Enhanced just-in-time modelling for online quality prediction in BF ironmaking

References

• Sugawara K, Morimoto K, Sugawara T and Dranoff JS: ‘Dynamic behavior of iron forms in rapid reduction of carbon-coated iron ore’, AIChE J., 1999, 45, 574–580.
   Web of Science ®Google Scholar
• Bi XG, Torrssel K and Wijk O: ‘Prediction of the blast furnace process by a mathematical model’, ISIJ Int., 1992, 32, 481–488.
   Web of Science ®Google Scholar
• Nogami H, Chu MS and Yaji J: ‘Multi-dimensional transient mathematical simulator of blast furnace process based on multi-fluid and kinetic theories’, Comput. Chem. Eng., 2005, 29, 2438–2448.
   Web of Science ®Google Scholar
• Nishioka K, Maeda T and Shimizu M: ‘A three-dimensional mathematical modelling of drainage behavior in blast furnace hearth’, ISIJ Int., 2005, 45, 669–676.
   Web of Science ®Google Scholar
• Radhakrishnan VR and Ram KM: ‘Mathematical model for predictive control of the bell-less top charging system of a blast furnace’, J. Process Contr., 2001, 11, 565–586.
   Web of Science ®Google Scholar
• Ueda S, Natsui S, Nogami H, Yagi JI and Tatsuro A: ‘Recent progress and future perspective on mathematical modelling of blast furnace’, ISIJ Int., 2010, 50, 914–923.
   Web of Science ®Google Scholar
• Singh H, Sridhar NV and Deo B: ‘Artificial neural nets for prediction of silicon content of blast furnace hot metal’, Steel Res. Int., 1996, 67, 521–527.
   Web of Science ®Google Scholar
• Radhakrishnan VR and Mohamed AR: ‘Neural networks for the identification and control of blast furnace hot metal quality’, J. Process Contr., 2000, 10, 509–524.
   Web of Science ®Google Scholar
• Chen J: ‘A predictive system for blast furnaces by integrating a neural network with qualitative analysis’, Eng. Appl. Artif. Intell., 2001, 14, 77–85.
   Web of Science ®Google Scholar
• Jimenez J, Mochon J, de Ayalai JS and Obeso F: ‘Blast furnace hot metal temperature prediction through neural networks-based models’, ISIJ Int., 2004, 44, 573–580.
   Web of Science ®Google Scholar
• Saxen H and Pettersson F: ‘Nonlinear prediction of the hot metal silicon content in the blast furnace’, ISIJ Int., 2007, 47, 1732–1737.
   Web of Science ®Google Scholar
• Pettersson F, Chakraborti N and Saxén H: ‘A genetic algorithm based multi objective neural net applied to noisy blast furnace data’, Appl. Soft Comput., 2007, 7, 387–397.
   Web of Science ®Google Scholar
• Nurkkala A, Pettersson F and Saxen H: ‘Nonlinear modelling method applied to prediction of hot metal silicon in the ironmaking blast furnace’, Industr. Eng. Chem. Res., 2011, 50, 9236–9248.
   Web of Science ®Google Scholar
• Hao XJ, Shen FM, Du G, Shen YS and Xie Z: ‘A blast furnace prediction model combining neural network with partial least square regression’, Steel Res. Int., 2005, 76, 694–699.
   Web of Science ®Google Scholar
• Bhattacharya T: ‘Prediction of silicon content in blast furnace hot metal using partial least squares (PLS)’, ISIJ Int., 2005, 45, 1943–1945.
   Web of Science ®Google Scholar
• Martin RD, Obeso F, Mochon J, Barea R and Jimenez J: ‘Hot metal temperature prediction in blast furnace using advanced model based on fuzzy logic tools’, Ironmak. Steelmak., 2007, 34, 241–247.
   Web of Science ®Google Scholar
• Waller M and Saxen H: ‘On the development of predictive models with applications to a metallurgical process’, Industr. Eng. Chem. Res., 2000, 39, 982–988.
   Web of Science ®Google Scholar
• Gao CH, Zhou ZM and Chen JM: ‘Assessing the predictability for blast furnace system through nonlinear time series analysis’, Industr. Eng. Chem. Res., 2008, 47, 3037–3045.
   Web of Science ®Google Scholar
• Waller M and Saxen H: ‘Application of nonlinear time series analysis to the prediction of silicon content of pig iron’, ISIJ Int., 2002, 42, 316–318.
   Web of Science ®Google Scholar
• Miyano T, Kimoto S, Shibuta H, Nakashima K, Ikenaga Y and Aihara K: ‘Time series analysis and prediction on complex dynamical behavior observed in a blast furnace’, Phys. D, 2000, 135, 305–330.
   Web of Science ®Google Scholar
• Zeng JS and Gao CH: ‘Improvement of identification of blast furnace ironmaking process by outlier detection and missing value imputation’, J. Process Contr., 2009, 19, 1519–1528.
   Web of Science ®Google Scholar
• Jian L, Gao CH and Xia ZQ: ‘A sliding-window smooth support vector regression model for nonlinear blast furnace system’, Steel Res. Int., 2011, 82, 169–179.
   Web of Science ®Google Scholar
• Gao CH, Zeng JS and Luo SH: ‘Modelling of the thermal state change of blast furnace hearth with support vector machines’, IEEE Trans. Industr. Electron., 2012, 59, 1134–1145.
   Web of Science ®Google Scholar
• Jian L, Shen SQ and Song YQ: ‘Improving the solution of least squares support vector machines with application to a blast furnace system’, J. Appl. Math., 2012, Article ID 949654.
   Web of Science ®Google Scholar
• Gao CH, Chen JM, Zeng JS, Liu XY and Sun YX: ‘A chaos-based iterated multistep predictor for blast furnace ironmaking process’, AIChE J., 2009, 55, 947–962.
   Web of Science ®Google Scholar
• Gao CH, Zeng JS and Zhou ZM: ‘Identification of multiscale nature and multiple dynamics of the blast furnace system from operating data’, AIChE J., 2011, 57, 3448–3458.
   Web of Science ®Google Scholar
• Chu YX and Gao CH: ‘Data-based multiscale modelling for blast furnace system’, AIChE J., 2014, 60, 2197–2210.
   Web of Science ®Google Scholar
• Luo SH, Gao CH, Zeng JS and Huang J: ‘Blast furnace system modelling by multivariate phase space reconstruction and neural networks’, Asian J. Contr., 2013, 15, 553–561.
   Web of Science ®Google Scholar
• Nurkkala A, Pettersson F and Saxen H: ‘A study of blast furnace dynamics using multiple autoregressive vector models’, ISIJ Int., 2012, 52, 1763–1770.
   Web of Science ®Google Scholar
• Saxen H, Gao CH and Gao ZW: Data-Driven time discrete models for dynamic prediction of the hot metal silicon content in the blast furnace—a review, IEEE Trans. Industr. Inform., 2013, 9, 2213–2225.
   Web of Science ®Google Scholar
• Kano M and Nakagawa Y: ‘Data-based process monitoring, process control, and quality improvement: Recent developments and applications in steel industry’, Comput. Chem. Eng., 2008, 32, 12–24.
   Web of Science ®Google Scholar
• Kadlec P, Gabrys B and Strandt S: ‘Data-driven soft sensors in the process industry’, Comput. Chem. Eng., 2009, 33, 795.
   Web of Science ®Google Scholar
• Vapnik VN: ‘The nature of statistical learning theory’; 1995, New York, Springer-Verlag.
   Google Scholar
• Suykens JAK, Van Gestel T, de Brabanter J, de Moor B and Vandewalle J: ‘Least squares support vector machines’; 2002, World Singapore, Scientific.
   Google Scholar
• Scholkopf B and Smola AJ: ‘Learning with kernels, support vector machines’; 2002, Cambridge, MA.
   Google Scholar
• Czekaj T, Wu W and Walczak B: ‘About kernel latent variable approaches and SVM’, J. Chemom., 2005, 19, 341–354.
   Web of Science ®Google Scholar
• Liu Y, Hu NP, Wang HQ and Li P: ‘Soft chemical analyzer development using adaptive least-squares support vector regression with selective pruning and variable moving window size’, Industr. Eng. Chem. Res., 2009, 48, 5731–5741.
   Web of Science ®Google Scholar
• Chiang LH, Pell RJ and Seasholtz MB: ‘Exploring process data with the use of robust outlier detection algorithms’, J. Process Contr., 2003, 13, 437–449.
   Web of Science ®Google Scholar
• Liu H, Shah SL and Jiang W: ‘Online outlier detection and data cleaning’, Comput. Chem. Eng., 2004, 28, 1635–1647.
   Web of Science ®Google Scholar
• Ben-Hur A, Horn D, Siegelmann H and Vapnik V: ‘Support vector clustering’, J. Mach. Learn. Res., 2002, 2, 125–137.
   Web of Science ®Google Scholar
• Chiang JH and Hao PY: ‘A new kernel-based fuzzy clustering approach: support vector clustering with cell growing’, IEEE Trans. Fuzzy Syst., 2003, 11, 518–527.
   Web of Science ®Google Scholar
• Wang JS and Chiang JC: ‘A cluster validity measure with outlier detection for support vector clustering’, IEEE Trans. Systems Man Cybern B: Cybern., 2008, 38, 78–89.
   PubMed Web of Science ®Google Scholar
• Atkeson CG, Moore AW and Schaal S: ‘Locally weighted learning’, Artif. Intell. Rev., 1997, 11, 11–73.
   Web of Science ®Google Scholar
• Bontempi G, Birattari M and Bersini H: ‘Lazy learning for local modelling and control design’, Int. J. Contr., 1999, 72, 643–658.
   Web of Science ®Google Scholar
• Cheng C and Chiu MS: ‘A new data-based methodology for nonlinear process modelling’, Chem. Eng. Sci., 2004, 59, 2801–2810.
   Web of Science ®Google Scholar
• Fujiwara K, Kano M, Hasebe S and Takinami A: ‘Soft-sensor development using correlation-based just-in-time modelling’, AIChE J., 2009, 55, 1754–1765.
   Web of Science ®Google Scholar
• Ge ZQ and Song ZH: ‘A comparative study of just-in-time-learning based methods for online soft sensor modelling’, Chemom. Intell. Labor. Syst., 2010, 104, 306–317.
   Web of Science ®Google Scholar
• Liu Y, Gao ZL, Li P and Wang HQ: ‘Just-in-time kernel learning with adaptive parameter selection for soft sensor modelling of batch processes’, Industr. Eng. Chem. Res., 2012, 51, 4313–4327.
   Web of Science ®Google Scholar
• Chen K, Ji J, Wang HQ, Liu Y and Song ZH: ‘Adaptive local kernel-based learning for soft sensor modelling of nonlinear processes’, Chem. Eng. Res. Des., 2011, 89, 2117–2124.
   Web of Science ®Google Scholar
• Cawley GC and Talbot NLC: ‘Fast exact leave-one-out cross validation of sparse least-squares support vector machines’, Neural Networks, 2004, 17, 1467–1475.
   PubMed Web of Science ®Google Scholar
• Huang D, Wang CD and Lai JH: ‘Incremental support vector clustering with outlier detection’, Proc. 21st Int. Conf. on ‘Pattern recognition (ICPR)’, 2012, 2339–2342.
   Google Scholar
• Chen T and Ren JH: ‘Bagging for Gaussian process regression’, Neurocomputing, 2009, 72, 1605–1610.
   Web of Science ®Google Scholar
• Chen J, Chan LLT and Cheng N: ‘Gaussian process regression based optimal design of combustion systems using flame images’, Appl. Energy, 2013, 111, 153–160.
   Web of Science ®Google Scholar
• Liu Y and Chen J: ‘Integrated soft sensor using just-in-time support vector regression and probabilistic analysis for quality prediction of multi-grade processes’, J. Process Contr., 2013, 23, 793–804.
   Web of Science ®Google Scholar