Abstract
In the study of blast furnace coke ratio, existing methods can only predict coke ratio of daily. At the same time, the data under abnormal furnace conditions are excluded, and the model’s robustness needs to be improved. In order to improve the prediction accuracy and time precision of the blast furnace mathematical simulation model, a blast furnace coke ratio prediction model based on fuzzy C-means (FCM) clustering and grid search optimization support vector regression (SVR) is proposed to achieve accurate prediction of coke ratio. First, preprocess the blast furnace sensor data and steel plant production data. Then, the FCM algorithm is used to cluster the data under different furnace conditions. Finally, the SVR model optimized by grid search is used to predict the coke ratio under different blast furnace conditions. The average absolute error of the improved model is 1.7721 kg/t, the hit rate within 0.5% error is 81.19%, the coefficient of determination R2 is 0.9474, and the prediction performance is better than ridge regression and decision tree regression. Experiments show that the model can predict the coke ratio of molten iron in each batch when the blast furnace conditions are going forward and fluctuating, and it has high time accuracy and stability. It objectively describes the changing trend of blast furnace conditions, and provides new research ideas for the practical application of blast furnace mathematical models.
Similar content being viewed by others
References
Abdul Quader M, Shamsuddin A (2016) A HYBRID FUZZY MCDM approach to identify critical factors and CO2 capture technology for sustainable iron and steel manufacturing[J]. Arab J Sci Eng 41(11):4411–4430
Magazzino C, Mele M (2020) A machine learning analysis of the relationship among iron and steel industries, air pollution, and economic growth in China[J]. J Clean Prod 277:123293
Ariyama T, Sato M (2006) Optimization of ironmaking process for reducing CO2 emissions in the integrated steel works[J]. ISIJ Int 46(12):1736–1744
Ueda S, Natsui S, Nogami H et al (2010) Recent progress and future perspective on mathematical modeling of blast furnace[J]. ISIJ Int 50(7):914–923
Zhou C, Tang GW, Wang JC et al (2016) Comprehensive numerical modeling of the blast furnace ironmaking process[J]. JOM 68(5):1353–1362
Chu MS, Wang HT, Liu ZG et al (2014) Research progress on mathematical modeling of blast furnace ironmaking process[J]. Iron & Steel 49(11):1–8
Jian C (2001) A predictive system for blast furnaces by integrating a neural network with qualitative analysis[J]. Eng Appl Artif Intell 14(1):77–85
Su X, Zhang S, Yin Y et al (2019) Prediction model of hot metal temperature for blast furnace based on improved multi-layer extreme learning machine[J]. Int J Mach Learn Cybern 10(10):2739–2752
Yang AM, Zhuansun YX, Shi Y et al (2021) IoT system for pellet proportioning based on BAS intelligent recommendation model[J]. IEEE Trans Industr Inf 17(2):934–942
Wang YH, Zhang H, Jiang ZG et al (2013) Research of coke rate prediction of blast furnace based on operative characteristics of auxiliary resources[J]. Adv Mater Res 605–607:1792–1797
Zhou H, Wu J, Hong Z et al (2021) Numerical simulation of coke collapse and its optimization during burden charging at the top of bell-less blast furnace[J]. Powder Technol 389:155–162
Henrik S, Frank P (2007) Non-linear prediction of the hot metal silicon content in the blast furnace[J]. ISIJ Int 47(12):1732–1737
Wu M, Ma JJ, Hu J et al (2018) Optimization of coke ratio for the second proportioning phase in a sintering process base on a model of temperature field of material layer[J]. Neurocomputing 275:10–18
Li H, Wang Y, Jiao K et al (2019) Study on alkali circulation process and its influence on coke ratio in blast furnace[M].10th International Symposium on High-Temperature Metallurgical Processing, pp 15–24
Fan Z, Qiu G, Jia J et al (2003) The investigation of predicting the coke rate based on BP neural network[C]. pp 491–496
Zhou Y, Wen-Wu YU, Dong XJ et al (2010) A prediction model for blast furnace coke ratio with clustering analysis and neural network[J]. J Univ Sci Technol Liaoning 33(3):4
Yue YJ, Hu YF, Zhao H et al (2015) Coke rate prediction model based on genetic algorithm optimized support vector machine[J]. Appl Mech Mater 740:600–603
Hu J, Wu M, Chen X et al (2016) Prediction model of comprehensive coke ratio based on principal component analysis for sintering process[C]. pp 3612–3617
Asghar MZ, Subhan F, Ahmad H et al (2020) Senti-eSystem: A sentiment-based eSystem-using hybridized fuzzy and deep neural network for measuring customer satisfaction[J]. Softw Pract Exp 51(3):571–594
Gadekallu TR, Gao XZ (2021) An efficient attribute reduction and fuzzy logic classifier for heart disease and diabetes prediction[J]. Recent Adv Comput Sci Commun (Formerly: Recent Patents on Computer Science) 14(1):158–165
Tang QL, Zhang JL, Li KJ et al (2017) New concept about replacement ratio between coke and coal[J]. J Iron Steel Res 29(5):345–351
Zhang D, Chen L, Wang Y et al (2021) The Research on Improving the Precision of The Polymer IFHI By BP Neural Network of The Method Data Normalization[C]. IOP Publishing, pp 032067
Yu K, Liu Z, Zhao G et al (2021) A novel protection method for a wind farm collector line based on FCM clustering analysis[J]. Int J Electr Power Energy Syst 129(16):106863
Zhou K, Yang S (2016) Exploring the uniform effect of FCM clustering: A data distribution perspective[J]. Knowl Based Syst 96:76–83
Zhang D, Xiang W, Cao Q et al (2020) Application of incremental support vector regression based on optimal training subset and improved particle swarm optimization algorithm in real-time sensor fault diagnosis[J]. Appl Intell 51(6):3323–3338
Hu J, Zheng K (2015) A novel support vector regression for data set with outliers[J]. Appl Soft Comput 31:405–411
Wu CH, Tzeng GH, Lin RH (2009) A novel hybrid genetic algorithm for kernel function and parameter optimization in support vector regression[J]. Expert Syst Appl 36(3):4725–4735
Acknowledgements
This research was funded by the National Natural Science Foundation of China (No.52074126); Hebei Province Natural Science Fund for Distinguished Young Scholars (NO.E2020209082).
Author information
Authors and Affiliations
Corresponding authors
Additional information
Publisher's note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Li, S., Chang, J., Chu, M. et al. A blast furnace coke ratio prediction model based on fuzzy cluster and grid search optimized support vector regression. Appl Intell 52, 13533–13542 (2022). https://doi.org/10.1007/s10489-022-03234-8
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-022-03234-8