Abstract
As one of the most complex industrial reactors, there remain some urgent issues for blast furnace (BF), such as BF automation, prediction of the inner thermal state, etc. In this work, the prediction of BF inner thermal state, which is represented by the silicon content in BF hot metal, is taken as an imbalanced binary classification problem and a Weighted Support Vector Machine (W-SVM) ensemble predictor based on AdaBoost is presented for the prediction task. Compared with the traditional W-SVM algorithm, the proposed predictor dynamically adjusts the weight distribution of training samples according to the performance of weak classifier, in this way to mine information lurked in the samples. The prediction can act as a guide to aid the operators for judging the thermal state of BF in time. Experiments results on five benchmark datasets and two real-world BFs datasets demonstrate the efficiency of the proposed W-SVM ensemble predictor.
Similar content being viewed by others
References
Bhattacharya T (2005) Prediction of silicon content in blast furnace hot metal using partial least squares (pls). ISIJ Int 45(12):1943–1945
Cai J, Zeng J, Luo S (2012) A state space model for monitoring of the dynamic blast furnace system. ISIJ Int 52(12):2194–2199
Cao Y, Miao QG, Liu JC, Gao L (2013) Advance and prospects of adaboost algorithm. Acta Automat Sin 39(6):745–758
Chang C, Lin C (2011) Libsvm: a library for support vector machines. ACM Trans Intell Syst Technol 2(3):27
Chen W, Wang BX, Han HL (2013) Prediction and control for silicon content in pig iron of blast furnace by integrating artificial neural network with genetic algorithm. Ironmaking & Steelmaking 37(6):458–463
Chuanhou G, Ling J, Xueyi L, Jiming C, Youxian S (2011) Data-driven modeling based on volterra series for multidimensional blast furnace system. IEEE Trans Neural Netw 22(12):2272–2283
Cui G, Jiang Z, Zhan W, Gu J (2015) Prediction of blast furnace temperature based on time series neural network. Metallurgy Automation 39(5):15–21
Demsar J (2006) Statistical comparisons of classifiers over multiple data sets. J Mach Learn Res 7(1):1–30
Elkin, G., Lozano, F.: Boosting support vector machines. International Conference on Machine Learning and Data Mining pp. 153–167 (2007)
Freund, Y., Schapire, R.E.: Experiments with a new boosting algorithm pp. 148–156 (1996)
Gao C, Ge Q, Ling J (2014) Rule extraction from fuzzy-based blast furnace svm multiclassifier for decision-making. IEEE Trans Fuzzy Syst 22(3):586–596
Gao C, Ling J, Luo S (2011) Modeling of the thermal state change of blast furnace hearth with support vector machines. IEEE Trans Ind Electron 59(2):1134–1145
Guo, H., Ma, J., Li, Z.: An improved adaboost-svm model based on sample weights and sampling equilibrium. In: 2016 4th international conference on electrical & electronics engineering and computer science (ICEEECS 2016). Atlantis Press (2016)
Guo W, Xu T, Tang K (2017) M-estimator-based online sequential extreme learning machine for predicting chaotic time series with outliers. Neural Comput & Applic 28(12):4093–4110
Hu JH, Xie SS, Yang F, Cai K, Wang HT (2007) Ensemble of classification methods based on svm and its application in diagnosis. Journal Of Propulsion Technology-BeiJing 28(6):669
Huang GB, Wang DH, Lan Y (2011) Extreme learning machines: a survey. Int J Mach Learn Cybern 2(2):107–122
Jian L, Li J, Liu H (2018) Exploiting multilabel information for noise-resilient feature selection. ACM Trans Intell Syst Technol 9(5):52
Jian L, Li J, Luo S (2017) Exploiting expertise rules for statistical data-driven modeling. IEEE Trans Ind Electron 64(11):8647–8656
Jian L, Song Y, Shen S, Wang Y, Yin H (2015) Adaptive least squares support vector machine predictor for blast furnace ironmaking process. ISIJ Int 55(4):845–850
Joachims T (1998) Making large-scale svm learning practical. Tech rep
Lin CF, Wang SD (2002) Fuzzy support vector machines. IEEE Trans Neural Netw 13(2):464–471
Ling J, Gao C, Xia Z (2012) Constructing multiple kernel learning framework for blast furnace automation. IEEE Transactions on Automation Science & Engineering 9(4):763–777
Luo S, Huang J, Zeng J, Zhang Q (2011) Identification of the optimal control center for blast furnace thermal state based on the fuzzy c-means clustering. ISIJ Int 51(10):1668–1673
Mitra T, Pettersson F, Saxén H, Chakraborti N (2017) Blast furnace charging optimization using multi-objective evolutionary and genetic algorithms. Mater Manuf Process 32(10):1179–1188
Nemenyi, P.B.: Distribution-free multiple comparisons (1963)
Ping Z, Song H, Hong W, Chai T (2017) Data-driven nonlinear subspace modeling for prediction and control of molten iron quality indices in blast furnace ironmaking. IEEE Trans Control Syst Technol 25(5):1761–1774
Saxen H, Gao C, Gao Z (2013) Data-driven time discrete models for dynamic prediction of the hot metal silicon content in the blast furnace-a review. IEEE Transactions on Industrial Informatics 9(4):2213–2225
Scholkopf, B., Smola, A.J.: Learning with kernels: support vector machines, Regularization, Optimization, and Beyond (2002)
Song X, Jian L, Song Y (2017) A chunk updating ls-svms based on block gaussian elimination method. Appl Soft Comput 51:96–104
Sun J, Li H, Fujita H, Fu B, Ai W (2020) Class-imbalanced dynamic financial distress prediction based on adaboost-svm ensemble combined with smote and time weighting. Information Fusion 54:128–144
Sun S, Xie X, Dong C (2019) Multiview learning with generalized eigenvalue proximal support vector machines. IEEE Transactions on Cybernetics 49:688–697
Tax DMJ, Duin RP (1999) Support vector domain description. Pattern Recogn Lett 20(11–13):1191–1199
Tiantian C, Hongwei L, Shuisheng Z (2009) Large scale classification with local diversity adaboost svm algorithm. J Syst Eng Electron 20(6):1344–1350
Vapnik, N.: The nature of statistical learning theory (2000)
Xie X (2018) Regularized multi-view least squares twin support vector machines. Appl Intell 48:3108–3115
Xie, X., Sun, S.: Multi-view support vector machines with the consensus and complementarity in- formation. IEEE Transactions on Knowledge and Data Engineering
Yang, X., Zhuang, M.A., Yuan, S.: Multi-class adaboost algorithm based on the adjusted weak classifier. Journal of Electronics & Information Technology (2016)
Zeng JS, Gao CH, Su HY (2010) Data-driven predictive control for blast furnace ironmaking process. Computers & Chemical Engineering 34(11):1854–1862
Zeng JS, Liu XG, Gao CH, Luo SH, Jian L (2008) Wiener model identification of blast furnace ironmaking process. ISIJ International 48(12):1734–1738
Zhang, Y., Ni, M., Zhang, C., Liang, S., Fang, S., Li, R., Tan, Z.: Research and application of adaboost algorithm based on svm. In: 2019 IEEE 8th Joint International Information Technology and Artificial Intelligence Conference (ITAIC), pp. 662–666. IEEE (2019)
Zhao J, Xu Y, Fujita H (2019) An improved non-parallel universum support vector machine and its safe sample screening rule. Knowl-Based Syst 170(15):79–88
Zong W, Huang GB, Chen Y (2013) Weighted extreme learning machine for imbalance learning. Neurocomputing 101:229–242
Acknowledgements
This research is partially supported by Natural Science Foundation of China under Grant Nos. 61973145 and 61873279, Foundation of the Education of Jiangxi Province under Grant No. GJJ180247, National Key Research and Development Program of Shandong Province under Grant No. 2018GSF120020 and Fundamental Research Funds for the Central Universities under Grant No. 19CX05027B.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
There is no conflict of interest from the 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
Luo, S., Dai, Z., Chen, T. et al. A weighted SVM ensemble predictor based on AdaBoost for blast furnace Ironmaking process. Appl Intell 50, 1997–2008 (2020). https://doi.org/10.1007/s10489-020-01662-y
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-020-01662-y