electron 60(9):3846–3856CrossRefGoogle Scholar
  44. 44.
    Jian L, Gao CH, Xia ZH (2012) Constructing multiple kernel learning framework for blast furnace automation. IEEE Trans Autom Sci Eng 9(4):763–777CrossRefGoogle Scholar
  45. 45.
    Li YJ, Zhang S, Yin YX, Zhang J, Xu ZG (2017) Quantitative association rule mining for blast furnace production data. In: Proceedings of 2017 Chinese automation congress, 2017, pp 2275–2280Google Scholar
  46. 46.
    Wang YK, Liu XG (2014) Chaotic Time series forecasting based on SVM for silicon content hot metal. In: Proceedings of the 33rd Chinese control conference, pp 5156–5161Google Scholar
  47. 47.
    Yuan M, Zhou P, Li ML, Li RF, Wang H, Chai TY (2015) Intelligent multivariable modeling of blast furnace molten iron quality based on dynamic AGA-ANN and PCA. J Iron Steel Res Int 22(6):487–495CrossRefGoogle Scholar
  48. 48.
    Ding J, Wang WS, Zhao YL (2002) General correlation coefficient between variables based on mutual information. J Sichuan Univ Eng Sci Ed 34(3):1–5Google Scholar
  49. 49.
    Liang NY, Huang GB, Saratchandran P, Sundararajan N (2006) A fast and accurate online sequential leaning algorithm for feedforward networks. IEEE Trans Neur Netw 17(6):1411–1423CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2018

Authors and Affiliations

  • Yanjiao Li
    • 1
    • 2
  • Sen Zhang
    • 1
    • 2
    Email author
  • Yixin Yin
    • 1
    • 2
  • Jie Zhang
    • 1
    • 2
  • Wendong Xiao
    • 1
    • 2
  1. 1.School of Automation and Electrical EngineeringUniversity of Science and Technology BeijingBeijingChina
  2. 2.Key Laboratory of Knowledge Automation for Industrial ProcessesMinistry of EducationBeijingChina

Personalised recommendations